wzhouad commited on
Commit
dcc9f87
1 Parent(s): 5ae2c8f

Model save

Browse files
README.md CHANGED
@@ -1,4 +1,6 @@
1
  ---
 
 
2
  tags:
3
  - trl
4
  - dpo
@@ -13,17 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
13
 
14
  # zephyr-7b-dpo-full
15
 
16
- This model was trained from scratch on the None dataset.
17
- It achieves the following results on the evaluation set:
18
- - Loss: 0.0411
19
- - Rewards/chosen: -0.5857
20
- - Rewards/rejected: -1.1337
21
- - Rewards/accuracies: 0.7383
22
- - Rewards/margins: 0.5480
23
- - Logps/rejected: -479.0815
24
- - Logps/chosen: -418.0253
25
- - Logits/rejected: 0.8172
26
- - Logits/chosen: 0.6972
27
 
28
  ## Model description
29
 
@@ -43,12 +35,12 @@ More information needed
43
 
44
  The following hyperparameters were used during training:
45
  - learning_rate: 5e-07
46
- - train_batch_size: 4
47
  - eval_batch_size: 8
48
- - seed: 5
49
  - distributed_type: multi-GPU
50
  - num_devices: 8
51
- - gradient_accumulation_steps: 4
52
  - total_train_batch_size: 128
53
  - total_eval_batch_size: 64
54
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
@@ -58,12 +50,6 @@ The following hyperparameters were used during training:
58
 
59
  ### Training results
60
 
61
- | Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
62
- |:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
63
- | 0.078 | 0.21 | 100 | 0.0782 | -0.0611 | -0.2385 | 0.6953 | 0.1774 | -389.5570 | -365.5567 | 0.5343 | 0.4690 |
64
- | 0.048 | 0.42 | 200 | 0.0473 | -0.4678 | -0.9057 | 0.7070 | 0.4379 | -456.2774 | -406.2315 | 0.7803 | 0.6603 |
65
- | 0.0386 | 0.63 | 300 | 0.0410 | -0.6126 | -1.1367 | 0.7188 | 0.5241 | -479.3783 | -420.7087 | 0.8701 | 0.7596 |
66
- | 0.0346 | 0.84 | 400 | 0.0411 | -0.5857 | -1.1337 | 0.7383 | 0.5480 | -479.0815 | -418.0253 | 0.8172 | 0.6972 |
67
 
68
 
69
  ### Framework versions
 
1
  ---
2
+ license: mit
3
+ base_model: HuggingFaceH4/mistral-7b-sft-beta
4
  tags:
5
  - trl
6
  - dpo
 
15
 
16
  # zephyr-7b-dpo-full
17
 
18
+ This model is a fine-tuned version of [HuggingFaceH4/mistral-7b-sft-beta](https://huggingface.co/HuggingFaceH4/mistral-7b-sft-beta) on the None dataset.
 
 
 
 
 
 
 
 
 
 
19
 
20
  ## Model description
21
 
 
35
 
36
  The following hyperparameters were used during training:
37
  - learning_rate: 5e-07
38
+ - train_batch_size: 8
39
  - eval_batch_size: 8
40
+ - seed: 3
41
  - distributed_type: multi-GPU
42
  - num_devices: 8
43
+ - gradient_accumulation_steps: 2
44
  - total_train_batch_size: 128
45
  - total_eval_batch_size: 64
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 
50
 
51
  ### Training results
52
 
 
 
 
 
 
 
53
 
54
 
55
  ### Framework versions
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 1.0,
3
- "train_loss": 0.05354936925432717,
4
- "train_runtime": 4393.8172,
5
- "train_samples": 61134,
6
- "train_samples_per_second": 13.914,
7
- "train_steps_per_second": 0.109
8
  }
 
1
  {
2
  "epoch": 1.0,
3
+ "train_loss": 0.08838768833213383,
4
+ "train_runtime": 3226.1286,
5
+ "train_samples": 51894,
6
+ "train_samples_per_second": 16.086,
7
+ "train_steps_per_second": 0.126
8
  }
config.json CHANGED
@@ -1,28 +1,25 @@
1
  {
2
- "_name_or_path": "/share5/projects/llm/finetune-accelerate/weight/Meta-Llama-3-8B-Instruct",
3
  "architectures": [
4
- "LlamaForCausalLM"
5
  ],
6
- "attention_bias": false,
7
- "attention_dropout": 0.0,
8
- "bos_token_id": 128000,
9
- "eos_token_id": 128009,
10
  "hidden_act": "silu",
11
  "hidden_size": 4096,
12
  "initializer_range": 0.02,
13
  "intermediate_size": 14336,
14
- "max_position_embeddings": 8192,
15
- "model_type": "llama",
16
  "num_attention_heads": 32,
17
  "num_hidden_layers": 32,
18
  "num_key_value_heads": 8,
19
- "pretraining_tp": 1,
20
  "rms_norm_eps": 1e-05,
21
- "rope_scaling": null,
22
- "rope_theta": 500000.0,
23
  "tie_word_embeddings": false,
24
  "torch_dtype": "bfloat16",
25
  "transformers_version": "4.35.2",
26
  "use_cache": false,
27
- "vocab_size": 128256
28
  }
 
1
  {
2
+ "_name_or_path": "HuggingFaceH4/mistral-7b-sft-beta",
3
  "architectures": [
4
+ "MistralForCausalLM"
5
  ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
 
 
8
  "hidden_act": "silu",
9
  "hidden_size": 4096,
10
  "initializer_range": 0.02,
11
  "intermediate_size": 14336,
12
+ "max_position_embeddings": 32768,
13
+ "model_type": "mistral",
14
  "num_attention_heads": 32,
15
  "num_hidden_layers": 32,
16
  "num_key_value_heads": 8,
 
17
  "rms_norm_eps": 1e-05,
18
+ "rope_theta": 10000.0,
19
+ "sliding_window": 4096,
20
  "tie_word_embeddings": false,
21
  "torch_dtype": "bfloat16",
22
  "transformers_version": "4.35.2",
23
  "use_cache": false,
24
+ "vocab_size": 32000
25
  }
generation_config.json CHANGED
@@ -1,12 +1,6 @@
1
  {
2
- "bos_token_id": 128000,
3
- "do_sample": true,
4
- "eos_token_id": [
5
- 128001,
6
- 128009
7
- ],
8
- "max_length": 4096,
9
- "temperature": 0.6,
10
- "top_p": 0.9,
11
  "transformers_version": "4.35.2"
12
  }
 
1
  {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
 
 
 
 
 
 
5
  "transformers_version": "4.35.2"
6
  }
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:db59a50be7e6345fac302c36e929a206c83491d5e691ace75b47e73bb42f24ef
3
  size 4943162336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bec2fc3a9f5c1b7f9a8338008c24ba39fa60cc0ce19d81fa4a80fc872b4d1a69
3
  size 4943162336
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca644134a25acb797f095e93c9292df6566d0c9eb28eb5be68b32e5c83d53239
3
  size 4999819336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99b9705334bc445b339c02b18833e0f94ca1f783c8936c7cfc80540fcdb914cc
3
  size 4999819336
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7a31317b824f1ccf76e71c4f9b87d927ddf2e76facc98c1f8e8a8394942fa865
3
  size 4540516344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:560b2231901e748076a7cfb0ff2787a4b3f6ab9c45609b9e95f6f3da85ee8e6d
3
  size 4540516344
model.safetensors.index.json CHANGED
@@ -1,298 +1,298 @@
1
  {
2
  "metadata": {
3
- "total_size": 16060522496
4
  },
5
  "weight_map": {
6
- "lm_head.weight": "model-00004-of-00004.safetensors",
7
- "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
- "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
- "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
- "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
11
- "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
12
- "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
13
- "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
14
- "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
15
- "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
16
- "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
17
- "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
18
- "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
19
- "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
20
- "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
21
- "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
22
- "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
23
- "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
24
- "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
25
- "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
26
- "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
27
- "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
28
- "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
29
- "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
30
- "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
31
- "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
32
- "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
33
- "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
34
- "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
35
- "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
36
- "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
37
- "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
38
- "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
39
- "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
40
- "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
41
- "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
42
- "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
43
- "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
44
- "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
45
- "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
46
- "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
47
- "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
48
- "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
49
- "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
50
- "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
51
- "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
52
- "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
53
- "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
54
- "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
55
- "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
56
- "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
57
- "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
58
- "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
59
- "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
60
- "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
61
- "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
62
- "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
63
- "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
64
- "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
65
- "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
66
- "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
67
- "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
68
- "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
69
- "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
70
- "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
71
- "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
72
- "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
73
- "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
74
- "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
75
- "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
76
- "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
77
- "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
78
- "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
79
- "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
80
- "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
81
- "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
82
- "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
83
- "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
84
- "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
85
- "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
86
- "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
87
- "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
88
- "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
89
- "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
90
- "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
91
- "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
92
- "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
93
- "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
94
- "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
95
- "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
96
- "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
97
- "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
98
- "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
99
- "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
100
- "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
101
- "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
102
- "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
103
- "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
104
- "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
105
- "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
106
- "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
107
- "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
108
- "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
109
- "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
110
- "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
111
- "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
112
- "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
113
- "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
114
- "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
115
- "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
116
- "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
117
- "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
118
- "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
119
- "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
120
- "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
121
- "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
122
- "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
123
- "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
124
- "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
125
- "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
126
- "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
127
- "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
128
- "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
129
- "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
130
- "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
131
- "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
132
- "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
133
- "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
134
- "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
135
- "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
136
- "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
137
- "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
138
- "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
139
- "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
140
- "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
141
- "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
142
- "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
143
- "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
144
- "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
145
- "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
146
- "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
147
- "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
148
- "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
149
- "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
150
- "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
151
- "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
152
- "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
153
- "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
154
- "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
155
- "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
156
- "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
157
- "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
158
- "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
159
- "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
160
- "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
161
- "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
162
- "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
163
- "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
164
- "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
165
- "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
166
- "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
167
- "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
168
- "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
169
- "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
170
- "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
171
- "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
172
- "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
173
- "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
174
- "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
175
- "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
176
- "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
177
- "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
178
- "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
179
- "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
180
- "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
181
- "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
182
- "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
183
- "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
184
- "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
185
- "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
186
- "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
187
- "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
188
- "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
189
- "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
190
- "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
191
- "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
192
- "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
193
- "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
194
- "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
195
- "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
196
- "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
197
- "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
198
- "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
199
- "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
200
- "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
201
- "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
202
- "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
203
- "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
204
- "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
205
- "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
206
- "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
207
- "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
208
- "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
209
- "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
210
- "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
211
- "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
212
- "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
213
- "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
214
- "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
215
- "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
216
- "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
217
- "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
218
- "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
219
- "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
220
- "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
221
- "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
222
- "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
223
- "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
224
- "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
225
- "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
226
- "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
227
- "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
228
- "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
229
- "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
230
- "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
231
- "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
232
- "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
233
- "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
234
- "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
235
- "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
236
- "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
237
- "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
238
- "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
239
- "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
240
- "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
241
- "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
242
- "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
243
- "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
244
- "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
245
- "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
246
- "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
247
- "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
248
- "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
249
- "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
250
- "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
251
- "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
252
- "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
253
- "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
254
- "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
255
- "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
256
- "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
257
- "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
258
- "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
259
- "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
260
- "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
261
- "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
262
- "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
263
- "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
264
- "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
265
- "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
266
- "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
267
- "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
268
- "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
269
- "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
270
- "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
271
- "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
272
- "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
273
- "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
274
- "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
275
- "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
276
- "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
277
- "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
278
- "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
279
- "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
280
- "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
281
- "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
282
- "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
283
- "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
284
- "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
285
- "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
286
- "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
287
- "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
288
- "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
289
- "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
290
- "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
291
- "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
292
- "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
293
- "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
294
- "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
295
- "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
296
- "model.norm.weight": "model-00004-of-00004.safetensors"
297
  }
298
  }
 
