Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-14B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: original
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# original
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-14B-Instruct) on the Sky-T1 dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 12
+- total_train_batch_size: 96
+- total_eval_batch_size: 64
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 2.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.4.0a0+f70bd71a48.nv24.06
+- Datasets 3.1.0
+- Tokenizers 0.20.3

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.9968,
+    "total_flos": 267307634917376.0,
+    "train_loss": 0.23609954519913748,
+    "train_runtime": 5830.6676,
+    "train_samples_per_second": 1.715,
+    "train_steps_per_second": 0.018
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-14B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 70,
+  "model_type": "qwen2",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.46.1"
+}

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f92a664883b8ba7fd815227b4e8c511900e553db78e0af39721d7143f3bc91d0
+size 4986211280

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c804f2148d7c85c21d7bc4f5b9e31d12cfafa25c6ec4ce2fdf4a40f6e238286e
+size 4954847344

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:882e09428eb7bd9649ded05032b59de136beed35f975a7e8b8e59305171d0887
+size 4954847392

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6311544cf67d1c0d1510a849085a6ce78bb25a7bfecff0e2717b9a2db94704c5
+size 4954847392

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38471b1aae699b327df8d9175fe22d86e23b5b22446ea872414d9c3d6b2c80be
+size 4954847392

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b8948902af5e45670692a6ceb549c55496e9b1bef368f1336db5baf0c92c873
+size 4734533160

model.safetensors.index.json

@@ -0,0 +1,586 @@
+{
+  "metadata": {
+    "total_size": 29540067328
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00006-of-00006.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.norm.weight": "model-00006-of-00006.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.9968,
+    "total_flos": 267307634917376.0,
+    "train_loss": 0.23609954519913748,
+    "train_runtime": 5830.6676,
+    "train_samples_per_second": 1.715,
+    "train_steps_per_second": 0.018
+}

trainer_log.jsonl

@@ -0,0 +1,105 @@
+{"current_steps": 1, "total_steps": 104, "loss": 0.8199, "lr": 1.8181818181818183e-06, "epoch": 0.0192, "percentage": 0.96, "elapsed_time": "0:02:06", "remaining_time": "3:37:12"}
+{"current_steps": 2, "total_steps": 104, "loss": 0.7853, "lr": 3.6363636363636366e-06, "epoch": 0.0384, "percentage": 1.92, "elapsed_time": "0:03:39", "remaining_time": "3:06:39"}
+{"current_steps": 3, "total_steps": 104, "loss": 0.8376, "lr": 5.4545454545454545e-06, "epoch": 0.0576, "percentage": 2.88, "elapsed_time": "0:05:50", "remaining_time": "3:16:27"}
+{"current_steps": 4, "total_steps": 104, "loss": 0.7952, "lr": 7.272727272727273e-06, "epoch": 0.0768, "percentage": 3.85, "elapsed_time": "0:07:51", "remaining_time": "3:16:34"}
+{"current_steps": 5, "total_steps": 104, "loss": 0.7799, "lr": 9.090909090909091e-06, "epoch": 0.096, "percentage": 4.81, "elapsed_time": "0:09:34", "remaining_time": "3:09:36"}
+{"current_steps": 6, "total_steps": 104, "loss": 0.7217, "lr": 1.0909090909090909e-05, "epoch": 0.1152, "percentage": 5.77, "elapsed_time": "0:11:22", "remaining_time": "3:05:51"}
+{"current_steps": 7, "total_steps": 104, "loss": 0.7105, "lr": 1.2727272727272728e-05, "epoch": 0.1344, "percentage": 6.73, "elapsed_time": "0:13:07", "remaining_time": "3:01:52"}
+{"current_steps": 8, "total_steps": 104, "loss": 0.649, "lr": 1.4545454545454546e-05, "epoch": 0.1536, "percentage": 7.69, "elapsed_time": "0:14:44", "remaining_time": "2:56:59"}
+{"current_steps": 9, "total_steps": 104, "loss": 0.6751, "lr": 1.6363636363636366e-05, "epoch": 0.1728, "percentage": 8.65, "elapsed_time": "0:16:30", "remaining_time": "2:54:19"}
+{"current_steps": 10, "total_steps": 104, "loss": 0.6391, "lr": 1.8181818181818182e-05, "epoch": 0.192, "percentage": 9.62, "elapsed_time": "0:18:24", "remaining_time": "2:53:02"}
+{"current_steps": 11, "total_steps": 104, "loss": 0.6314, "lr": 2e-05, "epoch": 0.2112, "percentage": 10.58, "elapsed_time": "0:20:09", "remaining_time": "2:50:24"}
+{"current_steps": 12, "total_steps": 104, "loss": 0.6343, "lr": 1.999429490929718e-05, "epoch": 0.2304, "percentage": 11.54, "elapsed_time": "0:22:00", "remaining_time": "2:48:41"}
+{"current_steps": 13, "total_steps": 104, "loss": 0.6096, "lr": 1.9977186146800707e-05, "epoch": 0.2496, "percentage": 12.5, "elapsed_time": "0:24:02", "remaining_time": "2:48:15"}
+{"current_steps": 14, "total_steps": 104, "loss": 0.5772, "lr": 1.994869323391895e-05, "epoch": 0.2688, "percentage": 13.46, "elapsed_time": "0:25:52", "remaining_time": "2:46:21"}
