Upload folder using huggingface_hub
Browse files- config.json +40 -0
- generation_config.json +12 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +261 -0
- special_tokens_map.json +17 -0
- tokenizer.json +0 -0
- tokenizer_config.json +2063 -0
- trainer_state.json +1248 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/GLOBALFS/gznwp_3/qxj/lgzhong/LLaMA-Factory/saves/llama31/Llama-3.2-3B-Instruct-SFT-v1.5",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 128000,
|
| 9 |
+
"eos_token_id": [
|
| 10 |
+
128001,
|
| 11 |
+
128008,
|
| 12 |
+
128009
|
| 13 |
+
],
|
| 14 |
+
"head_dim": 128,
|
| 15 |
+
"hidden_act": "silu",
|
| 16 |
+
"hidden_size": 3072,
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 8192,
|
| 19 |
+
"max_position_embeddings": 131072,
|
| 20 |
+
"mlp_bias": false,
|
| 21 |
+
"model_type": "llama",
|
| 22 |
+
"num_attention_heads": 24,
|
| 23 |
+
"num_hidden_layers": 28,
|
| 24 |
+
"num_key_value_heads": 8,
|
| 25 |
+
"pretraining_tp": 1,
|
| 26 |
+
"rms_norm_eps": 1e-05,
|
| 27 |
+
"rope_scaling": {
|
| 28 |
+
"factor": 32.0,
|
| 29 |
+
"high_freq_factor": 4.0,
|
| 30 |
+
"low_freq_factor": 1.0,
|
| 31 |
+
"original_max_position_embeddings": 8192,
|
| 32 |
+
"rope_type": "llama3"
|
| 33 |
+
},
|
| 34 |
+
"rope_theta": 500000.0,
|
| 35 |
+
"tie_word_embeddings": true,
|
| 36 |
+
"torch_dtype": "bfloat16",
|
| 37 |
+
"transformers_version": "4.43.4",
|
| 38 |
+
"use_cache": false,
|
| 39 |
+
"vocab_size": 128256
|
| 40 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 128000,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
128001,
|
| 6 |
+
128008,
|
| 7 |
+
128009
|
| 8 |
+
],
|
| 9 |
+
"temperature": 0.6,
|
| 10 |
+
"top_p": 0.9,
|
| 11 |
+
"transformers_version": "4.43.4"
|
| 12 |
+
}
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e0c09cc3942e33425dd04cab194b2e9bdc789f8f4518c37ad19c4594e8712a6d
|
| 3 |
+
size 4965799096
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:63664cd42eb53bf2397b7ce2453d73aa41849c62e79d2a9c3d7e467e8df1f6d4
|
| 3 |
+
size 1459729952
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,261 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 6425499648
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 7 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 8 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 9 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 10 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 11 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 12 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 16 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 17 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 18 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 19 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 20 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 22 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 24 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 25 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 26 |
+
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 27 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 28 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 29 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 30 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 31 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 32 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 34 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 37 |
+
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 38 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 39 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 40 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 41 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 42 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 43 |
+
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 44 |
+
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 48 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 49 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 50 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 51 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 52 |
+
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 53 |
+
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 54 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 55 |
+
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 56 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 58 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 59 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 61 |
+
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 62 |
+
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 63 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 64 |
+
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 65 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 66 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 67 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 68 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 72 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 73 |
+
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 74 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 75 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 76 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 77 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 78 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 79 |
+
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 80 |
+
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 82 |
+
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 84 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 85 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 86 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 87 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 88 |
+
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 89 |
+
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 90 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 91 |
+
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 92 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 93 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 94 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 95 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 97 |
+
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 98 |
+
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 99 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 100 |
+
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 101 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 102 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 103 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 104 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 106 |
+
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 108 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 109 |
+
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 110 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 111 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 112 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 113 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 114 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 115 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 116 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 117 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 118 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 119 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 120 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 121 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 122 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 123 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 124 |
+
"model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 125 |
+
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 126 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 127 |
+
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 128 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 129 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 130 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 131 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 132 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 133 |
+
"model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 134 |
+
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 135 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 136 |
+
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 137 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 138 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 139 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 140 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 141 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 142 |
+
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 143 |
+
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 144 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 145 |
+
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 146 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 147 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 148 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 149 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 150 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 151 |
+
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 152 |
+
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 153 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 154 |
+
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 155 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 156 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 157 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 158 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 159 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 160 |
+
"model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 161 |
+
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 162 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 163 |
+
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 164 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 165 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 166 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 167 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 168 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 169 |
+
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 170 |
+
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 171 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 172 |
+
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 173 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 174 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 175 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 176 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 177 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 178 |
+
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 179 |
+
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 180 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 181 |
+
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 182 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 183 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 184 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 185 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 186 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 187 |
+
"model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 188 |
+
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 189 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 190 |
+
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 191 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 192 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 193 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 194 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 195 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 196 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 197 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 198 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 199 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 200 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 201 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 202 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 203 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 204 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 205 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 206 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 207 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 208 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 209 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 210 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 211 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 212 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 213 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 214 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 215 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 216 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 217 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 218 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 219 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 220 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 221 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 222 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 223 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 224 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 225 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 226 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 227 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 228 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 229 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 230 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 231 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 232 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 233 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 234 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 235 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 236 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 237 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 238 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 239 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 240 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 241 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 242 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 243 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 244 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 245 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 246 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 247 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 248 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 249 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 250 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 251 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 252 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 253 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 254 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 255 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 256 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 257 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 258 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 259 |