1
  {
2
  "metadata": {
3
+ "total_size": 14483464192
4
  },
5
  "weight_map": {
6
+ "lm_head.weight": "model-00003-of-00003.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
296
+ "model.norm.weight": "model-00003-of-00003.safetensors"
297
  }
298
  }
special_tokens_map.json CHANGED
@@ -1,17 +1,35 @@
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
  }
 
1
  {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>"
6
+ ],
7
  "bos_token": {
8
+ "content": "<s>",
9
  "lstrip": false,
10
  "normalized": false,
11
  "rstrip": false,
12
  "single_word": false
13
  },
14
  "eos_token": {
15
+ "content": "</s>",
16
  "lstrip": false,
17
  "normalized": false,
18
  "rstrip": false,
19
  "single_word": false
20
  },
21
+ "pad_token": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "unk_token": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,2047 +1,23 @@
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": "<|reserved_special_token_2|>",
37
- "lstrip": false,
38
- "normalized": false,
39
- "rstrip": false,
40
- "single_word": false,
41
- "special": true
42
- },
43
- "128005": {
44
- "content": "<|reserved_special_token_3|>",
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": "<|reserved_special_token_4|>",
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": "<|reserved_special_token_5|>",
85
- "lstrip": false,
86
- "normalized": false,
87
- "rstrip": false,
88
- "single_word": false,
89
- "special": true
90
- },
91
- "128011": {
92
- "content": "<|reserved_special_token_6|>",
93
- "lstrip": false,
94
- "normalized": false,
95
- "rstrip": false,
96
- "single_word": false,
97
- "special": true
98
- },
99
- "128012": {
100
- "content": "<|reserved_special_token_7|>",
101
- "lstrip": false,
102
- "normalized": false,
103
- "rstrip": false,
104
- "single_word": false,
105
- "special": true
106
- },
107
- "128013": {
108
- "content": "<|reserved_special_token_8|>",
109
- "lstrip": false,
110
- "normalized": false,
111
- "rstrip": false,
112
- "single_word": false,
113
- "special": true
114
- },
115
- "128014": {
116
- "content": "<|reserved_special_token_9|>",
117
- "lstrip": false,
118
- "normalized": false,
119
- "rstrip": false,
120
- "single_word": false,
121
- "special": true
122
- },
123
- "128015": {
124
- "content": "<|reserved_special_token_10|>",
125
- "lstrip": false,
126
- "normalized": false,
127
- "rstrip": false,
128
- "single_word": false,
129
- "special": true
130
- },
131
- "128016": {
132
- "content": "<|reserved_special_token_11|>",
133
- "lstrip": false,
134
- "normalized": false,
135
- "rstrip": false,
136
- "single_word": false,
137
- "special": true
138
- },
139
- "128017": {
140
- "content": "<|reserved_special_token_12|>",
141
- "lstrip": false,
142
- "normalized": false,
143
- "rstrip": false,
144
- "single_word": false,
145
- "special": true
146
- },
147
- "128018": {
148
- "content": "<|reserved_special_token_13|>",
149
- "lstrip": false,
150
- "normalized": false,
151
- "rstrip": false,
152
- "single_word": false,
153
- "special": true
154
- },
155
- "128019": {
156
- "content": "<|reserved_special_token_14|>",
157
- "lstrip": false,
158
- "normalized": false,
159
- "rstrip": false,
160
- "single_word": false,
161
- "special": true
162
- },
163
- "128020": {
164
- "content": "<|reserved_special_token_15|>",
165
- "lstrip": false,
166
- "normalized": false,
167
- "rstrip": false,
168
- "single_word": false,
169
- "special": true
170
- },
171
- "128021": {
172
- "content": "<|reserved_special_token_16|>",
173
- "lstrip": false,
174
- "normalized": false,
175
- "rstrip": false,
176
- "single_word": false,
177
- "special": true
178
- },
179
- "128022": {
180
- "content": "<|reserved_special_token_17|>",
181
- "lstrip": false,
182
- "normalized": false,
183
- "rstrip": false,
184
- "single_word": false,
185
- "special": true
186
- },
187
- "128023": {
188
- "content": "<|reserved_special_token_18|>",
189
- "lstrip": false,
190
- "normalized": false,
191
- "rstrip": false,
192
- "single_word": false,
193
- "special": true
194
- },
195
- "128024": {
196
- "content": "<|reserved_special_token_19|>",
197
- "lstrip": false,
198
- "normalized": false,
199
- "rstrip": false,
200
- "single_word": false,
201
- "special": true
202
- },
203
- "128025": {
204
- "content": "<|reserved_special_token_20|>",
205
- "lstrip": false,
206
- "normalized": false,
207
- "rstrip": false,
208
- "single_word": false,
209
- "special": true
210
- },
211
- "128026": {
212
- "content": "<|reserved_special_token_21|>",
213
- "lstrip": false,
214
- "normalized": false,
215
- "rstrip": false,
216
- "single_word": false,
217
- "special": true
218
- },
219
- "128027": {
220
- "content": "<|reserved_special_token_22|>",
221
- "lstrip": false,
222
- "normalized": false,
223
- "rstrip": false,
224
- "single_word": false,
225
- "special": true
226
- },
227
- "128028": {
228
- "content": "<|reserved_special_token_23|>",
229
- "lstrip": false,
230
- "normalized": false,
231
- "rstrip": false,
232
- "single_word": false,
233
- "special": true
234
- },
235
- "128029": {
236
- "content": "<|reserved_special_token_24|>",
237
- "lstrip": false,
238
- "normalized": false,
239
- "rstrip": false,
240
- "single_word": false,
241
- "special": true
242
- },
243
- "128030": {
244
- "content": "<|reserved_special_token_25|>",
245
- "lstrip": false,
246
- "normalized": false,
247
- "rstrip": false,
248
- "single_word": false,
249
- "special": true
250
- },
251
- "128031": {
252
- "content": "<|reserved_special_token_26|>",
253
- "lstrip": false,
254
- "normalized": false,
255
- "rstrip": false,
256
- "single_word": false,
257
- "special": true
258
- },
259
- "128032": {
260
- "content": "<|reserved_special_token_27|>",
261
- "lstrip": false,
262
- "normalized": false,
263
- "rstrip": false,
264
- "single_word": false,
265
- "special": true
266
- },
267
- "128033": {
268
- "content": "<|reserved_special_token_28|>",
269
- "lstrip": false,
270
- "normalized": false,
271
- "rstrip": false,
272
- "single_word": false,
273
- "special": true
274
- },
275
- "128034": {
276
- "content": "<|reserved_special_token_29|>",
277
- "lstrip": false,
278
- "normalized": false,
279
- "rstrip": false,
280
- "single_word": false,
281
- "special": true
282
- },
283
- "128035": {
284
- "content": "<|reserved_special_token_30|>",
285
- "lstrip": false,
286
- "normalized": false,
287
- "rstrip": false,
288
- "single_word": false,
289
- "special": true
290
- },
291
- "128036": {
292
- "content": "<|reserved_special_token_31|>",
293
- "lstrip": false,
294
- "normalized": false,
295
- "rstrip": false,
296
- "single_word": false,
297
- "special": true
298
- },
299
- "128037": {
300
- "content": "<|reserved_special_token_32|>",
301
- "lstrip": false,
302
- "normalized": false,
303
- "rstrip": false,
304
- "single_word": false,
305
- "special": true
306
- },
307
- "128038": {
308
- "content": "<|reserved_special_token_33|>",
309
- "lstrip": false,
310
- "normalized": false,
311
- "rstrip": false,
312
- "single_word": false,
313
- "special": true
314
- },
315
- "128039": {
316
- "content": "<|reserved_special_token_34|>",
317
- "lstrip": false,
318
- "normalized": false,
319
- "rstrip": false,
320
- "single_word": false,
321
- "special": true
322
- },
323
- "128040": {
324
- "content": "<|reserved_special_token_35|>",
325
- "lstrip": false,
326
- "normalized": false,
327
- "rstrip": false,
328
- "single_word": false,
329
- "special": true
330
- },
331
- "128041": {
332
- "content": "<|reserved_special_token_36|>",
333
- "lstrip": false,
334
- "normalized": false,
335
- "rstrip": false,
336
- "single_word": false,
337
- "special": true
338
- },
339
- "128042": {
340
- "content": "<|reserved_special_token_37|>",
341
- "lstrip": false,
342
- "normalized": false,
343
- "rstrip": false,
344
- "single_word": false,
345
- "special": true
346
- },
347
- "128043": {
348
- "content": "<|reserved_special_token_38|>",
349
- "lstrip": false,
350
- "normalized": false,
351
- "rstrip": false,
352
- "single_word": false,
353
- "special": true
354
- },
355
- "128044": {
356
- "content": "<|reserved_special_token_39|>",
357
- "lstrip": false,
358
- "normalized": false,
359
- "rstrip": false,
360
- "single_word": false,
361
- "special": true
362
- },
363
- "128045": {
364
- "content": "<|reserved_special_token_40|>",
365
- "lstrip": false,
366
- "normalized": false,
367
- "rstrip": false,
368
- "single_word": false,
369
- "special": true
370
- },
371
- "128046": {
372
- "content": "<|reserved_special_token_41|>",
373
- "lstrip": false,
374
- "normalized": false,
375
- "rstrip": false,
376
- "single_word": false,