+{"current_steps": 15, "total_steps": 104, "loss": 0.6111, "lr": 1.990884868158239e-05, "epoch": 0.288, "percentage": 14.42, "elapsed_time": "0:27:23", "remaining_time": "2:42:29"}
+{"current_steps": 16, "total_steps": 104, "loss": 0.5721, "lr": 1.985769795314804e-05, "epoch": 0.3072, "percentage": 15.38, "elapsed_time": "0:29:14", "remaining_time": "2:40:50"}
+{"current_steps": 17, "total_steps": 104, "loss": 0.5889, "lr": 1.9795299412524948e-05, "epoch": 0.3264, "percentage": 16.35, "elapsed_time": "0:31:04", "remaining_time": "2:39:04"}
+{"current_steps": 18, "total_steps": 104, "loss": 0.5626, "lr": 1.9721724257579907e-05, "epoch": 0.3456, "percentage": 17.31, "elapsed_time": "0:32:32", "remaining_time": "2:35:30"}
+{"current_steps": 19, "total_steps": 104, "loss": 0.545, "lr": 1.963705643889941e-05, "epoch": 0.3648, "percentage": 18.27, "elapsed_time": "0:34:03", "remaining_time": "2:32:20"}
+{"current_steps": 20, "total_steps": 104, "loss": 0.568, "lr": 1.954139256400049e-05, "epoch": 0.384, "percentage": 19.23, "elapsed_time": "0:36:03", "remaining_time": "2:31:27"}
+{"current_steps": 21, "total_steps": 104, "loss": 0.5453, "lr": 1.9434841787099804e-05, "epoch": 0.4032, "percentage": 20.19, "elapsed_time": "0:37:59", "remaining_time": "2:30:09"}
+{"current_steps": 22, "total_steps": 104, "loss": 0.559, "lr": 1.9317525684566686e-05, "epoch": 0.4224, "percentage": 21.15, "elapsed_time": "0:39:42", "remaining_time": "2:28:00"}
+{"current_steps": 23, "total_steps": 104, "loss": 0.5853, "lr": 1.918957811620231e-05, "epoch": 0.4416, "percentage": 22.12, "elapsed_time": "0:41:17", "remaining_time": "2:25:24"}
+{"current_steps": 24, "total_steps": 104, "loss": 0.5406, "lr": 1.9051145072503216e-05, "epoch": 0.4608, "percentage": 23.08, "elapsed_time": "0:43:02", "remaining_time": "2:23:29"}
+{"current_steps": 25, "total_steps": 104, "loss": 0.5552, "lr": 1.8902384508083518e-05, "epoch": 0.48, "percentage": 24.04, "elapsed_time": "0:44:31", "remaining_time": "2:20:42"}
+{"current_steps": 26, "total_steps": 104, "loss": 0.5309, "lr": 1.8743466161445823e-05, "epoch": 0.4992, "percentage": 25.0, "elapsed_time": "0:46:08", "remaining_time": "2:18:25"}
+{"current_steps": 27, "total_steps": 104, "loss": 0.5259, "lr": 1.857457136130651e-05, "epoch": 0.5184, "percentage": 25.96, "elapsed_time": "0:47:56", "remaining_time": "2:16:44"}
+{"current_steps": 28, "total_steps": 104, "loss": 0.5379, "lr": 1.839589281969639e-05, "epoch": 0.5376, "percentage": 26.92, "elapsed_time": "0:49:37", "remaining_time": "2:14:41"}
+{"current_steps": 29, "total_steps": 104, "loss": 0.5275, "lr": 1.8207634412072765e-05, "epoch": 0.5568, "percentage": 27.88, "elapsed_time": "0:51:23", "remaining_time": "2:12:55"}
+{"current_steps": 30, "total_steps": 104, "loss": 0.555, "lr": 1.8010010944693846e-05, "epoch": 0.576, "percentage": 28.85, "elapsed_time": "0:52:56", "remaining_time": "2:10:36"}
+{"current_steps": 31, "total_steps": 104, "loss": 0.527, "lr": 1.780324790952092e-05, "epoch": 0.5952, "percentage": 29.81, "elapsed_time": "0:54:26", "remaining_time": "2:08:13"}
+{"current_steps": 32, "total_steps": 104, "loss": 0.5168, "lr": 1.758758122692791e-05, "epoch": 0.6144, "percentage": 30.77, "elapsed_time": "0:56:15", "remaining_time": "2:06:33"}
+{"current_steps": 33, "total_steps": 104, "loss": 0.5318, "lr": 1.7363256976511972e-05, "epoch": 0.6336, "percentage": 31.73, "elapsed_time": "0:58:11", "remaining_time": "2:05:12"}
+{"current_steps": 34, "total_steps": 104, "loss": 0.5116, "lr": 1.7130531116312202e-05, "epoch": 0.6528, "percentage": 32.69, "elapsed_time": "0:59:57", "remaining_time": "2:03:25"}
+{"current_steps": 35, "total_steps": 104, "loss": 0.5225, "lr": 1.688966919075687e-05, "epoch": 0.672, "percentage": 33.65, "elapsed_time": "1:01:30", "remaining_time": "2:01:15"}
+{"current_steps": 36, "total_steps": 104, "loss": 0.5205, "lr": 1.6640946027672395e-05, "epoch": 0.6912, "percentage": 34.62, "elapsed_time": "1:03:20", "remaining_time": "1:59:39"}
+{"current_steps": 37, "total_steps": 104, "loss": 0.5305, "lr": 1.6384645424699835e-05, "epoch": 0.7104, "percentage": 35.58, "elapsed_time": "1:05:19", "remaining_time": "1:58:17"}
+{"current_steps": 38, "total_steps": 104, "loss": 0.5262, "lr": 1.612105982547663e-05, "epoch": 0.7296, "percentage": 36.54, "elapsed_time": "1:07:26", "remaining_time": "1:57:08"}
+{"current_steps": 39, "total_steps": 104, "loss": 0.5281, "lr": 1.5850489985953076e-05, "epoch": 0.7488, "percentage": 37.5, "elapsed_time": "1:09:10", "remaining_time": "1:55:17"}
+{"current_steps": 40, "total_steps": 104, "loss": 0.5152, "lr": 1.5573244631224364e-05, "epoch": 0.768, "percentage": 38.46, "elapsed_time": "1:11:06", "remaining_time": "1:53:45"}
+{"current_steps": 41, "total_steps": 104, "loss": 0.5247, "lr": 1.5289640103269626e-05, "epoch": 0.7872, "percentage": 39.42, "elapsed_time": "1:12:51", "remaining_time": "1:51:56"}
