Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-5500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-6000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-5500/config.json

@@ -0,0 +1,36 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 128001,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.4",
+  "use_cache": true,
+  "vocab_size": 128256
+}

checkpoint-5500/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.52.4"
+}

checkpoint-5500/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ad2c738139d277f93c35a985d1c13c992806e8fb185f9376d41b32bb928420c
+size 4976698672

checkpoint-5500/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbb741082cca76cdd239ec900ba2179e3112962f026f7212429288d6bd3e1218
+size 4999802720

checkpoint-5500/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66a7908134dc7f3d5fea1c57232efa4bde0c62c2f78f828f14285a8da3f02fe9
+size 4915916176

checkpoint-5500/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c919524667a27b4e554774652c310ed803dda3a873239fb3f215b891bac0f703
+size 1168138808

checkpoint-5500/model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 16060522496
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

checkpoint-5500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a51b46090ded3127b47609085f2d7378339b74c79b953e2f03f7b595841ec58
+size 32121300399

checkpoint-5500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:098b29492211804ab324a36f37466821d948280bb74fce4ba895c03f13ecd878
+size 14645

checkpoint-5500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8dce2dfbf0239aa99f5c07c4322669f6eb0111504fc0cb6bc97ab78bb7b9fac
+size 1465

checkpoint-5500/special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|end_of_text|>"
+}

checkpoint-5500/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920

checkpoint-5500/tokenizer_config.json

@@ -0,0 +1,2063 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|end_of_text|>",
+  "tokenizer_class": "PreTrainedTokenizer"
+}