377
- "special": true
378
- },
379
- "128047": {
380
- "content": "<|reserved_special_token_42|>",
381
- "lstrip": false,
382
- "normalized": false,
383
- "rstrip": false,
384
- "single_word": false,
385
- "special": true
386
- },
387
- "128048": {
388
- "content": "<|reserved_special_token_43|>",
389
- "lstrip": false,
390
- "normalized": false,
391
- "rstrip": false,
392
- "single_word": false,
393
- "special": true
394
- },
395
- "128049": {
396
- "content": "<|reserved_special_token_44|>",
397
- "lstrip": false,
398
- "normalized": false,
399
- "rstrip": false,
400
- "single_word": false,
401
- "special": true
402
- },
403
- "128050": {
404
- "content": "<|reserved_special_token_45|>",
405
- "lstrip": false,
406
- "normalized": false,
407
- "rstrip": false,
408
- "single_word": false,
409
- "special": true
410
- },
411
- "128051": {
412
- "content": "<|reserved_special_token_46|>",
413
- "lstrip": false,
414
- "normalized": false,
415
- "rstrip": false,
416
- "single_word": false,
417
- "special": true
418
- },
419
- "128052": {
420
- "content": "<|reserved_special_token_47|>",
421
- "lstrip": false,
422
- "normalized": false,
423
- "rstrip": false,
424
- "single_word": false,
425
- "special": true
426
- },
427
- "128053": {
428
- "content": "<|reserved_special_token_48|>",
429
- "lstrip": false,
430
- "normalized": false,
431
- "rstrip": false,
432
- "single_word": false,
433
- "special": true
434
- },
435
- "128054": {
436
- "content": "<|reserved_special_token_49|>",
437
- "lstrip": false,
438
- "normalized": false,
439
- "rstrip": false,
440
- "single_word": false,
441
- "special": true
442
- },
443
- "128055": {
444
- "content": "<|reserved_special_token_50|>",
445
- "lstrip": false,
446
- "normalized": false,
447
- "rstrip": false,
448
- "single_word": false,
449
- "special": true
450
- },
451
- "128056": {
452
- "content": "<|reserved_special_token_51|>",
453
- "lstrip": false,
454
- "normalized": false,
455
- "rstrip": false,
456
- "single_word": false,
457
- "special": true
458
- },
459
- "128057": {
460
- "content": "<|reserved_special_token_52|>",
461
- "lstrip": false,
462
- "normalized": false,
463
- "rstrip": false,
464
- "single_word": false,
465
- "special": true
466
- },
467
- "128058": {
468
- "content": "<|reserved_special_token_53|>",
469
- "lstrip": false,
470
- "normalized": false,
471
- "rstrip": false,
472
- "single_word": false,
473
- "special": true
474
- },
475
- "128059": {
476
- "content": "<|reserved_special_token_54|>",
477
- "lstrip": false,
478
- "normalized": false,
479
- "rstrip": false,
480
- "single_word": false,
481
- "special": true
482
- },
483
- "128060": {
484
- "content": "<|reserved_special_token_55|>",
485
- "lstrip": false,
486
- "normalized": false,
487
- "rstrip": false,
488
- "single_word": false,
489
- "special": true
490
- },
491
- "128061": {
492
- "content": "<|reserved_special_token_56|>",
493
- "lstrip": false,
494
- "normalized": false,
495
- "rstrip": false,
496
- "single_word": false,
497
- "special": true
498
- },
499
- "128062": {
500
- "content": "<|reserved_special_token_57|>",
501
- "lstrip": false,
502
- "normalized": false,
503
- "rstrip": false,
504
- "single_word": false,
505
- "special": true
506
- },
507
- "128063": {
508
- "content": "<|reserved_special_token_58|>",
509
- "lstrip": false,
510
- "normalized": false,
511
- "rstrip": false,
512
- "single_word": false,
513
- "special": true
514
- },
515
- "128064": {
516
- "content": "<|reserved_special_token_59|>",
517
- "lstrip": false,
518
- "normalized": false,
519
- "rstrip": false,
520
- "single_word": false,
521
- "special": true
522
- },
523
- "128065": {
524
- "content": "<|reserved_special_token_60|>",
525
- "lstrip": false,
526
- "normalized": false,
527
- "rstrip": false,
528
- "single_word": false,
529
- "special": true
530
- },
531
- "128066": {
532
- "content": "<|reserved_special_token_61|>",
533
- "lstrip": false,
534
- "normalized": false,
535
- "rstrip": false,
536
- "single_word": false,
537
- "special": true
538
- },
539
- "128067": {
540
- "content": "<|reserved_special_token_62|>",
541
- "lstrip": false,
542
- "normalized": false,
543
- "rstrip": false,
544
- "single_word": false,
545
- "special": true
546
- },
547
- "128068": {
548
- "content": "<|reserved_special_token_63|>",
549
- "lstrip": false,
550
- "normalized": false,
551
- "rstrip": false,
552
- "single_word": false,
553
- "special": true
554
- },
555
- "128069": {
556
- "content": "<|reserved_special_token_64|>",
557
- "lstrip": false,
558
- "normalized": false,
559
- "rstrip": false,
560
- "single_word": false,
561
- "special": true
562
- },
563
- "128070": {
564
- "content": "<|reserved_special_token_65|>",
565
- "lstrip": false,
566
- "normalized": false,
567
- "rstrip": false,
568
- "single_word": false,
569
- "special": true
570
- },
571
- "128071": {
572
- "content": "<|reserved_special_token_66|>",
573
- "lstrip": false,
574
- "normalized": false,
575
- "rstrip": false,
576
- "single_word": false,
577
- "special": true
578
- },
579
- "128072": {
580
- "content": "<|reserved_special_token_67|>",
581
- "lstrip": false,
582
- "normalized": false,
583
- "rstrip": false,
584
- "single_word": false,
585
- "special": true
586
- },
587
- "128073": {
588
- "content": "<|reserved_special_token_68|>",
589
- "lstrip": false,
590
- "normalized": false,
591
- "rstrip": false,
592
- "single_word": false,
593
- "special": true
594
- },
595
- "128074": {
596
- "content": "<|reserved_special_token_69|>",
597
- "lstrip": false,
598
- "normalized": false,
599
- "rstrip": false,
600
- "single_word": false,
601
- "special": true
602
- },
603
- "128075": {
604
- "content": "<|reserved_special_token_70|>",
605
- "lstrip": false,
606
- "normalized": false,
607
- "rstrip": false,
608
- "single_word": false,
609
- "special": true
610
- },
611
- "128076": {
612
- "content": "<|reserved_special_token_71|>",
613
- "lstrip": false,
614
- "normalized": false,
615
- "rstrip": false,
616
- "single_word": false,
617
- "special": true
618
- },
619
- "128077": {
620
- "content": "<|reserved_special_token_72|>",
621
- "lstrip": false,
622
- "normalized": false,
623
- "rstrip": false,
624
- "single_word": false,
625
- "special": true
626
- },
627
- "128078": {
628
- "content": "<|reserved_special_token_73|>",
629
- "lstrip": false,
630
- "normalized": false,
631
- "rstrip": false,
632
- "single_word": false,
633
- "special": true
634
- },
635
- "128079": {
636
- "content": "<|reserved_special_token_74|>",
637
- "lstrip": false,
638
- "normalized": false,
639
- "rstrip": false,
640
- "single_word": false,
641
- "special": true
642
- },
643
- "128080": {
644
- "content": "<|reserved_special_token_75|>",
645
- "lstrip": false,
646
- "normalized": false,
647
- "rstrip": false,
648
- "single_word": false,
649
- "special": true
650
- },
651
- "128081": {
652
- "content": "<|reserved_special_token_76|>",
653
- "lstrip": false,
654
- "normalized": false,
655
- "rstrip": false,
656
- "single_word": false,
657
- "special": true
658
- },
659
- "128082": {
660
- "content": "<|reserved_special_token_77|>",
661
- "lstrip": false,
662
- "normalized": false,
663
- "rstrip": false,
664
- "single_word": false,
665
- "special": true
666
- },
667
- "128083": {
668
- "content": "<|reserved_special_token_78|>",
669
- "lstrip": false,
670
- "normalized": false,
671
- "rstrip": false,
672
- "single_word": false,
673
- "special": true
674
- },
675
- "128084": {
676
- "content": "<|reserved_special_token_79|>",
677
- "lstrip": false,
678
- "normalized": false,
679
- "rstrip": false,
680
- "single_word": false,
681
- "special": true
682
- },
683
- "128085": {
684
- "content": "<|reserved_special_token_80|>",
685
- "lstrip": false,
686
- "normalized": false,
687
- "rstrip": false,
688
- "single_word": false,
689
- "special": true
690
- },
691
- "128086": {
692
- "content": "<|reserved_special_token_81|>",
693
- "lstrip": false,
694
- "normalized": false,
695
- "rstrip": false,
696
- "single_word": false,
697
- "special": true
698
- },
699
- "128087": {
700
- "content": "<|reserved_special_token_82|>",
701
- "lstrip": false,
702
- "normalized": false,
703
- "rstrip": false,
704
- "single_word": false,
705
- "special": true
706
- },
707
- "128088": {
708
- "content": "<|reserved_special_token_83|>",
709
- "lstrip": false,
710
- "normalized": false,
711
- "rstrip": false,
712
- "single_word": false,
713
- "special": true
714
- },
715
- "128089": {
716
- "content": "<|reserved_special_token_84|>",
717
- "lstrip": false,
718
- "normalized": false,
719
- "rstrip": false,
720
- "single_word": false,
721