+{"current_steps": 42, "total_steps": 104, "loss": 0.4826, "lr": 1.5000000000000002e-05, "epoch": 0.8064, "percentage": 40.38, "elapsed_time": "1:14:42", "remaining_time": "1:50:17"}
+{"current_steps": 43, "total_steps": 104, "loss": 0.5118, "lr": 1.4704654806027558e-05, "epoch": 0.8256, "percentage": 41.35, "elapsed_time": "1:16:25", "remaining_time": "1:48:24"}
+{"current_steps": 44, "total_steps": 104, "loss": 0.4893, "lr": 1.4403941515576344e-05, "epoch": 0.8448, "percentage": 42.31, "elapsed_time": "1:18:43", "remaining_time": "1:47:21"}
+{"current_steps": 45, "total_steps": 104, "loss": 0.5241, "lr": 1.4098203247965876e-05, "epoch": 0.864, "percentage": 43.27, "elapsed_time": "1:20:30", "remaining_time": "1:45:33"}
+{"current_steps": 46, "total_steps": 104, "loss": 0.504, "lr": 1.3787788856105762e-05, "epoch": 0.8832, "percentage": 44.23, "elapsed_time": "1:22:09", "remaining_time": "1:43:35"}
+{"current_steps": 47, "total_steps": 104, "loss": 0.513, "lr": 1.3473052528448203e-05, "epoch": 0.9024, "percentage": 45.19, "elapsed_time": "1:24:09", "remaining_time": "1:42:03"}
+{"current_steps": 48, "total_steps": 104, "loss": 0.5241, "lr": 1.3154353384852559e-05, "epoch": 0.9216, "percentage": 46.15, "elapsed_time": "1:26:03", "remaining_time": "1:40:23"}
+{"current_steps": 49, "total_steps": 104, "loss": 0.5238, "lr": 1.283205506682304e-05, "epoch": 0.9408, "percentage": 47.12, "elapsed_time": "1:27:44", "remaining_time": "1:38:28"}
+{"current_steps": 50, "total_steps": 104, "loss": 0.5029, "lr": 1.2506525322587207e-05, "epoch": 0.96, "percentage": 48.08, "elapsed_time": "1:29:04", "remaining_time": "1:36:11"}
+{"current_steps": 51, "total_steps": 104, "loss": 0.4912, "lr": 1.2178135587488515e-05, "epoch": 0.9792, "percentage": 49.04, "elapsed_time": "0:01:41", "remaining_time": "0:01:45"}
+{"current_steps": 52, "total_steps": 104, "loss": 0.5033, "lr": 1.1847260560171895e-05, "epoch": 0.9984, "percentage": 50.0, "elapsed_time": "0:03:03", "remaining_time": "0:03:03"}
+{"current_steps": 53, "total_steps": 104, "loss": 0.8642, "lr": 1.1514277775045768e-05, "epoch": 1.0176, "percentage": 50.96, "elapsed_time": "0:04:49", "remaining_time": "0:04:38"}
+{"current_steps": 54, "total_steps": 104, "loss": 0.458, "lr": 1.1179567171508463e-05, "epoch": 1.0368, "percentage": 51.92, "elapsed_time": "0:06:37", "remaining_time": "0:06:08"}
+{"current_steps": 55, "total_steps": 104, "loss": 0.4255, "lr": 1.0843510660430447e-05, "epoch": 1.056, "percentage": 52.88, "elapsed_time": "0:08:07", "remaining_time": "0:07:13"}
+{"current_steps": 56, "total_steps": 104, "loss": 0.4859, "lr": 1.0506491688387128e-05, "epoch": 1.0752, "percentage": 53.85, "elapsed_time": "0:09:50", "remaining_time": "0:08:26"}
+{"current_steps": 57, "total_steps": 104, "loss": 0.4493, "lr": 1.0168894800139311e-05, "epoch": 1.0944, "percentage": 54.81, "elapsed_time": "0:11:58", "remaining_time": "0:09:52"}
+{"current_steps": 58, "total_steps": 104, "loss": 0.5028, "lr": 9.83110519986069e-06, "epoch": 1.1136, "percentage": 55.77, "elapsed_time": "0:14:36", "remaining_time": "0:11:35"}
+{"current_steps": 59, "total_steps": 104, "loss": 0.4706, "lr": 9.493508311612874e-06, "epoch": 1.1328, "percentage": 56.73, "elapsed_time": "0:16:13", "remaining_time": "0:12:22"}
+{"current_steps": 60, "total_steps": 104, "loss": 0.4484, "lr": 9.156489339569555e-06, "epoch": 1.152, "percentage": 57.69, "elapsed_time": "0:18:00", "remaining_time": "0:13:12"}
+{"current_steps": 61, "total_steps": 104, "loss": 0.4655, "lr": 8.820432828491542e-06, "epoch": 1.1712, "percentage": 58.65, "elapsed_time": "0:20:01", "remaining_time": "0:14:07"}
+{"current_steps": 62, "total_steps": 104, "loss": 0.44, "lr": 8.485722224954237e-06, "epoch": 1.1904, "percentage": 59.62, "elapsed_time": "0:21:42", "remaining_time": "0:14:42"}
+{"current_steps": 63, "total_steps": 104, "loss": 0.4229, "lr": 8.15273943982811e-06, "epoch": 1.2096, "percentage": 60.58, "elapsed_time": "0:23:13", "remaining_time": "0:15:06"}
+{"current_steps": 64, "total_steps": 104, "loss": 0.4952, "lr": 7.821864412511485e-06, "epoch": 1.2288000000000001, "percentage": 61.54, "elapsed_time": "0:25:16", "remaining_time": "0:15:48"}
+{"current_steps": 65, "total_steps": 104, "loss": 0.4252, "lr": 7.493474677412795e-06, "epoch": 1.248, "percentage": 62.5, "elapsed_time": "0:27:06", "remaining_time": "0:16:15"}
+{"current_steps": 66, "total_steps": 104, "loss": 0.4404, "lr": 7.16794493317696e-06, "epoch": 1.2671999999999999, "percentage": 63.46, "elapsed_time": "0:28:57", "remaining_time": "0:16:40"}
+{"current_steps": 67, "total_steps": 104, "loss": 0.4562, "lr": 6.845646615147445e-06, "epoch": 1.2864, "percentage": 64.42, "elapsed_time": "0:30:34", "remaining_time": "0:16:52"}
+{"current_steps": 68, "total_steps": 104, "loss": 0.4725, "lr": 6.526947471551799e-06, "epoch": 1.3056, "percentage": 65.38, "elapsed_time": "0:32:32", "remaining_time": "0:17:13"}
+{"current_steps": 69, "total_steps": 104, "loss": 0.4185, "lr": 6.21221114389424e-06, "epoch": 1.3248, "percentage": 66.35, "elapsed_time": "0:34:21", "remaining_time": "0:17:25"}