checkpoint-5500/trainer_state.json

@@ -0,0 +1,3884 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.2404149751917004,
+  "eval_steps": 500,
+  "global_step": 5500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0022552999548940008,
+      "grad_norm": 3.71875,
+      "learning_rate": 1.9970000000000004e-05,
+      "loss": 1.2486,
+      "step": 10
+    },
+    {
+      "epoch": 0.0045105999097880016,
+      "grad_norm": 2.9375,
+      "learning_rate": 1.993666666666667e-05,
+      "loss": 0.9533,
+      "step": 20
+    },
+    {
+      "epoch": 0.006765899864682003,
+      "grad_norm": 2.71875,
+      "learning_rate": 1.9903333333333333e-05,
+      "loss": 0.8758,
+      "step": 30
+    },
+    {
+      "epoch": 0.009021199819576003,
+      "grad_norm": 2.640625,
+      "learning_rate": 1.987e-05,
+      "loss": 0.8479,
+      "step": 40
+    },
+    {
+      "epoch": 0.011276499774470004,
+      "grad_norm": 2.5625,
+      "learning_rate": 1.983666666666667e-05,
+      "loss": 0.8127,
+      "step": 50
+    },
+    {
+      "epoch": 0.013531799729364006,
+      "grad_norm": 2.375,
+      "learning_rate": 1.9803333333333334e-05,
+      "loss": 0.812,
+      "step": 60
+    },
+    {
+      "epoch": 0.015787099684258007,
+      "grad_norm": 2.421875,
+      "learning_rate": 1.9770000000000002e-05,
+      "loss": 0.7799,
+      "step": 70
+    },
+    {
+      "epoch": 0.018042399639152006,
+      "grad_norm": 2.796875,
+      "learning_rate": 1.9736666666666667e-05,
+      "loss": 0.8005,
+      "step": 80
+    },
+    {
+      "epoch": 0.02029769959404601,
+      "grad_norm": 2.40625,
+      "learning_rate": 1.9703333333333335e-05,
+      "loss": 0.7766,
+      "step": 90
+    },
+    {
+      "epoch": 0.02255299954894001,
+      "grad_norm": 2.578125,
+      "learning_rate": 1.9670000000000003e-05,
+      "loss": 0.7611,
+      "step": 100
+    },
+    {
+      "epoch": 0.02480829950383401,
+      "grad_norm": 2.375,
+      "learning_rate": 1.9636666666666668e-05,
+      "loss": 0.7492,
+      "step": 110
+    },
+    {
+      "epoch": 0.02706359945872801,
+      "grad_norm": 2.421875,
+      "learning_rate": 1.9603333333333333e-05,
+      "loss": 0.7518,
+      "step": 120
+    },
+    {
+      "epoch": 0.02931889941362201,
+      "grad_norm": 2.296875,
+      "learning_rate": 1.957e-05,
+      "loss": 0.7677,
+      "step": 130
+    },
+    {
+      "epoch": 0.031574199368516014,
+      "grad_norm": 2.609375,
+      "learning_rate": 1.953666666666667e-05,
+      "loss": 0.7275,
+      "step": 140
+    },
+    {
+      "epoch": 0.03382949932341001,
+      "grad_norm": 2.65625,
+      "learning_rate": 1.9503333333333334e-05,
+      "loss": 0.7348,
+      "step": 150
+    },
+    {
+      "epoch": 0.03608479927830401,
+      "grad_norm": 2.421875,
+      "learning_rate": 1.947e-05,
+      "loss": 0.7438,
+      "step": 160
+    },
+    {
+      "epoch": 0.03834009923319801,
+      "grad_norm": 2.203125,
+      "learning_rate": 1.943666666666667e-05,
+      "loss": 0.7227,
+      "step": 170
+    },
+    {
+      "epoch": 0.04059539918809202,
+      "grad_norm": 2.453125,
+      "learning_rate": 1.9403333333333334e-05,
+      "loss": 0.7117,
+      "step": 180
+    },
+    {
+      "epoch": 0.04285069914298602,
+      "grad_norm": 2.1875,
+      "learning_rate": 1.9370000000000003e-05,
+      "loss": 0.7232,
+      "step": 190
+    },
+    {
+      "epoch": 0.04510599909788002,
+      "grad_norm": 2.25,
+      "learning_rate": 1.9336666666666667e-05,
+      "loss": 0.7289,
+      "step": 200
+    },
+    {
+      "epoch": 0.04736129905277402,
+      "grad_norm": 2.265625,
+      "learning_rate": 1.9303333333333335e-05,
+      "loss": 0.6979,
+      "step": 210
+    },
+    {
+      "epoch": 0.04961659900766802,
+      "grad_norm": 2.25,
+      "learning_rate": 1.9270000000000004e-05,
+      "loss": 0.6891,
+      "step": 220
+    },
+    {
+      "epoch": 0.05187189896256202,
+      "grad_norm": 2.1875,
+      "learning_rate": 1.9236666666666668e-05,
+      "loss": 0.7168,
+      "step": 230
+    },
+    {
+      "epoch": 0.05412719891745602,
+      "grad_norm": 2.578125,
+      "learning_rate": 1.9203333333333333e-05,
+      "loss": 0.6879,
+      "step": 240
+    },
+    {
+      "epoch": 0.05638249887235002,
+      "grad_norm": 2.4375,
+      "learning_rate": 1.917e-05,
+      "loss": 0.6775,
+      "step": 250
+    },
+    {
+      "epoch": 0.05863779882724402,
+      "grad_norm": 2.28125,
+      "learning_rate": 1.913666666666667e-05,
+      "loss": 0.6832,
+      "step": 260
+    },
+    {
+      "epoch": 0.06089309878213803,
+      "grad_norm": 2.203125,
+      "learning_rate": 1.9103333333333337e-05,
+      "loss": 0.6553,
+      "step": 270
+    },
+    {
+      "epoch": 0.06314839873703203,
+      "grad_norm": 2.265625,
+      "learning_rate": 1.9070000000000002e-05,
+      "loss": 0.6733,
+      "step": 280
+    },
+    {
+      "epoch": 0.06540369869192603,
+      "grad_norm": 2.1875,
+      "learning_rate": 1.9036666666666667e-05,
+      "loss": 0.6811,
+      "step": 290
+    },
+    {
+      "epoch": 0.06765899864682003,
+      "grad_norm": 2.40625,
+      "learning_rate": 1.9003333333333335e-05,
+      "loss": 0.668,
+      "step": 300
+    },
+    {
+      "epoch": 0.06991429860171403,
+      "grad_norm": 2.265625,
+      "learning_rate": 1.8970000000000003e-05,
+      "loss": 0.6659,
+      "step": 310
+    },
+    {
+      "epoch": 0.07216959855660803,
+      "grad_norm": 2.328125,
+      "learning_rate": 1.8936666666666668e-05,
+      "loss": 0.6776,
+      "step": 320
+    },
+    {
+      "epoch": 0.07442489851150202,
+      "grad_norm": 2.5625,
+      "learning_rate": 1.8903333333333336e-05,
+      "loss": 0.6605,
+      "step": 330
+    },
+    {
+      "epoch": 0.07668019846639602,
+      "grad_norm": 2.265625,
+      "learning_rate": 1.887e-05,
+      "loss": 0.6537,
+      "step": 340
+    },
+    {
+      "epoch": 0.07893549842129004,
+      "grad_norm": 2.28125,
+      "learning_rate": 1.883666666666667e-05,
+      "loss": 0.6474,
+      "step": 350
+    },
+    {
+      "epoch": 0.08119079837618404,
+      "grad_norm": 2.390625,
+      "learning_rate": 1.8803333333333337e-05,
+      "loss": 0.6272,
+      "step": 360
+    },
+    {
+      "epoch": 0.08344609833107804,
+      "grad_norm": 2.28125,
+      "learning_rate": 1.877e-05,
+      "loss": 0.6406,
+      "step": 370
+    },
+    {
+      "epoch": 0.08570139828597204,
+      "grad_norm": 2.296875,
+      "learning_rate": 1.8736666666666666e-05,
+      "loss": 0.6386,
+      "step": 380
+    },
+    {
+      "epoch": 0.08795669824086604,
+      "grad_norm": 2.359375,
+      "learning_rate": 1.8703333333333334e-05,
+      "loss": 0.621,
+      "step": 390
+    },
+    {
+      "epoch": 0.09021199819576003,
+      "grad_norm": 2.28125,
+      "learning_rate": 1.8670000000000003e-05,
+      "loss": 0.6657,
+      "step": 400
+    },
+    {
+      "epoch": 0.09246729815065403,
+      "grad_norm": 2.953125,
+      "learning_rate": 1.8636666666666667e-05,
+      "loss": 0.6331,
+      "step": 410
+    },
+    {
+      "epoch": 0.09472259810554803,
+      "grad_norm": 2.75,
+      "learning_rate": 1.8603333333333335e-05,
+      "loss": 0.6434,
+      "step": 420
+    },
+    {
+      "epoch": 0.09697789806044203,
+      "grad_norm": 2.328125,
+      "learning_rate": 1.857e-05,
+      "loss": 0.6152,
+      "step": 430
+    },
+    {
+      "epoch": 0.09923319801533605,
+      "grad_norm": 2.40625,
+      "learning_rate": 1.8536666666666668e-05,
+      "loss": 0.6462,
+      "step": 440
+    },
+    {
+      "epoch": 0.10148849797023005,
+      "grad_norm": 2.8125,
+      "learning_rate": 1.8503333333333336e-05,
+      "loss": 0.5954,
+      "step": 450
+    },
+    {
+      "epoch": 0.10374379792512405,
+      "grad_norm": 2.140625,
+      "learning_rate": 1.847e-05,
+      "loss": 0.6304,
+      "step": 460
+    },
+    {
+      "epoch": 0.10599909788001805,
+      "grad_norm": 2.359375,
+      "learning_rate": 1.8436666666666666e-05,
+      "loss": 0.6318,
+      "step": 470
+    },
+    {
+      "epoch": 0.10825439783491204,
+      "grad_norm": 2.375,
+      "learning_rate": 1.8403333333333334e-05,
+      "loss": 0.626,
+      "step": 480
+    },
+    {
+      "epoch": 0.11050969778980604,
+      "grad_norm": 2.53125,
+      "learning_rate": 1.8370000000000002e-05,
+      "loss": 0.6112,
+      "step": 490
+    },
+    {
+      "epoch": 0.11276499774470004,
+      "grad_norm": 2.359375,
+      "learning_rate": 1.8336666666666667e-05,
+      "loss": 0.6057,
+      "step": 500
+    },
+    {
+      "epoch": 0.11502029769959404,
+      "grad_norm": 2.59375,
+      "learning_rate": 1.8303333333333335e-05,
+      "loss": 0.5819,
+      "step": 510
+    },
+    {
+      "epoch": 0.11727559765448804,
+      "grad_norm": 2.65625,
+      "learning_rate": 1.827e-05,
+      "loss": 0.6126,
+      "step": 520
+    },
+    {
+      "epoch": 0.11953089760938204,
+      "grad_norm": 2.34375,
+      "learning_rate": 1.8236666666666668e-05,
+      "loss": 0.6287,
+      "step": 530
+    },
+    {
+      "epoch": 0.12178619756427606,
+      "grad_norm": 2.4375,
+      "learning_rate": 1.8203333333333336e-05,
+      "loss": 0.586,
+      "step": 540
+    },
+    {
+      "epoch": 0.12404149751917005,
+      "grad_norm": 2.28125,
+      "learning_rate": 1.817e-05,
+      "loss": 0.6016,
+      "step": 550
+    },
+    {
+      "epoch": 0.12629679747406405,
+      "grad_norm": 2.421875,
+      "learning_rate": 1.813666666666667e-05,
+      "loss": 0.582,
+      "step": 560
+    },
+    {
+      "epoch": 0.12855209742895804,
+      "grad_norm": 2.375,
+      "learning_rate": 1.8103333333333333e-05,
+      "loss": 0.5885,
+      "step": 570
+    },
+    {
+      "epoch": 0.13080739738385205,
+      "grad_norm": 2.515625,
+      "learning_rate": 1.807e-05,
+      "loss": 0.584,
+      "step": 580
+    },
+    {
+      "epoch": 0.13306269733874607,
+      "grad_norm": 2.484375,
+      "learning_rate": 1.803666666666667e-05,
+      "loss": 0.5487,
+      "step": 590
+    },
+    {
+      "epoch": 0.13531799729364005,
+      "grad_norm": 2.5,
+      "learning_rate": 1.8003333333333334e-05,
+      "loss": 0.5923,
+      "step": 600
+    },
+    {
+      "epoch": 0.13757329724853407,
+      "grad_norm": 2.375,
+      "learning_rate": 1.7970000000000002e-05,
+      "loss": 0.5666,
+      "step": 610
+    },
+    {
+      "epoch": 0.13982859720342805,
+      "grad_norm": 3.09375,
+      "learning_rate": 1.793666666666667e-05,
+      "loss": 0.5466,
+      "step": 620
+    },
+    {
+      "epoch": 0.14208389715832206,
+      "grad_norm": 2.5,
+      "learning_rate": 1.7903333333333335e-05,
+      "loss": 0.5908,
+      "step": 630
+    },
+    {
+      "epoch": 0.14433919711321605,
+      "grad_norm": 2.515625,
+      "learning_rate": 1.787e-05,
+      "loss": 0.5542,
+      "step": 640
+    },
+    {
+      "epoch": 0.14659449706811006,
+      "grad_norm": 2.515625,
+      "learning_rate": 1.7836666666666668e-05,
+      "loss": 0.5659,
+      "step": 650
+    },
+    {
+      "epoch": 0.14884979702300405,
+      "grad_norm": 2.578125,
+      "learning_rate": 1.7803333333333336e-05,
+      "loss": 0.5361,
+      "step": 660
+    },
+    {
+      "epoch": 0.15110509697789806,
+      "grad_norm": 2.4375,
+      "learning_rate": 1.777e-05,
+      "loss": 0.555,
+      "step": 670
+    },
+    {
+      "epoch": 0.15336039693279205,
+      "grad_norm": 2.609375,
+      "learning_rate": 1.773666666666667e-05,
+      "loss": 0.5435,
+      "step": 680
+    },
+    {
+      "epoch": 0.15561569688768606,
+      "grad_norm": 2.46875,
+      "learning_rate": 1.7703333333333334e-05,
+      "loss": 0.5713,
+      "step": 690
+    },
+    {
+      "epoch": 0.15787099684258007,
+      "grad_norm": 2.40625,
+      "learning_rate": 1.7670000000000002e-05,
+      "loss": 0.559,
+      "step": 700
+    },
+    {
+      "epoch": 0.16012629679747406,
+      "grad_norm": 2.421875,
+      "learning_rate": 1.763666666666667e-05,
+      "loss": 0.5696,
+      "step": 710
+    },
+    {
+      "epoch": 0.16238159675236807,
+      "grad_norm": 2.640625,
+      "learning_rate": 1.7603333333333335e-05,
+      "loss": 0.5345,
+      "step": 720
+    },
+    {
+      "epoch": 0.16463689670726206,
+      "grad_norm": 2.4375,
+      "learning_rate": 1.757e-05,
+      "loss": 0.5774,
+      "step": 730
+    },
+    {
+      "epoch": 0.16689219666215607,
+      "grad_norm": 2.375,
+      "learning_rate": 1.7536666666666668e-05,
+      "loss": 0.5448,
+      "step": 740
+    },
+    {
+      "epoch": 0.16914749661705006,
+      "grad_norm": 2.515625,
+      "learning_rate": 1.7503333333333336e-05,
+      "loss": 0.5436,
+      "step": 750
+    },
+    {
+      "epoch": 0.17140279657194407,
+      "grad_norm": 2.34375,
+      "learning_rate": 1.7470000000000004e-05,
+      "loss": 0.5383,
+      "step": 760
+    },
+    {
+      "epoch": 0.17365809652683806,
+      "grad_norm": 2.375,
+      "learning_rate": 1.743666666666667e-05,
+      "loss": 0.5385,
+      "step": 770
+    },
+    {
+      "epoch": 0.17591339648173207,
+      "grad_norm": 2.734375,
+      "learning_rate": 1.7403333333333333e-05,
+      "loss": 0.5367,
+      "step": 780
+    },
+    {
+      "epoch": 0.17816869643662608,
+      "grad_norm": 2.46875,
+      "learning_rate": 1.737e-05,
+      "loss": 0.5622,
+      "step": 790
+    },
+    {
+      "epoch": 0.18042399639152007,
+      "grad_norm": 2.59375,
+      "learning_rate": 1.733666666666667e-05,
+      "loss": 0.5064,
+      "step": 800
+    },
+    {
+      "epoch": 0.18267929634641408,
+      "grad_norm": 2.4375,
+      "learning_rate": 1.7303333333333334e-05,
+      "loss": 0.528,
+      "step": 810
+    },
+    {
+      "epoch": 0.18493459630130807,
+      "grad_norm": 2.53125,
+      "learning_rate": 1.7270000000000002e-05,
+      "loss": 0.5117,
+      "step": 820
+    },
+    {
+      "epoch": 0.18718989625620208,
+      "grad_norm": 2.625,
+      "learning_rate": 1.7236666666666667e-05,
+      "loss": 0.5477,
+      "step": 830
+    },
+    {
+      "epoch": 0.18944519621109607,
+      "grad_norm": 2.421875,
+      "learning_rate": 1.7203333333333335e-05,
+      "loss": 0.5131,
+      "step": 840
+    },
+    {
+      "epoch": 0.19170049616599008,
+      "grad_norm": 2.96875,
+      "learning_rate": 1.7170000000000003e-05,
+      "loss": 0.4921,
+      "step": 850
+    },
+    {
+      "epoch": 0.19395579612088407,
+      "grad_norm": 2.5625,
+      "learning_rate": 1.7136666666666668e-05,
+      "loss": 0.4937,
+      "step": 860
+    },
+    {
+      "epoch": 0.19621109607577808,
+      "grad_norm": 2.53125,
+      "learning_rate": 1.7103333333333333e-05,
+      "loss": 0.508,
+      "step": 870
+    },
+    {
+      "epoch": 0.1984663960306721,
+      "grad_norm": 2.625,
+      "learning_rate": 1.707e-05,
+      "loss": 0.5266,
+      "step": 880
+    },
+    {
+      "epoch": 0.20072169598556608,
+      "grad_norm": 2.96875,
+      "learning_rate": 1.703666666666667e-05,
+      "loss": 0.5097,
+      "step": 890
+    },
+    {
+      "epoch": 0.2029769959404601,
+      "grad_norm": 2.390625,
+      "learning_rate": 1.7003333333333334e-05,
+      "loss": 0.4993,
+      "step": 900
+    },
+    {
+      "epoch": 0.20523229589535408,
+      "grad_norm": 2.65625,
+      "learning_rate": 1.6970000000000002e-05,
+      "loss": 0.482,
+      "step": 910
+    },
+    {