- "special": true
722
- },
723
- "128090": {
724
- "content": "<|reserved_special_token_85|>",
725
- "lstrip": false,
726
- "normalized": false,
727
- "rstrip": false,
728
- "single_word": false,
729
- "special": true
730
- },
731
- "128091": {
732
- "content": "<|reserved_special_token_86|>",
733
- "lstrip": false,
734
- "normalized": false,
735
- "rstrip": false,
736
- "single_word": false,
737
- "special": true
738
- },
739
- "128092": {
740
- "content": "<|reserved_special_token_87|>",
741
- "lstrip": false,
742
- "normalized": false,
743
- "rstrip": false,
744
- "single_word": false,
745
- "special": true
746
- },
747
- "128093": {
748
- "content": "<|reserved_special_token_88|>",
749
- "lstrip": false,
750
- "normalized": false,
751
- "rstrip": false,
752
- "single_word": false,
753
- "special": true
754
- },
755
- "128094": {
756
- "content": "<|reserved_special_token_89|>",
757
- "lstrip": false,
758
- "normalized": false,
759
- "rstrip": false,
760
- "single_word": false,
761
- "special": true
762
- },
763
- "128095": {
764
- "content": "<|reserved_special_token_90|>",
765
- "lstrip": false,
766
- "normalized": false,
767
- "rstrip": false,
768
- "single_word": false,
769
- "special": true
770
- },
771
- "128096": {
772
- "content": "<|reserved_special_token_91|>",
773
- "lstrip": false,
774
- "normalized": false,
775
- "rstrip": false,
776
- "single_word": false,
777
- "special": true
778
- },
779
- "128097": {
780
- "content": "<|reserved_special_token_92|>",
781
- "lstrip": false,
782
- "normalized": false,
783
- "rstrip": false,
784
- "single_word": false,
785
- "special": true
786
- },
787
- "128098": {
788
- "content": "<|reserved_special_token_93|>",
789
- "lstrip": false,
790
- "normalized": false,
791
- "rstrip": false,
792
- "single_word": false,
793
- "special": true
794
- },
795
- "128099": {
796
- "content": "<|reserved_special_token_94|>",
797
- "lstrip": false,
798
- "normalized": false,
799
- "rstrip": false,
800
- "single_word": false,
801
- "special": true
802
- },
803
- "128100": {
804
- "content": "<|reserved_special_token_95|>",
805
- "lstrip": false,
806
- "normalized": false,
807
- "rstrip": false,
808
- "single_word": false,
809
- "special": true
810
- },
811
- "128101": {
812
- "content": "<|reserved_special_token_96|>",
813
- "lstrip": false,
814
- "normalized": false,
815
- "rstrip": false,
816
- "single_word": false,
817
- "special": true
818
- },
819
- "128102": {
820
- "content": "<|reserved_special_token_97|>",
821
- "lstrip": false,
822
- "normalized": false,
823
- "rstrip": false,
824
- "single_word": false,
825
- "special": true
826
- },
827
- "128103": {
828
- "content": "<|reserved_special_token_98|>",
829
- "lstrip": false,
830
- "normalized": false,
831
- "rstrip": false,
832
- "single_word": false,
833
- "special": true
834
- },
835
- "128104": {
836
- "content": "<|reserved_special_token_99|>",
837
- "lstrip": false,
838
- "normalized": false,
839
- "rstrip": false,
840
- "single_word": false,
841
- "special": true
842
- },
843
- "128105": {
844
- "content": "<|reserved_special_token_100|>",
845
- "lstrip": false,
846
- "normalized": false,
847
- "rstrip": false,
848
- "single_word": false,
849
- "special": true
850
- },
851
- "128106": {
852
- "content": "<|reserved_special_token_101|>",
853
- "lstrip": false,
854
- "normalized": false,
855
- "rstrip": false,
856
- "single_word": false,
857
- "special": true
858
- },
859
- "128107": {
860
- "content": "<|reserved_special_token_102|>",
861
- "lstrip": false,
862
- "normalized": false,
863
- "rstrip": false,
864
- "single_word": false,
865
- "special": true
866
- },
867
- "128108": {
868
- "content": "<|reserved_special_token_103|>",
869
- "lstrip": false,
870
- "normalized": false,
871
- "rstrip": false,
872
- "single_word": false,
873
- "special": true
874
- },
875
- "128109": {
876
- "content": "<|reserved_special_token_104|>",
877
- "lstrip": false,
878
- "normalized": false,
879
- "rstrip": false,
880
- "single_word": false,
881
- "special": true
882
- },
883
- "128110": {
884
- "content": "<|reserved_special_token_105|>",
885
- "lstrip": false,
886
- "normalized": false,
887
- "rstrip": false,
888
- "single_word": false,
889
- "special": true
890
- },
891
- "128111": {
892
- "content": "<|reserved_special_token_106|>",
893
- "lstrip": false,
894
- "normalized": false,
895
- "rstrip": false,
896
- "single_word": false,
897
- "special": true
898
- },
899
- "128112": {
900
- "content": "<|reserved_special_token_107|>",
901
- "lstrip": false,
902
- "normalized": false,
903
- "rstrip": false,
904
- "single_word": false,
905
- "special": true
906
- },
907
- "128113": {
908
- "content": "<|reserved_special_token_108|>",
909
- "lstrip": false,
910
- "normalized": false,
911
- "rstrip": false,
912
- "single_word": false,
913
- "special": true
914
- },
915
- "128114": {
916
- "content": "<|reserved_special_token_109|>",
917
- "lstrip": false,
918
- "normalized": false,
919
- "rstrip": false,
920
- "single_word": false,
921
- "special": true
922
- },
923
- "128115": {
924
- "content": "<|reserved_special_token_110|>",
925
- "lstrip": false,
926
- "normalized": false,
927
- "rstrip": false,
928
- "single_word": false,
929
- "special": true
930
- },
931
- "128116": {
932
- "content": "<|reserved_special_token_111|>",
933
- "lstrip": false,
934
- "normalized": false,
935
- "rstrip": false,
936
- "single_word": false,
937
- "special": true
938
- },
939
- "128117": {
940
- "content": "<|reserved_special_token_112|>",
941
- "lstrip": false,
942
- "normalized": false,
943
- "rstrip": false,
944
- "single_word": false,
945
- "special": true
946
- },
947
- "128118": {
948
- "content": "<|reserved_special_token_113|>",
949
- "lstrip": false,
950
- "normalized": false,
951
- "rstrip": false,
952
- "single_word": false,
953
- "special": true
954
- },
955
- "128119": {
956
- "content": "<|reserved_special_token_114|>",
957
- "lstrip": false,
958
- "normalized": false,
959
- "rstrip": false,
960
- "single_word": false,
961
- "special": true
962
- },
963
- "128120": {
964
- "content": "<|reserved_special_token_115|>",
965
- "lstrip": false,
966
- "normalized": false,
967
- "rstrip": false,
968
- "single_word": false,
969
- "special": true
970
- },
971
- "128121": {
972
- "content": "<|reserved_special_token_116|>",
973
- "lstrip": false,
974
- "normalized": false,
975
- "rstrip": false,
976
- "single_word": false,
977
- "special": true
978
- },
979
- "128122": {
980
- "content": "<|reserved_special_token_117|>",
981
- "lstrip": false,
982
- "normalized": false,
983
- "rstrip": false,
984
- "single_word": false,
985
- "special": true
986
- },
987
- "128123": {
988
- "content": "<|reserved_special_token_118|>",
989
- "lstrip": false,
990
- "normalized": false,
991
- "rstrip": false,
992
- "single_word": false,
993
- "special": true
994
- },
995
- "128124": {
996
- "content": "<|reserved_special_token_119|>",
997
- "lstrip": false,
998
- "normalized": false,
999
- "rstrip": false,
1000
- "single_word": false,
1001
- "special": true
1002
- },
1003
- "128125": {
1004
- "content": "<|reserved_special_token_120|>",
1005
- "lstrip": false,
1006
- "normalized": false,
1007
- "rstrip": false,
1008
- "single_word": false,
1009
- "special": true
1010
- },
1011
- "128126": {
1012
- "content": "<|reserved_special_token_121|>",
1013
- "lstrip": false,
1014
- "normalized": false,
1015
- "rstrip": false,
1016
- "single_word": false,
1017
- "special": true
1018
- },
1019
- "128127": {
1020
- "content": "<|reserved_special_token_122|>",
1021
- "lstrip": false,
1022
- "normalized": false,
1023
- "rstrip": false,
1024
- "single_word": false,
1025
- "special": true
1026
- },
1027
- "128128": {
1028
- "content": "<|reserved_special_token_123|>",
1029
- "lstrip": false,
1030
- "normalized": false,
1031
- "rstrip": false,
1032
- "single_word": false,
1033
- "special": true
1034
- },
1035
- "128129": {
1036
- "content": "<|reserved_special_token_124|>",
1037
- "lstrip": false,
1038
- "normalized": false,
1039
- "rstrip": false,
1040
- "single_word": false,
1041
- "special": true
1042
- },
1043
- "128130": {
1044
- "content": "<|reserved_special_token_125|>",
1045
- "lstrip": false,
1046
- "normalized": false,
1047
- "rstrip": false,
1048
- "single_word": false,
1049
- "special": true
1050
- },
1051
- "128131": {
1052
- "content": "<|reserved_special_token_126|>",
1053
- "lstrip": false,
1054
- "normalized": false,
1055
- "rstrip": false,
1056
- "single_word": false,
1057
- "special": true
1058
- },
1059
- "128132": {
1060
- "content": "<|reserved_special_token_127|>",
1061
- "lstrip": false,
1062