+{"current_steps": 70, "total_steps": 104, "loss": 0.4259, "lr": 5.901796752034128e-06, "epoch": 1.3439999999999999, "percentage": 67.31, "elapsed_time": "0:36:14", "remaining_time": "0:17:36"}
+{"current_steps": 71, "total_steps": 104, "loss": 0.4599, "lr": 5.5960584844236565e-06, "epoch": 1.3632, "percentage": 68.27, "elapsed_time": "0:38:13", "remaining_time": "0:17:45"}
+{"current_steps": 72, "total_steps": 104, "loss": 0.5083, "lr": 5.295345193972445e-06, "epoch": 1.3824, "percentage": 69.23, "elapsed_time": "0:40:34", "remaining_time": "0:18:02"}
+{"current_steps": 73, "total_steps": 104, "loss": 0.4262, "lr": 5.000000000000003e-06, "epoch": 1.4016, "percentage": 70.19, "elapsed_time": "0:41:59", "remaining_time": "0:17:49"}
+{"current_steps": 74, "total_steps": 104, "loss": 0.4334, "lr": 4.710359896730379e-06, "epoch": 1.4208, "percentage": 71.15, "elapsed_time": "0:43:31", "remaining_time": "0:17:38"}
+{"current_steps": 75, "total_steps": 104, "loss": 0.4651, "lr": 4.426755368775637e-06, "epoch": 1.44, "percentage": 72.12, "elapsed_time": "0:45:12", "remaining_time": "0:17:28"}
+{"current_steps": 76, "total_steps": 104, "loss": 0.4087, "lr": 4.149510014046922e-06, "epoch": 1.4592, "percentage": 73.08, "elapsed_time": "0:46:58", "remaining_time": "0:17:18"}
+{"current_steps": 77, "total_steps": 104, "loss": 0.4916, "lr": 3.878940174523371e-06, "epoch": 1.4784, "percentage": 74.04, "elapsed_time": "0:48:51", "remaining_time": "0:17:07"}
+{"current_steps": 78, "total_steps": 104, "loss": 0.4215, "lr": 3.6153545753001663e-06, "epoch": 1.4976, "percentage": 75.0, "elapsed_time": "0:50:37", "remaining_time": "0:16:52"}
+{"current_steps": 79, "total_steps": 104, "loss": 0.4473, "lr": 3.3590539723276083e-06, "epoch": 1.5168, "percentage": 75.96, "elapsed_time": "0:52:11", "remaining_time": "0:16:31"}
+{"current_steps": 80, "total_steps": 104, "loss": 0.4218, "lr": 3.110330809243134e-06, "epoch": 1.536, "percentage": 76.92, "elapsed_time": "0:53:46", "remaining_time": "0:16:07"}
+{"current_steps": 81, "total_steps": 104, "loss": 0.4817, "lr": 2.869468883687798e-06, "epoch": 1.5552000000000001, "percentage": 77.88, "elapsed_time": "0:55:30", "remaining_time": "0:15:45"}
+{"current_steps": 82, "total_steps": 104, "loss": 0.4191, "lr": 2.6367430234880286e-06, "epoch": 1.5744, "percentage": 78.85, "elapsed_time": "0:57:35", "remaining_time": "0:15:27"}
+{"current_steps": 83, "total_steps": 104, "loss": 0.4486, "lr": 2.4124187730720916e-06, "epoch": 1.5936, "percentage": 79.81, "elapsed_time": "0:59:23", "remaining_time": "0:15:01"}
+{"current_steps": 84, "total_steps": 104, "loss": 0.4148, "lr": 2.196752090479083e-06, "epoch": 1.6128, "percentage": 80.77, "elapsed_time": "1:00:48", "remaining_time": "0:14:28"}
+{"current_steps": 85, "total_steps": 104, "loss": 0.4394, "lr": 1.9899890553061565e-06, "epoch": 1.6320000000000001, "percentage": 81.73, "elapsed_time": "1:02:47", "remaining_time": "0:14:02"}
+{"current_steps": 86, "total_steps": 104, "loss": 0.4326, "lr": 1.7923655879272395e-06, "epoch": 1.6512, "percentage": 82.69, "elapsed_time": "1:04:04", "remaining_time": "0:13:24"}
+{"current_steps": 87, "total_steps": 104, "loss": 0.4171, "lr": 1.60410718030361e-06, "epoch": 1.6703999999999999, "percentage": 83.65, "elapsed_time": "1:05:44", "remaining_time": "0:12:50"}
+{"current_steps": 88, "total_steps": 104, "loss": 0.4435, "lr": 1.425428638693489e-06, "epoch": 1.6896, "percentage": 84.62, "elapsed_time": "1:07:32", "remaining_time": "0:12:16"}
+{"current_steps": 89, "total_steps": 104, "loss": 0.4674, "lr": 1.2565338385541792e-06, "epoch": 1.7088, "percentage": 85.58, "elapsed_time": "1:09:01", "remaining_time": "0:11:37"}
+{"current_steps": 90, "total_steps": 104, "loss": 0.4328, "lr": 1.097615491916485e-06, "epoch": 1.728, "percentage": 86.54, "elapsed_time": "1:10:26", "remaining_time": "0:10:57"}
+{"current_steps": 91, "total_steps": 104, "loss": 0.4546, "lr": 9.488549274967873e-07, "epoch": 1.7471999999999999, "percentage": 87.5, "elapsed_time": "1:12:15", "remaining_time": "0:10:19"}
+{"current_steps": 92, "total_steps": 104, "loss": 0.4093, "lr": 8.10421883797694e-07, "epoch": 1.7664, "percentage": 88.46, "elapsed_time": "1:13:58", "remaining_time": "0:09:38"}
+{"current_steps": 93, "total_steps": 104, "loss": 0.4375, "lr": 6.824743154333157e-07, "epoch": 1.7856, "percentage": 89.42, "elapsed_time": "1:15:45", "remaining_time": "0:08:57"}
+{"current_steps": 94, "total_steps": 104, "loss": 0.419, "lr": 5.651582129001987e-07, "epoch": 1.8048, "percentage": 90.38, "elapsed_time": "1:17:25", "remaining_time": "0:08:14"}
+{"current_steps": 95, "total_steps": 104, "loss": 0.4183, "lr": 4.5860743599951186e-07, "epoch": 1.8239999999999998, "percentage": 91.35, "elapsed_time": "1:18:55", "remaining_time": "0:07:28"}