+      "epoch": 0.2074875958502481,
+      "grad_norm": 2.796875,
+      "learning_rate": 1.6936666666666667e-05,
+      "loss": 0.496,
+      "step": 920
+    },
+    {
+      "epoch": 0.20974289580514208,
+      "grad_norm": 2.734375,
+      "learning_rate": 1.6903333333333335e-05,
+      "loss": 0.4805,
+      "step": 930
+    },
+    {
+      "epoch": 0.2119981957600361,
+      "grad_norm": 2.609375,
+      "learning_rate": 1.6870000000000003e-05,
+      "loss": 0.5179,
+      "step": 940
+    },
+    {
+      "epoch": 0.21425349571493008,
+      "grad_norm": 2.5,
+      "learning_rate": 1.6836666666666668e-05,
+      "loss": 0.4581,
+      "step": 950
+    },
+    {
+      "epoch": 0.2165087956698241,
+      "grad_norm": 2.671875,
+      "learning_rate": 1.6803333333333332e-05,
+      "loss": 0.4656,
+      "step": 960
+    },
+    {
+      "epoch": 0.21876409562471807,
+      "grad_norm": 2.640625,
+      "learning_rate": 1.677e-05,
+      "loss": 0.4973,
+      "step": 970
+    },
+    {
+      "epoch": 0.2210193955796121,
+      "grad_norm": 2.609375,
+      "learning_rate": 1.673666666666667e-05,
+      "loss": 0.4915,
+      "step": 980
+    },
+    {
+      "epoch": 0.2232746955345061,
+      "grad_norm": 2.546875,
+      "learning_rate": 1.6703333333333333e-05,
+      "loss": 0.4807,
+      "step": 990
+    },
+    {
+      "epoch": 0.2255299954894001,
+      "grad_norm": 2.484375,
+      "learning_rate": 1.667e-05,
+      "loss": 0.5139,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2277852954442941,
+      "grad_norm": 2.703125,
+      "learning_rate": 1.6636666666666666e-05,
+      "loss": 0.4795,
+      "step": 1010
+    },
+    {
+      "epoch": 0.23004059539918809,
+      "grad_norm": 2.640625,
+      "learning_rate": 1.6603333333333334e-05,
+      "loss": 0.4759,
+      "step": 1020
+    },
+    {
+      "epoch": 0.2322958953540821,
+      "grad_norm": 2.8125,
+      "learning_rate": 1.6570000000000002e-05,
+      "loss": 0.4646,
+      "step": 1030
+    },
+    {
+      "epoch": 0.23455119530897608,
+      "grad_norm": 2.75,
+      "learning_rate": 1.6536666666666667e-05,
+      "loss": 0.4653,
+      "step": 1040
+    },
+    {
+      "epoch": 0.2368064952638701,
+      "grad_norm": 2.640625,
+      "learning_rate": 1.6503333333333335e-05,
+      "loss": 0.4609,
+      "step": 1050
+    },
+    {
+      "epoch": 0.23906179521876408,
+      "grad_norm": 2.6875,
+      "learning_rate": 1.647e-05,
+      "loss": 0.4676,
+      "step": 1060
+    },
+    {
+      "epoch": 0.2413170951736581,
+      "grad_norm": 2.78125,
+      "learning_rate": 1.6436666666666668e-05,
+      "loss": 0.4495,
+      "step": 1070
+    },
+    {
+      "epoch": 0.2435723951285521,
+      "grad_norm": 2.6875,
+      "learning_rate": 1.6403333333333336e-05,
+      "loss": 0.4443,
+      "step": 1080
+    },
+    {
+      "epoch": 0.2458276950834461,
+      "grad_norm": 2.59375,
+      "learning_rate": 1.637e-05,
+      "loss": 0.4341,
+      "step": 1090
+    },
+    {
+      "epoch": 0.2480829950383401,
+      "grad_norm": 2.84375,
+      "learning_rate": 1.633666666666667e-05,
+      "loss": 0.4294,
+      "step": 1100
+    },
+    {
+      "epoch": 0.2503382949932341,
+      "grad_norm": 2.625,
+      "learning_rate": 1.6303333333333337e-05,
+      "loss": 0.439,
+      "step": 1110
+    },
+    {
+      "epoch": 0.2525935949481281,
+      "grad_norm": 3.046875,
+      "learning_rate": 1.6270000000000002e-05,
+      "loss": 0.443,
+      "step": 1120
+    },
+    {
+      "epoch": 0.2548488949030221,
+      "grad_norm": 2.65625,
+      "learning_rate": 1.6236666666666667e-05,
+      "loss": 0.4389,
+      "step": 1130
+    },
+    {
+      "epoch": 0.2571041948579161,
+      "grad_norm": 2.859375,
+      "learning_rate": 1.6203333333333335e-05,
+      "loss": 0.46,
+      "step": 1140
+    },
+    {
+      "epoch": 0.2593594948128101,
+      "grad_norm": 2.78125,
+      "learning_rate": 1.6170000000000003e-05,
+      "loss": 0.4469,
+      "step": 1150
+    },
+    {
+      "epoch": 0.2616147947677041,
+      "grad_norm": 2.671875,
+      "learning_rate": 1.6136666666666667e-05,
+      "loss": 0.4485,
+      "step": 1160
+    },
+    {
+      "epoch": 0.2638700947225981,
+      "grad_norm": 3.046875,
+      "learning_rate": 1.6103333333333336e-05,
+      "loss": 0.4414,
+      "step": 1170
+    },
+    {
+      "epoch": 0.26612539467749213,
+      "grad_norm": 2.84375,
+      "learning_rate": 1.607e-05,
+      "loss": 0.4126,
+      "step": 1180
+    },
+    {
+      "epoch": 0.2683806946323861,
+      "grad_norm": 3.078125,
+      "learning_rate": 1.603666666666667e-05,
+      "loss": 0.433,
+      "step": 1190
+    },
+    {
+      "epoch": 0.2706359945872801,
+      "grad_norm": 2.859375,
+      "learning_rate": 1.6003333333333337e-05,
+      "loss": 0.4404,
+      "step": 1200
+    },
+    {
+      "epoch": 0.2728912945421741,
+      "grad_norm": 2.921875,
+      "learning_rate": 1.597e-05,
+      "loss": 0.4279,
+      "step": 1210
+    },
+    {
+      "epoch": 0.27514659449706813,
+      "grad_norm": 2.9375,
+      "learning_rate": 1.5936666666666666e-05,
+      "loss": 0.4333,
+      "step": 1220
+    },
+    {
+      "epoch": 0.2774018944519621,
+      "grad_norm": 2.828125,
+      "learning_rate": 1.5903333333333334e-05,
+      "loss": 0.435,
+      "step": 1230
+    },
+    {
+      "epoch": 0.2796571944068561,
+      "grad_norm": 2.9375,
+      "learning_rate": 1.5870000000000002e-05,
+      "loss": 0.4123,
+      "step": 1240
+    },
+    {
+      "epoch": 0.2819124943617501,
+      "grad_norm": 3.03125,
+      "learning_rate": 1.5836666666666667e-05,
+      "loss": 0.4065,
+      "step": 1250
+    },
+    {
+      "epoch": 0.28416779431664413,
+      "grad_norm": 3.21875,
+      "learning_rate": 1.5803333333333335e-05,
+      "loss": 0.4287,
+      "step": 1260
+    },
+    {
+      "epoch": 0.2864230942715381,
+      "grad_norm": 2.96875,
+      "learning_rate": 1.577e-05,
+      "loss": 0.4649,
+      "step": 1270
+    },
+    {
+      "epoch": 0.2886783942264321,
+      "grad_norm": 3.046875,
+      "learning_rate": 1.5736666666666668e-05,
+      "loss": 0.4076,
+      "step": 1280
+    },
+    {
+      "epoch": 0.29093369418132614,
+      "grad_norm": 3.125,
+      "learning_rate": 1.5703333333333336e-05,
+      "loss": 0.421,
+      "step": 1290
+    },
+    {
+      "epoch": 0.2931889941362201,
+      "grad_norm": 3.5625,
+      "learning_rate": 1.567e-05,
+      "loss": 0.3982,
+      "step": 1300
+    },
+    {
+      "epoch": 0.2954442940911141,
+      "grad_norm": 2.828125,
+      "learning_rate": 1.563666666666667e-05,
+      "loss": 0.4121,
+      "step": 1310
+    },
+    {
+      "epoch": 0.2976995940460081,
+      "grad_norm": 3.0,
+      "learning_rate": 1.5603333333333334e-05,
+      "loss": 0.4032,
+      "step": 1320
+    },
+    {
+      "epoch": 0.29995489400090214,
+      "grad_norm": 2.890625,
+      "learning_rate": 1.5570000000000002e-05,
+      "loss": 0.423,
+      "step": 1330
+    },
+    {
+      "epoch": 0.3022101939557961,
+      "grad_norm": 2.875,
+      "learning_rate": 1.553666666666667e-05,
+      "loss": 0.4193,
+      "step": 1340
+    },
+    {
+      "epoch": 0.3044654939106901,
+      "grad_norm": 3.09375,
+      "learning_rate": 1.5503333333333335e-05,
+      "loss": 0.3834,
+      "step": 1350
+    },
+    {
+      "epoch": 0.3067207938655841,
+      "grad_norm": 3.46875,
+      "learning_rate": 1.547e-05,
+      "loss": 0.4204,
+      "step": 1360
+    },
+    {
+      "epoch": 0.30897609382047814,
+      "grad_norm": 2.65625,
+      "learning_rate": 1.5436666666666667e-05,
+      "loss": 0.4036,
+      "step": 1370
+    },
+    {
+      "epoch": 0.3112313937753721,
+      "grad_norm": 2.8125,
+      "learning_rate": 1.5403333333333335e-05,
+      "loss": 0.3845,
+      "step": 1380
+    },
+    {
+      "epoch": 0.3134866937302661,
+      "grad_norm": 3.234375,
+      "learning_rate": 1.537e-05,
+      "loss": 0.3615,
+      "step": 1390
+    },
+    {
+      "epoch": 0.31574199368516015,
+      "grad_norm": 2.6875,
+      "learning_rate": 1.533666666666667e-05,
+      "loss": 0.3754,
+      "step": 1400
+    },
+    {
+      "epoch": 0.31799729364005414,
+      "grad_norm": 3.15625,
+      "learning_rate": 1.5303333333333333e-05,
+      "loss": 0.3984,
+      "step": 1410
+    },
+    {
+      "epoch": 0.3202525935949481,
+      "grad_norm": 3.515625,
+      "learning_rate": 1.527e-05,
+      "loss": 0.4009,
+      "step": 1420
+    },
+    {
+      "epoch": 0.3225078935498421,
+      "grad_norm": 3.171875,
+      "learning_rate": 1.523666666666667e-05,
+      "loss": 0.3939,
+      "step": 1430
+    },
+    {
+      "epoch": 0.32476319350473615,
+      "grad_norm": 3.34375,
+      "learning_rate": 1.5203333333333334e-05,
+      "loss": 0.3621,
+      "step": 1440
+    },
+    {
+      "epoch": 0.32701849345963013,
+      "grad_norm": 3.71875,
+      "learning_rate": 1.517e-05,
+      "loss": 0.3901,
+      "step": 1450
+    },
+    {
+      "epoch": 0.3292737934145241,
+      "grad_norm": 3.015625,
+      "learning_rate": 1.5136666666666669e-05,
+      "loss": 0.3602,
+      "step": 1460
+    },
+    {
+      "epoch": 0.33152909336941816,
+      "grad_norm": 2.75,
+      "learning_rate": 1.5103333333333335e-05,
+      "loss": 0.3793,
+      "step": 1470
+    },
+    {
+      "epoch": 0.33378439332431215,
+      "grad_norm": 3.140625,
+      "learning_rate": 1.507e-05,
+      "loss": 0.3698,
+      "step": 1480
+    },
+    {
+      "epoch": 0.33603969327920613,
+      "grad_norm": 3.03125,
+      "learning_rate": 1.5036666666666668e-05,
+      "loss": 0.3785,
+      "step": 1490
+    },
+    {
+      "epoch": 0.3382949932341001,
+      "grad_norm": 3.265625,
+      "learning_rate": 1.5003333333333334e-05,
+      "loss": 0.378,
+      "step": 1500
+    },
+    {
+      "epoch": 0.34055029318899416,
+      "grad_norm": 3.515625,
+      "learning_rate": 1.4970000000000002e-05,
+      "loss": 0.3588,
+      "step": 1510
+    },
+    {
+      "epoch": 0.34280559314388814,
+      "grad_norm": 3.125,
+      "learning_rate": 1.4936666666666669e-05,
+      "loss": 0.3602,
+      "step": 1520
+    },
+    {
+      "epoch": 0.34506089309878213,
+      "grad_norm": 3.40625,
+      "learning_rate": 1.4903333333333334e-05,
+      "loss": 0.3342,
+      "step": 1530
+    },
+    {
+      "epoch": 0.3473161930536761,
+      "grad_norm": 3.203125,
+      "learning_rate": 1.4870000000000002e-05,
+      "loss": 0.3603,
+      "step": 1540
+    },
+    {
+      "epoch": 0.34957149300857016,
+      "grad_norm": 3.078125,
+      "learning_rate": 1.4836666666666668e-05,
+      "loss": 0.3346,
+      "step": 1550
+    },
+    {
+      "epoch": 0.35182679296346414,
+      "grad_norm": 2.9375,
+      "learning_rate": 1.4803333333333334e-05,
+      "loss": 0.3419,
+      "step": 1560
+    },
+    {
+      "epoch": 0.3540820929183581,
+      "grad_norm": 3.28125,
+      "learning_rate": 1.4770000000000003e-05,
+      "loss": 0.3459,
+      "step": 1570
+    },
+    {
+      "epoch": 0.35633739287325217,
+      "grad_norm": 2.890625,
+      "learning_rate": 1.4736666666666667e-05,
+      "loss": 0.3671,
+      "step": 1580
+    },
+    {
+      "epoch": 0.35859269282814615,
+      "grad_norm": 3.328125,
+      "learning_rate": 1.4703333333333334e-05,
+      "loss": 0.3479,
+      "step": 1590
+    },
+    {
+      "epoch": 0.36084799278304014,
+      "grad_norm": 3.125,
+      "learning_rate": 1.4670000000000002e-05,
+      "loss": 0.3564,
+      "step": 1600
+    },
+    {
+      "epoch": 0.3631032927379341,
+      "grad_norm": 3.171875,
+      "learning_rate": 1.4636666666666668e-05,
+      "loss": 0.3432,
+      "step": 1610
+    },
+    {
+      "epoch": 0.36535859269282817,
+      "grad_norm": 3.15625,
+      "learning_rate": 1.4603333333333333e-05,
+      "loss": 0.3485,
+      "step": 1620
+    },
+    {
+      "epoch": 0.36761389264772215,
+      "grad_norm": 3.265625,
+      "learning_rate": 1.4570000000000001e-05,
+      "loss": 0.3608,
+      "step": 1630
+    },
+    {
+      "epoch": 0.36986919260261614,
+      "grad_norm": 3.0625,
+      "learning_rate": 1.4536666666666668e-05,
+      "loss": 0.3593,
+      "step": 1640
+    },
+    {
+      "epoch": 0.3721244925575101,
+      "grad_norm": 3.0,
+      "learning_rate": 1.4503333333333334e-05,
+      "loss": 0.3225,
+      "step": 1650
+    },
+    {
+      "epoch": 0.37437979251240416,
+      "grad_norm": 3.078125,
+      "learning_rate": 1.4470000000000002e-05,
+      "loss": 0.3608,
+      "step": 1660
+    },
+    {
+      "epoch": 0.37663509246729815,
+      "grad_norm": 3.046875,
+      "learning_rate": 1.4436666666666668e-05,
+      "loss": 0.3625,
+      "step": 1670
+    },
+    {
+      "epoch": 0.37889039242219213,
+      "grad_norm": 3.25,
+      "learning_rate": 1.4403333333333333e-05,
+      "loss": 0.342,
+      "step": 1680
+    },
+    {
+      "epoch": 0.3811456923770862,
+      "grad_norm": 3.453125,
+      "learning_rate": 1.4370000000000001e-05,
+      "loss": 0.3633,
+      "step": 1690
+    },
+    {
+      "epoch": 0.38340099233198016,
+      "grad_norm": 3.21875,
+      "learning_rate": 1.4336666666666668e-05,
+      "loss": 0.3485,
+      "step": 1700
+    },
+    {
+      "epoch": 0.38565629228687415,
+      "grad_norm": 4.0,
+      "learning_rate": 1.4303333333333334e-05,
+      "loss": 0.3415,
+      "step": 1710
+    },
+    {
+      "epoch": 0.38791159224176813,
+      "grad_norm": 3.609375,
+      "learning_rate": 1.4270000000000002e-05,
+      "loss": 0.3303,
+      "step": 1720
+    },
+    {
+      "epoch": 0.3901668921966622,
+      "grad_norm": 3.71875,
+      "learning_rate": 1.4236666666666667e-05,
+      "loss": 0.3049,
+      "step": 1730
+    },
+    {
+      "epoch": 0.39242219215155616,
+      "grad_norm": 2.828125,
+      "learning_rate": 1.4203333333333333e-05,
+      "loss": 0.3412,
+      "step": 1740
+    },
+    {
+      "epoch": 0.39467749210645015,
+      "grad_norm": 3.125,
+      "learning_rate": 1.4170000000000002e-05,
+      "loss": 0.3199,
+      "step": 1750
+    },
+    {
+      "epoch": 0.3969327920613442,
+      "grad_norm": 4.5,
+      "learning_rate": 1.4136666666666668e-05,
+      "loss": 0.3247,
+      "step": 1760
+    },
+    {
+      "epoch": 0.39918809201623817,
+      "grad_norm": 3.671875,
+      "learning_rate": 1.4103333333333336e-05,
+      "loss": 0.3338,
+      "step": 1770
+    },
+    {
+      "epoch": 0.40144339197113216,
+      "grad_norm": 3.234375,
+      "learning_rate": 1.407e-05,
+      "loss": 0.3122,
+      "step": 1780
+    },
+    {
+      "epoch": 0.40369869192602614,
+      "grad_norm": 3.71875,
+      "learning_rate": 1.4036666666666667e-05,
+      "loss": 0.3121,
+      "step": 1790
+    },
+    {
+      "epoch": 0.4059539918809202,
+      "grad_norm": 3.03125,
+      "learning_rate": 1.4003333333333335e-05,
+      "loss": 0.3229,
+      "step": 1800
+    },
+    {
+      "epoch": 0.40820929183581417,
+      "grad_norm": 3.390625,
+      "learning_rate": 1.3970000000000002e-05,
+      "loss": 0.2885,
+      "step": 1810
+    },
+    {
+      "epoch": 0.41046459179070816,
+      "grad_norm": 3.125,
+      "learning_rate": 1.3936666666666666e-05,
+      "loss": 0.2934,
+      "step": 1820
+    },
+    {
+      "epoch": 0.41271989174560214,
+      "grad_norm": 3.234375,
+      "learning_rate": 1.3903333333333335e-05,
+      "loss": 0.2783,