+
"model.norm.weight": "model-00002-of-00002.safetensors"
|
| 260 |
+
}
|
| 261 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|begin_of_text|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|eot_id|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<|eot_id|>"
|
| 17 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,2063 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"128000": {
|
| 4 |
+
"content": "<|begin_of_text|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"128001": {
|
| 12 |
+
"content": "<|end_of_text|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"128002": {
|
| 20 |
+
"content": "<|reserved_special_token_0|>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"128003": {
|
| 28 |
+
"content": "<|reserved_special_token_1|>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"128004": {
|
| 36 |
+
"content": "<|finetune_right_pad_id|>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"128005": {
|
| 44 |
+
"content": "<|reserved_special_token_2|>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"128006": {
|
| 52 |
+
"content": "<|start_header_id|>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"128007": {
|
| 60 |
+
"content": "<|end_header_id|>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"128008": {
|
| 68 |
+
"content": "<|eom_id|>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"128009": {
|
| 76 |
+
"content": "<|eot_id|>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"128010": {
|
| 84 |
+
"content": "<|python_tag|>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"128011": {
|
| 92 |
+
"content": "<|reserved_special_token_3|>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"128012": {
|
| 100 |
+
"content": "<|reserved_special_token_4|>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"128013": {
|
| 108 |
+
"content": "<|reserved_special_token_5|>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"128014": {
|
| 116 |
+
"content": "<|reserved_special_token_6|>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"128015": {
|
| 124 |
+
"content": "<|reserved_special_token_7|>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"128016": {
|
| 132 |
+
"content": "<|reserved_special_token_8|>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"128017": {
|
| 140 |
+
"content": "<|reserved_special_token_9|>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"128018": {
|
| 148 |
+
"content": "<|reserved_special_token_10|>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"128019": {
|
| 156 |
+
"content": "<|reserved_special_token_11|>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"128020": {
|
| 164 |
+
"content": "<|reserved_special_token_12|>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"128021": {
|
| 172 |
+
"content": "<|reserved_special_token_13|>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"128022": {
|
| 180 |
+
"content": "<|reserved_special_token_14|>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"128023": {
|
| 188 |
+
"content": "<|reserved_special_token_15|>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"128024": {
|
| 196 |
+
"content": "<|reserved_special_token_16|>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"128025": {
|
| 204 |
+
"content": "<|reserved_special_token_17|>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"128026": {
|
| 212 |
+
"content": "<|reserved_special_token_18|>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"128027": {
|
| 220 |
+
"content": "<|reserved_special_token_19|>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"128028": {
|
| 228 |
+
"content": "<|reserved_special_token_20|>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"128029": {
|
| 236 |
+
"content": "<|reserved_special_token_21|>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"128030": {
|
| 244 |
+
"content": "<|reserved_special_token_22|>",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"128031": {
|
| 252 |
+
"content": "<|reserved_special_token_23|>",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"128032": {
|
| 260 |
+
"content": "<|reserved_special_token_24|>",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"128033": {
|
| 268 |
+
"content": "<|reserved_special_token_25|>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"128034": {
|
| 276 |
+
"content": "<|reserved_special_token_26|>",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"128035": {
|
| 284 |
+
"content": "<|reserved_special_token_27|>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
},
|
| 291 |
+
"128036": {
|
| 292 |
+
"content": "<|reserved_special_token_28|>",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
"128037": {
|
| 300 |
+
"content": "<|reserved_special_token_29|>",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": true
|
| 306 |
+
},
|
| 307 |
+
"128038": {
|
| 308 |
+
"content": "<|reserved_special_token_30|>",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": false,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": true
|
| 314 |
+
},
|
| 315 |
+
"128039": {
|
| 316 |
+
"content": "<|reserved_special_token_31|>",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": true
|
| 322 |
+
},
|
| 323 |
+
"128040": {
|
| 324 |
+
"content": "<|reserved_special_token_32|>",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": false,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": true
|
| 330 |
+
},
|
| 331 |
+
"128041": {
|
| 332 |
+
"content": "<|reserved_special_token_33|>",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
"128042": {
|
| 340 |
+
"content": "<|reserved_special_token_34|>",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": true
|
| 346 |
+
},
|
| 347 |
+
"128043": {
|
| 348 |
+
"content": "<|reserved_special_token_35|>",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": true
|
| 354 |
+
},
|
| 355 |
+
"128044": {
|
| 356 |
+
"content": "<|reserved_special_token_36|>",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": false,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": true
|
| 362 |
+
},
|
| 363 |
+
"128045": {
|
| 364 |
+
"content": "<|reserved_special_token_37|>",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
"128046": {
|
| 372 |
+
"content": "<|reserved_special_token_38|>",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": false,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": true
|
| 378 |
+
},
|
| 379 |
+
"128047": {
|
| 380 |
+
"content": "<|reserved_special_token_39|>",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": false,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": true
|
| 386 |
+
},
|
| 387 |
+
"128048": {
|
| 388 |
+
"content": "<|reserved_special_token_40|>",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": true
|
| 394 |
+
},
|
| 395 |
+
"128049": {
|
| 396 |
+
"content": "<|reserved_special_token_41|>",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": false,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": true
|
| 402 |
+
},
|
| 403 |
+
"128050": {
|
| 404 |
+
"content": "<|reserved_special_token_42|>",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": true
|
| 410 |
+
},
|
| 411 |
+
"128051": {
|
| 412 |
+
"content": "<|reserved_special_token_43|>",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": false,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": true
|
| 418 |
+
},
|
| 419 |
+
"128052": {
|
| 420 |
+
"content": "<|reserved_special_token_44|>",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": true
|
| 426 |
+
},
|
| 427 |
+
"128053": {
|
| 428 |
+
"content": "<|reserved_special_token_45|>",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": false,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": true
|
| 434 |
+
},
|
| 435 |
+
"128054": {
|
| 436 |
+
"content": "<|reserved_special_token_46|>",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": true
|
| 442 |
+
},
|
| 443 |
+
"128055": {
|
| 444 |
+
"content": "<|reserved_special_token_47|>",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": false,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": true
|
| 450 |
+
},
|
| 451 |
+
"128056": {
|
| 452 |
+
"content": "<|reserved_special_token_48|>",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": false,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": true
|
| 458 |
+
},
|
| 459 |
+
"128057": {
|
| 460 |
+
"content": "<|reserved_special_token_49|>",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": false,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": true
|
| 466 |
+
},
|
| 467 |
+
"128058": {
|
| 468 |
+
"content": "<|reserved_special_token_50|>",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": false,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": true
|
| 474 |
+
},
|
| 475 |
+
"128059": {
|
| 476 |
+
"content": "<|reserved_special_token_51|>",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": true
|
| 482 |
+
},
|
| 483 |
+
"128060": {
|
| 484 |
+
"content": "<|reserved_special_token_52|>",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": false,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": true
|
| 490 |
+
},
|
| 491 |
+
"128061": {
|
| 492 |
+
"content": "<|reserved_special_token_53|>",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": true
|
| 498 |
+
},
|
| 499 |
+
"128062": {
|
| 500 |
+
"content": "<|reserved_special_token_54|>",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": false,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": true
|
| 506 |
+
},
|
| 507 |
+
"128063": {
|
| 508 |
+
"content": "<|reserved_special_token_55|>",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": true
|
| 514 |
+
},
|
| 515 |
+
"128064": {
|
| 516 |
+
"content": "<|reserved_special_token_56|>",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": false,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": true
|
| 522 |
+
},
|
| 523 |
+
"128065": {
|
| 524 |
+
"content": "<|reserved_special_token_57|>",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": false,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": true
|
| 530 |
+
},
|
| 531 |
+
"128066": {
|
| 532 |
+
"content": "<|reserved_special_token_58|>",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": false,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": true
|
| 538 |
+
},
|
| 539 |
+
"128067": {
|
| 540 |
+
"content": "<|reserved_special_token_59|>",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": false,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": true
|
| 546 |
+
},
|
| 547 |
+
"128068": {
|
| 548 |
+
"content": "<|reserved_special_token_60|>",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": false,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": true
|
| 554 |
+
},
|
| 555 |
+
"128069": {
|
| 556 |
+
"content": "<|reserved_special_token_61|>",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": false,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": true
|
| 562 |
+
},
|
| 563 |
+
"128070": {
|
| 564 |
+
"content": "<|reserved_special_token_62|>",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": false,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": true
|
| 570 |
+
},
|
| 571 |
+
"128071": {
|
| 572 |
+
"content": "<|reserved_special_token_63|>",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": false,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": true
|
| 578 |
+
},
|
| 579 |
+
"128072": {
|
| 580 |
+
"content": "<|reserved_special_token_64|>",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": false,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": true
|
| 586 |
+
},
|
| 587 |
+
"128073": {
|
| 588 |
+
"content": "<|reserved_special_token_65|>",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": false,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": true
|
| 594 |
+
},
|
| 595 |
+
"128074": {
|
| 596 |
+
"content": "<|reserved_special_token_66|>",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": false,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": true
|
| 602 |
+
},
|
| 603 |
+
"128075": {
|
| 604 |
+
"content": "<|reserved_special_token_67|>",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": false,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": true
|
| 610 |
+
},
|
| 611 |
+
"128076": {
|
| 612 |
+
"content": "<|reserved_special_token_68|>",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": false,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": true
|
| 618 |
+
},
|
| 619 |
+
"128077": {
|
| 620 |
+
"content": "<|reserved_special_token_69|>",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": false,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": true
|
| 626 |
+
},
|
| 627 |
+
"128078": {
|
| 628 |
+
"content": "<|reserved_special_token_70|>",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": false,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": true
|
| 634 |
+
},
|
| 635 |
+
"128079": {
|
| 636 |
+
"content": "<|reserved_special_token_71|>",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": true
|
| 642 |
+
},
|
| 643 |
+
"128080": {
|
| 644 |
+
"content": "<|reserved_special_token_72|>",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": false,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": true
|
| 650 |
+
},
|
| 651 |
+
"128081": {
|
| 652 |
+
"content": "<|reserved_special_token_73|>",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": true
|
| 658 |
+
},
|
| 659 |
+
"128082": {
|
| 660 |
+
"content": "<|reserved_special_token_74|>",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": false,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": true
|
| 666 |
+
},
|
| 667 |
+
"128083": {
|
| 668 |
+
"content": "<|reserved_special_token_75|>",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": false,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": true
|
| 674 |
+
},
|
| 675 |
+
"128084": {
|
| 676 |
+
"content": "<|reserved_special_token_76|>",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": true
|
| 682 |
+
},
|
| 683 |
+
"128085": {
|
| 684 |
+
"content": "<|reserved_special_token_77|>",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": false,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": true
|
| 690 |
+
},
|
| 691 |
+
"128086": {
|
| 692 |
+
"content": "<|reserved_special_token_78|>",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": true
|
| 698 |
+
},
|
| 699 |
+
"128087": {
|
| 700 |
+
"content": "<|reserved_special_token_79|>",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": false,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": true
|
| 706 |
+
},
|
| 707 |
+
"128088": {
|
| 708 |
+
"content": "<|reserved_special_token_80|>",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": true
|
| 714 |
+
},
|
| 715 |
+
"128089": {
|
| 716 |
+
"content": "<|reserved_special_token_81|>",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": false,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": true
|
| 722 |
+
},
|
| 723 |
+
"128090": {
|
| 724 |
+
"content": "<|reserved_special_token_82|>",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": false,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": true
|
| 730 |
+
},
|
| 731 |
+
"128091": {
|
| 732 |
+
"content": "<|reserved_special_token_83|>",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": false,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": true
|
| 738 |
+
},
|
| 739 |
+
"128092": {
|
| 740 |
+
"content": "<|reserved_special_token_84|>",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": false,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": true