+{"current_steps": 96, "total_steps": 104, "loss": 0.4472, "lr": 3.629435611005916e-07, "epoch": 1.8432, "percentage": 92.31, "elapsed_time": "1:20:20", "remaining_time": "0:06:41"}
+{"current_steps": 97, "total_steps": 104, "loss": 0.3948, "lr": 2.7827574242009434e-07, "epoch": 1.8624, "percentage": 93.27, "elapsed_time": "1:22:04", "remaining_time": "0:05:55"}
+{"current_steps": 98, "total_steps": 104, "loss": 0.4302, "lr": 2.0470058747505516e-07, "epoch": 1.8816000000000002, "percentage": 94.23, "elapsed_time": "1:23:39", "remaining_time": "0:05:07"}
+{"current_steps": 99, "total_steps": 104, "loss": 0.423, "lr": 1.4230204685196202e-07, "epoch": 1.9008, "percentage": 95.19, "elapsed_time": "1:25:27", "remaining_time": "0:04:18"}
+{"current_steps": 100, "total_steps": 104, "loss": 0.454, "lr": 9.11513184176116e-08, "epoch": 1.92, "percentage": 96.15, "elapsed_time": "1:27:25", "remaining_time": "0:03:29"}
+{"current_steps": 101, "total_steps": 104, "loss": 0.4188, "lr": 5.1306766081048456e-08, "epoch": 1.9392, "percentage": 97.12, "elapsed_time": "1:30:40", "remaining_time": "0:02:41"}
+{"current_steps": 102, "total_steps": 104, "loss": 0.4735, "lr": 2.2813853199292745e-08, "epoch": 1.9584000000000001, "percentage": 98.08, "elapsed_time": "1:32:23", "remaining_time": "0:01:48"}
+{"current_steps": 103, "total_steps": 104, "loss": 0.4387, "lr": 5.705090702819993e-09, "epoch": 1.9776, "percentage": 99.04, "elapsed_time": "1:33:44", "remaining_time": "0:00:54"}
+{"current_steps": 104, "total_steps": 104, "loss": 0.4933, "lr": 0.0, "epoch": 1.9968, "percentage": 100.0, "elapsed_time": "1:35:48", "remaining_time": "0:00:00"}
+{"current_steps": 104, "total_steps": 104, "epoch": 1.9968, "percentage": 100.0, "elapsed_time": "1:37:09", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,770 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9968,
+  "eval_steps": 500,
+  "global_step": 104,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0192,
+      "grad_norm": 2.896285057067871,
+      "learning_rate": 1.8181818181818183e-06,
+      "loss": 0.8199,
+      "step": 1
+    },
+    {
+      "epoch": 0.0384,
+      "grad_norm": 2.9479026794433594,
+      "learning_rate": 3.6363636363636366e-06,
+      "loss": 0.7853,
+      "step": 2
+    },
+    {
+      "epoch": 0.0576,
+      "grad_norm": 2.7665855884552,
+      "learning_rate": 5.4545454545454545e-06,
+      "loss": 0.8376,
+      "step": 3
+    },
+    {
+      "epoch": 0.0768,
+      "grad_norm": 2.2083640098571777,
+      "learning_rate": 7.272727272727273e-06,
+      "loss": 0.7952,
+      "step": 4
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 2.123579263687134,
+      "learning_rate": 9.090909090909091e-06,
+      "loss": 0.7799,
+      "step": 5
+    },
+    {
+      "epoch": 0.1152,
+      "grad_norm": 2.0430407524108887,
+      "learning_rate": 1.0909090909090909e-05,
+      "loss": 0.7217,
+      "step": 6
+    },
+    {
+      "epoch": 0.1344,
+      "grad_norm": 1.832374095916748,
+      "learning_rate": 1.2727272727272728e-05,
+      "loss": 0.7105,
+      "step": 7
+    },
+    {
+      "epoch": 0.1536,
+      "grad_norm": 1.5578047037124634,
+      "learning_rate": 1.4545454545454546e-05,
+      "loss": 0.649,
+      "step": 8
+    },
+    {
+      "epoch": 0.1728,
+      "grad_norm": 1.4507675170898438,
+      "learning_rate": 1.6363636363636366e-05,
+      "loss": 0.6751,
+      "step": 9
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 0.933198094367981,
+      "learning_rate": 1.8181818181818182e-05,
+      "loss": 0.6391,
+      "step": 10
+    },
+    {
+      "epoch": 0.2112,
+      "grad_norm": 1.3391040563583374,
+      "learning_rate": 2e-05,
+      "loss": 0.6314,
+      "step": 11
+    },
+    {
+      "epoch": 0.2304,
+      "grad_norm": 1.0302867889404297,
+      "learning_rate": 1.999429490929718e-05,
+      "loss": 0.6343,
+      "step": 12
+    },
+    {
+      "epoch": 0.2496,
+      "grad_norm": 1.0636142492294312,
+      "learning_rate": 1.9977186146800707e-05,
+      "loss": 0.6096,
+      "step": 13
+    },
+    {
+      "epoch": 0.2688,
+      "grad_norm": 0.8283386826515198,
+      "learning_rate": 1.994869323391895e-05,
+      "loss": 0.5772,
+      "step": 14
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 0.835659384727478,
+      "learning_rate": 1.990884868158239e-05,
+      "loss": 0.6111,
+      "step": 15
+    },
+    {
+      "epoch": 0.3072,
+      "grad_norm": 0.7661851644515991,
+      "learning_rate": 1.985769795314804e-05,
+      "loss": 0.5721,
+      "step": 16
+    },
+    {
+      "epoch": 0.3264,
+      "grad_norm": 0.6115248203277588,
+      "learning_rate": 1.9795299412524948e-05,
+      "loss": 0.5889,
+      "step": 17
+    },
+    {
+      "epoch": 0.3456,
+      "grad_norm": 0.6775667667388916,
+      "learning_rate": 1.9721724257579907e-05,
+      "loss": 0.5626,
+      "step": 18
+    },
+    {
+      "epoch": 0.3648,
+      "grad_norm": 0.542281448841095,
+      "learning_rate": 1.963705643889941e-05,