+      "step": 1830
+    },
+    {
+      "epoch": 0.4149751917004962,
+      "grad_norm": 3.921875,
+      "learning_rate": 1.3870000000000001e-05,
+      "loss": 0.3128,
+      "step": 1840
+    },
+    {
+      "epoch": 0.41723049165539017,
+      "grad_norm": 3.078125,
+      "learning_rate": 1.3836666666666667e-05,
+      "loss": 0.3074,
+      "step": 1850
+    },
+    {
+      "epoch": 0.41948579161028415,
+      "grad_norm": 3.40625,
+      "learning_rate": 1.3803333333333336e-05,
+      "loss": 0.2985,
+      "step": 1860
+    },
+    {
+      "epoch": 0.4217410915651782,
+      "grad_norm": 3.40625,
+      "learning_rate": 1.377e-05,
+      "loss": 0.2824,
+      "step": 1870
+    },
+    {
+      "epoch": 0.4239963915200722,
+      "grad_norm": 3.453125,
+      "learning_rate": 1.3736666666666667e-05,
+      "loss": 0.2961,
+      "step": 1880
+    },
+    {
+      "epoch": 0.42625169147496617,
+      "grad_norm": 3.5,
+      "learning_rate": 1.3703333333333335e-05,
+      "loss": 0.2968,
+      "step": 1890
+    },
+    {
+      "epoch": 0.42850699142986015,
+      "grad_norm": 4.09375,
+      "learning_rate": 1.3670000000000001e-05,
+      "loss": 0.3198,
+      "step": 1900
+    },
+    {
+      "epoch": 0.4307622913847542,
+      "grad_norm": 3.296875,
+      "learning_rate": 1.3636666666666668e-05,
+      "loss": 0.2763,
+      "step": 1910
+    },
+    {
+      "epoch": 0.4330175913396482,
+      "grad_norm": 3.40625,
+      "learning_rate": 1.3603333333333336e-05,
+      "loss": 0.2945,
+      "step": 1920
+    },
+    {
+      "epoch": 0.43527289129454216,
+      "grad_norm": 3.140625,
+      "learning_rate": 1.357e-05,
+      "loss": 0.3013,
+      "step": 1930
+    },
+    {
+      "epoch": 0.43752819124943615,
+      "grad_norm": 3.453125,
+      "learning_rate": 1.3536666666666667e-05,
+      "loss": 0.2897,
+      "step": 1940
+    },
+    {
+      "epoch": 0.4397834912043302,
+      "grad_norm": 3.203125,
+      "learning_rate": 1.3503333333333335e-05,
+      "loss": 0.2591,
+      "step": 1950
+    },
+    {
+      "epoch": 0.4420387911592242,
+      "grad_norm": 3.15625,
+      "learning_rate": 1.3470000000000001e-05,
+      "loss": 0.3079,
+      "step": 1960
+    },
+    {
+      "epoch": 0.44429409111411816,
+      "grad_norm": 3.65625,
+      "learning_rate": 1.3436666666666666e-05,
+      "loss": 0.2955,
+      "step": 1970
+    },
+    {
+      "epoch": 0.4465493910690122,
+      "grad_norm": 3.1875,
+      "learning_rate": 1.3403333333333334e-05,
+      "loss": 0.2737,
+      "step": 1980
+    },
+    {
+      "epoch": 0.4488046910239062,
+      "grad_norm": 3.546875,
+      "learning_rate": 1.337e-05,
+      "loss": 0.2929,
+      "step": 1990
+    },
+    {
+      "epoch": 0.4510599909788002,
+      "grad_norm": 2.828125,
+      "learning_rate": 1.3336666666666667e-05,
+      "loss": 0.2924,
+      "step": 2000
+    },
+    {
+      "epoch": 0.45331529093369416,
+      "grad_norm": 4.3125,
+      "learning_rate": 1.3303333333333335e-05,
+      "loss": 0.2744,
+      "step": 2010
+    },
+    {
+      "epoch": 0.4555705908885882,
+      "grad_norm": 3.15625,
+      "learning_rate": 1.327e-05,
+      "loss": 0.275,
+      "step": 2020
+    },
+    {
+      "epoch": 0.4578258908434822,
+      "grad_norm": 3.578125,
+      "learning_rate": 1.3236666666666668e-05,
+      "loss": 0.2695,
+      "step": 2030
+    },
+    {
+      "epoch": 0.46008119079837617,
+      "grad_norm": 3.421875,
+      "learning_rate": 1.3203333333333335e-05,
+      "loss": 0.2761,
+      "step": 2040
+    },
+    {
+      "epoch": 0.46233649075327016,
+      "grad_norm": 3.375,
+      "learning_rate": 1.3170000000000001e-05,
+      "loss": 0.2953,
+      "step": 2050
+    },
+    {
+      "epoch": 0.4645917907081642,
+      "grad_norm": 3.8125,
+      "learning_rate": 1.3136666666666669e-05,
+      "loss": 0.2901,
+      "step": 2060
+    },
+    {
+      "epoch": 0.4668470906630582,
+      "grad_norm": 3.359375,
+      "learning_rate": 1.3103333333333334e-05,
+      "loss": 0.2906,
+      "step": 2070
+    },
+    {
+      "epoch": 0.46910239061795217,
+      "grad_norm": 3.546875,
+      "learning_rate": 1.307e-05,
+      "loss": 0.2747,
+      "step": 2080
+    },
+    {
+      "epoch": 0.4713576905728462,
+      "grad_norm": 3.59375,
+      "learning_rate": 1.3036666666666668e-05,
+      "loss": 0.2728,
+      "step": 2090
+    },
+    {
+      "epoch": 0.4736129905277402,
+      "grad_norm": 3.0,
+      "learning_rate": 1.3003333333333335e-05,
+      "loss": 0.2464,
+      "step": 2100
+    },
+    {
+      "epoch": 0.4758682904826342,
+      "grad_norm": 4.15625,
+      "learning_rate": 1.2970000000000001e-05,
+      "loss": 0.2853,
+      "step": 2110
+    },
+    {
+      "epoch": 0.47812359043752817,
+      "grad_norm": 3.078125,
+      "learning_rate": 1.293666666666667e-05,
+      "loss": 0.2751,
+      "step": 2120
+    },
+    {
+      "epoch": 0.4803788903924222,
+      "grad_norm": 3.109375,
+      "learning_rate": 1.2903333333333334e-05,
+      "loss": 0.2579,
+      "step": 2130
+    },
+    {
+      "epoch": 0.4826341903473162,
+      "grad_norm": 3.109375,
+      "learning_rate": 1.287e-05,
+      "loss": 0.2758,
+      "step": 2140
+    },
+    {
+      "epoch": 0.4848894903022102,
+      "grad_norm": 4.5,
+      "learning_rate": 1.2836666666666669e-05,
+      "loss": 0.2691,
+      "step": 2150
+    },
+    {
+      "epoch": 0.4871447902571042,
+      "grad_norm": 3.90625,
+      "learning_rate": 1.2803333333333335e-05,
+      "loss": 0.2439,
+      "step": 2160
+    },
+    {
+      "epoch": 0.4894000902119982,
+      "grad_norm": 3.59375,
+      "learning_rate": 1.277e-05,
+      "loss": 0.2501,
+      "step": 2170
+    },
+    {
+      "epoch": 0.4916553901668922,
+      "grad_norm": 2.953125,
+      "learning_rate": 1.2736666666666668e-05,
+      "loss": 0.2561,
+      "step": 2180
+    },
+    {
+      "epoch": 0.4939106901217862,
+      "grad_norm": 3.296875,
+      "learning_rate": 1.2703333333333334e-05,
+      "loss": 0.2318,
+      "step": 2190
+    },
+    {
+      "epoch": 0.4961659900766802,
+      "grad_norm": 3.328125,
+      "learning_rate": 1.267e-05,
+      "loss": 0.2397,
+      "step": 2200
+    },
+    {
+      "epoch": 0.4984212900315742,
+      "grad_norm": 3.6875,
+      "learning_rate": 1.2636666666666669e-05,
+      "loss": 0.2504,
+      "step": 2210
+    },
+    {
+      "epoch": 0.5006765899864682,
+      "grad_norm": 3.6875,
+      "learning_rate": 1.2603333333333334e-05,
+      "loss": 0.257,
+      "step": 2220
+    },
+    {
+      "epoch": 0.5029318899413622,
+      "grad_norm": 3.34375,
+      "learning_rate": 1.257e-05,
+      "loss": 0.2578,
+      "step": 2230
+    },
+    {
+      "epoch": 0.5051871898962562,
+      "grad_norm": 3.578125,
+      "learning_rate": 1.2536666666666668e-05,
+      "loss": 0.2626,
+      "step": 2240
+    },
+    {
+      "epoch": 0.5074424898511503,
+      "grad_norm": 3.609375,
+      "learning_rate": 1.2503333333333334e-05,
+      "loss": 0.2523,
+      "step": 2250
+    },
+    {
+      "epoch": 0.5096977898060442,
+      "grad_norm": 3.28125,
+      "learning_rate": 1.2470000000000003e-05,
+      "loss": 0.2452,
+      "step": 2260
+    },
+    {
+      "epoch": 0.5119530897609382,
+      "grad_norm": 5.125,
+      "learning_rate": 1.2436666666666667e-05,
+      "loss": 0.2278,
+      "step": 2270
+    },
+    {
+      "epoch": 0.5142083897158322,
+      "grad_norm": 3.46875,
+      "learning_rate": 1.2403333333333334e-05,
+      "loss": 0.235,
+      "step": 2280
+    },
+    {
+      "epoch": 0.5164636896707262,
+      "grad_norm": 3.78125,
+      "learning_rate": 1.2370000000000002e-05,
+      "loss": 0.2427,
+      "step": 2290
+    },
+    {
+      "epoch": 0.5187189896256202,
+      "grad_norm": 3.328125,
+      "learning_rate": 1.2336666666666668e-05,
+      "loss": 0.2522,
+      "step": 2300
+    },
+    {
+      "epoch": 0.5209742895805142,
+      "grad_norm": 3.296875,
+      "learning_rate": 1.2303333333333333e-05,
+      "loss": 0.2325,
+      "step": 2310
+    },
+    {
+      "epoch": 0.5232295895354082,
+      "grad_norm": 3.21875,
+      "learning_rate": 1.2270000000000001e-05,
+      "loss": 0.2595,
+      "step": 2320
+    },
+    {
+      "epoch": 0.5254848894903023,
+      "grad_norm": 3.3125,
+      "learning_rate": 1.2236666666666668e-05,
+      "loss": 0.2683,
+      "step": 2330
+    },
+    {
+      "epoch": 0.5277401894451962,
+      "grad_norm": 3.515625,
+      "learning_rate": 1.2203333333333334e-05,
+      "loss": 0.2327,
+      "step": 2340
+    },
+    {
+      "epoch": 0.5299954894000902,
+      "grad_norm": 3.359375,
+      "learning_rate": 1.2170000000000002e-05,
+      "loss": 0.2305,
+      "step": 2350
+    },
+    {
+      "epoch": 0.5322507893549843,
+      "grad_norm": 4.03125,
+      "learning_rate": 1.2136666666666668e-05,
+      "loss": 0.24,
+      "step": 2360
+    },
+    {
+      "epoch": 0.5345060893098782,
+      "grad_norm": 3.171875,
+      "learning_rate": 1.2103333333333333e-05,
+      "loss": 0.2226,
+      "step": 2370
+    },
+    {
+      "epoch": 0.5367613892647722,
+      "grad_norm": 3.046875,
+      "learning_rate": 1.2070000000000001e-05,
+      "loss": 0.2288,
+      "step": 2380
+    },
+    {
+      "epoch": 0.5390166892196662,
+      "grad_norm": 3.46875,
+      "learning_rate": 1.2036666666666668e-05,
+      "loss": 0.2564,
+      "step": 2390
+    },
+    {
+      "epoch": 0.5412719891745602,
+      "grad_norm": 3.703125,
+      "learning_rate": 1.2003333333333334e-05,
+      "loss": 0.2115,
+      "step": 2400
+    },
+    {
+      "epoch": 0.5435272891294542,
+      "grad_norm": 3.46875,
+      "learning_rate": 1.1970000000000002e-05,
+      "loss": 0.2255,
+      "step": 2410
+    },
+    {
+      "epoch": 0.5457825890843482,
+      "grad_norm": 3.765625,
+      "learning_rate": 1.1936666666666667e-05,
+      "loss": 0.2214,
+      "step": 2420
+    },
+    {
+      "epoch": 0.5480378890392422,
+      "grad_norm": 3.9375,
+      "learning_rate": 1.1903333333333333e-05,
+      "loss": 0.2212,
+      "step": 2430
+    },
+    {
+      "epoch": 0.5502931889941363,
+      "grad_norm": 3.796875,
+      "learning_rate": 1.1870000000000002e-05,
+      "loss": 0.2266,
+      "step": 2440
+    },
+    {
+      "epoch": 0.5525484889490302,
+      "grad_norm": 3.203125,
+      "learning_rate": 1.1836666666666668e-05,
+      "loss": 0.2291,
+      "step": 2450
+    },
+    {
+      "epoch": 0.5548037889039242,
+      "grad_norm": 4.6875,
+      "learning_rate": 1.1803333333333333e-05,
+      "loss": 0.212,
+      "step": 2460
+    },
+    {
+      "epoch": 0.5570590888588183,
+      "grad_norm": 2.953125,
+      "learning_rate": 1.177e-05,
+      "loss": 0.2133,
+      "step": 2470
+    },
+    {
+      "epoch": 0.5593143888137122,
+      "grad_norm": 4.1875,
+      "learning_rate": 1.1736666666666667e-05,
+      "loss": 0.2606,
+      "step": 2480
+    },
+    {
+      "epoch": 0.5615696887686062,
+      "grad_norm": 3.53125,
+      "learning_rate": 1.1703333333333334e-05,
+      "loss": 0.2446,
+      "step": 2490
+    },
+    {
+      "epoch": 0.5638249887235002,
+      "grad_norm": 3.546875,
+      "learning_rate": 1.1670000000000002e-05,
+      "loss": 0.2264,
+      "step": 2500
+    },
+    {
+      "epoch": 0.5660802886783942,
+      "grad_norm": 3.921875,
+      "learning_rate": 1.1636666666666666e-05,
+      "loss": 0.2218,
+      "step": 2510
+    },
+    {
+      "epoch": 0.5683355886332883,
+      "grad_norm": 3.015625,
+      "learning_rate": 1.1603333333333335e-05,
+      "loss": 0.196,
+      "step": 2520
+    },
+    {
+      "epoch": 0.5705908885881822,
+      "grad_norm": 3.59375,
+      "learning_rate": 1.1570000000000001e-05,
+      "loss": 0.2327,
+      "step": 2530
+    },
+    {
+      "epoch": 0.5728461885430762,
+      "grad_norm": 3.125,
+      "learning_rate": 1.1536666666666667e-05,
+      "loss": 0.2224,
+      "step": 2540
+    },
+    {
+      "epoch": 0.5751014884979703,
+      "grad_norm": 3.765625,
+      "learning_rate": 1.1503333333333336e-05,
+      "loss": 0.2198,
+      "step": 2550
+    },
+    {
+      "epoch": 0.5773567884528642,
+      "grad_norm": 3.28125,
+      "learning_rate": 1.147e-05,
+      "loss": 0.2146,
+      "step": 2560
+    },
+    {
+      "epoch": 0.5796120884077582,
+      "grad_norm": 4.0625,
+      "learning_rate": 1.1436666666666667e-05,
+      "loss": 0.2217,
+      "step": 2570
+    },
+    {
+      "epoch": 0.5818673883626523,
+      "grad_norm": 3.515625,
+      "learning_rate": 1.1403333333333335e-05,
+      "loss": 0.2039,
+      "step": 2580
+    },
+    {
+      "epoch": 0.5841226883175462,
+      "grad_norm": 3.484375,
+      "learning_rate": 1.1370000000000001e-05,
+      "loss": 0.218,
+      "step": 2590
+    },
+    {
+      "epoch": 0.5863779882724403,
+      "grad_norm": 3.921875,
+      "learning_rate": 1.1336666666666668e-05,
+      "loss": 0.2031,
+      "step": 2600
+    },
+    {
+      "epoch": 0.5886332882273342,
+      "grad_norm": 3.796875,
+      "learning_rate": 1.1303333333333336e-05,
+      "loss": 0.1942,
+      "step": 2610
+    },
+    {
+      "epoch": 0.5908885881822282,
+      "grad_norm": 4.03125,
+      "learning_rate": 1.127e-05,
+      "loss": 0.203,
+      "step": 2620
+    },
+    {
+      "epoch": 0.5931438881371223,
+      "grad_norm": 3.25,
+      "learning_rate": 1.1236666666666667e-05,
+      "loss": 0.2204,
+      "step": 2630
+    },
+    {
+      "epoch": 0.5953991880920162,
+      "grad_norm": 3.53125,
+      "learning_rate": 1.1203333333333335e-05,
+      "loss": 0.2046,
+      "step": 2640
+    },
+    {
+      "epoch": 0.5976544880469102,
+      "grad_norm": 4.0,
+      "learning_rate": 1.1170000000000001e-05,
+      "loss": 0.2083,
+      "step": 2650
+    },
+    {
+      "epoch": 0.5999097880018043,
+      "grad_norm": 4.15625,
+      "learning_rate": 1.1136666666666666e-05,
+      "loss": 0.2206,
+      "step": 2660
+    },
+    {
+      "epoch": 0.6021650879566982,
+      "grad_norm": 4.0625,
+      "learning_rate": 1.1103333333333334e-05,
+      "loss": 0.2108,
+      "step": 2670
+    },
+    {
+      "epoch": 0.6044203879115922,
+      "grad_norm": 3.90625,
+      "learning_rate": 1.107e-05,
+      "loss": 0.1931,
+      "step": 2680
+    },
+    {
+      "epoch": 0.6066756878664863,
+      "grad_norm": 4.8125,
+      "learning_rate": 1.1036666666666667e-05,
+      "loss": 0.1909,
+      "step": 2690
+    },
+    {
+      "epoch": 0.6089309878213802,
+      "grad_norm": 3.328125,
+      "learning_rate": 1.1003333333333335e-05,
+      "loss": 0.1994,
+      "step": 2700
+    },
+    {
+      "epoch": 0.6111862877762743,
+      "grad_norm": 3.0625,
+      "learning_rate": 1.097e-05,
+      "loss": 0.1967,
+      "step": 2710
+    },
+    {
+      "epoch": 0.6134415877311682,
+      "grad_norm": 3.546875,
+      "learning_rate": 1.0936666666666666e-05,
+      "loss": 0.2082,
+      "step": 2720
+    },
+    {
+      "epoch": 0.6156968876860622,
+      "grad_norm": 3.03125,
+      "learning_rate": 1.0903333333333335e-05,
+      "loss": 0.2245,
+      "step": 2730
+    },
+    {
+      "epoch": 0.6179521876409563,
+      "grad_norm": 3.25,
+      "learning_rate": 1.0870000000000001e-05,
+      "loss": 0.1893,
+      "step": 2740
+    },
+    {
+      "epoch": 0.6202074875958502,
+      "grad_norm": 3.671875,
+      "learning_rate": 1.0836666666666666e-05,