- "normalized": false,
1063
- "rstrip": false,
1064
- "single_word": false,
1065
- "special": true
1066
- },
1067
- "128133": {
1068
- "content": "<|reserved_special_token_128|>",
1069
- "lstrip": false,
1070
- "normalized": false,
1071
- "rstrip": false,
1072
- "single_word": false,
1073
- "special": true
1074
- },
1075
- "128134": {
1076
- "content": "<|reserved_special_token_129|>",
1077
- "lstrip": false,
1078
- "normalized": false,
1079
- "rstrip": false,
1080
- "single_word": false,
1081
- "special": true
1082
- },
1083
- "128135": {
1084
- "content": "<|reserved_special_token_130|>",
1085
- "lstrip": false,
1086
- "normalized": false,
1087
- "rstrip": false,
1088
- "single_word": false,
1089
- "special": true
1090
- },
1091
- "128136": {
1092
- "content": "<|reserved_special_token_131|>",
1093
- "lstrip": false,
1094
- "normalized": false,
1095
- "rstrip": false,
1096
- "single_word": false,
1097
- "special": true
1098
- },
1099
- "128137": {
1100
- "content": "<|reserved_special_token_132|>",
1101
- "lstrip": false,
1102
- "normalized": false,
1103
- "rstrip": false,
1104
- "single_word": false,
1105
- "special": true
1106
- },
1107
- "128138": {
1108
- "content": "<|reserved_special_token_133|>",
1109
- "lstrip": false,
1110
- "normalized": false,
1111
- "rstrip": false,
1112
- "single_word": false,
1113
- "special": true
1114
- },
1115
- "128139": {
1116
- "content": "<|reserved_special_token_134|>",
1117
- "lstrip": false,
1118
- "normalized": false,
1119
- "rstrip": false,
1120
- "single_word": false,
1121
- "special": true
1122
- },
1123
- "128140": {
1124
- "content": "<|reserved_special_token_135|>",
1125
- "lstrip": false,
1126
- "normalized": false,
1127
- "rstrip": false,
1128
- "single_word": false,
1129
- "special": true
1130
- },
1131
- "128141": {
1132
- "content": "<|reserved_special_token_136|>",
1133
- "lstrip": false,
1134
- "normalized": false,
1135
- "rstrip": false,
1136
- "single_word": false,
1137
- "special": true
1138
- },
1139
- "128142": {
1140
- "content": "<|reserved_special_token_137|>",
1141
- "lstrip": false,
1142
- "normalized": false,
1143
- "rstrip": false,
1144
- "single_word": false,
1145
- "special": true
1146
- },
1147
- "128143": {
1148
- "content": "<|reserved_special_token_138|>",
1149
- "lstrip": false,
1150
- "normalized": false,
1151
- "rstrip": false,
1152
- "single_word": false,
1153
- "special": true
1154
- },
1155
- "128144": {
1156
- "content": "<|reserved_special_token_139|>",
1157
- "lstrip": false,
1158
- "normalized": false,
1159
- "rstrip": false,
1160
- "single_word": false,
1161
- "special": true
1162
- },
1163
- "128145": {
1164
- "content": "<|reserved_special_token_140|>",
1165
- "lstrip": false,
1166
- "normalized": false,
1167
- "rstrip": false,
1168
- "single_word": false,
1169
- "special": true
1170
- },
1171
- "128146": {
1172
- "content": "<|reserved_special_token_141|>",
1173
- "lstrip": false,
1174
- "normalized": false,
1175
- "rstrip": false,
1176
- "single_word": false,
1177
- "special": true
1178
- },
1179
- "128147": {
1180
- "content": "<|reserved_special_token_142|>",
1181
- "lstrip": false,
1182
- "normalized": false,
1183
- "rstrip": false,
1184
- "single_word": false,
1185
- "special": true
1186
- },
1187
- "128148": {
1188
- "content": "<|reserved_special_token_143|>",
1189
- "lstrip": false,
1190
- "normalized": false,
1191
- "rstrip": false,
1192
- "single_word": false,
1193
- "special": true
1194
- },
1195
- "128149": {
1196
- "content": "<|reserved_special_token_144|>",
1197
- "lstrip": false,
1198
- "normalized": false,
1199
- "rstrip": false,
1200
- "single_word": false,
1201
- "special": true
1202
- },
1203
- "128150": {
1204
- "content": "<|reserved_special_token_145|>",
1205
- "lstrip": false,
1206
- "normalized": false,
1207
- "rstrip": false,
1208
- "single_word": false,
1209
- "special": true
1210
- },
1211
- "128151": {
1212
- "content": "<|reserved_special_token_146|>",
1213
- "lstrip": false,
1214
- "normalized": false,
1215
- "rstrip": false,
1216
- "single_word": false,
1217
- "special": true
1218
- },
1219
- "128152": {
1220
- "content": "<|reserved_special_token_147|>",
1221
- "lstrip": false,
1222
- "normalized": false,
1223
- "rstrip": false,
1224
- "single_word": false,
1225
- "special": true
1226
- },
1227
- "128153": {
1228
- "content": "<|reserved_special_token_148|>",
1229
- "lstrip": false,
1230
- "normalized": false,
1231
- "rstrip": false,
1232
- "single_word": false,
1233
- "special": true
1234
- },
1235
- "128154": {
1236
- "content": "<|reserved_special_token_149|>",
1237
- "lstrip": false,
1238
- "normalized": false,
1239
- "rstrip": false,
1240
- "single_word": false,
1241
- "special": true
1242
- },
1243
- "128155": {
1244
- "content": "<|reserved_special_token_150|>",
1245
- "lstrip": false,
1246
- "normalized": false,
1247
- "rstrip": false,
1248
- "single_word": false,
1249
- "special": true
1250
- },
1251
- "128156": {
1252
- "content": "<|reserved_special_token_151|>",
1253
- "lstrip": false,
1254
- "normalized": false,
1255
- "rstrip": false,
1256
- "single_word": false,
1257
- "special": true
1258
- },
1259
- "128157": {
1260
- "content": "<|reserved_special_token_152|>",
1261
- "lstrip": false,
1262
- "normalized": false,
1263
- "rstrip": false,
1264
- "single_word": false,
1265
- "special": true
1266
- },
1267
- "128158": {
1268
- "content": "<|reserved_special_token_153|>",
1269
- "lstrip": false,
1270
- "normalized": false,
1271
- "rstrip": false,
1272
- "single_word": false,
1273
- "special": true
1274
- },
1275
- "128159": {
1276
- "content": "<|reserved_special_token_154|>",
1277
- "lstrip": false,
1278
- "normalized": false,
1279
- "rstrip": false,
1280
- "single_word": false,
1281
- "special": true
1282
- },
1283
- "128160": {
1284
- "content": "<|reserved_special_token_155|>",
1285
- "lstrip": false,
1286
- "normalized": false,
1287
- "rstrip": false,
1288
- "single_word": false,
1289
- "special": true
1290
- },
1291
- "128161": {
1292
- "content": "<|reserved_special_token_156|>",
1293
- "lstrip": false,
1294
- "normalized": false,
1295
- "rstrip": false,
1296
- "single_word": false,
1297
- "special": true
1298
- },
1299
- "128162": {
1300
- "content": "<|reserved_special_token_157|>",
1301
- "lstrip": false,
1302
- "normalized": false,
1303
- "rstrip": false,
1304
- "single_word": false,
1305
- "special": true
1306
- },
1307
- "128163": {
1308
- "content": "<|reserved_special_token_158|>",
1309
- "lstrip": false,
1310
- "normalized": false,
1311
- "rstrip": false,
1312
- "single_word": false,
1313
- "special": true
1314
- },
1315
- "128164": {
1316
- "content": "<|reserved_special_token_159|>",
1317
- "lstrip": false,
1318
- "normalized": false,
1319
- "rstrip": false,
1320
- "single_word": false,
1321
- "special": true
1322
- },
1323
- "128165": {
1324
- "content": "<|reserved_special_token_160|>",
1325
- "lstrip": false,
1326
- "normalized": false,
1327
- "rstrip": false,
1328
- "single_word": false,
1329
- "special": true
1330
- },
1331
- "128166": {
1332
- "content": "<|reserved_special_token_161|>",
1333
- "lstrip": false,
1334
- "normalized": false,
1335
- "rstrip": false,
1336
- "single_word": false,
1337
- "special": true
1338
- },
1339
- "128167": {
1340
- "content": "<|reserved_special_token_162|>",
1341
- "lstrip": false,
1342
- "normalized": false,
1343
- "rstrip": false,
1344
- "single_word": false,
1345
- "special": true
1346
- },
1347
- "128168": {
1348
- "content": "<|reserved_special_token_163|>",
1349
- "lstrip": false,
1350
- "normalized": false,
1351
- "rstrip": false,
1352
- "single_word": false,
1353
- "special": true
1354
- },
1355
- "128169": {
1356
- "content": "<|reserved_special_token_164|>",
1357
- "lstrip": false,
1358
- "normalized": false,
1359
- "rstrip": false,
1360
- "single_word": false,
1361
- "special": true
1362
- },
1363
- "128170": {
1364
- "content": "<|reserved_special_token_165|>",
1365
- "lstrip": false,
1366
- "normalized": false,
1367
- "rstrip": false,
1368
- "single_word": false,
1369
- "special": true
1370
- },
1371
- "128171": {
1372
- "content": "<|reserved_special_token_166|>",
1373
- "lstrip": false,
1374
- "normalized": false,
1375
- "rstrip": false,
1376
- "single_word": false,
1377
- "special": true
1378
- },
1379
- "128172": {
1380
- "content": "<|reserved_special_token_167|>",
1381
- "lstrip": false,
1382
- "normalized": false,
1383
- "rstrip": false,
1384
- "single_word": false,
1385
- "special": true
1386
- },
1387
- "128173": {
1388
- "content": "<|reserved_special_token_168|>",
1389
- "lstrip": false,
1390
- "normalized": false,
1391
- "rstrip": false,