|
| 746 |
+
},
|
| 747 |
+
"128093": {
|
| 748 |
+
"content": "<|reserved_special_token_85|>",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": false,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": true
|
| 754 |
+
},
|
| 755 |
+
"128094": {
|
| 756 |
+
"content": "<|reserved_special_token_86|>",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": false,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": true
|
| 762 |
+
},
|
| 763 |
+
"128095": {
|
| 764 |
+
"content": "<|reserved_special_token_87|>",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": false,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": true
|
| 770 |
+
},
|
| 771 |
+
"128096": {
|
| 772 |
+
"content": "<|reserved_special_token_88|>",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": false,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": true
|
| 778 |
+
},
|
| 779 |
+
"128097": {
|
| 780 |
+
"content": "<|reserved_special_token_89|>",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": false,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": true
|
| 786 |
+
},
|
| 787 |
+
"128098": {
|
| 788 |
+
"content": "<|reserved_special_token_90|>",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": false,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": true
|
| 794 |
+
},
|
| 795 |
+
"128099": {
|
| 796 |
+
"content": "<|reserved_special_token_91|>",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": false,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": true
|
| 802 |
+
},
|
| 803 |
+
"128100": {
|
| 804 |
+
"content": "<|reserved_special_token_92|>",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": false,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": true
|
| 810 |
+
},
|
| 811 |
+
"128101": {
|
| 812 |
+
"content": "<|reserved_special_token_93|>",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": false,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": true
|
| 818 |
+
},
|
| 819 |
+
"128102": {
|
| 820 |
+
"content": "<|reserved_special_token_94|>",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": false,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": true
|
| 826 |
+
},
|
| 827 |
+
"128103": {
|
| 828 |
+
"content": "<|reserved_special_token_95|>",
|
| 829 |
+
"lstrip": false,
|
| 830 |
+
"normalized": false,
|
| 831 |
+
"rstrip": false,
|
| 832 |
+
"single_word": false,
|
| 833 |
+
"special": true
|
| 834 |
+
},
|
| 835 |
+
"128104": {
|
| 836 |
+
"content": "<|reserved_special_token_96|>",
|
| 837 |
+
"lstrip": false,
|
| 838 |
+
"normalized": false,
|
| 839 |
+
"rstrip": false,
|
| 840 |
+
"single_word": false,
|
| 841 |
+
"special": true
|
| 842 |
+
},
|
| 843 |
+
"128105": {
|
| 844 |
+
"content": "<|reserved_special_token_97|>",
|
| 845 |
+
"lstrip": false,
|
| 846 |
+
"normalized": false,
|
| 847 |
+
"rstrip": false,
|
| 848 |
+
"single_word": false,
|
| 849 |
+
"special": true
|
| 850 |
+
},
|
| 851 |
+
"128106": {
|
| 852 |
+
"content": "<|reserved_special_token_98|>",
|
| 853 |
+
"lstrip": false,
|
| 854 |
+
"normalized": false,
|
| 855 |
+
"rstrip": false,
|
| 856 |
+
"single_word": false,
|
| 857 |
+
"special": true
|
| 858 |
+
},
|
| 859 |
+
"128107": {
|
| 860 |
+
"content": "<|reserved_special_token_99|>",
|
| 861 |
+
"lstrip": false,
|
| 862 |
+
"normalized": false,
|
| 863 |
+
"rstrip": false,
|
| 864 |
+
"single_word": false,
|
| 865 |
+
"special": true
|
| 866 |
+
},
|
| 867 |
+
"128108": {
|
| 868 |
+
"content": "<|reserved_special_token_100|>",
|
| 869 |
+
"lstrip": false,
|
| 870 |
+
"normalized": false,
|
| 871 |
+
"rstrip": false,
|
| 872 |
+
"single_word": false,
|
| 873 |
+
"special": true
|
| 874 |
+
},
|
| 875 |
+
"128109": {
|
| 876 |
+
"content": "<|reserved_special_token_101|>",
|
| 877 |
+
"lstrip": false,
|
| 878 |
+
"normalized": false,
|
| 879 |
+
"rstrip": false,
|
| 880 |
+
"single_word": false,
|
| 881 |
+
"special": true
|
| 882 |
+
},
|
| 883 |
+
"128110": {
|
| 884 |
+
"content": "<|reserved_special_token_102|>",
|
| 885 |
+
"lstrip": false,
|
| 886 |
+
"normalized": false,
|
| 887 |
+
"rstrip": false,
|
| 888 |
+
"single_word": false,
|
| 889 |
+
"special": true
|
| 890 |
+
},
|
| 891 |
+
"128111": {
|
| 892 |
+
"content": "<|reserved_special_token_103|>",
|
| 893 |
+
"lstrip": false,
|
| 894 |
+
"normalized": false,
|
| 895 |
+
"rstrip": false,
|
| 896 |
+
"single_word": false,
|
| 897 |
+
"special": true
|
| 898 |
+
},
|
| 899 |
+
"128112": {
|
| 900 |
+
"content": "<|reserved_special_token_104|>",
|
| 901 |
+
"lstrip": false,
|
| 902 |
+
"normalized": false,
|
| 903 |
+
"rstrip": false,
|
| 904 |
+
"single_word": false,
|
| 905 |
+
"special": true
|
| 906 |
+
},
|
| 907 |
+
"128113": {
|
| 908 |
+
"content": "<|reserved_special_token_105|>",
|
| 909 |
+
"lstrip": false,
|
| 910 |
+
"normalized": false,
|
| 911 |
+
"rstrip": false,
|
| 912 |
+
"single_word": false,
|
| 913 |
+
"special": true
|
| 914 |
+
},
|
| 915 |
+
"128114": {
|
| 916 |
+
"content": "<|reserved_special_token_106|>",
|
| 917 |
+
"lstrip": false,
|
| 918 |
+
"normalized": false,
|
| 919 |
+
"rstrip": false,
|
| 920 |
+
"single_word": false,
|
| 921 |
+
"special": true
|
| 922 |
+
},
|
| 923 |
+
"128115": {
|
| 924 |
+
"content": "<|reserved_special_token_107|>",
|
| 925 |
+
"lstrip": false,
|
| 926 |
+
"normalized": false,
|
| 927 |
+
"rstrip": false,
|
| 928 |
+
"single_word": false,
|
| 929 |
+
"special": true
|
| 930 |
+
},
|
| 931 |
+
"128116": {
|
| 932 |
+
"content": "<|reserved_special_token_108|>",
|
| 933 |
+
"lstrip": false,
|
| 934 |
+
"normalized": false,
|
| 935 |
+
"rstrip": false,
|
| 936 |
+
"single_word": false,
|
| 937 |
+
"special": true
|
| 938 |
+
},
|
| 939 |
+
"128117": {
|
| 940 |
+
"content": "<|reserved_special_token_109|>",
|
| 941 |
+
"lstrip": false,
|
| 942 |
+
"normalized": false,
|
| 943 |
+
"rstrip": false,
|
| 944 |
+
"single_word": false,
|
| 945 |
+
"special": true
|
| 946 |
+
},
|
| 947 |
+
"128118": {
|
| 948 |
+
"content": "<|reserved_special_token_110|>",
|
| 949 |
+
"lstrip": false,
|
| 950 |
+
"normalized": false,
|
| 951 |
+
"rstrip": false,
|
| 952 |
+
"single_word": false,
|
| 953 |
+
"special": true
|
| 954 |
+
},
|
| 955 |
+
"128119": {
|
| 956 |
+
"content": "<|reserved_special_token_111|>",
|
| 957 |
+
"lstrip": false,
|
| 958 |
+
"normalized": false,
|
| 959 |
+
"rstrip": false,
|
| 960 |
+
"single_word": false,
|
| 961 |
+
"special": true
|
| 962 |
+
},
|
| 963 |
+
"128120": {
|
| 964 |
+
"content": "<|reserved_special_token_112|>",
|
| 965 |
+
"lstrip": false,
|
| 966 |
+
"normalized": false,
|
| 967 |
+
"rstrip": false,
|
| 968 |
+
"single_word": false,
|
| 969 |
+
"special": true
|
| 970 |
+
},
|
| 971 |
+
"128121": {
|
| 972 |
+
"content": "<|reserved_special_token_113|>",
|
| 973 |
+
"lstrip": false,
|
| 974 |
+
"normalized": false,
|
| 975 |
+
"rstrip": false,
|
| 976 |
+
"single_word": false,
|
| 977 |
+
"special": true
|
| 978 |
+
},
|
| 979 |
+
"128122": {
|
| 980 |
+
"content": "<|reserved_special_token_114|>",
|
| 981 |
+
"lstrip": false,
|
| 982 |
+
"normalized": false,
|
| 983 |
+
"rstrip": false,
|
| 984 |
+
"single_word": false,
|
| 985 |
+
"special": true
|
| 986 |
+
},
|
| 987 |
+
"128123": {
|
| 988 |
+
"content": "<|reserved_special_token_115|>",
|
| 989 |
+
"lstrip": false,
|
| 990 |
+
"normalized": false,
|
| 991 |
+
"rstrip": false,
|
| 992 |
+
"single_word": false,
|
| 993 |
+
"special": true
|
| 994 |
+
},
|
| 995 |
+
"128124": {
|
| 996 |
+
"content": "<|reserved_special_token_116|>",
|
| 997 |
+
"lstrip": false,
|
| 998 |
+
"normalized": false,
|
| 999 |
+
"rstrip": false,
|
| 1000 |
+
"single_word": false,
|
| 1001 |
+
"special": true
|
| 1002 |
+
},
|
| 1003 |
+
"128125": {
|
| 1004 |
+
"content": "<|reserved_special_token_117|>",
|
| 1005 |
+
"lstrip": false,
|
| 1006 |
+
"normalized": false,
|
| 1007 |
+
"rstrip": false,
|
| 1008 |
+
"single_word": false,
|
| 1009 |
+
"special": true
|
| 1010 |
+
},
|
| 1011 |
+
"128126": {
|
| 1012 |
+
"content": "<|reserved_special_token_118|>",
|
| 1013 |
+
"lstrip": false,
|
| 1014 |
+
"normalized": false,
|
| 1015 |
+
"rstrip": false,
|
| 1016 |
+
"single_word": false,
|
| 1017 |
+
"special": true
|
| 1018 |
+
},
|
| 1019 |
+
"128127": {
|
| 1020 |
+
"content": "<|reserved_special_token_119|>",
|
| 1021 |
+
"lstrip": false,
|
| 1022 |
+
"normalized": false,
|
| 1023 |
+
"rstrip": false,
|
| 1024 |
+
"single_word": false,
|
| 1025 |
+
"special": true
|
| 1026 |
+
},
|
| 1027 |
+
"128128": {
|
| 1028 |
+
"content": "<|reserved_special_token_120|>",
|
| 1029 |
+
"lstrip": false,
|
| 1030 |
+
"normalized": false,
|
| 1031 |
+
"rstrip": false,
|
| 1032 |
+
"single_word": false,
|
| 1033 |
+
"special": true
|
| 1034 |
+
},
|
| 1035 |
+
"128129": {
|
| 1036 |
+
"content": "<|reserved_special_token_121|>",
|
| 1037 |
+
"lstrip": false,
|
| 1038 |
+
"normalized": false,
|
| 1039 |
+
"rstrip": false,
|
| 1040 |
+
"single_word": false,
|
| 1041 |
+
"special": true
|
| 1042 |
+
},
|
| 1043 |
+
"128130": {
|
| 1044 |
+
"content": "<|reserved_special_token_122|>",
|
| 1045 |
+
"lstrip": false,
|
| 1046 |
+
"normalized": false,
|
| 1047 |
+
"rstrip": false,
|
| 1048 |
+
"single_word": false,
|
| 1049 |
+
"special": true
|
| 1050 |
+
},
|
| 1051 |
+
"128131": {
|
| 1052 |
+
"content": "<|reserved_special_token_123|>",
|
| 1053 |
+
"lstrip": false,
|
| 1054 |
+
"normalized": false,
|
| 1055 |
+
"rstrip": false,
|
| 1056 |
+
"single_word": false,
|
| 1057 |
+
"special": true
|
| 1058 |
+
},
|
| 1059 |
+
"128132": {
|
| 1060 |
+
"content": "<|reserved_special_token_124|>",
|
| 1061 |
+
"lstrip": false,
|
| 1062 |
+
"normalized": false,
|
| 1063 |
+
"rstrip": false,
|
| 1064 |
+
"single_word": false,
|
| 1065 |
+
"special": true
|
| 1066 |
+
},
|
| 1067 |
+
"128133": {
|
| 1068 |
+
"content": "<|reserved_special_token_125|>",
|
| 1069 |
+
"lstrip": false,
|
| 1070 |
+
"normalized": false,
|
| 1071 |
+
"rstrip": false,
|
| 1072 |
+
"single_word": false,
|
| 1073 |
+
"special": true
|
| 1074 |
+
},
|
| 1075 |
+
"128134": {
|
| 1076 |
+
"content": "<|reserved_special_token_126|>",
|
| 1077 |
+
"lstrip": false,
|
| 1078 |
+
"normalized": false,
|
| 1079 |
+
"rstrip": false,
|
| 1080 |
+
"single_word": false,
|
| 1081 |
+
"special": true
|
| 1082 |
+
},
|
| 1083 |
+
"128135": {
|
| 1084 |
+
"content": "<|reserved_special_token_127|>",
|
| 1085 |
+
"lstrip": false,
|
| 1086 |
+
"normalized": false,
|
| 1087 |
+
"rstrip": false,
|
| 1088 |
+
"single_word": false,
|
| 1089 |
+
"special": true
|
| 1090 |
+
},
|
| 1091 |
+
"128136": {
|
| 1092 |
+
"content": "<|reserved_special_token_128|>",
|
| 1093 |
+
"lstrip": false,
|
| 1094 |
+
"normalized": false,
|
| 1095 |
+
"rstrip": false,
|
| 1096 |
+
"single_word": false,
|
| 1097 |
+
"special": true
|
| 1098 |
+
},
|
| 1099 |
+
"128137": {
|
| 1100 |
+
"content": "<|reserved_special_token_129|>",
|
| 1101 |
+
"lstrip": false,
|
| 1102 |
+
"normalized": false,
|
| 1103 |
+
"rstrip": false,
|
| 1104 |
+
"single_word": false,
|
| 1105 |
+
"special": true
|
| 1106 |
+
},
|
| 1107 |
+
"128138": {
|
| 1108 |
+
"content": "<|reserved_special_token_130|>",
|
| 1109 |
+
"lstrip": false,
|
| 1110 |
+
"normalized": false,
|
| 1111 |
+
"rstrip": false,
|
| 1112 |
+
"single_word": false,
|
| 1113 |
+
"special": true
|
| 1114 |
+
},
|
| 1115 |
+
"128139": {
|
| 1116 |
+
"content": "<|reserved_special_token_131|>",
|
| 1117 |
+
"lstrip": false,
|
| 1118 |
+
"normalized": false,
|
| 1119 |
+
"rstrip": false,
|
| 1120 |
+
"single_word": false,
|
| 1121 |
+
"special": true
|
| 1122 |
+
},
|
| 1123 |
+
"128140": {
|
| 1124 |
+
"content": "<|reserved_special_token_132|>",
|
| 1125 |
+
"lstrip": false,
|
| 1126 |
+
"normalized": false,
|
| 1127 |
+
"rstrip": false,
|
| 1128 |
+
"single_word": false,
|
| 1129 |
+
"special": true
|
| 1130 |
+
},
|
| 1131 |
+
"128141": {
|
| 1132 |
+
"content": "<|reserved_special_token_133|>",
|
| 1133 |
+
"lstrip": false,
|
| 1134 |
+
"normalized": false,
|
| 1135 |
+
"rstrip": false,
|
| 1136 |
+
"single_word": false,
|
| 1137 |
+
"special": true
|
| 1138 |
+
},
|
| 1139 |
+
"128142": {
|
| 1140 |
+
"content": "<|reserved_special_token_134|>",
|
| 1141 |
+
"lstrip": false,
|
| 1142 |
+
"normalized": false,
|
| 1143 |
+
"rstrip": false,
|
| 1144 |
+
"single_word": false,
|
| 1145 |
+
"special": true
|
| 1146 |
+
},
|
| 1147 |
+
"128143": {
|
| 1148 |
+
"content": "<|reserved_special_token_135|>",
|
| 1149 |
+
"lstrip": false,
|
| 1150 |
+
"normalized": false,
|
| 1151 |
+
"rstrip": false,
|
| 1152 |
+
"single_word": false,
|
| 1153 |
+
"special": true
|
| 1154 |
+
},
|
| 1155 |
+
"128144": {
|
| 1156 |
+
"content": "<|reserved_special_token_136|>",
|
| 1157 |
+
"lstrip": false,
|
| 1158 |
+
"normalized": false,
|
| 1159 |
+
"rstrip": false,
|
| 1160 |
+
"single_word": false,
|
| 1161 |
+
"special": true
|
| 1162 |
+
},
|
| 1163 |
+
"128145": {
|
| 1164 |
+
"content": "<|reserved_special_token_137|>",
|
| 1165 |
+
"lstrip": false,
|
| 1166 |
+
"normalized": false,
|
| 1167 |
+
"rstrip": false,
|
| 1168 |
+
"single_word": false,
|
| 1169 |
+
"special": true
|
| 1170 |
+
},
|
| 1171 |
+
"128146": {
|
| 1172 |
+
"content": "<|reserved_special_token_138|>",
|
| 1173 |
+
"lstrip": false,
|
| 1174 |
+
"normalized": false,
|
| 1175 |
+
"rstrip": false,
|
| 1176 |
+
"single_word": false,
|
| 1177 |
+
"special": true
|
| 1178 |
+
},
|
| 1179 |
+
"128147": {
|
| 1180 |
+
"content": "<|reserved_special_token_139|>",
|
| 1181 |
+
"lstrip": false,
|
| 1182 |
+
"normalized": false,
|
| 1183 |
+
"rstrip": false,
|
| 1184 |
+
"single_word": false,
|
| 1185 |
+
"special": true
|
| 1186 |
+
},
|
| 1187 |
+
"128148": {
|
| 1188 |
+
"content": "<|reserved_special_token_140|>",
|
| 1189 |
+
"lstrip": false,
|
| 1190 |
+
"normalized": false,
|
| 1191 |
+
"rstrip": false,
|
| 1192 |
+
"single_word": false,
|
| 1193 |
+
"special": true
|
| 1194 |
+
},
|
| 1195 |
+
"128149": {
|
| 1196 |
+
"content": "<|reserved_special_token_141|>",
|
| 1197 |
+
"lstrip": false,
|
| 1198 |
+
"normalized": false,
|
| 1199 |
+
"rstrip": false,
|
| 1200 |
+
"single_word": false,
|
| 1201 |
+
"special": true
|
| 1202 |
+
},
|
| 1203 |
+
"128150": {
|
| 1204 |
+
"content": "<|reserved_special_token_142|>",
|
| 1205 |
+
"lstrip": false,
|
| 1206 |
+
"normalized": false,
|
| 1207 |
+
"rstrip": false,
|
| 1208 |
+
"single_word": false,
|
| 1209 |
+
"special": true
|
| 1210 |
+
},
|
| 1211 |
+
"128151": {
|
| 1212 |
+
"content": "<|reserved_special_token_143|>",
|
| 1213 |
+
"lstrip": false,
|
| 1214 |
+
"normalized": false,
|
| 1215 |
+
"rstrip": false,
|
| 1216 |
+
"single_word": false,
|
| 1217 |
+
"special": true
|
| 1218 |
+
},
|
| 1219 |
+
"128152": {
|
| 1220 |
+
"content": "<|reserved_special_token_144|>",
|
| 1221 |
+
"lstrip": false,
|
| 1222 |
+
"normalized": false,
|
| 1223 |
+
"rstrip": false,
|
| 1224 |
+
"single_word": false,
|
| 1225 |
+
"special": true
|
| 1226 |
+
},
|
| 1227 |
+
"128153": {
|
| 1228 |
+
"content": "<|reserved_special_token_145|>",
|
| 1229 |
+
"lstrip": false,
|
| 1230 |
+
"normalized": false,
|
| 1231 |
+
"rstrip": false,
|
| 1232 |
+
"single_word": false,
|
| 1233 |
+
"special": true
|
| 1234 |
+
},
|
| 1235 |
+
"128154": {
|
| 1236 |
+
"content": "<|reserved_special_token_146|>",
|
| 1237 |
+
"lstrip": false,
|
| 1238 |
+
"normalized": false,
|
| 1239 |
+
"rstrip": false,
|
| 1240 |
+
"single_word": false,
|
| 1241 |
+
"special": true
|
| 1242 |
+
},
|
| 1243 |
+
"128155": {
|
| 1244 |
+
"content": "<|reserved_special_token_147|>",
|
| 1245 |
+
"lstrip": false,
|
| 1246 |
+
"normalized": false,
|
| 1247 |
+
"rstrip": false,
|
| 1248 |
+
"single_word": false,
|
| 1249 |
+
"special": true
|
| 1250 |
+
},
|
| 1251 |
+