+      "loss": 0.2133,
+      "step": 2750
+    },
+    {
+      "epoch": 0.6224627875507442,
+      "grad_norm": 3.625,
+      "learning_rate": 1.0803333333333334e-05,
+      "loss": 0.1912,
+      "step": 2760
+    },
+    {
+      "epoch": 0.6247180875056383,
+      "grad_norm": 3.609375,
+      "learning_rate": 1.077e-05,
+      "loss": 0.1967,
+      "step": 2770
+    },
+    {
+      "epoch": 0.6269733874605322,
+      "grad_norm": 3.1875,
+      "learning_rate": 1.0736666666666668e-05,
+      "loss": 0.1858,
+      "step": 2780
+    },
+    {
+      "epoch": 0.6292286874154263,
+      "grad_norm": 3.546875,
+      "learning_rate": 1.0703333333333335e-05,
+      "loss": 0.1995,
+      "step": 2790
+    },
+    {
+      "epoch": 0.6314839873703203,
+      "grad_norm": 4.875,
+      "learning_rate": 1.0670000000000001e-05,
+      "loss": 0.1911,
+      "step": 2800
+    },
+    {
+      "epoch": 0.6337392873252142,
+      "grad_norm": 4.3125,
+      "learning_rate": 1.063666666666667e-05,
+      "loss": 0.1938,
+      "step": 2810
+    },
+    {
+      "epoch": 0.6359945872801083,
+      "grad_norm": 4.625,
+      "learning_rate": 1.0603333333333334e-05,
+      "loss": 0.215,
+      "step": 2820
+    },
+    {
+      "epoch": 0.6382498872350022,
+      "grad_norm": 2.78125,
+      "learning_rate": 1.057e-05,
+      "loss": 0.2065,
+      "step": 2830
+    },
+    {
+      "epoch": 0.6405051871898962,
+      "grad_norm": 3.0625,
+      "learning_rate": 1.0536666666666669e-05,
+      "loss": 0.1796,
+      "step": 2840
+    },
+    {
+      "epoch": 0.6427604871447903,
+      "grad_norm": 3.796875,
+      "learning_rate": 1.0503333333333335e-05,
+      "loss": 0.1766,
+      "step": 2850
+    },
+    {
+      "epoch": 0.6450157870996842,
+      "grad_norm": 4.5,
+      "learning_rate": 1.047e-05,
+      "loss": 0.1652,
+      "step": 2860
+    },
+    {
+      "epoch": 0.6472710870545783,
+      "grad_norm": 3.421875,
+      "learning_rate": 1.0436666666666668e-05,
+      "loss": 0.1858,
+      "step": 2870
+    },
+    {
+      "epoch": 0.6495263870094723,
+      "grad_norm": 3.28125,
+      "learning_rate": 1.0403333333333334e-05,
+      "loss": 0.1756,
+      "step": 2880
+    },
+    {
+      "epoch": 0.6517816869643662,
+      "grad_norm": 3.265625,
+      "learning_rate": 1.037e-05,
+      "loss": 0.176,
+      "step": 2890
+    },
+    {
+      "epoch": 0.6540369869192603,
+      "grad_norm": 3.203125,
+      "learning_rate": 1.0336666666666669e-05,
+      "loss": 0.1903,
+      "step": 2900
+    },
+    {
+      "epoch": 0.6562922868741543,
+      "grad_norm": 4.0,
+      "learning_rate": 1.0303333333333334e-05,
+      "loss": 0.1878,
+      "step": 2910
+    },
+    {
+      "epoch": 0.6585475868290482,
+      "grad_norm": 4.21875,
+      "learning_rate": 1.027e-05,
+      "loss": 0.1806,
+      "step": 2920
+    },
+    {
+      "epoch": 0.6608028867839423,
+      "grad_norm": 3.109375,
+      "learning_rate": 1.0236666666666668e-05,
+      "loss": 0.1777,
+      "step": 2930
+    },
+    {
+      "epoch": 0.6630581867388363,
+      "grad_norm": 4.0625,
+      "learning_rate": 1.0203333333333334e-05,
+      "loss": 0.1851,
+      "step": 2940
+    },
+    {
+      "epoch": 0.6653134866937302,
+      "grad_norm": 2.90625,
+      "learning_rate": 1.017e-05,
+      "loss": 0.1684,
+      "step": 2950
+    },
+    {
+      "epoch": 0.6675687866486243,
+      "grad_norm": 3.625,
+      "learning_rate": 1.0136666666666667e-05,
+      "loss": 0.1687,
+      "step": 2960
+    },
+    {
+      "epoch": 0.6698240866035182,
+      "grad_norm": 3.375,
+      "learning_rate": 1.0103333333333334e-05,
+      "loss": 0.1723,
+      "step": 2970
+    },
+    {
+      "epoch": 0.6720793865584123,
+      "grad_norm": 2.96875,
+      "learning_rate": 1.007e-05,
+      "loss": 0.1795,
+      "step": 2980
+    },
+    {
+      "epoch": 0.6743346865133063,
+      "grad_norm": 3.484375,
+      "learning_rate": 1.0036666666666668e-05,
+      "loss": 0.1718,
+      "step": 2990
+    },
+    {
+      "epoch": 0.6765899864682002,
+      "grad_norm": 3.5625,
+      "learning_rate": 1.0003333333333333e-05,
+      "loss": 0.1691,
+      "step": 3000
+    },
+    {
+      "epoch": 0.6788452864230943,
+      "grad_norm": 3.203125,
+      "learning_rate": 9.970000000000001e-06,
+      "loss": 0.1805,
+      "step": 3010
+    },
+    {
+      "epoch": 0.6811005863779883,
+      "grad_norm": 2.78125,
+      "learning_rate": 9.936666666666668e-06,
+      "loss": 0.1844,
+      "step": 3020
+    },
+    {
+      "epoch": 0.6833558863328822,
+      "grad_norm": 4.21875,
+      "learning_rate": 9.903333333333334e-06,
+      "loss": 0.1612,
+      "step": 3030
+    },
+    {
+      "epoch": 0.6856111862877763,
+      "grad_norm": 3.140625,
+      "learning_rate": 9.87e-06,
+      "loss": 0.1719,
+      "step": 3040
+    },
+    {
+      "epoch": 0.6878664862426703,
+      "grad_norm": 3.78125,
+      "learning_rate": 9.836666666666668e-06,
+      "loss": 0.1639,
+      "step": 3050
+    },
+    {
+      "epoch": 0.6901217861975643,
+      "grad_norm": 3.59375,
+      "learning_rate": 9.803333333333333e-06,
+      "loss": 0.1555,
+      "step": 3060
+    },
+    {
+      "epoch": 0.6923770861524583,
+      "grad_norm": 3.109375,
+      "learning_rate": 9.770000000000001e-06,
+      "loss": 0.1695,
+      "step": 3070
+    },
+    {
+      "epoch": 0.6946323861073522,
+      "grad_norm": 3.203125,
+      "learning_rate": 9.736666666666668e-06,
+      "loss": 0.1684,
+      "step": 3080
+    },
+    {
+      "epoch": 0.6968876860622463,
+      "grad_norm": 3.546875,
+      "learning_rate": 9.703333333333334e-06,
+      "loss": 0.1669,
+      "step": 3090
+    },
+    {
+      "epoch": 0.6991429860171403,
+      "grad_norm": 3.6875,
+      "learning_rate": 9.67e-06,
+      "loss": 0.1789,
+      "step": 3100
+    },
+    {
+      "epoch": 0.7013982859720342,
+      "grad_norm": 3.578125,
+      "learning_rate": 9.636666666666667e-06,
+      "loss": 0.1776,
+      "step": 3110
+    },
+    {
+      "epoch": 0.7036535859269283,
+      "grad_norm": 3.125,
+      "learning_rate": 9.603333333333335e-06,
+      "loss": 0.1561,
+      "step": 3120
+    },
+    {
+      "epoch": 0.7059088858818223,
+      "grad_norm": 3.125,
+      "learning_rate": 9.57e-06,
+      "loss": 0.1609,
+      "step": 3130
+    },
+    {
+      "epoch": 0.7081641858367163,
+      "grad_norm": 3.75,
+      "learning_rate": 9.536666666666668e-06,
+      "loss": 0.1398,
+      "step": 3140
+    },
+    {
+      "epoch": 0.7104194857916103,
+      "grad_norm": 3.3125,
+      "learning_rate": 9.503333333333334e-06,
+      "loss": 0.167,
+      "step": 3150
+    },
+    {
+      "epoch": 0.7126747857465043,
+      "grad_norm": 3.75,
+      "learning_rate": 9.47e-06,
+      "loss": 0.1546,
+      "step": 3160
+    },
+    {
+      "epoch": 0.7149300857013983,
+      "grad_norm": 3.546875,
+      "learning_rate": 9.436666666666667e-06,
+      "loss": 0.1555,
+      "step": 3170
+    },
+    {
+      "epoch": 0.7171853856562923,
+      "grad_norm": 3.15625,
+      "learning_rate": 9.403333333333334e-06,
+      "loss": 0.1766,
+      "step": 3180
+    },
+    {
+      "epoch": 0.7194406856111862,
+      "grad_norm": 3.390625,
+      "learning_rate": 9.370000000000002e-06,
+      "loss": 0.1705,
+      "step": 3190
+    },
+    {
+      "epoch": 0.7216959855660803,
+      "grad_norm": 3.671875,
+      "learning_rate": 9.336666666666666e-06,
+      "loss": 0.1784,
+      "step": 3200
+    },
+    {
+      "epoch": 0.7239512855209743,
+      "grad_norm": 3.125,
+      "learning_rate": 9.303333333333335e-06,
+      "loss": 0.1705,
+      "step": 3210
+    },
+    {
+      "epoch": 0.7262065854758682,
+      "grad_norm": 3.28125,
+      "learning_rate": 9.270000000000001e-06,
+      "loss": 0.1562,
+      "step": 3220
+    },
+    {
+      "epoch": 0.7284618854307623,
+      "grad_norm": 2.96875,
+      "learning_rate": 9.236666666666667e-06,
+      "loss": 0.1421,
+      "step": 3230
+    },
+    {
+      "epoch": 0.7307171853856563,
+      "grad_norm": 3.609375,
+      "learning_rate": 9.203333333333334e-06,
+      "loss": 0.1663,
+      "step": 3240
+    },
+    {
+      "epoch": 0.7329724853405503,
+      "grad_norm": 2.84375,
+      "learning_rate": 9.17e-06,
+      "loss": 0.1729,
+      "step": 3250
+    },
+    {
+      "epoch": 0.7352277852954443,
+      "grad_norm": 2.921875,
+      "learning_rate": 9.136666666666667e-06,
+      "loss": 0.1572,
+      "step": 3260
+    },
+    {
+      "epoch": 0.7374830852503383,
+      "grad_norm": 2.75,
+      "learning_rate": 9.103333333333335e-06,
+      "loss": 0.1574,
+      "step": 3270
+    },
+    {
+      "epoch": 0.7397383852052323,
+      "grad_norm": 4.0,
+      "learning_rate": 9.070000000000001e-06,
+      "loss": 0.158,
+      "step": 3280
+    },
+    {
+      "epoch": 0.7419936851601263,
+      "grad_norm": 3.140625,
+      "learning_rate": 9.036666666666668e-06,
+      "loss": 0.1743,
+      "step": 3290
+    },
+    {
+      "epoch": 0.7442489851150202,
+      "grad_norm": 3.125,
+      "learning_rate": 9.003333333333334e-06,
+      "loss": 0.1492,
+      "step": 3300
+    },
+    {
+      "epoch": 0.7465042850699143,
+      "grad_norm": 3.578125,
+      "learning_rate": 8.97e-06,
+      "loss": 0.1544,
+      "step": 3310
+    },
+    {
+      "epoch": 0.7487595850248083,
+      "grad_norm": 3.046875,
+      "learning_rate": 8.936666666666669e-06,
+      "loss": 0.154,
+      "step": 3320
+    },
+    {
+      "epoch": 0.7510148849797023,
+      "grad_norm": 3.234375,
+      "learning_rate": 8.903333333333333e-06,
+      "loss": 0.1515,
+      "step": 3330
+    },
+    {
+      "epoch": 0.7532701849345963,
+      "grad_norm": 3.234375,
+      "learning_rate": 8.870000000000001e-06,
+      "loss": 0.1601,
+      "step": 3340
+    },
+    {
+      "epoch": 0.7555254848894903,
+      "grad_norm": 5.375,
+      "learning_rate": 8.836666666666668e-06,
+      "loss": 0.1541,
+      "step": 3350
+    },
+    {
+      "epoch": 0.7577807848443843,
+      "grad_norm": 3.0,
+      "learning_rate": 8.803333333333334e-06,
+      "loss": 0.137,
+      "step": 3360
+    },
+    {
+      "epoch": 0.7600360847992783,
+      "grad_norm": 4.3125,
+      "learning_rate": 8.77e-06,
+      "loss": 0.1518,
+      "step": 3370
+    },
+    {
+      "epoch": 0.7622913847541724,
+      "grad_norm": 2.96875,
+      "learning_rate": 8.736666666666667e-06,
+      "loss": 0.1557,
+      "step": 3380
+    },
+    {
+      "epoch": 0.7645466847090663,
+      "grad_norm": 3.171875,
+      "learning_rate": 8.703333333333334e-06,
+      "loss": 0.1459,
+      "step": 3390
+    },
+    {
+      "epoch": 0.7668019846639603,
+      "grad_norm": 3.390625,
+      "learning_rate": 8.67e-06,
+      "loss": 0.1457,
+      "step": 3400
+    },
+    {
+      "epoch": 0.7690572846188543,
+      "grad_norm": 2.828125,
+      "learning_rate": 8.636666666666668e-06,
+      "loss": 0.1437,
+      "step": 3410
+    },
+    {
+      "epoch": 0.7713125845737483,
+      "grad_norm": 3.53125,
+      "learning_rate": 8.603333333333333e-06,
+      "loss": 0.1575,
+      "step": 3420
+    },
+    {
+      "epoch": 0.7735678845286423,
+      "grad_norm": 2.765625,
+      "learning_rate": 8.570000000000001e-06,
+      "loss": 0.1405,
+      "step": 3430
+    },
+    {
+      "epoch": 0.7758231844835363,
+      "grad_norm": 2.46875,
+      "learning_rate": 8.536666666666667e-06,
+      "loss": 0.1479,
+      "step": 3440
+    },
+    {
+      "epoch": 0.7780784844384303,
+      "grad_norm": 3.140625,
+      "learning_rate": 8.503333333333334e-06,
+      "loss": 0.1513,
+      "step": 3450
+    },
+    {
+      "epoch": 0.7803337843933243,
+      "grad_norm": 3.3125,
+      "learning_rate": 8.47e-06,
+      "loss": 0.1437,
+      "step": 3460
+    },
+    {
+      "epoch": 0.7825890843482183,
+      "grad_norm": 2.875,
+      "learning_rate": 8.436666666666667e-06,
+      "loss": 0.1434,
+      "step": 3470
+    },
+    {
+      "epoch": 0.7848443843031123,
+      "grad_norm": 2.34375,
+      "learning_rate": 8.403333333333335e-06,
+      "loss": 0.1442,
+      "step": 3480
+    },
+    {
+      "epoch": 0.7870996842580064,
+      "grad_norm": 3.578125,
+      "learning_rate": 8.370000000000001e-06,
+      "loss": 0.1449,
+      "step": 3490
+    },
+    {
+      "epoch": 0.7893549842129003,
+      "grad_norm": 3.453125,
+      "learning_rate": 8.336666666666668e-06,
+      "loss": 0.151,
+      "step": 3500
+    },
+    {
+      "epoch": 0.7916102841677943,
+      "grad_norm": 2.796875,
+      "learning_rate": 8.303333333333334e-06,
+      "loss": 0.1407,
+      "step": 3510
+    },
+    {
+      "epoch": 0.7938655841226884,
+      "grad_norm": 3.015625,
+      "learning_rate": 8.27e-06,
+      "loss": 0.1566,
+      "step": 3520
+    },
+    {
+      "epoch": 0.7961208840775823,
+      "grad_norm": 3.328125,
+      "learning_rate": 8.236666666666667e-06,
+      "loss": 0.1574,
+      "step": 3530
+    },
+    {
+      "epoch": 0.7983761840324763,
+      "grad_norm": 2.78125,
+      "learning_rate": 8.203333333333335e-06,
+      "loss": 0.1434,
+      "step": 3540
+    },
+    {
+      "epoch": 0.8006314839873703,
+      "grad_norm": 2.671875,
+      "learning_rate": 8.17e-06,
+      "loss": 0.1379,
+      "step": 3550
+    },
+    {
+      "epoch": 0.8028867839422643,
+      "grad_norm": 2.984375,
+      "learning_rate": 8.136666666666668e-06,
+      "loss": 0.1685,
+      "step": 3560
+    },
+    {
+      "epoch": 0.8051420838971584,
+      "grad_norm": 2.875,
+      "learning_rate": 8.103333333333334e-06,
+      "loss": 0.1564,
+      "step": 3570
+    },
+    {
+      "epoch": 0.8073973838520523,
+      "grad_norm": 3.765625,
+      "learning_rate": 8.07e-06,
+      "loss": 0.1399,
+      "step": 3580
+    },
+    {
+      "epoch": 0.8096526838069463,
+      "grad_norm": 3.71875,
+      "learning_rate": 8.036666666666667e-06,
+      "loss": 0.1422,
+      "step": 3590
+    },
+    {
+      "epoch": 0.8119079837618404,
+      "grad_norm": 3.015625,
+      "learning_rate": 8.003333333333334e-06,
+      "loss": 0.1439,
+      "step": 3600
+    },
+    {
+      "epoch": 0.8141632837167343,
+      "grad_norm": 3.3125,
+      "learning_rate": 7.970000000000002e-06,
+      "loss": 0.1473,
+      "step": 3610
+    },
+    {
+      "epoch": 0.8164185836716283,
+      "grad_norm": 3.484375,
+      "learning_rate": 7.936666666666666e-06,
+      "loss": 0.1598,
+      "step": 3620
+    },
+    {
+      "epoch": 0.8186738836265224,
+      "grad_norm": 3.671875,
+      "learning_rate": 7.903333333333334e-06,
+      "loss": 0.1431,
+      "step": 3630
+    },
+    {
+      "epoch": 0.8209291835814163,
+      "grad_norm": 3.375,
+      "learning_rate": 7.870000000000001e-06,
+      "loss": 0.1338,
+      "step": 3640
+    },
+    {
+      "epoch": 0.8231844835363104,
+      "grad_norm": 4.34375,
+      "learning_rate": 7.836666666666667e-06,
+      "loss": 0.1437,
+      "step": 3650
+    },
+    {
+      "epoch": 0.8254397834912043,
+      "grad_norm": 4.5625,
+      "learning_rate": 7.803333333333334e-06,
+      "loss": 0.1383,
+      "step": 3660
+    },
+    {
+      "epoch": 0.8276950834460983,
+      "grad_norm": 2.84375,
+      "learning_rate": 7.77e-06,
+      "loss": 0.1452,
+      "step": 3670
+    },
+    {
+      "epoch": 0.8299503834009924,
+      "grad_norm": 3.6875,
+      "learning_rate": 7.736666666666667e-06,