+      "loss": 0.545,
+      "step": 19
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 0.6435730457305908,
+      "learning_rate": 1.954139256400049e-05,
+      "loss": 0.568,
+      "step": 20
+    },
+    {
+      "epoch": 0.4032,
+      "grad_norm": 0.5503963232040405,
+      "learning_rate": 1.9434841787099804e-05,
+      "loss": 0.5453,
+      "step": 21
+    },
+    {
+      "epoch": 0.4224,
+      "grad_norm": 0.5672121047973633,
+      "learning_rate": 1.9317525684566686e-05,
+      "loss": 0.559,
+      "step": 22
+    },
+    {
+      "epoch": 0.4416,
+      "grad_norm": 0.5936136245727539,
+      "learning_rate": 1.918957811620231e-05,
+      "loss": 0.5853,
+      "step": 23
+    },
+    {
+      "epoch": 0.4608,
+      "grad_norm": 0.47528502345085144,
+      "learning_rate": 1.9051145072503216e-05,
+      "loss": 0.5406,
+      "step": 24
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 2.3298187255859375,
+      "learning_rate": 1.8902384508083518e-05,
+      "loss": 0.5552,
+      "step": 25
+    },
+    {
+      "epoch": 0.4992,
+      "grad_norm": 0.6550001502037048,
+      "learning_rate": 1.8743466161445823e-05,
+      "loss": 0.5309,
+      "step": 26
+    },
+    {
+      "epoch": 0.5184,
+      "grad_norm": 0.5006310343742371,
+      "learning_rate": 1.857457136130651e-05,
+      "loss": 0.5259,
+      "step": 27
+    },
+    {
+      "epoch": 0.5376,
+      "grad_norm": 0.4581935703754425,
+      "learning_rate": 1.839589281969639e-05,
+      "loss": 0.5379,
+      "step": 28
+    },
+    {
+      "epoch": 0.5568,
+      "grad_norm": 0.874056875705719,
+      "learning_rate": 1.8207634412072765e-05,
+      "loss": 0.5275,
+      "step": 29
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 0.46912455558776855,
+      "learning_rate": 1.8010010944693846e-05,
+      "loss": 0.555,
+      "step": 30
+    },
+    {
+      "epoch": 0.5952,
+      "grad_norm": 0.39538028836250305,
+      "learning_rate": 1.780324790952092e-05,
+      "loss": 0.527,
+      "step": 31
+    },
+    {
+      "epoch": 0.6144,
+      "grad_norm": 0.4353641867637634,
+      "learning_rate": 1.758758122692791e-05,
+      "loss": 0.5168,
+      "step": 32
+    },
+    {
+      "epoch": 0.6336,
+      "grad_norm": 0.38645562529563904,
+      "learning_rate": 1.7363256976511972e-05,
+      "loss": 0.5318,
+      "step": 33
+    },
+    {
+      "epoch": 0.6528,
+      "grad_norm": 0.357766330242157,
+      "learning_rate": 1.7130531116312202e-05,
+      "loss": 0.5116,
+      "step": 34
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 0.3727206885814667,
+      "learning_rate": 1.688966919075687e-05,
+      "loss": 0.5225,
+      "step": 35
+    },
+    {
+      "epoch": 0.6912,
+      "grad_norm": 0.37882763147354126,
+      "learning_rate": 1.6640946027672395e-05,
+      "loss": 0.5205,
+      "step": 36
+    },
+    {
+      "epoch": 0.7104,
+      "grad_norm": 0.4564473330974579,
+      "learning_rate": 1.6384645424699835e-05,
+      "loss": 0.5305,
+      "step": 37
+    },
+    {
+      "epoch": 0.7296,
+      "grad_norm": 0.3431626260280609,
+      "learning_rate": 1.612105982547663e-05,
+      "loss": 0.5262,
+      "step": 38
+    },
+    {
+      "epoch": 0.7488,
+      "grad_norm": 0.40978795289993286,
+      "learning_rate": 1.5850489985953076e-05,
+      "loss": 0.5281,
+      "step": 39
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 0.41154518723487854,
+      "learning_rate": 1.5573244631224364e-05,
+      "loss": 0.5152,
+      "step": 40
+    },
+    {
+      "epoch": 0.7872,
+      "grad_norm": 0.3955947160720825,
+      "learning_rate": 1.5289640103269626e-05,
+      "loss": 0.5247,
+      "step": 41
+    },
+    {
+      "epoch": 0.8064,
+      "grad_norm": 0.35674619674682617,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.4826,
+      "step": 42
+    },
+    {
+      "epoch": 0.8256,
+      "grad_norm": 0.3856222331523895,
+      "learning_rate": 1.4704654806027558e-05,
+      "loss": 0.5118,
+      "step": 43
+    },
+    {
+      "epoch": 0.8448,
+      "grad_norm": 0.295108437538147,
+      "learning_rate": 1.4403941515576344e-05,
+      "loss": 0.4893,
+      "step": 44
+    },
+    {
+      "epoch": 0.864,
+      "grad_norm": 0.3720819354057312,
+      "learning_rate": 1.4098203247965876e-05,
+      "loss": 0.5241,
+      "step": 45
+    },
+    {
+      "epoch": 0.8832,
+      "grad_norm": 0.33612871170043945,
+      "learning_rate": 1.3787788856105762e-05,
+      "loss": 0.504,
+      "step": 46
+    },
+    {
+      "epoch": 0.9024,
+      "grad_norm": 0.34449711441993713,
+      "learning_rate": 1.3473052528448203e-05,
+      "loss": 0.513,
+      "step": 47
+    },
+    {
+      "epoch": 0.9216,
+      "grad_norm": 0.32105591893196106,
+      "learning_rate": 1.3154353384852559e-05,
+      "loss": 0.5241,
+      "step": 48
+    },
+    {
+      "epoch": 0.9408,
+      "grad_norm": 0.32718291878700256,