1392
- "single_word": false,
1393
- "special": true
1394
- },
1395
- "128174": {
1396
- "content": "<|reserved_special_token_169|>",
1397
- "lstrip": false,
1398
- "normalized": false,
1399
- "rstrip": false,
1400
- "single_word": false,
1401
- "special": true
1402
- },
1403
- "128175": {
1404
- "content": "<|reserved_special_token_170|>",
1405
- "lstrip": false,
1406
- "normalized": false,
1407
- "rstrip": false,
1408
- "single_word": false,
1409
- "special": true
1410
- },
1411
- "128176": {
1412
- "content": "<|reserved_special_token_171|>",
1413
- "lstrip": false,
1414
- "normalized": false,
1415
- "rstrip": false,
1416
- "single_word": false,
1417
- "special": true
1418
- },
1419
- "128177": {
1420
- "content": "<|reserved_special_token_172|>",
1421
- "lstrip": false,
1422
- "normalized": false,
1423
- "rstrip": false,
1424
- "single_word": false,
1425
- "special": true
1426
- },
1427
- "128178": {
1428
- "content": "<|reserved_special_token_173|>",
1429
- "lstrip": false,
1430
- "normalized": false,
1431
- "rstrip": false,
1432
- "single_word": false,
1433
- "special": true
1434
- },
1435
- "128179": {
1436
- "content": "<|reserved_special_token_174|>",
1437
- "lstrip": false,
1438
- "normalized": false,
1439
- "rstrip": false,
1440
- "single_word": false,
1441
- "special": true
1442
- },
1443
- "128180": {
1444
- "content": "<|reserved_special_token_175|>",
1445
- "lstrip": false,
1446
- "normalized": false,
1447
- "rstrip": false,
1448
- "single_word": false,
1449
- "special": true
1450
- },
1451
- "128181": {
1452
- "content": "<|reserved_special_token_176|>",
1453
- "lstrip": false,
1454
- "normalized": false,
1455
- "rstrip": false,
1456
- "single_word": false,
1457
- "special": true
1458
- },
1459
- "128182": {
1460
- "content": "<|reserved_special_token_177|>",
1461
- "lstrip": false,
1462
- "normalized": false,
1463
- "rstrip": false,
1464
- "single_word": false,
1465
- "special": true
1466
- },
1467
- "128183": {
1468
- "content": "<|reserved_special_token_178|>",
1469
- "lstrip": false,
1470
- "normalized": false,
1471
- "rstrip": false,
1472
- "single_word": false,
1473
- "special": true
1474
- },
1475
- "128184": {
1476
- "content": "<|reserved_special_token_179|>",
1477
- "lstrip": false,
1478
- "normalized": false,
1479
- "rstrip": false,
1480
- "single_word": false,
1481
- "special": true
1482
- },
1483
- "128185": {
1484
- "content": "<|reserved_special_token_180|>",
1485
- "lstrip": false,
1486
- "normalized": false,
1487
- "rstrip": false,
1488
- "single_word": false,
1489
- "special": true
1490
- },
1491
- "128186": {
1492
- "content": "<|reserved_special_token_181|>",
1493
- "lstrip": false,
1494
- "normalized": false,
1495
- "rstrip": false,
1496
- "single_word": false,
1497
- "special": true
1498
- },
1499
- "128187": {
1500
- "content": "<|reserved_special_token_182|>",
1501
- "lstrip": false,
1502
- "normalized": false,
1503
- "rstrip": false,
1504
- "single_word": false,
1505
- "special": true
1506
- },
1507
- "128188": {
1508
- "content": "<|reserved_special_token_183|>",
1509
- "lstrip": false,
1510
- "normalized": false,
1511
- "rstrip": false,
1512
- "single_word": false,
1513
- "special": true
1514
- },
1515
- "128189": {
1516
- "content": "<|reserved_special_token_184|>",
1517
- "lstrip": false,
1518
- "normalized": false,
1519
- "rstrip": false,
1520
- "single_word": false,
1521
- "special": true
1522
- },
1523
- "128190": {
1524
- "content": "<|reserved_special_token_185|>",
1525
- "lstrip": false,
1526
- "normalized": false,
1527
- "rstrip": false,
1528
- "single_word": false,
1529
- "special": true
1530
- },
1531
- "128191": {
1532
- "content": "<|reserved_special_token_186|>",
1533
- "lstrip": false,
1534
- "normalized": false,
1535
- "rstrip": false,
1536
- "single_word": false,
1537
- "special": true
1538
- },
1539
- "128192": {
1540
- "content": "<|reserved_special_token_187|>",
1541
- "lstrip": false,
1542
- "normalized": false,
1543
- "rstrip": false,
1544
- "single_word": false,
1545
- "special": true
1546
- },
1547
- "128193": {
1548
- "content": "<|reserved_special_token_188|>",
1549
- "lstrip": false,
1550
- "normalized": false,
1551
- "rstrip": false,
1552
- "single_word": false,
1553
- "special": true
1554
- },
1555
- "128194": {
1556
- "content": "<|reserved_special_token_189|>",
1557
- "lstrip": false,
1558
- "normalized": false,
1559
- "rstrip": false,
1560
- "single_word": false,
1561
- "special": true
1562
- },
1563
- "128195": {
1564
- "content": "<|reserved_special_token_190|>",
1565
- "lstrip": false,
1566
- "normalized": false,
1567
- "rstrip": false,
1568
- "single_word": false,
1569
- "special": true
1570
- },
1571
- "128196": {
1572
- "content": "<|reserved_special_token_191|>",
1573
- "lstrip": false,
1574
- "normalized": false,
1575
- "rstrip": false,
1576
- "single_word": false,
1577
- "special": true
1578
- },
1579
- "128197": {
1580
- "content": "<|reserved_special_token_192|>",
1581
- "lstrip": false,
1582
- "normalized": false,
1583
- "rstrip": false,
1584
- "single_word": false,
1585
- "special": true
1586
- },
1587
- "128198": {
1588
- "content": "<|reserved_special_token_193|>",
1589
- "lstrip": false,
1590
- "normalized": false,
1591
- "rstrip": false,
1592
- "single_word": false,
1593
- "special": true
1594
- },
1595
- "128199": {
1596
- "content": "<|reserved_special_token_194|>",
1597
- "lstrip": false,
1598
- "normalized": false,
1599
- "rstrip": false,
1600
- "single_word": false,
1601
- "special": true
1602
- },
1603
- "128200": {
1604
- "content": "<|reserved_special_token_195|>",
1605
- "lstrip": false,
1606
- "normalized": false,
1607
- "rstrip": false,
1608
- "single_word": false,
1609
- "special": true
1610
- },
1611
- "128201": {
1612
- "content": "<|reserved_special_token_196|>",
1613
- "lstrip": false,
1614
- "normalized": false,
1615
- "rstrip": false,
1616
- "single_word": false,
1617
- "special": true
1618
- },
1619
- "128202": {
1620
- "content": "<|reserved_special_token_197|>",
1621
- "lstrip": false,
1622
- "normalized": false,
1623
- "rstrip": false,
1624
- "single_word": false,
1625
- "special": true
1626
- },
1627
- "128203": {
1628
- "content": "<|reserved_special_token_198|>",
1629
- "lstrip": false,
1630
- "normalized": false,
1631
- "rstrip": false,
1632
- "single_word": false,
1633
- "special": true
1634
- },
1635
- "128204": {
1636
- "content": "<|reserved_special_token_199|>",
1637
- "lstrip": false,
1638
- "normalized": false,
1639
- "rstrip": false,
1640
- "single_word": false,
1641
- "special": true
1642
- },
1643
- "128205": {
1644
- "content": "<|reserved_special_token_200|>",
1645
- "lstrip": false,
1646
- "normalized": false,
1647
- "rstrip": false,
1648
- "single_word": false,
1649
- "special": true
1650
- },
1651
- "128206": {
1652
- "content": "<|reserved_special_token_201|>",
1653
- "lstrip": false,
1654
- "normalized": false,
1655
- "rstrip": false,
1656
- "single_word": false,
1657
- "special": true
1658
- },
1659
- "128207": {
1660
- "content": "<|reserved_special_token_202|>",
1661
- "lstrip": false,
1662
- "normalized": false,
1663
- "rstrip": false,
1664
- "single_word": false,
1665
- "special": true
1666
- },
1667
- "128208": {
1668
- "content": "<|reserved_special_token_203|>",
1669
- "lstrip": false,
1670
- "normalized": false,
1671
- "rstrip": false,
1672
- "single_word": false,
1673
- "special": true
1674
- },
1675
- "128209": {
1676
- "content": "<|reserved_special_token_204|>",
1677
- "lstrip": false,
1678
- "normalized": false,
1679
- "rstrip": false,
1680
- "single_word": false,
1681
- "special": true
1682
- },
1683
- "128210": {
1684
- "content": "<|reserved_special_token_205|>",
1685
- "lstrip": false,
1686
- "normalized": false,
1687
- "rstrip": false,
1688
- "single_word": false,
1689
- "special": true
1690
- },
1691
- "128211": {
1692
- "content": "<|reserved_special_token_206|>",
1693
- "lstrip": false,
1694
- "normalized": false,
1695
- "rstrip": false,
1696
- "single_word": false,
1697
- "special": true
1698
- },
1699
- "128212": {
1700
- "content": "<|reserved_special_token_207|>",
1701
- "lstrip": false,
1702
- "normalized": false,
1703
- "rstrip": false,
1704
- "single_word": false,
1705
- "special": true
1706
- },
1707
- "128213": {
1708
- "content": "<|reserved_special_token_208|>",
1709
- "lstrip": false,
1710
- "normalized": false,
1711
- "rstrip": false,
1712
- "single_word": false,
1713
- "special": true
1714
- },
1715
- "128214": {
1716
- "content": "<|reserved_special_token_209|>",
1717
- "lstrip": false,
1718
- "normalized": false,
1719
- "rstrip": false,
1720
- "single_word": false,
1721