+      "loss": 0.1566,
+      "step": 3680
+    },
+    {
+      "epoch": 0.8322056833558863,
+      "grad_norm": 3.4375,
+      "learning_rate": 7.703333333333333e-06,
+      "loss": 0.1416,
+      "step": 3690
+    },
+    {
+      "epoch": 0.8344609833107803,
+      "grad_norm": 3.21875,
+      "learning_rate": 7.670000000000001e-06,
+      "loss": 0.1296,
+      "step": 3700
+    },
+    {
+      "epoch": 0.8367162832656744,
+      "grad_norm": 2.78125,
+      "learning_rate": 7.636666666666668e-06,
+      "loss": 0.1422,
+      "step": 3710
+    },
+    {
+      "epoch": 0.8389715832205683,
+      "grad_norm": 3.765625,
+      "learning_rate": 7.603333333333334e-06,
+      "loss": 0.1448,
+      "step": 3720
+    },
+    {
+      "epoch": 0.8412268831754623,
+      "grad_norm": 2.859375,
+      "learning_rate": 7.57e-06,
+      "loss": 0.135,
+      "step": 3730
+    },
+    {
+      "epoch": 0.8434821831303564,
+      "grad_norm": 3.0,
+      "learning_rate": 7.536666666666668e-06,
+      "loss": 0.1428,
+      "step": 3740
+    },
+    {
+      "epoch": 0.8457374830852503,
+      "grad_norm": 3.28125,
+      "learning_rate": 7.503333333333333e-06,
+      "loss": 0.138,
+      "step": 3750
+    },
+    {
+      "epoch": 0.8479927830401444,
+      "grad_norm": 3.375,
+      "learning_rate": 7.4700000000000005e-06,
+      "loss": 0.125,
+      "step": 3760
+    },
+    {
+      "epoch": 0.8502480829950383,
+      "grad_norm": 2.296875,
+      "learning_rate": 7.436666666666668e-06,
+      "loss": 0.1317,
+      "step": 3770
+    },
+    {
+      "epoch": 0.8525033829499323,
+      "grad_norm": 3.296875,
+      "learning_rate": 7.403333333333333e-06,
+      "loss": 0.1258,
+      "step": 3780
+    },
+    {
+      "epoch": 0.8547586829048264,
+      "grad_norm": 2.671875,
+      "learning_rate": 7.370000000000001e-06,
+      "loss": 0.1403,
+      "step": 3790
+    },
+    {
+      "epoch": 0.8570139828597203,
+      "grad_norm": 4.03125,
+      "learning_rate": 7.336666666666668e-06,
+      "loss": 0.1466,
+      "step": 3800
+    },
+    {
+      "epoch": 0.8592692828146143,
+      "grad_norm": 2.546875,
+      "learning_rate": 7.3033333333333334e-06,
+      "loss": 0.1262,
+      "step": 3810
+    },
+    {
+      "epoch": 0.8615245827695084,
+      "grad_norm": 1.9921875,
+      "learning_rate": 7.270000000000001e-06,
+      "loss": 0.1427,
+      "step": 3820
+    },
+    {
+      "epoch": 0.8637798827244023,
+      "grad_norm": 3.546875,
+      "learning_rate": 7.236666666666667e-06,
+      "loss": 0.1193,
+      "step": 3830
+    },
+    {
+      "epoch": 0.8660351826792964,
+      "grad_norm": 4.1875,
+      "learning_rate": 7.203333333333334e-06,
+      "loss": 0.1337,
+      "step": 3840
+    },
+    {
+      "epoch": 0.8682904826341904,
+      "grad_norm": 2.78125,
+      "learning_rate": 7.17e-06,
+      "loss": 0.1472,
+      "step": 3850
+    },
+    {
+      "epoch": 0.8705457825890843,
+      "grad_norm": 2.75,
+      "learning_rate": 7.136666666666667e-06,
+      "loss": 0.1531,
+      "step": 3860
+    },
+    {
+      "epoch": 0.8728010825439784,
+      "grad_norm": 2.296875,
+      "learning_rate": 7.1033333333333345e-06,
+      "loss": 0.1334,
+      "step": 3870
+    },
+    {
+      "epoch": 0.8750563824988723,
+      "grad_norm": 2.765625,
+      "learning_rate": 7.07e-06,
+      "loss": 0.1339,
+      "step": 3880
+    },
+    {
+      "epoch": 0.8773116824537663,
+      "grad_norm": 3.234375,
+      "learning_rate": 7.036666666666667e-06,
+      "loss": 0.1369,
+      "step": 3890
+    },
+    {
+      "epoch": 0.8795669824086604,
+      "grad_norm": 3.765625,
+      "learning_rate": 7.003333333333335e-06,
+      "loss": 0.1214,
+      "step": 3900
+    },
+    {
+      "epoch": 0.8818222823635543,
+      "grad_norm": 2.734375,
+      "learning_rate": 6.97e-06,
+      "loss": 0.1387,
+      "step": 3910
+    },
+    {
+      "epoch": 0.8840775823184484,
+      "grad_norm": 3.125,
+      "learning_rate": 6.9366666666666675e-06,
+      "loss": 0.1469,
+      "step": 3920
+    },
+    {
+      "epoch": 0.8863328822733424,
+      "grad_norm": 2.5,
+      "learning_rate": 6.903333333333334e-06,
+      "loss": 0.1432,
+      "step": 3930
+    },
+    {
+      "epoch": 0.8885881822282363,
+      "grad_norm": 2.984375,
+      "learning_rate": 6.870000000000001e-06,
+      "loss": 0.1337,
+      "step": 3940
+    },
+    {
+      "epoch": 0.8908434821831304,
+      "grad_norm": 2.6875,
+      "learning_rate": 6.836666666666667e-06,
+      "loss": 0.131,
+      "step": 3950
+    },
+    {
+      "epoch": 0.8930987821380244,
+      "grad_norm": 2.78125,
+      "learning_rate": 6.803333333333334e-06,
+      "loss": 0.1385,
+      "step": 3960
+    },
+    {
+      "epoch": 0.8953540820929183,
+      "grad_norm": 2.1875,
+      "learning_rate": 6.770000000000001e-06,
+      "loss": 0.1379,
+      "step": 3970
+    },
+    {
+      "epoch": 0.8976093820478124,
+      "grad_norm": 2.640625,
+      "learning_rate": 6.736666666666667e-06,
+      "loss": 0.1307,
+      "step": 3980
+    },
+    {
+      "epoch": 0.8998646820027063,
+      "grad_norm": 3.109375,
+      "learning_rate": 6.703333333333334e-06,
+      "loss": 0.1199,
+      "step": 3990
+    },
+    {
+      "epoch": 0.9021199819576003,
+      "grad_norm": 3.109375,
+      "learning_rate": 6.6700000000000005e-06,
+      "loss": 0.1262,
+      "step": 4000
+    },
+    {
+      "epoch": 0.9043752819124944,
+      "grad_norm": 3.453125,
+      "learning_rate": 6.636666666666667e-06,
+      "loss": 0.1275,
+      "step": 4010
+    },
+    {
+      "epoch": 0.9066305818673883,
+      "grad_norm": 3.21875,
+      "learning_rate": 6.603333333333334e-06,
+      "loss": 0.1321,
+      "step": 4020
+    },
+    {
+      "epoch": 0.9088858818222824,
+      "grad_norm": 2.71875,
+      "learning_rate": 6.570000000000001e-06,
+      "loss": 0.1275,
+      "step": 4030
+    },
+    {
+      "epoch": 0.9111411817771764,
+      "grad_norm": 3.375,
+      "learning_rate": 6.536666666666667e-06,
+      "loss": 0.1068,
+      "step": 4040
+    },
+    {
+      "epoch": 0.9133964817320703,
+      "grad_norm": 2.984375,
+      "learning_rate": 6.5033333333333335e-06,
+      "loss": 0.1214,
+      "step": 4050
+    },
+    {
+      "epoch": 0.9156517816869644,
+      "grad_norm": 3.28125,
+      "learning_rate": 6.470000000000001e-06,
+      "loss": 0.1306,
+      "step": 4060
+    },
+    {
+      "epoch": 0.9179070816418584,
+      "grad_norm": 3.40625,
+      "learning_rate": 6.436666666666668e-06,
+      "loss": 0.1331,
+      "step": 4070
+    },
+    {
+      "epoch": 0.9201623815967523,
+      "grad_norm": 3.578125,
+      "learning_rate": 6.403333333333334e-06,
+      "loss": 0.1334,
+      "step": 4080
+    },
+    {
+      "epoch": 0.9224176815516464,
+      "grad_norm": 2.40625,
+      "learning_rate": 6.370000000000001e-06,
+      "loss": 0.1352,
+      "step": 4090
+    },
+    {
+      "epoch": 0.9246729815065403,
+      "grad_norm": 2.734375,
+      "learning_rate": 6.336666666666667e-06,
+      "loss": 0.1138,
+      "step": 4100
+    },
+    {
+      "epoch": 0.9269282814614344,
+      "grad_norm": 2.984375,
+      "learning_rate": 6.303333333333334e-06,
+      "loss": 0.1163,
+      "step": 4110
+    },
+    {
+      "epoch": 0.9291835814163284,
+      "grad_norm": 3.21875,
+      "learning_rate": 6.27e-06,
+      "loss": 0.1235,
+      "step": 4120
+    },
+    {
+      "epoch": 0.9314388813712223,
+      "grad_norm": 3.40625,
+      "learning_rate": 6.236666666666667e-06,
+      "loss": 0.128,
+      "step": 4130
+    },
+    {
+      "epoch": 0.9336941813261164,
+      "grad_norm": 2.828125,
+      "learning_rate": 6.203333333333334e-06,
+      "loss": 0.1254,
+      "step": 4140
+    },
+    {
+      "epoch": 0.9359494812810104,
+      "grad_norm": 2.78125,
+      "learning_rate": 6.17e-06,
+      "loss": 0.1272,
+      "step": 4150
+    },
+    {
+      "epoch": 0.9382047812359043,
+      "grad_norm": 2.390625,
+      "learning_rate": 6.1366666666666675e-06,
+      "loss": 0.1294,
+      "step": 4160
+    },
+    {
+      "epoch": 0.9404600811907984,
+      "grad_norm": 2.515625,
+      "learning_rate": 6.103333333333333e-06,
+      "loss": 0.1231,
+      "step": 4170
+    },
+    {
+      "epoch": 0.9427153811456924,
+      "grad_norm": 2.6875,
+      "learning_rate": 6.07e-06,
+      "loss": 0.1424,
+      "step": 4180
+    },
+    {
+      "epoch": 0.9449706811005864,
+      "grad_norm": 2.71875,
+      "learning_rate": 6.036666666666668e-06,
+      "loss": 0.1214,
+      "step": 4190
+    },
+    {
+      "epoch": 0.9472259810554804,
+      "grad_norm": 3.15625,
+      "learning_rate": 6.003333333333334e-06,
+      "loss": 0.1147,
+      "step": 4200
+    },
+    {
+      "epoch": 0.9494812810103744,
+      "grad_norm": 2.546875,
+      "learning_rate": 5.9700000000000004e-06,
+      "loss": 0.1256,
+      "step": 4210
+    },
+    {
+      "epoch": 0.9517365809652684,
+      "grad_norm": 2.796875,
+      "learning_rate": 5.936666666666667e-06,
+      "loss": 0.1232,
+      "step": 4220
+    },
+    {
+      "epoch": 0.9539918809201624,
+      "grad_norm": 2.765625,
+      "learning_rate": 5.903333333333334e-06,
+      "loss": 0.1103,
+      "step": 4230
+    },
+    {
+      "epoch": 0.9562471808750563,
+      "grad_norm": 4.09375,
+      "learning_rate": 5.8700000000000005e-06,
+      "loss": 0.1294,
+      "step": 4240
+    },
+    {
+      "epoch": 0.9585024808299504,
+      "grad_norm": 2.46875,
+      "learning_rate": 5.836666666666667e-06,
+      "loss": 0.1243,
+      "step": 4250
+    },
+    {
+      "epoch": 0.9607577807848444,
+      "grad_norm": 2.4375,
+      "learning_rate": 5.803333333333334e-06,
+      "loss": 0.1165,
+      "step": 4260
+    },
+    {
+      "epoch": 0.9630130807397383,
+      "grad_norm": 3.4375,
+      "learning_rate": 5.77e-06,
+      "loss": 0.1192,
+      "step": 4270
+    },
+    {
+      "epoch": 0.9652683806946324,
+      "grad_norm": 2.28125,
+      "learning_rate": 5.736666666666667e-06,
+      "loss": 0.1175,
+      "step": 4280
+    },
+    {
+      "epoch": 0.9675236806495264,
+      "grad_norm": 2.328125,
+      "learning_rate": 5.703333333333334e-06,
+      "loss": 0.1214,
+      "step": 4290
+    },
+    {
+      "epoch": 0.9697789806044204,
+      "grad_norm": 2.765625,
+      "learning_rate": 5.67e-06,
+      "loss": 0.1162,
+      "step": 4300
+    },
+    {
+      "epoch": 0.9720342805593144,
+      "grad_norm": 2.765625,
+      "learning_rate": 5.636666666666667e-06,
+      "loss": 0.1221,
+      "step": 4310
+    },
+    {
+      "epoch": 0.9742895805142084,
+      "grad_norm": 2.828125,
+      "learning_rate": 5.603333333333334e-06,
+      "loss": 0.1135,
+      "step": 4320
+    },
+    {
+      "epoch": 0.9765448804691024,
+      "grad_norm": 2.40625,
+      "learning_rate": 5.570000000000001e-06,
+      "loss": 0.1137,
+      "step": 4330
+    },
+    {
+      "epoch": 0.9788001804239964,
+      "grad_norm": 2.71875,
+      "learning_rate": 5.5366666666666665e-06,
+      "loss": 0.1209,
+      "step": 4340
+    },
+    {
+      "epoch": 0.9810554803788903,
+      "grad_norm": 2.203125,
+      "learning_rate": 5.503333333333334e-06,
+      "loss": 0.1373,
+      "step": 4350
+    },
+    {
+      "epoch": 0.9833107803337844,
+      "grad_norm": 2.640625,
+      "learning_rate": 5.470000000000001e-06,
+      "loss": 0.1196,
+      "step": 4360
+    },
+    {
+      "epoch": 0.9855660802886784,
+      "grad_norm": 3.0625,
+      "learning_rate": 5.4366666666666666e-06,
+      "loss": 0.1194,
+      "step": 4370
+    },
+    {
+      "epoch": 0.9878213802435724,
+      "grad_norm": 3.3125,
+      "learning_rate": 5.403333333333334e-06,
+      "loss": 0.1098,
+      "step": 4380
+    },
+    {
+      "epoch": 0.9900766801984664,
+      "grad_norm": 2.59375,
+      "learning_rate": 5.370000000000001e-06,
+      "loss": 0.1192,
+      "step": 4390
+    },
+    {
+      "epoch": 0.9923319801533604,
+      "grad_norm": 2.734375,
+      "learning_rate": 5.336666666666667e-06,
+      "loss": 0.1077,
+      "step": 4400
+    },
+    {
+      "epoch": 0.9945872801082544,
+      "grad_norm": 2.546875,
+      "learning_rate": 5.303333333333334e-06,
+      "loss": 0.126,
+      "step": 4410
+    },
+    {
+      "epoch": 0.9968425800631484,
+      "grad_norm": 2.828125,
+      "learning_rate": 5.27e-06,
+      "loss": 0.1223,
+      "step": 4420
+    },
+    {
+      "epoch": 0.9990978800180425,
+      "grad_norm": 3.515625,
+      "learning_rate": 5.236666666666667e-06,
+      "loss": 0.1176,
+      "step": 4430
+    },
+    {
+      "epoch": 1.0013531799729365,
+      "grad_norm": 2.640625,
+      "learning_rate": 5.203333333333333e-06,
+      "loss": 0.1064,
+      "step": 4440
+    },
+    {
+      "epoch": 1.0036084799278304,
+      "grad_norm": 1.5625,
+      "learning_rate": 5.1700000000000005e-06,
+      "loss": 0.1128,
+      "step": 4450
+    },
+    {
+      "epoch": 1.0058637798827244,
+      "grad_norm": 2.078125,
+      "learning_rate": 5.136666666666668e-06,
+      "loss": 0.0987,
+      "step": 4460
+    },
+    {
+      "epoch": 1.0081190798376185,
+      "grad_norm": 2.359375,
+      "learning_rate": 5.103333333333333e-06,
+      "loss": 0.1084,
+      "step": 4470
+    },
+    {
+      "epoch": 1.0103743797925124,
+      "grad_norm": 2.0,
+      "learning_rate": 5.070000000000001e-06,
+      "loss": 0.1035,
+      "step": 4480
+    },
+    {
+      "epoch": 1.0126296797474064,
+      "grad_norm": 2.234375,
+      "learning_rate": 5.036666666666668e-06,
+      "loss": 0.1083,
+      "step": 4490
+    },
+    {
+      "epoch": 1.0148849797023005,
+      "grad_norm": 2.359375,
+      "learning_rate": 5.0033333333333334e-06,
+      "loss": 0.117,
+      "step": 4500
+    },
+    {
+      "epoch": 1.0171402796571944,
+      "grad_norm": 3.234375,
+      "learning_rate": 4.970000000000001e-06,
+      "loss": 0.0979,
+      "step": 4510
+    },
+    {
+      "epoch": 1.0193955796120884,
+      "grad_norm": 1.9765625,
+      "learning_rate": 4.936666666666667e-06,
+      "loss": 0.0954,
+      "step": 4520
+    },
+    {
+      "epoch": 1.0216508795669823,
+      "grad_norm": 2.890625,
+      "learning_rate": 4.9033333333333335e-06,
+      "loss": 0.0957,
+      "step": 4530
+    },
+    {
+      "epoch": 1.0239061795218765,
+      "grad_norm": 3.046875,
+      "learning_rate": 4.87e-06,
+      "loss": 0.1065,
+      "step": 4540
+    },
+    {
+      "epoch": 1.0261614794767704,
+      "grad_norm": 2.046875,
+      "learning_rate": 4.836666666666667e-06,
+      "loss": 0.0878,
+      "step": 4550
+    },
+    {
+      "epoch": 1.0284167794316643,
+      "grad_norm": 2.390625,
+      "learning_rate": 4.803333333333334e-06,
+      "loss": 0.1011,
+      "step": 4560
+    },
+    {
+      "epoch": 1.0306720793865585,
+      "grad_norm": 2.828125,
+      "learning_rate": 4.77e-06,
+      "loss": 0.0977,
+      "step": 4570
+    },
+    {
+      "epoch": 1.0329273793414524,
+      "grad_norm": 2.59375,
+      "learning_rate": 4.736666666666667e-06,
+      "loss": 0.1086,
+      "step": 4580
+    },
+    {
+      "epoch": 1.0351826792963463,
+      "grad_norm": 2.203125,
+      "learning_rate": 4.703333333333334e-06,
+      "loss": 0.1006,
+      "step": 4590
+    },
+    {
+      "epoch": 1.0374379792512405,
+      "grad_norm": 3.65625,
+      "learning_rate": 4.670000000000001e-06,