"128156": {
|
| 1252 |
+
"content": "<|reserved_special_token_148|>",
|
| 1253 |
+
"lstrip": false,
|
| 1254 |
+
"normalized": false,
|
| 1255 |
+
"rstrip": false,
|
| 1256 |
+
"single_word": false,
|
| 1257 |
+
"special": true
|
| 1258 |
+
},
|
| 1259 |
+
"128157": {
|
| 1260 |
+
"content": "<|reserved_special_token_149|>",
|
| 1261 |
+
"lstrip": false,
|
| 1262 |
+
"normalized": false,
|
| 1263 |
+
"rstrip": false,
|
| 1264 |
+
"single_word": false,
|
| 1265 |
+
"special": true
|
| 1266 |
+
},
|
| 1267 |
+
"128158": {
|
| 1268 |
+
"content": "<|reserved_special_token_150|>",
|
| 1269 |
+
"lstrip": false,
|
| 1270 |
+
"normalized": false,
|
| 1271 |
+
"rstrip": false,
|
| 1272 |
+
"single_word": false,
|
| 1273 |
+
"special": true
|
| 1274 |
+
},
|
| 1275 |
+
"128159": {
|
| 1276 |
+
"content": "<|reserved_special_token_151|>",
|
| 1277 |
+
"lstrip": false,
|
| 1278 |
+
"normalized": false,
|
| 1279 |
+
"rstrip": false,
|
| 1280 |
+
"single_word": false,
|
| 1281 |
+
"special": true
|
| 1282 |
+
},
|
| 1283 |
+
"128160": {
|
| 1284 |
+
"content": "<|reserved_special_token_152|>",
|
| 1285 |
+
"lstrip": false,
|
| 1286 |
+
"normalized": false,
|
| 1287 |
+
"rstrip": false,
|
| 1288 |
+
"single_word": false,
|
| 1289 |
+
"special": true
|
| 1290 |
+
},
|
| 1291 |
+
"128161": {
|
| 1292 |
+
"content": "<|reserved_special_token_153|>",
|
| 1293 |
+
"lstrip": false,
|
| 1294 |
+
"normalized": false,
|
| 1295 |
+
"rstrip": false,
|
| 1296 |
+
"single_word": false,
|
| 1297 |
+
"special": true
|
| 1298 |
+
},
|
| 1299 |
+
"128162": {
|
| 1300 |
+
"content": "<|reserved_special_token_154|>",
|
| 1301 |
+
"lstrip": false,
|
| 1302 |
+
"normalized": false,
|
| 1303 |
+
"rstrip": false,
|
| 1304 |
+
"single_word": false,
|
| 1305 |
+
"special": true
|
| 1306 |
+
},
|
| 1307 |
+
"128163": {
|
| 1308 |
+
"content": "<|reserved_special_token_155|>",
|
| 1309 |
+
"lstrip": false,
|
| 1310 |
+
"normalized": false,
|
| 1311 |
+
"rstrip": false,
|
| 1312 |
+
"single_word": false,
|
| 1313 |
+
"special": true
|
| 1314 |
+
},
|
| 1315 |
+
"128164": {
|
| 1316 |
+
"content": "<|reserved_special_token_156|>",
|
| 1317 |
+
"lstrip": false,
|
| 1318 |
+
"normalized": false,
|
| 1319 |
+
"rstrip": false,
|
| 1320 |
+
"single_word": false,
|
| 1321 |
+
"special": true
|
| 1322 |
+
},
|
| 1323 |
+
"128165": {
|
| 1324 |
+
"content": "<|reserved_special_token_157|>",
|
| 1325 |
+
"lstrip": false,
|
| 1326 |
+
"normalized": false,
|
| 1327 |
+
"rstrip": false,
|
| 1328 |
+
"single_word": false,
|
| 1329 |
+
"special": true
|
| 1330 |
+
},
|
| 1331 |
+
"128166": {
|
| 1332 |
+
"content": "<|reserved_special_token_158|>",
|
| 1333 |
+
"lstrip": false,
|
| 1334 |
+
"normalized": false,
|
| 1335 |
+
"rstrip": false,
|
| 1336 |
+
"single_word": false,
|
| 1337 |
+
"special": true
|
| 1338 |
+
},
|
| 1339 |
+
"128167": {
|
| 1340 |
+
"content": "<|reserved_special_token_159|>",
|
| 1341 |
+
"lstrip": false,
|
| 1342 |
+
"normalized": false,
|
| 1343 |
+
"rstrip": false,
|
| 1344 |
+
"single_word": false,
|
| 1345 |
+
"special": true
|
| 1346 |
+
},
|
| 1347 |
+
"128168": {
|
| 1348 |
+
"content": "<|reserved_special_token_160|>",
|
| 1349 |
+
"lstrip": false,
|
| 1350 |
+
"normalized": false,
|
| 1351 |
+
"rstrip": false,
|
| 1352 |
+
"single_word": false,
|
| 1353 |
+
"special": true
|
| 1354 |
+
},
|
| 1355 |
+
"128169": {
|
| 1356 |
+
"content": "<|reserved_special_token_161|>",
|
| 1357 |
+
"lstrip": false,
|
| 1358 |
+
"normalized": false,
|
| 1359 |
+
"rstrip": false,
|
| 1360 |
+
"single_word": false,
|
| 1361 |
+
"special": true
|
| 1362 |
+
},
|
| 1363 |
+
"128170": {
|
| 1364 |
+
"content": "<|reserved_special_token_162|>",
|
| 1365 |
+
"lstrip": false,
|
| 1366 |
+
"normalized": false,
|
| 1367 |
+
"rstrip": false,
|
| 1368 |
+
"single_word": false,
|
| 1369 |
+
"special": true
|
| 1370 |
+
},
|
| 1371 |
+
"128171": {
|
| 1372 |
+
"content": "<|reserved_special_token_163|>",
|
| 1373 |
+
"lstrip": false,
|
| 1374 |
+
"normalized": false,
|
| 1375 |
+
"rstrip": false,
|
| 1376 |
+
"single_word": false,
|
| 1377 |
+
"special": true
|
| 1378 |
+
},
|
| 1379 |
+
"128172": {
|
| 1380 |
+
"content": "<|reserved_special_token_164|>",
|
| 1381 |
+
"lstrip": false,
|
| 1382 |
+
"normalized": false,
|
| 1383 |
+
"rstrip": false,
|
| 1384 |
+
"single_word": false,
|
| 1385 |
+
"special": true
|
| 1386 |
+
},
|
| 1387 |
+
"128173": {
|
| 1388 |
+
"content": "<|reserved_special_token_165|>",
|
| 1389 |
+
"lstrip": false,
|
| 1390 |
+
"normalized": false,
|
| 1391 |
+
"rstrip": false,
|
| 1392 |
+
"single_word": false,
|
| 1393 |
+
"special": true
|
| 1394 |
+
},
|
| 1395 |
+
"128174": {
|
| 1396 |
+
"content": "<|reserved_special_token_166|>",
|
| 1397 |
+
"lstrip": false,
|
| 1398 |
+
"normalized": false,
|
| 1399 |
+
"rstrip": false,
|
| 1400 |
+
"single_word": false,
|
| 1401 |
+
"special": true
|
| 1402 |
+
},
|
| 1403 |
+
"128175": {
|
| 1404 |
+
"content": "<|reserved_special_token_167|>",
|
| 1405 |
+
"lstrip": false,
|
| 1406 |
+
"normalized": false,
|
| 1407 |
+
"rstrip": false,
|
| 1408 |
+
"single_word": false,
|
| 1409 |
+
"special": true
|
| 1410 |
+
},
|
| 1411 |
+
"128176": {
|
| 1412 |
+
"content": "<|reserved_special_token_168|>",
|
| 1413 |
+
"lstrip": false,
|
| 1414 |
+
"normalized": false,
|
| 1415 |
+
"rstrip": false,
|
| 1416 |
+
"single_word": false,
|
| 1417 |
+
"special": true
|
| 1418 |
+
},
|
| 1419 |
+
"128177": {
|
| 1420 |
+
"content": "<|reserved_special_token_169|>",
|
| 1421 |
+
"lstrip": false,
|
| 1422 |
+
"normalized": false,
|
| 1423 |
+
"rstrip": false,
|
| 1424 |
+
"single_word": false,
|
| 1425 |
+
"special": true
|
| 1426 |
+
},
|
| 1427 |
+
"128178": {
|
| 1428 |
+
"content": "<|reserved_special_token_170|>",
|
| 1429 |
+
"lstrip": false,
|
| 1430 |
+
"normalized": false,
|
| 1431 |
+
"rstrip": false,
|
| 1432 |
+
"single_word": false,
|
| 1433 |
+
"special": true
|
| 1434 |
+
},
|
| 1435 |
+
"128179": {
|
| 1436 |
+
"content": "<|reserved_special_token_171|>",
|
| 1437 |
+
"lstrip": false,
|
| 1438 |
+
"normalized": false,
|
| 1439 |
+
"rstrip": false,
|
| 1440 |
+
"single_word": false,
|
| 1441 |
+
"special": true
|
| 1442 |
+
},
|
| 1443 |
+
"128180": {
|
| 1444 |
+
"content": "<|reserved_special_token_172|>",
|
| 1445 |
+
"lstrip": false,
|
| 1446 |
+
"normalized": false,
|
| 1447 |
+
"rstrip": false,
|
| 1448 |
+
"single_word": false,
|
| 1449 |
+
"special": true
|
| 1450 |
+
},
|
| 1451 |
+
"128181": {
|
| 1452 |
+
"content": "<|reserved_special_token_173|>",
|
| 1453 |
+
"lstrip": false,
|
| 1454 |
+
"normalized": false,
|
| 1455 |
+
"rstrip": false,
|
| 1456 |
+
"single_word": false,
|
| 1457 |
+
"special": true
|
| 1458 |
+
},
|
| 1459 |
+
"128182": {
|
| 1460 |
+
"content": "<|reserved_special_token_174|>",
|
| 1461 |
+
"lstrip": false,
|
| 1462 |
+
"normalized": false,
|
| 1463 |
+
"rstrip": false,
|
| 1464 |
+
"single_word": false,
|
| 1465 |
+
"special": true
|
| 1466 |
+
},
|
| 1467 |
+
"128183": {
|
| 1468 |
+
"content": "<|reserved_special_token_175|>",
|
| 1469 |
+
"lstrip": false,
|
| 1470 |
+
"normalized": false,
|
| 1471 |
+
"rstrip": false,
|
| 1472 |
+
"single_word": false,
|
| 1473 |
+
"special": true
|
| 1474 |
+
},
|
| 1475 |
+
"128184": {
|
| 1476 |
+
"content": "<|reserved_special_token_176|>",
|
| 1477 |
+
"lstrip": false,
|
| 1478 |
+
"normalized": false,
|
| 1479 |
+
"rstrip": false,
|
| 1480 |
+
"single_word": false,
|
| 1481 |
+
"special": true
|
| 1482 |
+
},
|
| 1483 |
+
"128185": {
|
| 1484 |
+
"content": "<|reserved_special_token_177|>",
|
| 1485 |
+
"lstrip": false,
|
| 1486 |
+
"normalized": false,
|
| 1487 |
+
"rstrip": false,
|
| 1488 |
+
"single_word": false,
|
| 1489 |
+
"special": true
|
| 1490 |
+
},
|
| 1491 |
+
"128186": {
|
| 1492 |
+
"content": "<|reserved_special_token_178|>",
|
| 1493 |
+
"lstrip": false,
|
| 1494 |
+
"normalized": false,
|
| 1495 |
+
"rstrip": false,
|
| 1496 |
+
"single_word": false,
|
| 1497 |
+
"special": true
|
| 1498 |
+
},
|
| 1499 |
+
"128187": {
|
| 1500 |
+
"content": "<|reserved_special_token_179|>",
|
| 1501 |
+
"lstrip": false,
|
| 1502 |
+
"normalized": false,
|
| 1503 |
+
"rstrip": false,
|
| 1504 |
+
"single_word": false,
|
| 1505 |
+
"special": true
|
| 1506 |
+
},
|
| 1507 |
+
"128188": {
|
| 1508 |
+
"content": "<|reserved_special_token_180|>",
|
| 1509 |
+
"lstrip": false,
|
| 1510 |
+
"normalized": false,
|
| 1511 |
+
"rstrip": false,
|
| 1512 |
+
"single_word": false,
|
| 1513 |
+
"special": true
|
| 1514 |
+
},
|
| 1515 |
+
"128189": {
|
| 1516 |
+
"content": "<|reserved_special_token_181|>",
|
| 1517 |
+
"lstrip": false,
|
| 1518 |
+
"normalized": false,
|
| 1519 |
+
"rstrip": false,
|
| 1520 |
+
"single_word": false,
|
| 1521 |
+
"special": true
|
| 1522 |
+
},
|
| 1523 |
+
"128190": {
|
| 1524 |
+
"content": "<|reserved_special_token_182|>",
|
| 1525 |
+
"lstrip": false,
|
| 1526 |
+
"normalized": false,
|
| 1527 |
+
"rstrip": false,
|
| 1528 |
+
"single_word": false,
|
| 1529 |
+
"special": true
|
| 1530 |
+
},
|
| 1531 |
+
"128191": {
|
| 1532 |
+
"content": "<|reserved_special_token_183|>",
|
| 1533 |
+
"lstrip": false,
|
| 1534 |
+
"normalized": false,
|
| 1535 |
+
"rstrip": false,
|
| 1536 |
+
"single_word": false,
|
| 1537 |
+
"special": true
|
| 1538 |
+
},
|
| 1539 |
+
"128192": {
|
| 1540 |
+
"content": "<|reserved_special_token_184|>",
|
| 1541 |
+
"lstrip": false,
|
| 1542 |
+
"normalized": false,
|
| 1543 |
+
"rstrip": false,
|
| 1544 |
+
"single_word": false,
|
| 1545 |
+
"special": true
|
| 1546 |
+
},
|
| 1547 |
+
"128193": {
|
| 1548 |
+
"content": "<|reserved_special_token_185|>",
|
| 1549 |
+
"lstrip": false,
|
| 1550 |
+
"normalized": false,
|
| 1551 |
+
"rstrip": false,
|
| 1552 |
+
"single_word": false,
|
| 1553 |
+
"special": true
|
| 1554 |
+
},
|
| 1555 |
+
"128194": {
|
| 1556 |
+
"content": "<|reserved_special_token_186|>",
|
| 1557 |
+
"lstrip": false,
|
| 1558 |
+
"normalized": false,
|
| 1559 |
+
"rstrip": false,
|
| 1560 |
+
"single_word": false,
|
| 1561 |
+
"special": true
|
| 1562 |
+
},
|
| 1563 |
+
"128195": {
|
| 1564 |
+
"content": "<|reserved_special_token_187|>",
|
| 1565 |
+
"lstrip": false,
|
| 1566 |
+
"normalized": false,
|
| 1567 |
+
"rstrip": false,
|
| 1568 |
+
"single_word": false,
|
| 1569 |
+
"special": true
|
| 1570 |
+
},
|
| 1571 |
+
"128196": {
|
| 1572 |
+
"content": "<|reserved_special_token_188|>",
|
| 1573 |
+
"lstrip": false,
|
| 1574 |
+
"normalized": false,
|
| 1575 |
+
"rstrip": false,
|
| 1576 |
+
"single_word": false,
|
| 1577 |
+
"special": true
|
| 1578 |
+
},
|
| 1579 |
+
"128197": {
|
| 1580 |
+
"content": "<|reserved_special_token_189|>",
|
| 1581 |
+
"lstrip": false,
|
| 1582 |
+
"normalized": false,
|
| 1583 |
+
"rstrip": false,
|
| 1584 |
+
"single_word": false,
|
| 1585 |
+
"special": true
|
| 1586 |
+
},
|
| 1587 |
+
"128198": {
|
| 1588 |
+
"content": "<|reserved_special_token_190|>",
|
| 1589 |
+
"lstrip": false,
|
| 1590 |
+
"normalized": false,
|
| 1591 |
+
"rstrip": false,
|
| 1592 |
+
"single_word": false,
|
| 1593 |
+
"special": true
|
| 1594 |
+
},
|
| 1595 |
+
"128199": {
|
| 1596 |
+
"content": "<|reserved_special_token_191|>",
|
| 1597 |
+
"lstrip": false,
|
| 1598 |
+
"normalized": false,
|
| 1599 |
+
"rstrip": false,
|
| 1600 |
+
"single_word": false,
|
| 1601 |
+
"special": true
|
| 1602 |
+
},
|
| 1603 |
+
"128200": {
|
| 1604 |
+
"content": "<|reserved_special_token_192|>",
|
| 1605 |
+
"lstrip": false,
|
| 1606 |
+
"normalized": false,
|
| 1607 |
+
"rstrip": false,
|
| 1608 |
+
"single_word": false,
|
| 1609 |
+
"special": true
|
| 1610 |
+
},
|
| 1611 |
+
"128201": {
|
| 1612 |
+
"content": "<|reserved_special_token_193|>",
|
| 1613 |
+
"lstrip": false,
|
| 1614 |
+
"normalized": false,
|
| 1615 |
+
"rstrip": false,
|
| 1616 |
+
"single_word": false,
|
| 1617 |
+
"special": true
|
| 1618 |
+
},
|
| 1619 |
+
"128202": {
|
| 1620 |
+
"content": "<|reserved_special_token_194|>",
|
| 1621 |
+
"lstrip": false,
|
| 1622 |
+
"normalized": false,
|
| 1623 |
+
"rstrip": false,
|
| 1624 |
+
"single_word": false,
|
| 1625 |
+
"special": true
|
| 1626 |
+
},
|
| 1627 |
+
"128203": {
|
| 1628 |
+
"content": "<|reserved_special_token_195|>",
|
| 1629 |
+
"lstrip": false,
|
| 1630 |
+
"normalized": false,
|
| 1631 |
+
"rstrip": false,
|
| 1632 |
+
"single_word": false,
|
| 1633 |
+
"special": true
|
| 1634 |
+
},
|
| 1635 |
+
"128204": {
|
| 1636 |
+
"content": "<|reserved_special_token_196|>",
|
| 1637 |
+
"lstrip": false,
|
| 1638 |
+
"normalized": false,
|
| 1639 |
+
"rstrip": false,
|
| 1640 |
+
"single_word": false,
|
| 1641 |
+
"special": true
|
| 1642 |
+
},
|
| 1643 |
+
"128205": {
|
| 1644 |
+
"content": "<|reserved_special_token_197|>",
|
| 1645 |
+
"lstrip": false,
|
| 1646 |
+
"normalized": false,
|
| 1647 |
+
"rstrip": false,
|
| 1648 |
+
"single_word": false,
|
| 1649 |
+
"special": true
|
| 1650 |
+
},
|
| 1651 |
+
"128206": {
|
| 1652 |
+
"content": "<|reserved_special_token_198|>",
|
| 1653 |
+
"lstrip": false,
|
| 1654 |
+
"normalized": false,
|
| 1655 |
+
"rstrip": false,
|
| 1656 |
+
"single_word": false,
|
| 1657 |
+
"special": true
|
| 1658 |
+
},
|
| 1659 |
+
"128207": {
|
| 1660 |
+
"content": "<|reserved_special_token_199|>",
|
| 1661 |
+
"lstrip": false,
|
| 1662 |
+
"normalized": false,
|
| 1663 |
+
"rstrip": false,
|
| 1664 |
+
"single_word": false,
|
| 1665 |
+
"special": true
|
| 1666 |
+
},
|
| 1667 |
+
"128208": {
|
| 1668 |
+
"content": "<|reserved_special_token_200|>",
|
| 1669 |
+
"lstrip": false,
|
| 1670 |
+
"normalized": false,
|
| 1671 |
+
"rstrip": false,
|
| 1672 |
+
"single_word": false,
|
| 1673 |
+
"special": true
|
| 1674 |
+
},
|
| 1675 |
+
"128209": {
|
| 1676 |
+
"content": "<|reserved_special_token_201|>",
|
| 1677 |
+
"lstrip": false,
|
| 1678 |
+
"normalized": false,
|
| 1679 |
+
"rstrip": false,
|
| 1680 |
+
"single_word": false,
|
| 1681 |
+
"special": true
|
| 1682 |
+
},
|
| 1683 |
+
"128210": {
|
| 1684 |
+
"content": "<|reserved_special_token_202|>",
|
| 1685 |
+
"lstrip": false,
|
| 1686 |
+
"normalized": false,
|
| 1687 |
+
"rstrip": false,
|
| 1688 |
+
"single_word": false,
|
| 1689 |
+
"special": true
|
| 1690 |
+
},
|
| 1691 |
+
"128211": {
|
| 1692 |
+
"content": "<|reserved_special_token_203|>",
|
| 1693 |
+
"lstrip": false,
|
| 1694 |
+
"normalized": false,
|
| 1695 |
+
"rstrip": false,
|
| 1696 |
+
"single_word": false,
|
| 1697 |
+
"special": true
|
| 1698 |
+
},
|
| 1699 |
+
"128212": {
|
| 1700 |
+
"content": "<|reserved_special_token_204|>",
|
| 1701 |
+
"lstrip": false,
|
| 1702 |
+
"normalized": false,
|
| 1703 |
+
"rstrip": false,
|
| 1704 |
+
"single_word": false,
|
| 1705 |
+
"special": true
|
| 1706 |
+
},
|
| 1707 |
+
"128213": {
|
| 1708 |
+
"content": "<|reserved_special_token_205|>",
|
| 1709 |
+
"lstrip": false,
|
| 1710 |
+
"normalized": false,
|
| 1711 |
+
"rstrip": false,
|
| 1712 |
+
"single_word": false,
|
| 1713 |
+
"special": true
|
| 1714 |
+
},
|
| 1715 |
+
"128214": {
|
| 1716 |
+
"content": "<|reserved_special_token_206|>",
|
| 1717 |
+
"lstrip": false,
|
| 1718 |
+
"normalized": false,
|
| 1719 |
+
"rstrip": false,
|
| 1720 |
+
"single_word": false,
|
| 1721 |
+
"special": true
|
| 1722 |
+
},
|
| 1723 |
+
"128215": {
|
| 1724 |
+
"content": "<|reserved_special_token_207|>",
|
| 1725 |
+
"lstrip": false,
|
| 1726 |
+
"normalized": false,
|
| 1727 |
+
"rstrip": false,
|
| 1728 |
+
"single_word": false,
|
| 1729 |
+
"special": true
|
| 1730 |
+
},
|
| 1731 |
+
"128216": {
|
| 1732 |
+
"content": "<|reserved_special_token_208|>",
|
| 1733 |
+
"lstrip": false,
|
| 1734 |
+
"normalized": false,
|
| 1735 |
+
"rstrip": false,
|
| 1736 |
+
"single_word": false,
|
| 1737 |
+
"special": true
|
| 1738 |
+
},
|