- "special": true
1722
- },
1723
- "128215": {
1724
- "content": "<|reserved_special_token_210|>",
1725
- "lstrip": false,
1726
- "normalized": false,
1727
- "rstrip": false,
1728
- "single_word": false,
1729
- "special": true
1730
- },
1731
- "128216": {
1732
- "content": "<|reserved_special_token_211|>",
1733
- "lstrip": false,
1734
- "normalized": false,
1735
- "rstrip": false,
1736
- "single_word": false,
1737
- "special": true
1738
- },
1739
- "128217": {
1740
- "content": "<|reserved_special_token_212|>",
1741
- "lstrip": false,
1742
- "normalized": false,
1743
- "rstrip": false,
1744
- "single_word": false,
1745
- "special": true
1746
- },
1747
- "128218": {
1748
- "content": "<|reserved_special_token_213|>",
1749
- "lstrip": false,
1750
- "normalized": false,
1751
- "rstrip": false,
1752
- "single_word": false,
1753
- "special": true
1754
- },
1755
- "128219": {
1756
- "content": "<|reserved_special_token_214|>",
1757
- "lstrip": false,
1758
- "normalized": false,
1759
- "rstrip": false,
1760
- "single_word": false,
1761
- "special": true
1762
- },
1763
- "128220": {
1764
- "content": "<|reserved_special_token_215|>",
1765
- "lstrip": false,
1766
- "normalized": false,
1767
- "rstrip": false,
1768
- "single_word": false,
1769
- "special": true
1770
- },
1771
- "128221": {
1772
- "content": "<|reserved_special_token_216|>",
1773
- "lstrip": false,
1774
- "normalized": false,
1775
- "rstrip": false,
1776
- "single_word": false,
1777
- "special": true
1778
- },
1779
- "128222": {
1780
- "content": "<|reserved_special_token_217|>",
1781
- "lstrip": false,
1782
- "normalized": false,
1783
- "rstrip": false,
1784
- "single_word": false,
1785
- "special": true
1786
- },
1787
- "128223": {
1788
- "content": "<|reserved_special_token_218|>",
1789
- "lstrip": false,
1790
- "normalized": false,
1791
- "rstrip": false,
1792
- "single_word": false,
1793
- "special": true
1794
- },
1795
- "128224": {
1796
- "content": "<|reserved_special_token_219|>",
1797
- "lstrip": false,
1798
- "normalized": false,
1799
- "rstrip": false,
1800
- "single_word": false,
1801
- "special": true
1802
- },
1803
- "128225": {
1804
- "content": "<|reserved_special_token_220|>",
1805
- "lstrip": false,
1806
- "normalized": false,
1807
- "rstrip": false,
1808
- "single_word": false,
1809
- "special": true
1810
- },
1811
- "128226": {
1812
- "content": "<|reserved_special_token_221|>",
1813
- "lstrip": false,
1814
- "normalized": false,
1815
- "rstrip": false,
1816
- "single_word": false,
1817
- "special": true
1818
- },
1819
- "128227": {
1820
- "content": "<|reserved_special_token_222|>",
1821
- "lstrip": false,
1822
- "normalized": false,
1823
- "rstrip": false,
1824
- "single_word": false,
1825
- "special": true
1826
- },
1827
- "128228": {
1828
- "content": "<|reserved_special_token_223|>",
1829
- "lstrip": false,
1830
- "normalized": false,
1831
- "rstrip": false,
1832
- "single_word": false,
1833
- "special": true
1834
- },
1835
- "128229": {
1836
- "content": "<|reserved_special_token_224|>",
1837
- "lstrip": false,
1838
- "normalized": false,
1839
- "rstrip": false,
1840
- "single_word": false,
1841
- "special": true
1842
- },
1843
- "128230": {
1844
- "content": "<|reserved_special_token_225|>",
1845
- "lstrip": false,
1846
- "normalized": false,
1847
- "rstrip": false,
1848
- "single_word": false,
1849
- "special": true
1850
- },
1851
- "128231": {
1852
- "content": "<|reserved_special_token_226|>",
1853
- "lstrip": false,
1854
- "normalized": false,
1855
- "rstrip": false,
1856
- "single_word": false,
1857
- "special": true
1858
- },
1859
- "128232": {
1860
- "content": "<|reserved_special_token_227|>",
1861
- "lstrip": false,
1862
- "normalized": false,
1863
- "rstrip": false,
1864
- "single_word": false,
1865
- "special": true
1866
- },
1867
- "128233": {
1868
- "content": "<|reserved_special_token_228|>",
1869
- "lstrip": false,
1870
- "normalized": false,
1871
- "rstrip": false,
1872
- "single_word": false,
1873
- "special": true
1874
- },
1875
- "128234": {
1876
- "content": "<|reserved_special_token_229|>",
1877
- "lstrip": false,
1878
- "normalized": false,
1879
- "rstrip": false,
1880
- "single_word": false,
1881
- "special": true
1882
- },
1883
- "128235": {
1884
- "content": "<|reserved_special_token_230|>",
1885
- "lstrip": false,
1886
- "normalized": false,
1887
- "rstrip": false,
1888
- "single_word": false,
1889
- "special": true
1890
- },
1891
- "128236": {
1892
- "content": "<|reserved_special_token_231|>",
1893
- "lstrip": false,
1894
- "normalized": false,
1895
- "rstrip": false,
1896
- "single_word": false,
1897
- "special": true
1898
- },
1899
- "128237": {
1900
- "content": "<|reserved_special_token_232|>",
1901
- "lstrip": false,
1902
- "normalized": false,
1903
- "rstrip": false,
1904
- "single_word": false,
1905
- "special": true
1906
- },
1907
- "128238": {
1908
- "content": "<|reserved_special_token_233|>",
1909
- "lstrip": false,
1910
- "normalized": false,
1911
- "rstrip": false,
1912
- "single_word": false,
1913
- "special": true
1914
- },
1915
- "128239": {
1916
- "content": "<|reserved_special_token_234|>",
1917
- "lstrip": false,
1918
- "normalized": false,
1919
- "rstrip": false,
1920
- "single_word": false,
1921
- "special": true
1922
- },
1923
- "128240": {
1924
- "content": "<|reserved_special_token_235|>",
1925
- "lstrip": false,
1926
- "normalized": false,
1927
- "rstrip": false,
1928
- "single_word": false,
1929
- "special": true
1930
- },
1931
- "128241": {
1932
- "content": "<|reserved_special_token_236|>",
1933
- "lstrip": false,
1934
- "normalized": false,
1935
- "rstrip": false,
1936
- "single_word": false,
1937
- "special": true
1938
- },
1939
- "128242": {
1940
- "content": "<|reserved_special_token_237|>",
1941
- "lstrip": false,
1942
- "normalized": false,
1943
- "rstrip": false,
1944
- "single_word": false,
1945
- "special": true
1946
- },
1947
- "128243": {
1948
- "content": "<|reserved_special_token_238|>",
1949
- "lstrip": false,
1950
- "normalized": false,
1951
- "rstrip": false,
1952
- "single_word": false,
1953
- "special": true
1954
- },
1955
- "128244": {
1956
- "content": "<|reserved_special_token_239|>",
1957
- "lstrip": false,
1958
- "normalized": false,
1959
- "rstrip": false,
1960
- "single_word": false,
1961
- "special": true
1962
- },
1963
- "128245": {
1964
- "content": "<|reserved_special_token_240|>",
1965
- "lstrip": false,
1966
- "normalized": false,
1967
- "rstrip": false,
1968
- "single_word": false,
1969
- "special": true
1970
- },
1971
- "128246": {
1972
- "content": "<|reserved_special_token_241|>",
1973
- "lstrip": false,
1974
- "normalized": false,
1975
- "rstrip": false,
1976
- "single_word": false,
1977
- "special": true
1978
- },
1979
- "128247": {
1980
- "content": "<|reserved_special_token_242|>",
1981
- "lstrip": false,
1982
- "normalized": false,
1983
- "rstrip": false,
1984
- "single_word": false,
1985
- "special": true
1986
- },
1987
- "128248": {
1988
- "content": "<|reserved_special_token_243|>",
1989
- "lstrip": false,
1990
- "normalized": false,
1991
- "rstrip": false,
1992
- "single_word": false,
1993
- "special": true
1994
- },
1995
- "128249": {
1996
- "content": "<|reserved_special_token_244|>",
1997
- "lstrip": false,
1998
- "normalized": false,
1999
- "rstrip": false,
2000
- "single_word": false,
2001
- "special": true
2002
- },
2003
- "128250": {
2004
- "content": "<|reserved_special_token_245|>",
2005
- "lstrip": false,
2006
- "normalized": false,
2007
- "rstrip": false,
2008
- "single_word": false,
2009
- "special": true
2010
- },
2011
- "128251": {
2012
- "content": "<|reserved_special_token_246|>",
2013
- "lstrip": false,
2014
- "normalized": false,
2015
- "rstrip": false,
2016
- "single_word": false,
2017
- "special": true
2018
- },
2019
- "128252": {
2020
- "content": "<|reserved_special_token_247|>",
2021
- "lstrip": false,
2022
- "normalized": false,
2023
- "rstrip": false,
2024
- "single_word": false,
2025
- "special": true
2026
- },
2027
- "128253": {
2028
- "content": "<|reserved_special_token_248|>",
2029
- "lstrip": false,
2030
- "normalized": false,
2031
- "rstrip": false,
2032
- "single_word": false,
2033
- "special": true
2034
- },
2035
- "128254": {
2036
- "content": "<|reserved_special_token_249|>",
2037
- "lstrip": false,
2038
- "normalized": false,
2039
- "rstrip": false,
2040
- "single_word": false,
2041
- "special": true
2042
- },
2043
- "128255": {
2044
- "content": "<|reserved_special_token_250|>",
2045
  "lstrip": false,
2046
  "normalized": false,
2047
  "rstrip": false,
@@ -2049,15 +25,22 @@
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
  }
 