+      "loss": 0.1144,
+      "step": 4600
+    },
+    {
+      "epoch": 1.0396932792061344,
+      "grad_norm": 2.40625,
+      "learning_rate": 4.6366666666666674e-06,
+      "loss": 0.101,
+      "step": 4610
+    },
+    {
+      "epoch": 1.0419485791610283,
+      "grad_norm": 2.171875,
+      "learning_rate": 4.603333333333334e-06,
+      "loss": 0.0841,
+      "step": 4620
+    },
+    {
+      "epoch": 1.0442038791159225,
+      "grad_norm": 3.921875,
+      "learning_rate": 4.57e-06,
+      "loss": 0.1046,
+      "step": 4630
+    },
+    {
+      "epoch": 1.0464591790708164,
+      "grad_norm": 2.4375,
+      "learning_rate": 4.536666666666667e-06,
+      "loss": 0.0975,
+      "step": 4640
+    },
+    {
+      "epoch": 1.0487144790257104,
+      "grad_norm": 3.171875,
+      "learning_rate": 4.503333333333333e-06,
+      "loss": 0.0955,
+      "step": 4650
+    },
+    {
+      "epoch": 1.0509697789806045,
+      "grad_norm": 2.546875,
+      "learning_rate": 4.47e-06,
+      "loss": 0.1083,
+      "step": 4660
+    },
+    {
+      "epoch": 1.0532250789354984,
+      "grad_norm": 2.078125,
+      "learning_rate": 4.436666666666667e-06,
+      "loss": 0.1139,
+      "step": 4670
+    },
+    {
+      "epoch": 1.0554803788903924,
+      "grad_norm": 2.421875,
+      "learning_rate": 4.403333333333334e-06,
+      "loss": 0.1052,
+      "step": 4680
+    },
+    {
+      "epoch": 1.0577356788452865,
+      "grad_norm": 2.09375,
+      "learning_rate": 4.3700000000000005e-06,
+      "loss": 0.0956,
+      "step": 4690
+    },
+    {
+      "epoch": 1.0599909788001805,
+      "grad_norm": 2.578125,
+      "learning_rate": 4.336666666666667e-06,
+      "loss": 0.0991,
+      "step": 4700
+    },
+    {
+      "epoch": 1.0622462787550744,
+      "grad_norm": 2.15625,
+      "learning_rate": 4.303333333333334e-06,
+      "loss": 0.1256,
+      "step": 4710
+    },
+    {
+      "epoch": 1.0645015787099683,
+      "grad_norm": 2.34375,
+      "learning_rate": 4.270000000000001e-06,
+      "loss": 0.1075,
+      "step": 4720
+    },
+    {
+      "epoch": 1.0667568786648625,
+      "grad_norm": 2.234375,
+      "learning_rate": 4.236666666666667e-06,
+      "loss": 0.0935,
+      "step": 4730
+    },
+    {
+      "epoch": 1.0690121786197564,
+      "grad_norm": 1.78125,
+      "learning_rate": 4.2033333333333335e-06,
+      "loss": 0.1012,
+      "step": 4740
+    },
+    {
+      "epoch": 1.0712674785746503,
+      "grad_norm": 2.0625,
+      "learning_rate": 4.17e-06,
+      "loss": 0.1035,
+      "step": 4750
+    },
+    {
+      "epoch": 1.0735227785295445,
+      "grad_norm": 3.328125,
+      "learning_rate": 4.136666666666667e-06,
+      "loss": 0.1075,
+      "step": 4760
+    },
+    {
+      "epoch": 1.0757780784844384,
+      "grad_norm": 1.9296875,
+      "learning_rate": 4.1033333333333336e-06,
+      "loss": 0.1054,
+      "step": 4770
+    },
+    {
+      "epoch": 1.0780333784393323,
+      "grad_norm": 2.265625,
+      "learning_rate": 4.07e-06,
+      "loss": 0.0883,
+      "step": 4780
+    },
+    {
+      "epoch": 1.0802886783942265,
+      "grad_norm": 2.390625,
+      "learning_rate": 4.036666666666667e-06,
+      "loss": 0.0988,
+      "step": 4790
+    },
+    {
+      "epoch": 1.0825439783491204,
+      "grad_norm": 3.078125,
+      "learning_rate": 4.003333333333334e-06,
+      "loss": 0.1047,
+      "step": 4800
+    },
+    {
+      "epoch": 1.0847992783040143,
+      "grad_norm": 2.84375,
+      "learning_rate": 3.97e-06,
+      "loss": 0.123,
+      "step": 4810
+    },
+    {
+      "epoch": 1.0870545782589085,
+      "grad_norm": 2.671875,
+      "learning_rate": 3.936666666666667e-06,
+      "loss": 0.0982,
+      "step": 4820
+    },
+    {
+      "epoch": 1.0893098782138024,
+      "grad_norm": 2.515625,
+      "learning_rate": 3.903333333333334e-06,
+      "loss": 0.1112,
+      "step": 4830
+    },
+    {
+      "epoch": 1.0915651781686964,
+      "grad_norm": 2.59375,
+      "learning_rate": 3.87e-06,
+      "loss": 0.119,
+      "step": 4840
+    },
+    {
+      "epoch": 1.0938204781235905,
+      "grad_norm": 1.9765625,
+      "learning_rate": 3.836666666666667e-06,
+      "loss": 0.0939,
+      "step": 4850
+    },
+    {
+      "epoch": 1.0960757780784844,
+      "grad_norm": 2.734375,
+      "learning_rate": 3.803333333333334e-06,
+      "loss": 0.0933,
+      "step": 4860
+    },
+    {
+      "epoch": 1.0983310780333784,
+      "grad_norm": 3.265625,
+      "learning_rate": 3.7700000000000003e-06,
+      "loss": 0.0983,
+      "step": 4870
+    },
+    {
+      "epoch": 1.1005863779882725,
+      "grad_norm": 1.8203125,
+      "learning_rate": 3.7366666666666667e-06,
+      "loss": 0.1099,
+      "step": 4880
+    },
+    {
+      "epoch": 1.1028416779431665,
+      "grad_norm": 2.203125,
+      "learning_rate": 3.7033333333333336e-06,
+      "loss": 0.0952,
+      "step": 4890
+    },
+    {
+      "epoch": 1.1050969778980604,
+      "grad_norm": 2.0625,
+      "learning_rate": 3.6700000000000004e-06,
+      "loss": 0.0789,
+      "step": 4900
+    },
+    {
+      "epoch": 1.1073522778529545,
+      "grad_norm": 2.234375,
+      "learning_rate": 3.6366666666666673e-06,
+      "loss": 0.1048,
+      "step": 4910
+    },
+    {
+      "epoch": 1.1096075778078485,
+      "grad_norm": 2.765625,
+      "learning_rate": 3.6033333333333337e-06,
+      "loss": 0.1165,
+      "step": 4920
+    },
+    {
+      "epoch": 1.1118628777627424,
+      "grad_norm": 3.46875,
+      "learning_rate": 3.57e-06,
+      "loss": 0.1013,
+      "step": 4930
+    },
+    {
+      "epoch": 1.1141181777176365,
+      "grad_norm": 2.609375,
+      "learning_rate": 3.536666666666667e-06,
+      "loss": 0.1291,
+      "step": 4940
+    },
+    {
+      "epoch": 1.1163734776725305,
+      "grad_norm": 2.3125,
+      "learning_rate": 3.5033333333333334e-06,
+      "loss": 0.1018,
+      "step": 4950
+    },
+    {
+      "epoch": 1.1186287776274244,
+      "grad_norm": 2.890625,
+      "learning_rate": 3.4700000000000002e-06,
+      "loss": 0.1039,
+      "step": 4960
+    },
+    {
+      "epoch": 1.1208840775823186,
+      "grad_norm": 2.65625,
+      "learning_rate": 3.436666666666667e-06,
+      "loss": 0.0958,
+      "step": 4970
+    },
+    {
+      "epoch": 1.1231393775372125,
+      "grad_norm": 2.140625,
+      "learning_rate": 3.4033333333333335e-06,
+      "loss": 0.0811,
+      "step": 4980
+    },
+    {
+      "epoch": 1.1253946774921064,
+      "grad_norm": 2.078125,
+      "learning_rate": 3.3700000000000003e-06,
+      "loss": 0.1002,
+      "step": 4990
+    },
+    {
+      "epoch": 1.1276499774470006,
+      "grad_norm": 2.53125,
+      "learning_rate": 3.3366666666666668e-06,
+      "loss": 0.1201,
+      "step": 5000
+    },
+    {
+      "epoch": 1.1299052774018945,
+      "grad_norm": 2.109375,
+      "learning_rate": 3.303333333333333e-06,
+      "loss": 0.1172,
+      "step": 5010
+    },
+    {
+      "epoch": 1.1321605773567884,
+      "grad_norm": 2.109375,
+      "learning_rate": 3.2700000000000005e-06,
+      "loss": 0.1013,
+      "step": 5020
+    },
+    {
+      "epoch": 1.1344158773116824,
+      "grad_norm": 2.859375,
+      "learning_rate": 3.236666666666667e-06,
+      "loss": 0.0815,
+      "step": 5030
+    },
+    {
+      "epoch": 1.1366711772665765,
+      "grad_norm": 1.859375,
+      "learning_rate": 3.2033333333333337e-06,
+      "loss": 0.1105,
+      "step": 5040
+    },
+    {
+      "epoch": 1.1389264772214704,
+      "grad_norm": 2.078125,
+      "learning_rate": 3.17e-06,
+      "loss": 0.1004,
+      "step": 5050
+    },
+    {
+      "epoch": 1.1411817771763644,
+      "grad_norm": 2.515625,
+      "learning_rate": 3.1366666666666666e-06,
+      "loss": 0.0956,
+      "step": 5060
+    },
+    {
+      "epoch": 1.1434370771312585,
+      "grad_norm": 2.234375,
+      "learning_rate": 3.103333333333334e-06,
+      "loss": 0.0966,
+      "step": 5070
+    },
+    {
+      "epoch": 1.1456923770861525,
+      "grad_norm": 1.671875,
+      "learning_rate": 3.0700000000000003e-06,
+      "loss": 0.1093,
+      "step": 5080
+    },
+    {
+      "epoch": 1.1479476770410464,
+      "grad_norm": 1.8984375,
+      "learning_rate": 3.0366666666666667e-06,
+      "loss": 0.1048,
+      "step": 5090
+    },
+    {
+      "epoch": 1.1502029769959405,
+      "grad_norm": 2.46875,
+      "learning_rate": 3.0033333333333335e-06,
+      "loss": 0.096,
+      "step": 5100
+    },
+    {
+      "epoch": 1.1524582769508345,
+      "grad_norm": 2.1875,
+      "learning_rate": 2.97e-06,
+      "loss": 0.1086,
+      "step": 5110
+    },
+    {
+      "epoch": 1.1547135769057284,
+      "grad_norm": 2.265625,
+      "learning_rate": 2.936666666666667e-06,
+      "loss": 0.107,
+      "step": 5120
+    },
+    {
+      "epoch": 1.1569688768606226,
+      "grad_norm": 2.359375,
+      "learning_rate": 2.9033333333333336e-06,
+      "loss": 0.101,
+      "step": 5130
+    },
+    {
+      "epoch": 1.1592241768155165,
+      "grad_norm": 1.9140625,
+      "learning_rate": 2.87e-06,
+      "loss": 0.0915,
+      "step": 5140
+    },
+    {
+      "epoch": 1.1614794767704104,
+      "grad_norm": 2.328125,
+      "learning_rate": 2.836666666666667e-06,
+      "loss": 0.1138,
+      "step": 5150
+    },
+    {
+      "epoch": 1.1637347767253043,
+      "grad_norm": 2.328125,
+      "learning_rate": 2.8033333333333333e-06,
+      "loss": 0.1046,
+      "step": 5160
+    },
+    {
+      "epoch": 1.1659900766801985,
+      "grad_norm": 2.953125,
+      "learning_rate": 2.7700000000000006e-06,
+      "loss": 0.1082,
+      "step": 5170
+    },
+    {
+      "epoch": 1.1682453766350924,
+      "grad_norm": 1.75,
+      "learning_rate": 2.736666666666667e-06,
+      "loss": 0.102,
+      "step": 5180
+    },
+    {
+      "epoch": 1.1705006765899864,
+      "grad_norm": 2.296875,
+      "learning_rate": 2.7033333333333334e-06,
+      "loss": 0.0988,
+      "step": 5190
+    },
+    {
+      "epoch": 1.1727559765448805,
+      "grad_norm": 3.015625,
+      "learning_rate": 2.6700000000000003e-06,
+      "loss": 0.1008,
+      "step": 5200
+    },
+    {
+      "epoch": 1.1750112764997744,
+      "grad_norm": 2.0625,
+      "learning_rate": 2.6366666666666667e-06,
+      "loss": 0.1001,
+      "step": 5210
+    },
+    {
+      "epoch": 1.1772665764546684,
+      "grad_norm": 1.765625,
+      "learning_rate": 2.603333333333334e-06,
+      "loss": 0.102,
+      "step": 5220
+    },
+    {
+      "epoch": 1.1795218764095625,
+      "grad_norm": 2.1875,
+      "learning_rate": 2.5700000000000004e-06,
+      "loss": 0.0954,
+      "step": 5230
+    },
+    {
+      "epoch": 1.1817771763644564,
+      "grad_norm": 2.546875,
+      "learning_rate": 2.536666666666667e-06,
+      "loss": 0.1014,
+      "step": 5240
+    },
+    {
+      "epoch": 1.1840324763193504,
+      "grad_norm": 1.6875,
+      "learning_rate": 2.5033333333333336e-06,
+      "loss": 0.1032,
+      "step": 5250
+    },
+    {
+      "epoch": 1.1862877762742445,
+      "grad_norm": 2.078125,
+      "learning_rate": 2.47e-06,
+      "loss": 0.1037,
+      "step": 5260
+    },
+    {
+      "epoch": 1.1885430762291385,
+      "grad_norm": 2.171875,
+      "learning_rate": 2.436666666666667e-06,
+      "loss": 0.0912,
+      "step": 5270
+    },
+    {
+      "epoch": 1.1907983761840324,
+      "grad_norm": 2.546875,
+      "learning_rate": 2.4033333333333338e-06,
+      "loss": 0.0874,
+      "step": 5280
+    },
+    {
+      "epoch": 1.1930536761389265,
+      "grad_norm": 2.296875,
+      "learning_rate": 2.37e-06,
+      "loss": 0.0877,
+      "step": 5290
+    },
+    {
+      "epoch": 1.1953089760938205,
+      "grad_norm": 2.875,
+      "learning_rate": 2.3366666666666666e-06,
+      "loss": 0.0966,
+      "step": 5300
+    },
+    {
+      "epoch": 1.1975642760487144,
+      "grad_norm": 1.9921875,
+      "learning_rate": 2.3033333333333334e-06,
+      "loss": 0.096,
+      "step": 5310
+    },
+    {
+      "epoch": 1.1998195760036086,
+      "grad_norm": 2.234375,
+      "learning_rate": 2.2700000000000003e-06,
+      "loss": 0.1119,
+      "step": 5320
+    },
+    {
+      "epoch": 1.2020748759585025,
+      "grad_norm": 2.078125,
+      "learning_rate": 2.236666666666667e-06,
+      "loss": 0.0967,
+      "step": 5330
+    },
+    {
+      "epoch": 1.2043301759133964,
+      "grad_norm": 1.921875,
+      "learning_rate": 2.2033333333333336e-06,
+      "loss": 0.1065,
+      "step": 5340
+    },
+    {
+      "epoch": 1.2065854758682906,
+      "grad_norm": 3.65625,
+      "learning_rate": 2.17e-06,
+      "loss": 0.1093,
+      "step": 5350
+    },
+    {
+      "epoch": 1.2088407758231845,
+      "grad_norm": 2.28125,
+      "learning_rate": 2.136666666666667e-06,
+      "loss": 0.1131,
+      "step": 5360
+    },
+    {
+      "epoch": 1.2110960757780784,
+      "grad_norm": 2.25,
+      "learning_rate": 2.1033333333333337e-06,
+      "loss": 0.0938,
+      "step": 5370
+    },
+    {
+      "epoch": 1.2133513757329726,
+      "grad_norm": 2.203125,
+      "learning_rate": 2.07e-06,
+      "loss": 0.0951,
+      "step": 5380
+    },
+    {
+      "epoch": 1.2156066756878665,
+      "grad_norm": 2.09375,
+      "learning_rate": 2.036666666666667e-06,
+      "loss": 0.1138,
+      "step": 5390
+    },
+    {
+      "epoch": 1.2178619756427604,
+      "grad_norm": 2.34375,
+      "learning_rate": 2.0033333333333334e-06,
+      "loss": 0.0944,
+      "step": 5400
+    },
+    {
+      "epoch": 1.2201172755976546,
+      "grad_norm": 1.9296875,
+      "learning_rate": 1.97e-06,
+      "loss": 0.0991,
+      "step": 5410
+    },
+    {
+      "epoch": 1.2223725755525485,
+      "grad_norm": 2.234375,
+      "learning_rate": 1.9366666666666666e-06,
+      "loss": 0.1096,
+      "step": 5420
+    },
+    {
+      "epoch": 1.2246278755074425,
+      "grad_norm": 2.03125,
+      "learning_rate": 1.9033333333333335e-06,
+      "loss": 0.1197,
+      "step": 5430
+    },
+    {
+      "epoch": 1.2268831754623366,
+      "grad_norm": 2.15625,
+      "learning_rate": 1.87e-06,
+      "loss": 0.1,
+      "step": 5440
+    },
+    {
+      "epoch": 1.2291384754172305,
+      "grad_norm": 2.15625,
+      "learning_rate": 1.836666666666667e-06,
+      "loss": 0.1017,
+      "step": 5450
+    },
+    {
+      "epoch": 1.2313937753721245,
+      "grad_norm": 2.234375,
+      "learning_rate": 1.8033333333333336e-06,
+      "loss": 0.1099,
+      "step": 5460
+    },
+    {
+      "epoch": 1.2336490753270186,
+      "grad_norm": 2.109375,
+      "learning_rate": 1.77e-06,
+      "loss": 0.1058,
+      "step": 5470
+    },
+    {
+      "epoch": 1.2359043752819125,
+      "grad_norm": 2.171875,
+      "learning_rate": 1.7366666666666668e-06,
+      "loss": 0.1007,
+      "step": 5480
+    },
+    {
+      "epoch": 1.2381596752368065,
+      "grad_norm": 2.375,
+      "learning_rate": 1.7033333333333335e-06,
+      "loss": 0.0947,
+      "step": 5490
+    },
+    {
+      "epoch": 1.2404149751917004,
+      "grad_norm": 2.125,
+      "learning_rate": 1.6700000000000003e-06,
+      "loss": 0.0936,
+      "step": 5500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 6000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.057702632259584e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-5500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d042ceb0f99409e5363cbf25011ab03a2f85fa4970a15d9c56414937a5327915
+size 5713