| 1739 |
+
"128217": {
|
| 1740 |
+
"content": "<|reserved_special_token_209|>",
|
| 1741 |
+
"lstrip": false,
|
| 1742 |
+
"normalized": false,
|
| 1743 |
+
"rstrip": false,
|
| 1744 |
+
"single_word": false,
|
| 1745 |
+
"special": true
|
| 1746 |
+
},
|
| 1747 |
+
"128218": {
|
| 1748 |
+
"content": "<|reserved_special_token_210|>",
|
| 1749 |
+
"lstrip": false,
|
| 1750 |
+
"normalized": false,
|
| 1751 |
+
"rstrip": false,
|
| 1752 |
+
"single_word": false,
|
| 1753 |
+
"special": true
|
| 1754 |
+
},
|
| 1755 |
+
"128219": {
|
| 1756 |
+
"content": "<|reserved_special_token_211|>",
|
| 1757 |
+
"lstrip": false,
|
| 1758 |
+
"normalized": false,
|
| 1759 |
+
"rstrip": false,
|
| 1760 |
+
"single_word": false,
|
| 1761 |
+
"special": true
|
| 1762 |
+
},
|
| 1763 |
+
"128220": {
|
| 1764 |
+
"content": "<|reserved_special_token_212|>",
|
| 1765 |
+
"lstrip": false,
|
| 1766 |
+
"normalized": false,
|
| 1767 |
+
"rstrip": false,
|
| 1768 |
+
"single_word": false,
|
| 1769 |
+
"special": true
|
| 1770 |
+
},
|
| 1771 |
+
"128221": {
|
| 1772 |
+
"content": "<|reserved_special_token_213|>",
|
| 1773 |
+
"lstrip": false,
|
| 1774 |
+
"normalized": false,
|
| 1775 |
+
"rstrip": false,
|
| 1776 |
+
"single_word": false,
|
| 1777 |
+
"special": true
|
| 1778 |
+
},
|
| 1779 |
+
"128222": {
|
| 1780 |
+
"content": "<|reserved_special_token_214|>",
|
| 1781 |
+
"lstrip": false,
|
| 1782 |
+
"normalized": false,
|
| 1783 |
+
"rstrip": false,
|
| 1784 |
+
"single_word": false,
|
| 1785 |
+
"special": true
|
| 1786 |
+
},
|
| 1787 |
+
"128223": {
|
| 1788 |
+
"content": "<|reserved_special_token_215|>",
|
| 1789 |
+
"lstrip": false,
|
| 1790 |
+
"normalized": false,
|
| 1791 |
+
"rstrip": false,
|
| 1792 |
+
"single_word": false,
|
| 1793 |
+
"special": true
|
| 1794 |
+
},
|
| 1795 |
+
"128224": {
|
| 1796 |
+
"content": "<|reserved_special_token_216|>",
|
| 1797 |
+
"lstrip": false,
|
| 1798 |
+
"normalized": false,
|
| 1799 |
+
"rstrip": false,
|
| 1800 |
+
"single_word": false,
|
| 1801 |
+
"special": true
|
| 1802 |
+
},
|
| 1803 |
+
"128225": {
|
| 1804 |
+
"content": "<|reserved_special_token_217|>",
|
| 1805 |
+
"lstrip": false,
|
| 1806 |
+
"normalized": false,
|
| 1807 |
+
"rstrip": false,
|
| 1808 |
+
"single_word": false,
|
| 1809 |
+
"special": true
|
| 1810 |
+
},
|
| 1811 |
+
"128226": {
|
| 1812 |
+
"content": "<|reserved_special_token_218|>",
|
| 1813 |
+
"lstrip": false,
|
| 1814 |
+
"normalized": false,
|
| 1815 |
+
"rstrip": false,
|
| 1816 |
+
"single_word": false,
|
| 1817 |
+
"special": true
|
| 1818 |
+
},
|
| 1819 |
+
"128227": {
|
| 1820 |
+
"content": "<|reserved_special_token_219|>",
|
| 1821 |
+
"lstrip": false,
|
| 1822 |
+
"normalized": false,
|
| 1823 |
+
"rstrip": false,
|
| 1824 |
+
"single_word": false,
|
| 1825 |
+
"special": true
|
| 1826 |
+
},
|
| 1827 |
+
"128228": {
|
| 1828 |
+
"content": "<|reserved_special_token_220|>",
|
| 1829 |
+
"lstrip": false,
|
| 1830 |
+
"normalized": false,
|
| 1831 |
+
"rstrip": false,
|
| 1832 |
+
"single_word": false,
|
| 1833 |
+
"special": true
|
| 1834 |
+
},
|
| 1835 |
+
"128229": {
|
| 1836 |
+
"content": "<|reserved_special_token_221|>",
|
| 1837 |
+
"lstrip": false,
|
| 1838 |
+
"normalized": false,
|
| 1839 |
+
"rstrip": false,
|
| 1840 |
+
"single_word": false,
|
| 1841 |
+
"special": true
|
| 1842 |
+
},
|
| 1843 |
+
"128230": {
|
| 1844 |
+
"content": "<|reserved_special_token_222|>",
|
| 1845 |
+
"lstrip": false,
|
| 1846 |
+
"normalized": false,
|
| 1847 |
+
"rstrip": false,
|
| 1848 |
+
"single_word": false,
|
| 1849 |
+
"special": true
|
| 1850 |
+
},
|
| 1851 |
+
"128231": {
|
| 1852 |
+
"content": "<|reserved_special_token_223|>",
|
| 1853 |
+
"lstrip": false,
|
| 1854 |
+
"normalized": false,
|
| 1855 |
+
"rstrip": false,
|
| 1856 |
+
"single_word": false,
|
| 1857 |
+
"special": true
|
| 1858 |
+
},
|
| 1859 |
+
"128232": {
|
| 1860 |
+
"content": "<|reserved_special_token_224|>",
|
| 1861 |
+
"lstrip": false,
|
| 1862 |
+
"normalized": false,
|
| 1863 |
+
"rstrip": false,
|
| 1864 |
+
"single_word": false,
|
| 1865 |
+
"special": true
|
| 1866 |
+
},
|
| 1867 |
+
"128233": {
|
| 1868 |
+
"content": "<|reserved_special_token_225|>",
|
| 1869 |
+
"lstrip": false,
|
| 1870 |
+
"normalized": false,
|
| 1871 |
+
"rstrip": false,
|
| 1872 |
+
"single_word": false,
|
| 1873 |
+
"special": true
|
| 1874 |
+
},
|
| 1875 |
+
"128234": {
|
| 1876 |
+
"content": "<|reserved_special_token_226|>",
|
| 1877 |
+
"lstrip": false,
|
| 1878 |
+
"normalized": false,
|
| 1879 |
+
"rstrip": false,
|
| 1880 |
+
"single_word": false,
|
| 1881 |
+
"special": true
|
| 1882 |
+
},
|
| 1883 |
+
"128235": {
|
| 1884 |
+
"content": "<|reserved_special_token_227|>",
|
| 1885 |
+
"lstrip": false,
|
| 1886 |
+
"normalized": false,
|
| 1887 |
+
"rstrip": false,
|
| 1888 |
+
"single_word": false,
|
| 1889 |
+
"special": true
|
| 1890 |
+
},
|
| 1891 |
+
"128236": {
|
| 1892 |
+
"content": "<|reserved_special_token_228|>",
|
| 1893 |
+
"lstrip": false,
|
| 1894 |
+
"normalized": false,
|
| 1895 |
+
"rstrip": false,
|
| 1896 |
+
"single_word": false,
|
| 1897 |
+
"special": true
|
| 1898 |
+
},
|
| 1899 |
+
"128237": {
|
| 1900 |
+
"content": "<|reserved_special_token_229|>",
|
| 1901 |
+
"lstrip": false,
|
| 1902 |
+
"normalized": false,
|
| 1903 |
+
"rstrip": false,
|
| 1904 |
+
"single_word": false,
|
| 1905 |
+
"special": true
|
| 1906 |
+
},
|
| 1907 |
+
"128238": {
|
| 1908 |
+
"content": "<|reserved_special_token_230|>",
|
| 1909 |
+
"lstrip": false,
|
| 1910 |
+
"normalized": false,
|
| 1911 |
+
"rstrip": false,
|
| 1912 |
+
"single_word": false,
|
| 1913 |
+
"special": true
|
| 1914 |
+
},
|
| 1915 |
+
"128239": {
|
| 1916 |
+
"content": "<|reserved_special_token_231|>",
|
| 1917 |
+
"lstrip": false,
|
| 1918 |
+
"normalized": false,
|
| 1919 |
+
"rstrip": false,
|
| 1920 |
+
"single_word": false,
|
| 1921 |
+
"special": true
|
| 1922 |
+
},
|
| 1923 |
+
"128240": {
|
| 1924 |
+
"content": "<|reserved_special_token_232|>",
|
| 1925 |
+
"lstrip": false,
|
| 1926 |
+
"normalized": false,
|
| 1927 |
+
"rstrip": false,
|
| 1928 |
+
"single_word": false,
|
| 1929 |
+
"special": true
|
| 1930 |
+
},
|
| 1931 |
+
"128241": {
|
| 1932 |
+
"content": "<|reserved_special_token_233|>",
|
| 1933 |
+
"lstrip": false,
|
| 1934 |
+
"normalized": false,
|
| 1935 |
+
"rstrip": false,
|
| 1936 |
+
"single_word": false,
|
| 1937 |
+
"special": true
|
| 1938 |
+
},
|
| 1939 |
+
"128242": {
|
| 1940 |
+
"content": "<|reserved_special_token_234|>",
|
| 1941 |
+
"lstrip": false,
|
| 1942 |
+
"normalized": false,
|
| 1943 |
+
"rstrip": false,
|
| 1944 |
+
"single_word": false,
|
| 1945 |
+
"special": true
|
| 1946 |
+
},
|
| 1947 |
+
"128243": {
|
| 1948 |
+
"content": "<|reserved_special_token_235|>",
|
| 1949 |
+
"lstrip": false,
|
| 1950 |
+
"normalized": false,
|
| 1951 |
+
"rstrip": false,
|
| 1952 |
+
"single_word": false,
|
| 1953 |
+
"special": true
|
| 1954 |
+
},
|
| 1955 |
+
"128244": {
|
| 1956 |
+
"content": "<|reserved_special_token_236|>",
|
| 1957 |
+
"lstrip": false,
|
| 1958 |
+
"normalized": false,
|
| 1959 |
+
"rstrip": false,
|
| 1960 |
+
"single_word": false,
|
| 1961 |
+
"special": true
|
| 1962 |
+
},
|
| 1963 |
+
"128245": {
|
| 1964 |
+
"content": "<|reserved_special_token_237|>",
|
| 1965 |
+
"lstrip": false,
|
| 1966 |
+
"normalized": false,
|
| 1967 |
+
"rstrip": false,
|
| 1968 |
+
"single_word": false,
|
| 1969 |
+
"special": true
|
| 1970 |
+
},
|
| 1971 |
+
"128246": {
|
| 1972 |
+
"content": "<|reserved_special_token_238|>",
|
| 1973 |
+
"lstrip": false,
|
| 1974 |
+
"normalized": false,
|
| 1975 |
+
"rstrip": false,
|
| 1976 |
+
"single_word": false,
|
| 1977 |
+
"special": true
|
| 1978 |
+
},
|
| 1979 |
+
"128247": {
|
| 1980 |
+
"content": "<|reserved_special_token_239|>",
|
| 1981 |
+
"lstrip": false,
|
| 1982 |
+
"normalized": false,
|
| 1983 |
+
"rstrip": false,
|
| 1984 |
+
"single_word": false,
|
| 1985 |
+
"special": true
|
| 1986 |
+
},
|
| 1987 |
+
"128248": {
|
| 1988 |
+
"content": "<|reserved_special_token_240|>",
|
| 1989 |
+
"lstrip": false,
|
| 1990 |
+
"normalized": false,
|
| 1991 |
+
"rstrip": false,
|
| 1992 |
+
"single_word": false,
|
| 1993 |
+
"special": true
|
| 1994 |
+
},
|
| 1995 |
+
"128249": {
|
| 1996 |
+
"content": "<|reserved_special_token_241|>",
|
| 1997 |
+
"lstrip": false,
|
| 1998 |
+
"normalized": false,
|
| 1999 |
+
"rstrip": false,
|
| 2000 |
+
"single_word": false,
|
| 2001 |
+
"special": true
|
| 2002 |
+
},
|
| 2003 |
+
"128250": {
|
| 2004 |
+
"content": "<|reserved_special_token_242|>",
|
| 2005 |
+
"lstrip": false,
|
| 2006 |
+
"normalized": false,
|
| 2007 |
+
"rstrip": false,
|
| 2008 |
+
"single_word": false,
|
| 2009 |
+
"special": true
|
| 2010 |
+
},
|
| 2011 |
+
"128251": {
|
| 2012 |
+
"content": "<|reserved_special_token_243|>",
|
| 2013 |
+
"lstrip": false,
|
| 2014 |
+
"normalized": false,
|
| 2015 |
+
"rstrip": false,
|
| 2016 |
+
"single_word": false,
|
| 2017 |
+
"special": true
|
| 2018 |
+
},
|
| 2019 |
+
"128252": {
|
| 2020 |
+
"content": "<|reserved_special_token_244|>",
|
| 2021 |
+
"lstrip": false,
|
| 2022 |
+
"normalized": false,
|
| 2023 |
+
"rstrip": false,
|
| 2024 |
+
"single_word": false,
|
| 2025 |
+
"special": true
|
| 2026 |
+
},
|
| 2027 |
+
"128253": {
|
| 2028 |
+
"content": "<|reserved_special_token_245|>",
|
| 2029 |
+
"lstrip": false,
|
| 2030 |
+
"normalized": false,
|
| 2031 |
+
"rstrip": false,
|
| 2032 |
+
"single_word": false,
|
| 2033 |
+
"special": true
|
| 2034 |
+
},
|
| 2035 |
+
"128254": {
|
| 2036 |
+
"content": "<|reserved_special_token_246|>",
|
| 2037 |
+
"lstrip": false,
|
| 2038 |
+
"normalized": false,
|
| 2039 |
+
"rstrip": false,
|
| 2040 |
+
"single_word": false,
|
| 2041 |
+
"special": true
|
| 2042 |
+
},
|
| 2043 |
+
"128255": {
|
| 2044 |
+
"content": "<|reserved_special_token_247|>",
|
| 2045 |
+
"lstrip": false,
|
| 2046 |
+
"normalized": false,
|
| 2047 |
+
"rstrip": false,
|
| 2048 |
+
"single_word": false,
|
| 2049 |
+
"special": true
|
| 2050 |
+
}
|
| 2051 |
+
},
|
| 2052 |
+
"bos_token": "<|begin_of_text|>",
|
| 2053 |
+
"chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
|
| 2054 |
+
"clean_up_tokenization_spaces": true,
|
| 2055 |
+
"eos_token": "<|eot_id|>",
|
| 2056 |
+
"model_input_names": [
|
| 2057 |
+
"input_ids",
|
| 2058 |
+
"attention_mask"
|
| 2059 |
+
],
|
| 2060 |
+
"model_max_length": 2048,
|
| 2061 |
+
"pad_token": "<|eot_id|>",
|
| 2062 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 2063 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1248 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.8063872255489022,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 404,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.001996007984031936,
|
| 13 |
+
"grad_norm": 19.011175567956343,
|
| 14 |
+
"learning_rate": 1.9607843137254902e-08,
|
| 15 |
+
"logits/chosen": -0.23683343827724457,
|
| 16 |
+
"logits/rejected": -0.2160334289073944,
|
| 17 |
+
"logps/chosen": -0.7725335359573364,
|
| 18 |
+
"logps/rejected": -0.7464257478713989,
|
| 19 |
+
"loss": 0.6931,
|
| 20 |
+
"rewards/accuracies": 0.0,
|
| 21 |
+
"rewards/chosen": 0.0,
|
| 22 |
+
"rewards/margins": 0.0,
|
| 23 |
+
"rewards/rejected": 0.0,
|
| 24 |
+
"step": 1
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.00998003992015968,
|
| 28 |
+
"grad_norm": 24.85303405730939,
|
| 29 |
+
"learning_rate": 9.80392156862745e-08,
|
| 30 |
+
"logits/chosen": -0.17754913866519928,
|
| 31 |
+
"logits/rejected": -0.1510540395975113,
|
| 32 |
+
"logps/chosen": -0.6808110475540161,
|
| 33 |
+
"logps/rejected": -0.7670315504074097,
|
| 34 |
+
"loss": 0.6946,
|
| 35 |
+
"rewards/accuracies": 0.296875,
|
| 36 |
+
"rewards/chosen": -0.003806930035352707,
|
| 37 |
+
"rewards/margins": -0.0012099393643438816,
|
| 38 |
+
"rewards/rejected": -0.0025969906710088253,
|
| 39 |
+
"step": 5
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.01996007984031936,
|
| 43 |
+
"grad_norm": 27.331245165405218,
|
| 44 |
+
"learning_rate": 1.96078431372549e-07,
|
| 45 |
+
"logits/chosen": -0.21193155646324158,
|
| 46 |
+
"logits/rejected": -0.14373356103897095,
|
| 47 |
+
"logps/chosen": -0.6621003746986389,
|
| 48 |
+
"logps/rejected": -0.7422515153884888,
|
| 49 |
+
"loss": 0.6942,
|
| 50 |
+
"rewards/accuracies": 0.5,
|
| 51 |
+
"rewards/chosen": -0.003911865875124931,
|
| 52 |
+
"rewards/margins": -0.00975899025797844,
|
| 53 |
+
"rewards/rejected": 0.005847124848514795,
|
| 54 |
+
"step": 10
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.029940119760479042,
|
| 58 |
+
"grad_norm": 18.13812492001746,
|
| 59 |
+
"learning_rate": 2.941176470588235e-07,
|
| 60 |
+
"logits/chosen": -0.2625748813152313,
|
| 61 |
+
"logits/rejected": -0.21968011558055878,
|
| 62 |
+
"logps/chosen": -0.7216169238090515,
|
| 63 |
+
"logps/rejected": -0.7573580741882324,
|
| 64 |
+
"loss": 0.6955,
|
| 65 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 66 |
+
"rewards/chosen": -0.0036083627492189407,
|
| 67 |
+
"rewards/margins": 0.0002948194742202759,
|
| 68 |
+
"rewards/rejected": -0.0039031822234392166,
|
| 69 |
+
"step": 15
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.03992015968063872,
|
| 73 |
+
"grad_norm": 29.30189659403405,
|
| 74 |
+
"learning_rate": 3.92156862745098e-07,
|
| 75 |
+
"logits/chosen": -0.2208031415939331,
|
| 76 |
+
"logits/rejected": -0.21727153658866882,
|
| 77 |
+
"logps/chosen": -0.806796669960022,
|
| 78 |
+
"logps/rejected": -0.7866016626358032,
|
| 79 |
+
"loss": 0.6931,
|
| 80 |
+
"rewards/accuracies": 0.550000011920929,
|
| 81 |
+
"rewards/chosen": 0.011953282169997692,
|
| 82 |
+
"rewards/margins": 0.00740851229056716,
|
| 83 |
+
"rewards/rejected": 0.0045447684824466705,
|
| 84 |
+
"step": 20
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.0499001996007984,
|
| 88 |
+
"grad_norm": 17.484098617193414,
|
| 89 |
+
"learning_rate": 4.901960784313725e-07,
|
| 90 |
+
"logits/chosen": -0.23456409573554993,
|
| 91 |
+
"logits/rejected": -0.20080241560935974,
|
| 92 |
+
"logps/chosen": -0.752682089805603,
|
| 93 |
+
"logps/rejected": -0.81329745054245,
|
| 94 |
+
"loss": 0.6933,
|
| 95 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 96 |
+
"rewards/chosen": -0.008837291970849037,
|
| 97 |
+
"rewards/margins": -0.008301705121994019,
|
| 98 |
+
"rewards/rejected": -0.0005355868488550186,
|
| 99 |
+
"step": 25
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.059880239520958084,
|
| 103 |
+
"grad_norm": 22.79460314618375,
|
| 104 |
+
"learning_rate": 5.88235294117647e-07,
|
| 105 |
+
"logits/chosen": -0.19971349835395813,
|
| 106 |
+
"logits/rejected": -0.1838277131319046,
|
| 107 |
+
"logps/chosen": -0.741012454032898,
|
| 108 |
+
"logps/rejected": -0.8006389737129211,
|
| 109 |
+
"loss": 0.6905,
|
| 110 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 111 |
+
"rewards/chosen": -0.007402450777590275,
|
| 112 |
+
"rewards/margins": 0.008965044282376766,
|
| 113 |
+
"rewards/rejected": -0.01636749505996704,
|
| 114 |
+
"step": 30
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.06986027944111776,
|
| 118 |
+
"grad_norm": 19.972022304372274,
|
| 119 |
+
"learning_rate": 6.862745098039216e-07,
|
| 120 |
+
"logits/chosen": -0.20151765644550323,
|
| 121 |
+
"logits/rejected": -0.19096672534942627,
|
| 122 |
+
"logps/chosen": -0.7682427167892456,
|
| 123 |
+
"logps/rejected": -0.8185433149337769,
|
| 124 |
+
"loss": 0.6912,
|
| 125 |
+
"rewards/accuracies": 0.4375,
|
| 126 |
+
"rewards/chosen": -0.011349962092936039,
|
| 127 |
+
"rewards/margins": -0.0024173937272280455,
|
| 128 |
+
"rewards/rejected": -0.00893256813287735,
|
| 129 |
+
"step": 35
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.07984031936127745,