+      "learning_rate": 1.283205506682304e-05,
+      "loss": 0.5238,
+      "step": 49
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.3497180640697479,
+      "learning_rate": 1.2506525322587207e-05,
+      "loss": 0.5029,
+      "step": 50
+    },
+    {
+      "epoch": 0.9792,
+      "grad_norm": 0.35996726155281067,
+      "learning_rate": 1.2178135587488515e-05,
+      "loss": 0.4912,
+      "step": 51
+    },
+    {
+      "epoch": 0.9984,
+      "grad_norm": 0.34026089310646057,
+      "learning_rate": 1.1847260560171895e-05,
+      "loss": 0.5033,
+      "step": 52
+    },
+    {
+      "epoch": 1.0176,
+      "grad_norm": 1.0328508615493774,
+      "learning_rate": 1.1514277775045768e-05,
+      "loss": 0.8642,
+      "step": 53
+    },
+    {
+      "epoch": 1.0368,
+      "grad_norm": 0.3849644064903259,
+      "learning_rate": 1.1179567171508463e-05,
+      "loss": 0.458,
+      "step": 54
+    },
+    {
+      "epoch": 1.056,
+      "grad_norm": 0.42965736985206604,
+      "learning_rate": 1.0843510660430447e-05,
+      "loss": 0.4255,
+      "step": 55
+    },
+    {
+      "epoch": 1.0752,
+      "grad_norm": 0.44312649965286255,
+      "learning_rate": 1.0506491688387128e-05,
+      "loss": 0.4859,
+      "step": 56
+    },
+    {
+      "epoch": 1.0944,
+      "grad_norm": 0.4057353734970093,
+      "learning_rate": 1.0168894800139311e-05,
+      "loss": 0.4493,
+      "step": 57
+    },
+    {
+      "epoch": 1.1136,
+      "grad_norm": 0.5063387155532837,
+      "learning_rate": 9.83110519986069e-06,
+      "loss": 0.5028,
+      "step": 58
+    },
+    {
+      "epoch": 1.1328,
+      "grad_norm": 0.41317084431648254,
+      "learning_rate": 9.493508311612874e-06,
+      "loss": 0.4706,
+      "step": 59
+    },
+    {
+      "epoch": 1.152,
+      "grad_norm": 0.40928763151168823,
+      "learning_rate": 9.156489339569555e-06,
+      "loss": 0.4484,
+      "step": 60
+    },
+    {
+      "epoch": 1.1712,
+      "grad_norm": 0.4534441828727722,
+      "learning_rate": 8.820432828491542e-06,
+      "loss": 0.4655,
+      "step": 61
+    },
+    {
+      "epoch": 1.1904,
+      "grad_norm": 0.36893245577812195,
+      "learning_rate": 8.485722224954237e-06,
+      "loss": 0.44,
+      "step": 62
+    },
+    {
+      "epoch": 1.2096,
+      "grad_norm": 0.39535439014434814,
+      "learning_rate": 8.15273943982811e-06,
+      "loss": 0.4229,
+      "step": 63
+    },
+    {
+      "epoch": 1.2288000000000001,
+      "grad_norm": 0.4255315661430359,
+      "learning_rate": 7.821864412511485e-06,
+      "loss": 0.4952,
+      "step": 64
+    },
+    {
+      "epoch": 1.248,
+      "grad_norm": 0.3675838112831116,
+      "learning_rate": 7.493474677412795e-06,
+      "loss": 0.4252,
+      "step": 65
+    },
+    {
+      "epoch": 1.2671999999999999,
+      "grad_norm": 0.36970463395118713,
+      "learning_rate": 7.16794493317696e-06,
+      "loss": 0.4404,
+      "step": 66
+    },
+    {
+      "epoch": 1.2864,
+      "grad_norm": 0.34677854180336,
+      "learning_rate": 6.845646615147445e-06,
+      "loss": 0.4562,
+      "step": 67
+    },
+    {
+      "epoch": 1.3056,
+      "grad_norm": 0.3653252124786377,
+      "learning_rate": 6.526947471551799e-06,
+      "loss": 0.4725,
+      "step": 68
+    },
+    {
+      "epoch": 1.3248,
+      "grad_norm": 0.3889782428741455,
+      "learning_rate": 6.21221114389424e-06,
+      "loss": 0.4185,
+      "step": 69
+    },
+    {
+      "epoch": 1.3439999999999999,
+      "grad_norm": 0.3504191040992737,
+      "learning_rate": 5.901796752034128e-06,
+      "loss": 0.4259,
+      "step": 70
+    },
+    {
+      "epoch": 1.3632,
+      "grad_norm": 0.34810832142829895,
+      "learning_rate": 5.5960584844236565e-06,
+      "loss": 0.4599,
+      "step": 71
+    },
+    {
+      "epoch": 1.3824,
+      "grad_norm": 0.42849788069725037,
+      "learning_rate": 5.295345193972445e-06,
+      "loss": 0.5083,
+      "step": 72
+    },
+    {
+      "epoch": 1.4016,
+      "grad_norm": 0.32271483540534973,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.4262,
+      "step": 73
+    },
+    {
+      "epoch": 1.4208,
+      "grad_norm": 0.37454429268836975,
+      "learning_rate": 4.710359896730379e-06,
+      "loss": 0.4334,
+      "step": 74
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.36040475964546204,
+      "learning_rate": 4.426755368775637e-06,
+      "loss": 0.4651,
+      "step": 75
+    },
+    {
+      "epoch": 1.4592,
+      "grad_norm": 0.3899717628955841,
+      "learning_rate": 4.149510014046922e-06,
+      "loss": 0.4087,
+      "step": 76
+    },
+    {
+      "epoch": 1.4784,
+      "grad_norm": 0.4442329406738281,
+      "learning_rate": 3.878940174523371e-06,
+      "loss": 0.4916,
+      "step": 77
+    },
+    {
+      "epoch": 1.4976,
+      "grad_norm": 0.34105443954467773,
+      "learning_rate": 3.6153545753001663e-06,
+      "loss": 0.4215,