checkpoint-6000/config.json

@@ -0,0 +1,36 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 128001,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.4",
+  "use_cache": true,
+  "vocab_size": 128256
+}

checkpoint-6000/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.52.4"
+}

checkpoint-6000/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:341a70deb96c6b1cbac97435a1abfb34ce224895a6a88484ec44e1a08db779ba
+size 4976698672

checkpoint-6000/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f14e95fa68893c8a96044d574a9dabc7fc6db983b982a110879f6c99cf8508b
+size 4999802720

checkpoint-6000/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0abaada6de5839c7489365684d8ebe8f4b8fadf08c450c55288a071f03c5f8d5
+size 4915916176

checkpoint-6000/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c559ba726c0eb5e8ae5b0a1ca8d58d4036ecf8d32dce3aa2cbf323227fed4a16
+size 1168138808

checkpoint-6000/model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 16060522496
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

checkpoint-6000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8d924c6802fca8754ad88ce182553370f65bd26fa718d8e8ec3634acebf6802
+size 32121300399

checkpoint-6000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:098b29492211804ab324a36f37466821d948280bb74fce4ba895c03f13ecd878
+size 14645

checkpoint-6000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:301718863545c7cf8fd66b71415965fe9d2c5a655750646259ef0cd7ebae441c
+size 1465

checkpoint-6000/special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|end_of_text|>"
+}

checkpoint-6000/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920

checkpoint-6000/tokenizer_config.json

@@ -0,0 +1,2063 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|end_of_text|>",
+  "tokenizer_class": "PreTrainedTokenizer"
+}

checkpoint-6000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d042ceb0f99409e5363cbf25011ab03a2f85fa4970a15d9c56414937a5327915
+size 5713

config.json

@@ -0,0 +1,36 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 128001,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.4",
+  "use_cache": true,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.52.4"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:341a70deb96c6b1cbac97435a1abfb34ce224895a6a88484ec44e1a08db779ba
+size 4976698672

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f14e95fa68893c8a96044d574a9dabc7fc6db983b982a110879f6c99cf8508b
+size 4999802720

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0abaada6de5839c7489365684d8ebe8f4b8fadf08c450c55288a071f03c5f8d5
+size 4915916176

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c559ba726c0eb5e8ae5b0a1ca8d58d4036ecf8d32dce3aa2cbf323227fed4a16
+size 1168138808

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 16060522496
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

runs/Jun25_17-04-09_192-222-56-146/events.out.tfevents.1750871050.192-222-56-146.7221.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a24cc4dba2608ddd0549cd11838a2a098728fd8a7867bd8dc8da7fe56d4ef237
+size 5359

runs/Jun25_17-05-40_192-222-56-146/events.out.tfevents.1750871140.192-222-56-146.7483.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1726be0eb748ba56d217a1dd2c73f1d3a6d2b09ccf01811bf480ab378b832af9
+size 4184

runs/Jun25_17-05-56_192-222-56-146/events.out.tfevents.1750871156.192-222-56-146.7539.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e793b76d660484d8d5d261d20b1b66348cc295a476d5565f7871839e3985b85d
+size 132057

special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|end_of_text|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920

tokenizer_config.json

@@ -0,0 +1,2063 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|end_of_text|>",
+  "tokenizer_class": "PreTrainedTokenizer"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d042ceb0f99409e5363cbf25011ab03a2f85fa4970a15d9c56414937a5327915
+size 5713