|
| 133 |
+
"grad_norm": 18.601712274112785,
|
| 134 |
+
"learning_rate": 7.84313725490196e-07,
|
| 135 |
+
"logits/chosen": -0.24523372948169708,
|
| 136 |
+
"logits/rejected": -0.2008388340473175,
|
| 137 |
+
"logps/chosen": -0.784850537776947,
|
| 138 |
+
"logps/rejected": -0.8351114392280579,
|
| 139 |
+
"loss": 0.6888,
|
| 140 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 141 |
+
"rewards/chosen": -0.019527489319443703,
|
| 142 |
+
"rewards/margins": 0.02737308107316494,
|
| 143 |
+
"rewards/rejected": -0.04690057039260864,
|
| 144 |
+
"step": 40
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.08982035928143713,
|
| 148 |
+
"grad_norm": 22.21021114642223,
|
| 149 |
+
"learning_rate": 8.823529411764705e-07,
|
| 150 |
+
"logits/chosen": -0.20831866562366486,
|
| 151 |
+
"logits/rejected": -0.19121626019477844,
|
| 152 |
+
"logps/chosen": -0.7837399244308472,
|
| 153 |
+
"logps/rejected": -0.8101400136947632,
|
| 154 |
+
"loss": 0.6787,
|
| 155 |
+
"rewards/accuracies": 0.6000000238418579,
|
| 156 |
+
"rewards/chosen": -0.02101544663310051,
|
| 157 |
+
"rewards/margins": 0.036486249417066574,
|
| 158 |
+
"rewards/rejected": -0.057501696050167084,
|
| 159 |
+
"step": 45
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.0998003992015968,
|
| 163 |
+
"grad_norm": 35.946736239250875,
|
| 164 |
+
"learning_rate": 9.80392156862745e-07,
|
| 165 |
+
"logits/chosen": -0.2484116554260254,
|
| 166 |
+
"logits/rejected": -0.21271376311779022,
|
| 167 |
+
"logps/chosen": -0.7204190492630005,
|
| 168 |
+
"logps/rejected": -0.8208059072494507,
|
| 169 |
+
"loss": 0.6745,
|
| 170 |
+
"rewards/accuracies": 0.699999988079071,
|
| 171 |
+
"rewards/chosen": -0.018808891996741295,
|
| 172 |
+
"rewards/margins": 0.07578931748867035,
|
| 173 |
+
"rewards/rejected": -0.0945982038974762,
|
| 174 |
+
"step": 50
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.10978043912175649,
|
| 178 |
+
"grad_norm": 17.586104380746775,
|
| 179 |
+
"learning_rate": 9.99805057520177e-07,
|
| 180 |
+
"logits/chosen": -0.22446580231189728,
|
| 181 |
+
"logits/rejected": -0.21255891025066376,
|
| 182 |
+
"logps/chosen": -0.768947958946228,
|
| 183 |
+
"logps/rejected": -0.7895203828811646,
|
| 184 |
+
"loss": 0.6709,
|
| 185 |
+
"rewards/accuracies": 0.675000011920929,
|
| 186 |
+
"rewards/chosen": -0.03166341781616211,
|
| 187 |
+
"rewards/margins": 0.14431020617485046,
|
| 188 |
+
"rewards/rejected": -0.17597363889217377,
|
| 189 |
+
"step": 55
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.11976047904191617,
|
| 193 |
+
"grad_norm": 16.613461293187417,
|
| 194 |
+
"learning_rate": 9.990133642141357e-07,
|
| 195 |
+
"logits/chosen": -0.24056999385356903,
|
| 196 |
+
"logits/rejected": -0.2318592071533203,
|
| 197 |
+
"logps/chosen": -0.7434613108634949,
|
| 198 |
+
"logps/rejected": -0.8091262578964233,
|
| 199 |
+
"loss": 0.6692,
|
| 200 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 201 |
+
"rewards/chosen": -0.08080559223890305,
|
| 202 |
+
"rewards/margins": 0.17325755953788757,
|
| 203 |
+
"rewards/rejected": -0.2540631592273712,
|
| 204 |
+
"step": 60
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.12974051896207583,
|
| 208 |
+
"grad_norm": 20.90647324488342,
|
| 209 |
+
"learning_rate": 9.976136999909155e-07,
|
| 210 |
+
"logits/chosen": -0.18930143117904663,
|
| 211 |
+
"logits/rejected": -0.17337587475776672,
|
| 212 |
+
"logps/chosen": -0.7673609852790833,
|
| 213 |
+
"logps/rejected": -0.7971418499946594,
|
| 214 |
+
"loss": 0.6651,
|
| 215 |
+
"rewards/accuracies": 0.6875,
|
| 216 |
+
"rewards/chosen": -0.06646038591861725,
|
| 217 |
+
"rewards/margins": 0.06751471757888794,
|
| 218 |
+
"rewards/rejected": -0.133975088596344,
|
| 219 |
+
"step": 65
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.13972055888223553,
|
| 223 |
+
"grad_norm": 29.878943207680674,
|
| 224 |
+
"learning_rate": 9.956077701257707e-07,
|
| 225 |
+
"logits/chosen": -0.2409631907939911,
|
| 226 |
+
"logits/rejected": -0.2077023983001709,
|
| 227 |
+
"logps/chosen": -0.7360613346099854,
|
| 228 |
+
"logps/rejected": -0.7820955514907837,
|
| 229 |
+
"loss": 0.6524,
|
| 230 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 231 |
+
"rewards/chosen": -0.04467972368001938,
|
| 232 |
+
"rewards/margins": 0.07468457520008087,
|
| 233 |
+
"rewards/rejected": -0.11936430633068085,
|
| 234 |
+
"step": 70
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.1497005988023952,
|
| 238 |
+
"grad_norm": 23.171174553493415,
|
| 239 |
+
"learning_rate": 9.929980185352525e-07,
|
| 240 |
+
"logits/chosen": -0.3143348693847656,
|
| 241 |
+
"logits/rejected": -0.31170645356178284,
|
| 242 |
+
"logps/chosen": -0.7954690456390381,
|
| 243 |
+
"logps/rejected": -0.8250002861022949,
|
| 244 |
+
"loss": 0.6568,
|
| 245 |
+
"rewards/accuracies": 0.75,
|
| 246 |
+
"rewards/chosen": -0.09316639602184296,
|
| 247 |
+
"rewards/margins": 0.060890208929777145,
|
| 248 |
+
"rewards/rejected": -0.1540566086769104,
|
| 249 |
+
"step": 75
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.1596806387225549,
|
| 253 |
+
"grad_norm": 17.553227599037466,
|
| 254 |
+
"learning_rate": 9.89787624799672e-07,
|
| 255 |
+
"logits/chosen": -0.38358816504478455,
|
| 256 |
+
"logits/rejected": -0.32817578315734863,
|
| 257 |
+
"logps/chosen": -0.7703452110290527,
|
| 258 |
+
"logps/rejected": -0.8151019811630249,
|
| 259 |
+
"loss": 0.6486,
|
| 260 |
+
"rewards/accuracies": 0.737500011920929,
|
| 261 |
+
"rewards/chosen": -0.10643620789051056,
|
| 262 |
+
"rewards/margins": 0.10724379867315292,
|
| 263 |
+
"rewards/rejected": -0.2136799842119217,
|
| 264 |
+
"step": 80
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.16966067864271456,
|
| 268 |
+
"grad_norm": 13.431691131153842,
|
| 269 |
+
"learning_rate": 9.859805002892731e-07,
|
| 270 |
+
"logits/chosen": -0.3225359618663788,
|
| 271 |
+
"logits/rejected": -0.3592807650566101,
|
| 272 |
+
"logps/chosen": -0.7858971357345581,
|
| 273 |
+
"logps/rejected": -0.8596378564834595,
|
| 274 |
+
"loss": 0.6523,
|
| 275 |
+
"rewards/accuracies": 0.625,
|
| 276 |
+
"rewards/chosen": -0.1400977075099945,
|
| 277 |
+
"rewards/margins": 0.16820211708545685,
|
| 278 |
+
"rewards/rejected": -0.30829980969429016,
|
| 279 |
+
"step": 85
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.17964071856287425,
|
| 283 |
+
"grad_norm": 27.30667277119807,
|
| 284 |
+
"learning_rate": 9.81581283398829e-07,
|
| 285 |
+
"logits/chosen": -0.34176284074783325,
|
| 286 |
+
"logits/rejected": -0.34205198287963867,
|
| 287 |
+
"logps/chosen": -0.7768250703811646,
|
| 288 |
+
"logps/rejected": -0.820307731628418,
|
| 289 |
+
"loss": 0.6451,
|
| 290 |
+
"rewards/accuracies": 0.75,
|
| 291 |
+
"rewards/chosen": -0.07238658517599106,
|
| 292 |
+
"rewards/margins": 0.23312333226203918,
|
| 293 |
+
"rewards/rejected": -0.30550986528396606,
|
| 294 |
+
"step": 90
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.18962075848303392,
|
| 298 |
+
"grad_norm": 20.047219809230725,
|
| 299 |
+
"learning_rate": 9.765953338964734e-07,
|
| 300 |
+
"logits/chosen": -0.4065936207771301,
|
| 301 |
+
"logits/rejected": -0.37638360261917114,
|
| 302 |
+
"logps/chosen": -0.8715718388557434,
|
| 303 |
+
"logps/rejected": -0.9510416984558105,
|
| 304 |
+
"loss": 0.6336,
|
| 305 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 306 |
+
"rewards/chosen": -0.1532100886106491,
|
| 307 |
+
"rewards/margins": 0.2994120717048645,
|
| 308 |
+
"rewards/rejected": -0.4526221752166748,
|
| 309 |
+
"step": 95
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.1996007984031936,
|
| 313 |
+
"grad_norm": 36.23944490923282,
|
| 314 |
+
"learning_rate": 9.710287263936483e-07,
|
| 315 |
+
"logits/chosen": -0.43931150436401367,
|
| 316 |
+
"logits/rejected": -0.44534721970558167,
|
| 317 |
+
"logps/chosen": -0.8958739042282104,
|
| 318 |
+
"logps/rejected": -0.9571765065193176,
|
| 319 |
+
"loss": 0.6432,
|
| 320 |
+
"rewards/accuracies": 0.75,
|
| 321 |
+
"rewards/chosen": -0.27455487847328186,
|
| 322 |
+
"rewards/margins": 0.25604015588760376,
|
| 323 |
+
"rewards/rejected": -0.5305949449539185,
|
| 324 |
+
"step": 100
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.20958083832335328,
|
| 328 |
+
"grad_norm": 25.004187021683798,
|
| 329 |
+
"learning_rate": 9.648882429441256e-07,
|
| 330 |
+
"logits/chosen": -0.44500723481178284,
|
| 331 |
+
"logits/rejected": -0.4199863076210022,
|
| 332 |
+
"logps/chosen": -0.7884619832038879,
|
| 333 |
+
"logps/rejected": -0.7948769330978394,
|
| 334 |
+
"loss": 0.6333,
|
| 335 |
+
"rewards/accuracies": 0.699999988079071,
|
| 336 |
+
"rewards/chosen": -0.23280362784862518,
|
| 337 |
+
"rewards/margins": 0.13038918375968933,
|
| 338 |
+
"rewards/rejected": -0.3631927967071533,
|
| 339 |
+
"step": 105
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.21956087824351297,
|
| 343 |
+
"grad_norm": 15.650165706867742,
|
| 344 |
+
"learning_rate": 9.581813647811197e-07,
|
| 345 |
+
"logits/chosen": -0.47238340973854065,
|
| 346 |
+
"logits/rejected": -0.46014589071273804,
|
| 347 |
+
"logps/chosen": -0.7871894240379333,
|
| 348 |
+
"logps/rejected": -0.8054457902908325,
|
| 349 |
+
"loss": 0.6277,
|
| 350 |
+
"rewards/accuracies": 0.6875,
|
| 351 |
+
"rewards/chosen": -0.25777310132980347,
|
| 352 |
+
"rewards/margins": 0.21288836002349854,
|
| 353 |
+
"rewards/rejected": -0.470661461353302,
|
| 354 |
+
"step": 110
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.22954091816367264,
|
| 358 |
+
"grad_norm": 18.380315632232364,
|
| 359 |
+
"learning_rate": 9.509162632025569e-07,
|
| 360 |
+
"logits/chosen": -0.5215901732444763,
|
| 361 |
+
"logits/rejected": -0.5049930214881897,
|
| 362 |
+
"logps/chosen": -0.9149976968765259,
|
| 363 |
+
"logps/rejected": -0.9515384435653687,
|
| 364 |
+
"loss": 0.6358,
|
| 365 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 366 |
+
"rewards/chosen": -0.3461766839027405,
|
| 367 |
+
"rewards/margins": 0.15195634961128235,
|
| 368 |
+
"rewards/rejected": -0.49813300371170044,
|
| 369 |
+
"step": 115
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.23952095808383234,
|
| 373 |
+
"grad_norm": 21.138881533254413,
|
| 374 |
+
"learning_rate": 9.431017896156073e-07,
|
| 375 |
+
"logits/chosen": -0.4705902636051178,
|
| 376 |
+
"logits/rejected": -0.4593280255794525,
|
| 377 |
+
"logps/chosen": -0.8069537281990051,
|
| 378 |
+
"logps/rejected": -0.8675839304924011,
|
| 379 |
+
"loss": 0.614,
|
| 380 |
+
"rewards/accuracies": 0.625,
|
| 381 |
+
"rewards/chosen": -0.29863637685775757,
|
| 382 |
+
"rewards/margins": 0.31691476702690125,
|
| 383 |
+
"rewards/rejected": -0.6155511140823364,
|
| 384 |
+
"step": 120
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.249500998003992,
|
| 388 |
+
"grad_norm": 18.813175578776896,
|
| 389 |
+
"learning_rate": 9.347474647526095e-07,
|
| 390 |
+
"logits/chosen": -0.4284445345401764,
|
| 391 |
+
"logits/rejected": -0.3746599555015564,
|
| 392 |
+
"logps/chosen": -0.7812046408653259,
|
| 393 |
+
"logps/rejected": -0.8142662048339844,
|
| 394 |
+
"loss": 0.6011,
|
| 395 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 396 |
+
"rewards/chosen": -0.3037291169166565,
|
| 397 |
+
"rewards/margins": 0.3044063150882721,
|
| 398 |
+
"rewards/rejected": -0.6081355214118958,
|
| 399 |
+
"step": 125
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.25948103792415167,
|
| 403 |
+
"grad_norm": 17.070591448816156,
|
| 404 |
+
"learning_rate": 9.258634670715237e-07,
|
| 405 |
+
"logits/chosen": -0.5489827394485474,
|
| 406 |
+
"logits/rejected": -0.5030359029769897,
|
| 407 |
+
"logps/chosen": -0.7899664044380188,
|
| 408 |
+
"logps/rejected": -0.8873406648635864,
|
| 409 |
+
"loss": 0.6085,
|
| 410 |
+
"rewards/accuracies": 0.762499988079071,
|
| 411 |
+
"rewards/chosen": -0.3300507664680481,
|
| 412 |
+
"rewards/margins": 0.2699635326862335,
|
| 413 |
+
"rewards/rejected": -0.600014328956604,
|
| 414 |
+
"step": 130
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 0.2694610778443114,
|
| 418 |
+
"grad_norm": 18.560449924688594,
|
| 419 |
+
"learning_rate": 9.164606203550497e-07,
|
| 420 |
+
"logits/chosen": -0.5027534365653992,
|
| 421 |
+
"logits/rejected": -0.45569664239883423,
|
| 422 |
+
"logps/chosen": -0.7548262476921082,
|
| 423 |
+
"logps/rejected": -0.8240019083023071,
|
| 424 |
+
"loss": 0.5993,
|
| 425 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 426 |
+
"rewards/chosen": -0.33843767642974854,
|
| 427 |
+
"rewards/margins": 0.27864545583724976,
|
| 428 |
+
"rewards/rejected": -0.6170830726623535,
|
| 429 |
+
"step": 135
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.27944111776447106,
|
| 433 |
+
"grad_norm": 15.456587593946033,
|
| 434 |
+
"learning_rate": 9.065503805235137e-07,
|
| 435 |
+
"logits/chosen": -0.5412222146987915,
|
| 436 |
+
"logits/rejected": -0.5133959054946899,
|
| 437 |
+
"logps/chosen": -0.8278282284736633,
|
| 438 |
+
"logps/rejected": -0.8514043092727661,
|
| 439 |
+
"loss": 0.6118,
|
| 440 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 441 |
+
"rewards/chosen": -0.515911340713501,
|
| 442 |
+
"rewards/margins": 0.23073478043079376,
|
| 443 |
+
"rewards/rejected": -0.7466461658477783,
|
| 444 |
+
"step": 140
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.2894211576846307,
|
| 448 |
+
"grad_norm": 13.75653652171432,
|
| 449 |
+
"learning_rate": 8.961448216775953e-07,
|
| 450 |
+
"logits/chosen": -0.531816303730011,
|
| 451 |
+
"logits/rejected": -0.5432392358779907,
|
| 452 |
+
"logps/chosen": -0.8441339731216431,
|
| 453 |
+
"logps/rejected": -0.9052772521972656,
|
| 454 |
+
"loss": 0.6047,
|
| 455 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 456 |
+
"rewards/chosen": -0.6214492917060852,
|
| 457 |
+
"rewards/margins": 0.40321844816207886,
|
| 458 |
+
"rewards/rejected": -1.024667739868164,
|
| 459 |
+
"step": 145
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.2994011976047904,
|
| 463 |
+
"grad_norm": 14.061323030297434,
|
| 464 |
+
"learning_rate": 8.852566213878946e-07,
|
| 465 |
+
"logits/chosen": -0.5842114686965942,
|
| 466 |
+
"logits/rejected": -0.5797411203384399,
|
| 467 |
+
"logps/chosen": -0.7897329926490784,
|
| 468 |
+
"logps/rejected": -0.8609731793403625,
|
| 469 |
+
"loss": 0.6038,
|
| 470 |
+
"rewards/accuracies": 0.75,
|
| 471 |
+
"rewards/chosen": -0.49532920122146606,
|
| 472 |
+
"rewards/margins": 0.36390385031700134,
|
| 473 |
+
"rewards/rejected": -0.859233021736145,
|
| 474 |
+
"step": 150
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.3093812375249501,
|
| 478 |
+
"grad_norm": 12.749472652825297,
|
| 479 |
+
"learning_rate": 8.73899045249266e-07,
|
| 480 |
+
"logits/chosen": -0.6203972697257996,
|
| 481 |
+
"logits/rejected": -0.6109431982040405,
|
| 482 |
+
"logps/chosen": -0.8315925598144531,
|
| 483 |
+
"logps/rejected": -0.9241877794265747,
|
| 484 |
+
"loss": 0.5848,
|
| 485 |
+
"rewards/accuracies": 0.737500011920929,
|
| 486 |
+
"rewards/chosen": -0.6116100549697876,
|
| 487 |
+
"rewards/margins": 0.5322220325469971,
|
| 488 |
+
"rewards/rejected": -1.1438319683074951,
|
| 489 |
+
"step": 155
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.3193612774451098,
|
| 493 |
+
"grad_norm": 18.453987933361336,
|
| 494 |
+
"learning_rate": 8.620859307187338e-07,
|
| 495 |
+
"logits/chosen": -0.5765129923820496,
|
| 496 |
+
"logits/rejected": -0.5761350393295288,
|
| 497 |
+
"logps/chosen": -0.8263224363327026,
|
| 498 |
+
"logps/rejected": -0.8567667007446289,
|
| 499 |
+
"loss": 0.5871,
|
| 500 |
+
"rewards/accuracies": 0.6875,
|
| 501 |
+
"rewards/chosen": -0.5846480131149292,
|
| 502 |
+
"rewards/margins": 0.3195909559726715,
|
| 503 |
+