+      "step": 78
+    },
+    {
+      "epoch": 1.5168,
+      "grad_norm": 0.3295229971408844,
+      "learning_rate": 3.3590539723276083e-06,
+      "loss": 0.4473,
+      "step": 79
+    },
+    {
+      "epoch": 1.536,
+      "grad_norm": 0.38341015577316284,
+      "learning_rate": 3.110330809243134e-06,
+      "loss": 0.4218,
+      "step": 80
+    },
+    {
+      "epoch": 1.5552000000000001,
+      "grad_norm": 0.3848922550678253,
+      "learning_rate": 2.869468883687798e-06,
+      "loss": 0.4817,
+      "step": 81
+    },
+    {
+      "epoch": 1.5744,
+      "grad_norm": 0.3421174883842468,
+      "learning_rate": 2.6367430234880286e-06,
+      "loss": 0.4191,
+      "step": 82
+    },
+    {
+      "epoch": 1.5936,
+      "grad_norm": 0.361130952835083,
+      "learning_rate": 2.4124187730720916e-06,
+      "loss": 0.4486,
+      "step": 83
+    },
+    {
+      "epoch": 1.6128,
+      "grad_norm": 0.3822689354419708,
+      "learning_rate": 2.196752090479083e-06,
+      "loss": 0.4148,
+      "step": 84
+    },
+    {
+      "epoch": 1.6320000000000001,
+      "grad_norm": 0.3798927068710327,
+      "learning_rate": 1.9899890553061565e-06,
+      "loss": 0.4394,
+      "step": 85
+    },
+    {
+      "epoch": 1.6512,
+      "grad_norm": 0.359497606754303,
+      "learning_rate": 1.7923655879272395e-06,
+      "loss": 0.4326,
+      "step": 86
+    },
+    {
+      "epoch": 1.6703999999999999,
+      "grad_norm": 0.36847516894340515,
+      "learning_rate": 1.60410718030361e-06,
+      "loss": 0.4171,
+      "step": 87
+    },
+    {
+      "epoch": 1.6896,
+      "grad_norm": 0.34353190660476685,
+      "learning_rate": 1.425428638693489e-06,
+      "loss": 0.4435,
+      "step": 88
+    },
+    {
+      "epoch": 1.7088,
+      "grad_norm": 0.35583794116973877,
+      "learning_rate": 1.2565338385541792e-06,
+      "loss": 0.4674,
+      "step": 89
+    },
+    {
+      "epoch": 1.728,
+      "grad_norm": 0.38606297969818115,
+      "learning_rate": 1.097615491916485e-06,
+      "loss": 0.4328,
+      "step": 90
+    },
+    {
+      "epoch": 1.7471999999999999,
+      "grad_norm": 0.34435537457466125,
+      "learning_rate": 9.488549274967873e-07,
+      "loss": 0.4546,
+      "step": 91
+    },
+    {
+      "epoch": 1.7664,
+      "grad_norm": 0.3836256265640259,
+      "learning_rate": 8.10421883797694e-07,
+      "loss": 0.4093,
+      "step": 92
+    },
+    {
+      "epoch": 1.7856,
+      "grad_norm": 0.3552085757255554,
+      "learning_rate": 6.824743154333157e-07,
+      "loss": 0.4375,
+      "step": 93
+    },
+    {
+      "epoch": 1.8048,
+      "grad_norm": 0.3539055585861206,
+      "learning_rate": 5.651582129001987e-07,
+      "loss": 0.419,
+      "step": 94
+    },
+    {
+      "epoch": 1.8239999999999998,
+      "grad_norm": 0.3704381287097931,
+      "learning_rate": 4.5860743599951186e-07,
+      "loss": 0.4183,
+      "step": 95
+    },
+    {
+      "epoch": 1.8432,
+      "grad_norm": 0.3986278474330902,
+      "learning_rate": 3.629435611005916e-07,
+      "loss": 0.4472,
+      "step": 96
+    },
+    {
+      "epoch": 1.8624,
+      "grad_norm": 0.38493794202804565,
+      "learning_rate": 2.7827574242009434e-07,
+      "loss": 0.3948,
+      "step": 97
+    },
+    {
+      "epoch": 1.8816000000000002,
+      "grad_norm": 0.4022544324398041,
+      "learning_rate": 2.0470058747505516e-07,
+      "loss": 0.4302,
+      "step": 98
+    },
+    {
+      "epoch": 1.9008,
+      "grad_norm": 0.3475199043750763,
+      "learning_rate": 1.4230204685196202e-07,
+      "loss": 0.423,
+      "step": 99
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.4098152816295624,
+      "learning_rate": 9.11513184176116e-08,
+      "loss": 0.454,
+      "step": 100
+    },
+    {
+      "epoch": 1.9392,
+      "grad_norm": 0.3654698133468628,
+      "learning_rate": 5.1306766081048456e-08,
+      "loss": 0.4188,
+      "step": 101
+    },
+    {
+      "epoch": 1.9584000000000001,
+      "grad_norm": 0.3904590904712677,
+      "learning_rate": 2.2813853199292745e-08,
+      "loss": 0.4735,
+      "step": 102
+    },
+    {
+      "epoch": 1.9776,
+      "grad_norm": 0.3612796664237976,
+      "learning_rate": 5.705090702819993e-09,
+      "loss": 0.4387,
+      "step": 103
+    },
+    {
+      "epoch": 1.9968,
+      "grad_norm": 0.38515302538871765,
+      "learning_rate": 0.0,
+      "loss": 0.4933,
+      "step": 104
+    },
+    {
+      "epoch": 1.9968,
+      "step": 104,
+      "total_flos": 267307634917376.0,
+      "train_loss": 0.23609954519913748,
+      "train_runtime": 5830.6676,
+      "train_samples_per_second": 1.715,
+      "train_steps_per_second": 0.018
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 104,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 267307634917376.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:460a907651ce5763939d8328ca2b660a8bc2a558e9b9730ddf801b621be0d869
+size 7544