"rewards/rejected": -0.9042388796806335,
|
| 504 |
+
"step": 160
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 0.32934131736526945,
|
| 508 |
+
"grad_norm": 24.93482299590875,
|
| 509 |
+
"learning_rate": 8.498316702566826e-07,
|
| 510 |
+
"logits/chosen": -0.6133869886398315,
|
| 511 |
+
"logits/rejected": -0.5582712292671204,
|
| 512 |
+
"logps/chosen": -0.828209400177002,
|
| 513 |
+
"logps/rejected": -0.893822193145752,
|
| 514 |
+
"loss": 0.5702,
|
| 515 |
+
"rewards/accuracies": 0.699999988079071,
|
| 516 |
+
"rewards/chosen": -0.8109213709831238,
|
| 517 |
+
"rewards/margins": 0.3340582847595215,
|
| 518 |
+
"rewards/rejected": -1.14497971534729,
|
| 519 |
+
"step": 165
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.3393213572854291,
|
| 523 |
+
"grad_norm": 14.606101127926557,
|
| 524 |
+
"learning_rate": 8.371511937918617e-07,
|
| 525 |
+
"logits/chosen": -0.6824047565460205,
|
| 526 |
+
"logits/rejected": -0.664223313331604,
|
| 527 |
+
"logps/chosen": -0.8030799031257629,
|
| 528 |
+
"logps/rejected": -0.8865512013435364,
|
| 529 |
+
"loss": 0.6006,
|
| 530 |
+
"rewards/accuracies": 0.737500011920929,
|
| 531 |
+
"rewards/chosen": -0.6996228694915771,
|
| 532 |
+
"rewards/margins": 0.5749022960662842,
|
| 533 |
+
"rewards/rejected": -1.2745250463485718,
|
| 534 |
+
"step": 170
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.34930139720558884,
|
| 538 |
+
"grad_norm": 14.615105697665864,
|
| 539 |
+
"learning_rate": 8.240599505315654e-07,
|
| 540 |
+
"logits/chosen": -0.6872956156730652,
|
| 541 |
+
"logits/rejected": -0.6839295625686646,
|
| 542 |
+
"logps/chosen": -0.8706089854240417,
|
| 543 |
+
"logps/rejected": -0.9267762899398804,
|
| 544 |
+
"loss": 0.5737,
|
| 545 |
+
"rewards/accuracies": 0.762499988079071,
|
| 546 |
+
"rewards/chosen": -0.7884671688079834,
|
| 547 |
+
"rewards/margins": 0.42132559418678284,
|
| 548 |
+
"rewards/rejected": -1.2097927331924438,
|
| 549 |
+
"step": 175
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.3592814371257485,
|
| 553 |
+
"grad_norm": 17.325663221044394,
|
| 554 |
+
"learning_rate": 8.105738901391551e-07,
|
| 555 |
+
"logits/chosen": -0.702431857585907,
|
| 556 |
+
"logits/rejected": -0.6738135814666748,
|
| 557 |
+
"logps/chosen": -0.8363839387893677,
|
| 558 |
+
"logps/rejected": -0.8939155340194702,
|
| 559 |
+
"loss": 0.5712,
|
| 560 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 561 |
+
"rewards/chosen": -0.724533200263977,
|
| 562 |
+
"rewards/margins": 0.3838126063346863,
|
| 563 |
+
"rewards/rejected": -1.108345866203308,
|
| 564 |
+
"step": 180
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.36926147704590817,
|
| 568 |
+
"grad_norm": 16.365607087163703,
|
| 569 |
+
"learning_rate": 7.967094433018508e-07,
|
| 570 |
+
"logits/chosen": -0.7076471447944641,
|
| 571 |
+
"logits/rejected": -0.6945314407348633,
|
| 572 |
+
"logps/chosen": -0.9004107713699341,
|
| 573 |
+
"logps/rejected": -1.046083688735962,
|
| 574 |
+
"loss": 0.5742,
|
| 575 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 576 |
+
"rewards/chosen": -0.9093888401985168,
|
| 577 |
+
"rewards/margins": 0.6952089071273804,
|
| 578 |
+
"rewards/rejected": -1.6045976877212524,
|
| 579 |
+
"step": 185
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.37924151696606784,
|
| 583 |
+
"grad_norm": 43.74908736902799,
|
| 584 |
+
"learning_rate": 7.82483501712469e-07,
|
| 585 |
+
"logits/chosen": -0.6856539845466614,
|
| 586 |
+
"logits/rejected": -0.6615663766860962,
|
| 587 |
+
"logps/chosen": -0.9109293222427368,
|
| 588 |
+
"logps/rejected": -0.9081963300704956,
|
| 589 |
+
"loss": 0.5967,
|
| 590 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 591 |
+
"rewards/chosen": -0.9922858476638794,
|
| 592 |
+
"rewards/margins": 0.4050213396549225,
|
| 593 |
+
"rewards/rejected": -1.39730703830719,
|
| 594 |
+
"step": 190
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 0.38922155688622756,
|
| 598 |
+
"grad_norm": 19.60550699714766,
|
| 599 |
+
"learning_rate": 7.679133974894982e-07,
|
| 600 |
+
"logits/chosen": -0.6713054180145264,
|
| 601 |
+
"logits/rejected": -0.6843950748443604,
|
| 602 |
+
"logps/chosen": -0.8581186532974243,
|
| 603 |
+
"logps/rejected": -0.9895851016044617,
|
| 604 |
+
"loss": 0.5531,
|
| 605 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 606 |
+
"rewards/chosen": -0.9614213705062866,
|
| 607 |
+
"rewards/margins": 0.7596980929374695,
|
| 608 |
+
"rewards/rejected": -1.7211196422576904,
|
| 609 |
+
"step": 195
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.3992015968063872,
|
| 613 |
+
"grad_norm": 15.996993544634163,
|
| 614 |
+
"learning_rate": 7.530168820605818e-07,
|
| 615 |
+
"logits/chosen": -0.6824347972869873,
|
| 616 |
+
"logits/rejected": -0.6842206120491028,
|
| 617 |
+
"logps/chosen": -0.9382361173629761,
|
| 618 |
+
"logps/rejected": -0.9921613931655884,
|
| 619 |
+
"loss": 0.5583,
|
| 620 |
+
"rewards/accuracies": 0.762499988079071,
|
| 621 |
+
"rewards/chosen": -1.1333320140838623,
|
| 622 |
+
"rewards/margins": 0.5768089890480042,
|
| 623 |
+
"rewards/rejected": -1.7101409435272217,
|
| 624 |
+
"step": 200
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 0.4091816367265469,
|
| 628 |
+
"grad_norm": 15.558869167043554,
|
| 629 |
+
"learning_rate": 7.378121045351377e-07,
|
| 630 |
+
"logits/chosen": -0.6672806739807129,
|
| 631 |
+
"logits/rejected": -0.6542935371398926,
|
| 632 |
+
"logps/chosen": -0.8662320375442505,
|
| 633 |
+
"logps/rejected": -0.9581985473632812,
|
| 634 |
+
"loss": 0.5465,
|
| 635 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 636 |
+
"rewards/chosen": -1.0950018167495728,
|
| 637 |
+
"rewards/margins": 0.47961243987083435,
|
| 638 |
+
"rewards/rejected": -1.57461416721344,
|
| 639 |
+
"step": 205
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.41916167664670656,
|
| 643 |
+
"grad_norm": 28.887132861516903,
|
| 644 |
+
"learning_rate": 7.223175895924637e-07,
|
| 645 |
+
"logits/chosen": -0.690104603767395,
|
| 646 |
+
"logits/rejected": -0.6761881709098816,
|
| 647 |
+
"logps/chosen": -0.863226592540741,
|
| 648 |
+
"logps/rejected": -0.9225906133651733,
|
| 649 |
+
"loss": 0.5553,
|
| 650 |
+
"rewards/accuracies": 0.824999988079071,
|
| 651 |
+
"rewards/chosen": -1.0103793144226074,
|
| 652 |
+
"rewards/margins": 0.6174372434616089,
|
| 653 |
+
"rewards/rejected": -1.6278165578842163,
|
| 654 |
+
"step": 210
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.4291417165668663,
|
| 658 |
+
"grad_norm": 15.081565074387589,
|
| 659 |
+
"learning_rate": 7.065522149122709e-07,
|
| 660 |
+
"logits/chosen": -0.7095133662223816,
|
| 661 |
+
"logits/rejected": -0.6953072547912598,
|
| 662 |
+
"logps/chosen": -0.9815180897712708,
|
| 663 |
+
"logps/rejected": -1.0388023853302002,
|
| 664 |
+
"loss": 0.5393,
|
| 665 |
+
"rewards/accuracies": 0.75,
|
| 666 |
+
"rewards/chosen": -1.4431049823760986,
|
| 667 |
+
"rewards/margins": 0.5409745573997498,
|
| 668 |
+
"rewards/rejected": -1.9840797185897827,
|
| 669 |
+
"step": 215
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.43912175648702595,
|
| 673 |
+
"grad_norm": 27.859691103168426,
|
| 674 |
+
"learning_rate": 6.905351881751371e-07,
|
| 675 |
+
"logits/chosen": -0.7326300144195557,
|
| 676 |
+
"logits/rejected": -0.7271891832351685,
|
| 677 |
+
"logps/chosen": -0.886702835559845,
|
| 678 |
+
"logps/rejected": -0.9949976205825806,
|
| 679 |
+
"loss": 0.5524,
|
| 680 |
+
"rewards/accuracies": 0.699999988079071,
|
| 681 |
+
"rewards/chosen": -1.178215742111206,
|
| 682 |
+
"rewards/margins": 0.5899935364723206,
|
| 683 |
+
"rewards/rejected": -1.7682092189788818,
|
| 684 |
+
"step": 220
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 0.4491017964071856,
|
| 688 |
+
"grad_norm": 20.049309145299137,
|
| 689 |
+
"learning_rate": 6.742860236609076e-07,
|
| 690 |
+
"logits/chosen": -0.7312344312667847,
|
| 691 |
+
"logits/rejected": -0.7114800810813904,
|
| 692 |
+
"logps/chosen": -0.9219420552253723,
|
| 693 |
+
"logps/rejected": -0.9769749641418457,
|
| 694 |
+
"loss": 0.5397,
|
| 695 |
+
"rewards/accuracies": 0.737500011920929,
|
| 696 |
+
"rewards/chosen": -1.2608001232147217,
|
| 697 |
+
"rewards/margins": 0.6559053659439087,
|
| 698 |
+
"rewards/rejected": -1.9167054891586304,
|
| 699 |
+
"step": 225
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.4590818363273453,
|
| 703 |
+
"grad_norm": 21.600145701212536,
|
| 704 |
+
"learning_rate": 6.578245184735512e-07,
|
| 705 |
+
"logits/chosen": -0.7300236225128174,
|
| 706 |
+
"logits/rejected": -0.7002195119857788,
|
| 707 |
+
"logps/chosen": -0.9393006563186646,
|
| 708 |
+
"logps/rejected": -0.9583779573440552,
|
| 709 |
+
"loss": 0.5285,
|
| 710 |
+
"rewards/accuracies": 0.675000011920929,
|
| 711 |
+
"rewards/chosen": -1.3502466678619385,
|
| 712 |
+
"rewards/margins": 0.5810690522193909,
|
| 713 |
+
"rewards/rejected": -1.9313156604766846,
|
| 714 |
+
"step": 230
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 0.469061876247505,
|
| 718 |
+
"grad_norm": 15.102196954163185,
|
| 719 |
+
"learning_rate": 6.411707284214383e-07,
|
| 720 |
+
"logits/chosen": -0.7769094705581665,
|
| 721 |
+
"logits/rejected": -0.784206211566925,
|
| 722 |
+
"logps/chosen": -0.937769889831543,
|
| 723 |
+
"logps/rejected": -1.0256552696228027,
|
| 724 |
+
"loss": 0.5481,
|
| 725 |
+
"rewards/accuracies": 0.699999988079071,
|
| 726 |
+
"rewards/chosen": -1.3135572671890259,
|
| 727 |
+
"rewards/margins": 0.6154013872146606,
|
| 728 |
+
"rewards/rejected": -1.928958535194397,
|
| 729 |
+
"step": 235
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.47904191616766467,
|
| 733 |
+
"grad_norm": 22.589088897581874,
|
| 734 |
+
"learning_rate": 6.243449435824276e-07,
|
| 735 |
+
"logits/chosen": -0.7115018367767334,
|
| 736 |
+
"logits/rejected": -0.6854550242424011,
|
| 737 |
+
"logps/chosen": -0.8389812707901001,
|
| 738 |
+
"logps/rejected": -0.9537237882614136,
|
| 739 |
+
"loss": 0.5204,
|
| 740 |
+
"rewards/accuracies": 0.75,
|
| 741 |
+
"rewards/chosen": -1.3218843936920166,
|
| 742 |
+
"rewards/margins": 0.7666546106338501,
|
| 743 |
+
"rewards/rejected": -2.088538885116577,
|
| 744 |
+
"step": 240
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.48902195608782434,
|
| 748 |
+
"grad_norm": 17.05950897502288,
|
| 749 |
+
"learning_rate": 6.073676635835316e-07,
|
| 750 |
+
"logits/chosen": -0.7151886820793152,
|
| 751 |
+
"logits/rejected": -0.7269682884216309,
|
| 752 |
+
"logps/chosen": -0.8353130221366882,
|
| 753 |
+
"logps/rejected": -1.045952320098877,
|
| 754 |
+
"loss": 0.5198,
|
| 755 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 756 |
+
"rewards/chosen": -1.2784829139709473,
|
| 757 |
+
"rewards/margins": 1.028085470199585,
|
| 758 |
+
"rewards/rejected": -2.3065686225891113,
|
| 759 |
+
"step": 245
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.499001996007984,
|
| 763 |
+
"grad_norm": 22.204919215887884,
|
| 764 |
+
"learning_rate": 5.9025957262528e-07,
|
| 765 |
+
"logits/chosen": -0.7427772879600525,
|
| 766 |
+
"logits/rejected": -0.7114007472991943,
|
| 767 |
+
"logps/chosen": -0.8959082365036011,
|
| 768 |
+
"logps/rejected": -1.015169382095337,
|
| 769 |
+
"loss": 0.5047,
|
| 770 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 771 |
+
"rewards/chosen": -1.4343379735946655,
|
| 772 |
+
"rewards/margins": 0.8260199427604675,
|
| 773 |
+
"rewards/rejected": -2.260357618331909,
|
| 774 |
+
"step": 250
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 0.5089820359281437,
|
| 778 |
+
"grad_norm": 29.103918291256367,
|
| 779 |
+
"learning_rate": 5.730415142812058e-07,
|
| 780 |
+
"logits/chosen": -0.7786175608634949,
|
| 781 |
+
"logits/rejected": -0.7618826627731323,
|
| 782 |
+
"logps/chosen": -0.9678372144699097,
|
| 783 |
+
"logps/rejected": -1.090914011001587,
|
| 784 |
+
"loss": 0.5111,
|
| 785 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 786 |
+
"rewards/chosen": -1.7259149551391602,
|
| 787 |
+
"rewards/margins": 0.8811995387077332,
|
| 788 |
+
"rewards/rejected": -2.607114315032959,
|
| 789 |
+
"step": 255
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.5189620758483033,
|
| 793 |
+
"grad_norm": 17.21881262945149,
|
| 794 |
+
"learning_rate": 5.557344661031627e-07,
|
| 795 |
+
"logits/chosen": -0.7823535799980164,
|
| 796 |
+
"logits/rejected": -0.7699525356292725,
|
| 797 |
+
"logps/chosen": -0.9408347010612488,
|
| 798 |
+
"logps/rejected": -1.0648287534713745,
|
| 799 |
+
"loss": 0.5406,
|
| 800 |
+
"rewards/accuracies": 0.75,
|
| 801 |
+
"rewards/chosen": -1.5965430736541748,
|
| 802 |
+
"rewards/margins": 1.0114134550094604,
|
| 803 |
+
"rewards/rejected": -2.6079564094543457,
|
| 804 |
+
"step": 260
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 0.5289421157684631,
|
| 808 |
+
"grad_norm": 15.711105031107639,
|
| 809 |
+
"learning_rate": 5.383595140634093e-07,
|
| 810 |
+
"logits/chosen": -0.7325602769851685,
|
| 811 |
+
"logits/rejected": -0.7186430096626282,
|
| 812 |
+
"logps/chosen": -0.943433403968811,
|
| 813 |
+
"logps/rejected": -1.0095100402832031,
|
| 814 |
+
"loss": 0.5276,
|
| 815 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 816 |
+
"rewards/chosen": -1.7036699056625366,
|
| 817 |
+
"rewards/margins": 0.8646278381347656,
|
| 818 |
+
"rewards/rejected": -2.5682976245880127,
|
| 819 |
+
"step": 265
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 0.5389221556886228,
|
| 823 |
+
"grad_norm": 13.20029610671174,
|
| 824 |
+
"learning_rate": 5.209378268645997e-07,
|
| 825 |
+
"logits/chosen": -0.7176939249038696,
|
| 826 |
+
"logits/rejected": -0.7001760601997375,
|
| 827 |
+
"logps/chosen": -0.8967610597610474,
|
| 828 |
+
"logps/rejected": -1.0068597793579102,
|
| 829 |
+
"loss": 0.5582,
|
| 830 |
+
"rewards/accuracies": 0.800000011920929,
|
| 831 |
+
"rewards/chosen": -1.737532377243042,
|
| 832 |
+
"rewards/margins": 0.5873457193374634,
|
| 833 |
+
"rewards/rejected": -2.324878215789795,
|
| 834 |
+
"step": 270
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 0.5489021956087824,
|
| 838 |
+
"grad_norm": 20.138444852189,
|
| 839 |
+
"learning_rate": 5.034906301489807e-07,
|
| 840 |
+
"logits/chosen": -0.7280402779579163,
|
| 841 |
+
"logits/rejected": -0.717974066734314,
|
| 842 |
+
"logps/chosen": -0.9318618774414062,
|
| 843 |
+
"logps/rejected": -1.0344207286834717,
|
| 844 |
+
"loss": 0.5238,
|
| 845 |
+
"rewards/accuracies": 0.75,
|
| 846 |
+
"rewards/chosen": -1.814552903175354,
|
| 847 |
+
"rewards/margins": 0.8326984643936157,
|
| 848 |
+
"rewards/rejected": -2.647251605987549,
|
| 849 |
+
"step": 275
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.5588822355289421,
|
| 853 |
+
"grad_norm": 37.63172145615237,
|
| 854 |
+
"learning_rate": 4.860391806382156e-07,
|
| 855 |
+
"logits/chosen": -0.8018016815185547,
|
| 856 |
+
"logits/rejected": -0.8149466514587402,
|
| 857 |
+
"logps/chosen": -0.9740177392959595,
|
| 858 |
+
"logps/rejected": -1.010301113128662,
|
| 859 |
+
"loss": 0.5217,
|
| 860 |
+
"rewards/accuracies": 0.8125,
|
| 861 |
+
"rewards/chosen": -1.8418344259262085,
|
| 862 |
+
"rewards/margins": 0.7042922973632812,
|
| 863 |
+
"rewards/rejected": -2.5461268424987793,
|
| 864 |
+
"step": 280
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.5688622754491018,
|
| 868 |
+
"grad_norm": 20.60319293019308,
|
| 869 |
+
"learning_rate": 4.686047402353433e-07,
|
| 870 |
+
"logits/chosen": -0.7303526997566223,
|
| 871 |
+
"logits/rejected": -0.7184230089187622,
|
| 872 |
+
"logps/chosen": -0.9589718580245972,
|
| 873 |
+
"logps/rejected": -1.045867681503296,
|
| 874 |
+
"loss": 0.523,
|
| 875 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 876 |
+
"rewards/chosen": -1.8164526224136353,
|
| 877 |
+
"rewards/margins": 0.7647993564605713,
|
| 878 |
+
"rewards/rejected": -2.581251621246338,
|
| 879 |
+
"step": 285
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 0.5788423153692615,
|
| 883 |
+
"grad_norm": 31.323512708787323,
|
| 884 |
+
"learning_rate": 4.512085501204253e-07,
|
| 885 |
+
"logits/chosen": -0.7896037101745605,
|
| 886 |
+
"logits/rejected": -0.7570759057998657,
|
| 887 |
+
"logps/chosen": -0.9357205629348755,
|
| 888 |
+
"logps/rejected": -1.0159623622894287,
|
| 889 |
+
"loss": 0.5636,
|
| 890 |
+
"rewards/accuracies": 0.737500011920929,
|
| 891 |
+
"rewards/chosen": -1.7307599782943726,
|
| 892 |
+
"rewards/margins": 0.7415143251419067,
|
| 893 |
+
"rewards/rejected": -2.4722743034362793,
|
| 894 |
+
"step": 290
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 0.5888223552894212,
|
| 898 |
+
"grad_norm": 16.113569930607966,
|
| 899 |
+
"learning_rate": 4.338718048714387e-07,
|
| 900 |
+
"logits/chosen": -0.7748357057571411,
|
| 901 |
+
"logits/rejected": -0.7527580857276917,
|
| 902 |
+
"logps/chosen": -0.9312615394592285,
|
| 903 |
+
"logps/rejected": -0.9944890141487122,
|
| 904 |
+
"loss": 0.5261,
|
| 905 |
+
"rewards/accuracies": 0.862500011920929,
|
| 906 |
+
"rewards/chosen": -1.7469574213027954,
|
| 907 |
+
"rewards/margins": 0.5817708969116211,
|
| 908 |
+
"rewards/rejected": -2.328728675842285,
|
| 909 |
+
"step": 295
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 0.5988023952095808,
|
| 913 |
+
"grad_norm": 28.923235923466983,
|
| 914 |
+
"learning_rate": 4.166156266419489e-07,
|
| 915 |
+
"logits/chosen": -0.7699166536331177,
|
| 916 |
+
"logits/rejected": -0.7807640433311462,
|
| 917 |
+
"logps/chosen": -0.8693283200263977,
|
| 918 |
+
"logps/rejected": -1.0598359107971191,
|
| 919 |
+
"loss": 0.5223,
|
| 920 |
+
"rewards/accuracies": 0.8125,
|
| 921 |
+
"rewards/chosen": -1.6791868209838867,
|
| 922 |
+
"rewards/margins": 1.093235969543457,
|
| 923 |
+
"rewards/rejected": -2.7724227905273438,
|
| 924 |
+
"step": 300
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 0.6087824351297405,
|
| 928 |
+
"grad_norm": 43.24348090401382,
|
| 929 |
+
"learning_rate": 3.9946103942701775e-07,
|
| 930 |
+
"logits/chosen": -0.713184118270874,
|
| 931 |
+
"logits/rejected": -0.7183653116226196,
|
| 932 |
+
"logps/chosen": -0.877181887626648,
|
| 933 |
+
"logps/rejected": -1.0504357814788818,
|
| 934 |
+
"loss": 0.5006,
|
| 935 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 936 |
+
"rewards/chosen": -1.6295019388198853,
|
| 937 |
+
"rewards/margins": 0.8480024337768555,
|
| 938 |
+
"rewards/rejected": -2.477504253387451,
|
| 939 |
+
"step": 305
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 0.6187624750499002,
|
| 943 |
+
"grad_norm": 18.17532898488996,
|
| 944 |
+
"learning_rate": 3.8242894344870495e-07,
|
| 945 |
+
"logits/chosen": -0.7871264815330505,
|
| 946 |
+
"logits/rejected": -0.7895926237106323,
|
| 947 |
+
"logps/chosen": -0.9971866607666016,
|
| 948 |
+
"logps/rejected": -1.110032558441162,
|
| 949 |
+
"loss": 0.5224,
|
| 950 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 951 |
+
"rewards/chosen": -2.071504592895508,
|
| 952 |
+
"rewards/margins": 0.8322666883468628,
|
| 953 |
+
"rewards/rejected": -2.90377140045166,
|
| 954 |
+
"step": 310
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.6287425149700598,
|
| 958 |
+
"grad_norm": 22.503824878122693,
|
| 959 |
+
"learning_rate": 3.6554008969236715e-07,
|
| 960 |
+
"logits/chosen": -0.7987596392631531,
|
| 961 |
+
"logits/rejected": -0.8034515380859375,
|
| 962 |
+
"logps/chosen": -0.9355812072753906,
|
| 963 |
+
"logps/rejected": -1.101746916770935,
|
| 964 |
+
"loss": 0.4993,
|
| 965 |
+
"rewards/accuracies": 0.8374999761581421,
|
| 966 |
+
"rewards/chosen": -1.8815546035766602,
|
| 967 |
+
"rewards/margins": 1.0128275156021118,
|
| 968 |
+
"rewards/rejected": -2.8943822383880615,
|
| 969 |
+
"step": 315
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.6387225548902196,
|
| 973 |
+
"grad_norm": 18.4314421544152,
|
| 974 |
+
"learning_rate": 3.488150546247778e-07,
|
| 975 |
+
"logits/chosen": -0.7646247148513794,
|
| 976 |
+
"logits/rejected": -0.7596274018287659,
|
| 977 |
+
"logps/chosen": -0.9071539640426636,
|
| 978 |
+
"logps/rejected": -0.9974797964096069,
|
| 979 |
+
"loss": 0.5067,
|
| 980 |
+
"rewards/accuracies": 0.824999988079071,
|
| 981 |
+
"rewards/chosen": -1.761649489402771,
|
| 982 |
+
"rewards/margins": 0.7561764717102051,
|
| 983 |
+
"rewards/rejected": -2.5178260803222656,
|
| 984 |
+
"step": 320
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 0.6487025948103793,
|
| 988 |
+
"grad_norm": 13.46220126387281,
|
| 989 |
+
"learning_rate": 3.3227421512487255e-07,
|
| 990 |
+
"logits/chosen": -0.7663795948028564,
|
| 991 |
+
"logits/rejected": -0.7689803838729858,
|
| 992 |
+
"logps/chosen": -0.9501086473464966,
|
| 993 |
+
"logps/rejected": -1.0315439701080322,
|
| 994 |
+
"loss": 0.5057,
|
| 995 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 996 |
+
"rewards/chosen": -1.9115231037139893,
|
| 997 |
+
"rewards/margins": 0.7186993360519409,
|
| 998 |
+
"rewards/rejected": -2.630222797393799,
|
| 999 |
+
"step": 325
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.6586826347305389,
|
| 1003 |
+
"grad_norm": 43.00875479745304,
|
| 1004 |
+
"learning_rate": 3.15937723657661e-07,
|
| 1005 |
+
"logits/chosen": -0.8140354156494141,
|
| 1006 |
+
"logits/rejected": -0.8173881769180298,
|
| 1007 |
+
"logps/chosen": -0.9712478518486023,
|
| 1008 |
+
"logps/rejected": -1.0843861103057861,
|
| 1009 |
+
"loss": 0.5873,
|
| 1010 |
+
"rewards/accuracies": 0.737500011920929,
|
| 1011 |
+
"rewards/chosen": -2.222109794616699,
|
| 1012 |
+
"rewards/margins": 0.6900671720504761,
|
| 1013 |
+
"rewards/rejected": -2.9121768474578857,
|
| 1014 |
+
"step": 330
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 0.6686626746506986,
|
| 1018 |
+
"grad_norm": 32.97485130184056,
|
| 1019 |
+
"learning_rate": 2.9982548372155256e-07,
|
| 1020 |
+
"logits/chosen": -0.7841066718101501,
|
| 1021 |
+
"logits/rejected": -0.801399827003479,
|
| 1022 |
+
"logps/chosen": -0.9092627763748169,
|
| 1023 |
+
"logps/rejected": -1.0644382238388062,
|
| 1024 |
+
"loss": 0.5121,
|
| 1025 |
+
"rewards/accuracies": 0.8374999761581421,
|
| 1026 |
+
"rewards/chosen": -1.8617267608642578,
|
| 1027 |
+
"rewards/margins": 1.0364662408828735,
|
| 1028 |
+
"rewards/rejected": -2.898192882537842,
|
| 1029 |
+
"step": 335
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 0.6786427145708582,
|
| 1033 |
+
"grad_norm": 50.76904692556944,
|
| 1034 |
+
"learning_rate": 2.8395712559900874e-07,
|
| 1035 |
+
"logits/chosen": -0.8244466781616211,
|
| 1036 |
+
"logits/rejected": -0.8209226727485657,
|
| 1037 |
+
"logps/chosen": -1.0543348789215088,
|
| 1038 |
+
"logps/rejected": -1.1451005935668945,
|
| 1039 |
+
"loss": 0.5205,
|
| 1040 |
+
"rewards/accuracies": 0.75,
|
| 1041 |
+
"rewards/chosen": -2.412365674972534,
|
| 1042 |
+
"rewards/margins": 0.8550116419792175,
|
| 1043 |
+
"rewards/rejected": -3.2673773765563965,
|
| 1044 |
+
"step": 340
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 0.688622754491018,
|
| 1048 |
+
"grad_norm": 27.915007397999354,
|
| 1049 |
+
"learning_rate": 2.683519824400692e-07,
|
| 1050 |
+
"logits/chosen": -0.8374012112617493,
|
| 1051 |
+
"logits/rejected": -0.8106748461723328,
|
| 1052 |
+
"logps/chosen": -0.9777308702468872,
|
| 1053 |
+
"logps/rejected": -1.1284379959106445,
|
| 1054 |
+
"loss": 0.5234,
|
| 1055 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 1056 |
+
"rewards/chosen": -2.029723882675171,
|
| 1057 |
+
"rewards/margins": 1.0547873973846436,
|
| 1058 |
+
"rewards/rejected": -3.0845110416412354,
|
| 1059 |
+
"step": 345
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.6986027944111777,
|
| 1063 |
+
"grad_norm": 22.882772557486724,
|
| 1064 |
+
"learning_rate": 2.530290667078846e-07,
|
| 1065 |
+
"logits/chosen": -0.8036109805107117,
|
| 1066 |
+
"logits/rejected": -0.7900259494781494,
|
| 1067 |
+
"logps/chosen": -0.9737772941589355,
|
| 1068 |
+
"logps/rejected": -1.085715651512146,
|
| 1069 |
+
"loss": 0.5015,
|
| 1070 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 1071 |
+
"rewards/chosen": -2.1590065956115723,
|
| 1072 |
+
"rewards/margins": 0.7729440927505493,
|
| 1073 |
+
"rewards/rejected": -2.931950807571411,
|
| 1074 |
+
"step": 350
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.7085828343313373,
|
| 1078 |
+
"grad_norm": 18.205286801888395,
|
| 1079 |
+
"learning_rate": 2.380070470149605e-07,
|
| 1080 |
+
"logits/chosen": -0.8169373273849487,
|
| 1081 |
+
"logits/rejected": -0.8327714204788208,
|
| 1082 |
+
"logps/chosen": -0.9806594848632812,
|
| 1083 |
+
"logps/rejected": -1.1701897382736206,
|
| 1084 |
+
"loss": 0.496,
|
| 1085 |
+
"rewards/accuracies": 0.75,
|
| 1086 |
+
"rewards/chosen": -2.151632308959961,
|
| 1087 |
+
"rewards/margins": 1.1866142749786377,
|
| 1088 |
+
"rewards/rejected": -3.3382461071014404,
|
| 1089 |
+
"step": 355
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 0.718562874251497,
|
| 1093 |
+
"grad_norm": 41.98073419560719,
|
| 1094 |
+
"learning_rate": 2.23304225378328e-07,
|
| 1095 |
+
"logits/chosen": -0.8116399049758911,
|
| 1096 |
+
"logits/rejected": -0.7772837281227112,
|
| 1097 |
+
"logps/chosen": -1.0802838802337646,
|
| 1098 |
+
"logps/rejected": -1.1937668323516846,
|
| 1099 |
+
"loss": 0.5124,
|
| 1100 |
+
"rewards/accuracies": 0.800000011920929,
|
| 1101 |
+
"rewards/chosen": -2.334536075592041,
|
| 1102 |
+
"rewards/margins": 1.168308138847351,
|
| 1103 |
+
"rewards/rejected": -3.5028443336486816,
|
| 1104 |
+
"step": 360
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 0.7285429141716567,
|
| 1108 |
+
"grad_norm": 27.12760666687319,
|
| 1109 |
+
"learning_rate": 2.0893851492135532e-07,
|
| 1110 |
+
"logits/chosen": -0.8288819193840027,
|
| 1111 |
+
"logits/rejected": -0.8238687515258789,
|
| 1112 |
+
"logps/chosen": -0.9590953588485718,
|
| 1113 |
+
"logps/rejected": -1.1089394092559814,
|
| 1114 |
+
"loss": 0.5151,
|
| 1115 |
+
"rewards/accuracies": 0.762499988079071,
|
| 1116 |
+
"rewards/chosen": -1.967963457107544,
|
| 1117 |
+
"rewards/margins": 1.0413198471069336,
|
| 1118 |
+
"rewards/rejected": -3.0092828273773193,
|
| 1119 |
+
"step": 365
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.7385229540918163,
|
| 1123 |
+
"grad_norm": 28.594288392858182,
|
| 1124 |
+
"learning_rate": 1.9492741804936618e-07,
|
| 1125 |
+
"logits/chosen": -0.8266215324401855,
|
| 1126 |
+
"logits/rejected": -0.8546527028083801,
|
| 1127 |
+
"logps/chosen": -1.0014851093292236,
|
| 1128 |
+
"logps/rejected": -1.0811948776245117,
|
| 1129 |
+
"loss": 0.5134,
|
| 1130 |
+
"rewards/accuracies": 0.737500011920929,
|
| 1131 |
+
"rewards/chosen": -2.126549482345581,
|
| 1132 |
+
"rewards/margins": 0.8130427598953247,
|
| 1133 |
+
"rewards/rejected": -2.939592123031616,
|
| 1134 |
+
"step": 370
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 0.7485029940119761,
|
| 1138 |
+
"grad_norm": 16.69085619906614,
|
| 1139 |
+
"learning_rate": 1.812880051256551e-07,
|
| 1140 |
+
"logits/chosen": -0.8046598434448242,
|
| 1141 |
+
"logits/rejected": -0.8114801645278931,
|
| 1142 |
+
"logps/chosen": -0.9752721786499023,
|
| 1143 |
+
"logps/rejected": -1.0586512088775635,
|
| 1144 |
+
"loss": 0.4999,
|
| 1145 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 1146 |
+
"rewards/chosen": -2.1684842109680176,
|
| 1147 |
+
"rewards/margins": 0.6114571690559387,
|
| 1148 |
+
"rewards/rejected": -2.7799415588378906,
|
| 1149 |
+
"step": 375
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 0.7584830339321357,
|
| 1153 |
+
"grad_norm": 15.627879784878328,
|
| 1154 |
+
"learning_rate": 1.6803689367387918e-07,
|
| 1155 |
+
"logits/chosen": -0.823495090007782,
|
| 1156 |
+
"logits/rejected": -0.7943788170814514,
|
| 1157 |
+
"logps/chosen": -0.8508175015449524,
|
| 1158 |
+
"logps/rejected": -0.9670391082763672,
|
| 1159 |
+
"loss": 0.5187,
|
| 1160 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 1161 |
+
"rewards/chosen": -1.9837039709091187,
|
| 1162 |
+
"rewards/margins": 0.5095661878585815,
|
| 1163 |
+
"rewards/rejected": -2.4932703971862793,
|
| 1164 |
+
"step": 380
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.7684630738522954,
|
| 1168 |
+
"grad_norm": 14.609956803422161,
|
| 1169 |
+
"learning_rate": 1.551902281321651e-07,
|
| 1170 |
+
"logits/chosen": -0.8435534238815308,
|
| 1171 |
+
"logits/rejected": -0.8091138601303101,
|
| 1172 |
+
"logps/chosen": -0.998641848564148,
|
| 1173 |
+
"logps/rejected": -1.133357286453247,
|
| 1174 |
+
"loss": 0.4954,
|
| 1175 |
+
"rewards/accuracies": 0.887499988079071,
|
| 1176 |
+
"rewards/chosen": -1.9779011011123657,
|
| 1177 |
+
"rewards/margins": 1.3220001459121704,
|
| 1178 |
+
"rewards/rejected": -3.2999014854431152,
|
| 1179 |
+
"step": 385
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.7784431137724551,
|
| 1183 |
+
"grad_norm": 27.689053757448693,
|
| 1184 |
+
"learning_rate": 1.4276366018359842e-07,
|
| 1185 |
+
"logits/chosen": -0.8398737907409668,
|
| 1186 |
+
"logits/rejected": -0.811150848865509,
|
| 1187 |
+
"logps/chosen": -0.9453309178352356,
|
| 1188 |
+
"logps/rejected": -1.0934703350067139,
|
| 1189 |
+
"loss": 0.5225,
|
| 1190 |
+
"rewards/accuracies": 0.762499988079071,
|
| 1191 |
+
"rewards/chosen": -2.0561106204986572,
|
| 1192 |
+
"rewards/margins": 1.0419596433639526,
|
| 1193 |
+
"rewards/rejected": -3.0980706214904785,
|
| 1194 |
+
"step": 390
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 0.7884231536926147,
|
| 1198 |
+
"grad_norm": 37.02718002584944,
|
| 1199 |
+
"learning_rate": 1.3077232968705805e-07,
|
| 1200 |
+
"logits/chosen": -0.8516527414321899,
|
| 1201 |
+
"logits/rejected": -0.8527445793151855,
|
| 1202 |
+
"logps/chosen": -0.969285786151886,
|
| 1203 |
+
"logps/rejected": -1.0676743984222412,
|
| 1204 |
+
"loss": 0.4928,
|
| 1205 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 1206 |
+
"rewards/chosen": -1.9902063608169556,
|
| 1207 |
+
"rewards/margins": 0.7401792407035828,
|
| 1208 |
+
"rewards/rejected": -2.7303855419158936,
|
| 1209 |
+
"step": 395
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 0.7984031936127745,
|
| 1213 |
+
"grad_norm": 14.525059669424861,
|
| 1214 |
+
"learning_rate": 1.192308462316317e-07,
|
| 1215 |
+
"logits/chosen": -0.7803691625595093,
|
| 1216 |
+
"logits/rejected": -0.7951369285583496,
|
| 1217 |
+
"logps/chosen": -0.9650856852531433,
|
| 1218 |
+
"logps/rejected": -1.1078399419784546,
|
| 1219 |
+
"loss": 0.4959,
|
| 1220 |
+
"rewards/accuracies": 0.824999988079071,
|
| 1221 |
+
"rewards/chosen": -2.048185110092163,
|
| 1222 |
+
"rewards/margins": 0.8834241628646851,
|
| 1223 |
+
"rewards/rejected": -2.9316093921661377,
|
| 1224 |
+
"step": 400
|
| 1225 |
+
}
|
| 1226 |
+
],
|
| 1227 |
+
"logging_steps": 5,
|
| 1228 |
+
"max_steps": 501,
|
| 1229 |
+
"num_input_tokens_seen": 0,
|
| 1230 |
+
"num_train_epochs": 1,
|
| 1231 |
+
"save_steps": 101,
|
| 1232 |
+
"stateful_callbacks": {
|
| 1233 |
+
"TrainerControl": {
|
| 1234 |
+
"args": {
|
| 1235 |
+
"should_epoch_stop": false,
|
| 1236 |
+
"should_evaluate": false,
|
| 1237 |
+
"should_log": false,
|
| 1238 |
+
"should_save": true,
|
| 1239 |
+
"should_training_stop": false
|
| 1240 |
+
},
|
| 1241 |
+
"attributes": {}
|
| 1242 |
+
}
|
| 1243 |
+
},
|
| 1244 |
+
"total_flos": 0.0,
|
| 1245 |
+
"train_batch_size": 4,
|
| 1246 |
+
"trial_name": null,
|
| 1247 |
+
"trial_params": null
|
| 1248 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fd0f3ab114b13eaae5e496cd21afb47138ace5cedd5dba79365b642ee2968b93
|
| 3 |
+
size 7544
|