1
  {
2
  "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
8
  "single_word": false,
9
  "special": true
10
  },
11
+ "1": {
12
+ "content": "<s>",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
16
  "single_word": false,
17
  "special": true
18
  },
19
+ "2": {
20
+ "content": "</s>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
 
25
  "special": true
26
  }
27
  },
28
+ "additional_special_tokens": [
29
+ "<unk>",
30
+ "<s>",
31
+ "</s>"
 
 
 
32
  ],
33
+ "bos_token": "<s>",
34
+ "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
35
+ "clean_up_tokenization_spaces": false,
36
+ "eos_token": "</s>",
37
+ "legacy": true,
38
  "model_max_length": 2048,
39
+ "pad_token": "</s>",
40
+ "sp_model_kwargs": {},
41
+ "spaces_between_special_tokens": false,
42
+ "tokenizer_class": "LlamaTokenizer",
43
+ "truncation_side": "left",
44
+ "unk_token": "<unk>",
45
+ "use_default_system_prompt": true
46
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 1.0,
3
- "train_loss": 0.05354936925432717,
4
- "train_runtime": 4393.8172,
5
- "train_samples": 61134,
6
- "train_samples_per_second": 13.914,
7
- "train_steps_per_second": 0.109
8
  }
 
1
  {
2
  "epoch": 1.0,
3
+ "train_loss": 0.08838768833213383,
4
+ "train_runtime": 3226.1286,
5
+ "train_samples": 51894,
6
+ "train_samples_per_second": 16.086,
7
+ "train_steps_per_second": 0.126
8
  }
trainer_state.json CHANGED
@@ -1,21 +1,21 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.9984301412872841,
5
- "eval_steps": 100,
6
- "global_step": 477,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
  "epoch": 0.0,
13
- "learning_rate": 1.0416666666666666e-08,
14
- "logits/chosen": 0.12788674235343933,
15
- "logits/rejected": 0.34812721610069275,
16
- "logps/chosen": -504.64813232421875,
17
- "logps/rejected": -353.6391906738281,
18
- "loss": 0.0873,
19
  "rewards/accuracies": 0.0,
20
  "rewards/chosen": 0.0,
21
  "rewards/margins": 0.0,
@@ -24,738 +24,576 @@
24
  },
25
  {
26
  "epoch": 0.02,
27
- "learning_rate": 1.0416666666666667e-07,
28
- "logits/chosen": 0.22212976217269897,
29
- "logits/rejected": 0.3389735519886017,
30
- "logps/chosen": -343.8792419433594,
31
- "logps/rejected": -345.3973388671875,
32
- "loss": 0.0889,
33
- "rewards/accuracies": 0.4583333432674408,
34
- "rewards/chosen": 0.0006486935308203101,
35
- "rewards/margins": 0.0006935929413884878,
36
- "rewards/rejected": -4.48995124315843e-05,
37
  "step": 10
38
  },
39
  {
40
- "epoch": 0.04,
41
- "learning_rate": 2.0833333333333333e-07,
42
- "logits/chosen": 0.24278604984283447,
43
- "logits/rejected": 0.2772199511528015,
44
- "logps/chosen": -342.1460876464844,
45
- "logps/rejected": -352.69818115234375,
46
- "loss": 0.0886,
47
- "rewards/accuracies": 0.5249999761581421,
48
- "rewards/chosen": -0.00040716020157560706,
49
- "rewards/margins": 0.0005563176237046719,
50
- "rewards/rejected": -0.000963477767072618,
51
  "step": 20
52
  },
53
  {
54
- "epoch": 0.06,
55
- "learning_rate": 3.1249999999999997e-07,
56
- "logits/chosen": 0.22536441683769226,
57
- "logits/rejected": 0.22937357425689697,
58
- "logps/chosen": -402.98822021484375,
59
- "logps/rejected": -395.0972595214844,
60
- "loss": 0.0902,
61
- "rewards/accuracies": 0.668749988079071,
62
- "rewards/chosen": -0.000842810608446598,
63
- "rewards/margins": 0.0034794104285538197,
64
- "rewards/rejected": -0.004322221037000418,
65
  "step": 30
66
  },
67
  {
68
- "epoch": 0.08,
69
- "learning_rate": 4.1666666666666667e-07,
70
- "logits/chosen": 0.2755671739578247,
71
- "logits/rejected": 0.33087944984436035,
72
- "logps/chosen": -352.0638732910156,
73
- "logps/rejected": -338.8406982421875,
74
- "loss": 0.089,
75
- "rewards/accuracies": 0.606249988079071,
76
- "rewards/chosen": -0.006839037872850895,
77
- "rewards/margins": 0.004006261937320232,
78
- "rewards/rejected": -0.010845299810171127,
79
  "step": 40
80
  },
81
  {
82
- "epoch": 0.1,
83
- "learning_rate": 4.999731868769026e-07,
84
- "logits/chosen": 0.22722303867340088,
85
- "logits/rejected": 0.3114616572856903,
86
- "logps/chosen": -363.44488525390625,
87
- "logps/rejected": -358.5865783691406,
88
- "loss": 0.0844,
89
- "rewards/accuracies": 0.6937500238418579,
90
- "rewards/chosen": -0.005490039009600878,
91
- "rewards/margins": 0.02063574083149433,
92
- "rewards/rejected": -0.02612578310072422,
93
  "step": 50
94
  },
95
  {
96
- "epoch": 0.13,
97
- "learning_rate": 4.990353313429303e-07,
98
- "logits/chosen": 0.3604680299758911,
99
- "logits/rejected": 0.384317547082901,
100
- "logps/chosen": -336.05914306640625,
101
- "logps/rejected": -334.6701965332031,
102
- "loss": 0.0853,
103
- "rewards/accuracies": 0.6499999761581421,
104
- "rewards/chosen": -0.01469508744776249,
105
- "rewards/margins": 0.03407812491059303,
106
- "rewards/rejected": -0.048773206770420074,
107
  "step": 60
108
  },
109
  {
110
- "epoch": 0.15,
111
- "learning_rate": 4.967625656594781e-07,
112
- "logits/chosen": 0.23509681224822998,
113
- "logits/rejected": 0.33425503969192505,
114
- "logps/chosen": -350.3525390625,
115
- "logps/rejected": -307.4208068847656,
116
- "loss": 0.0836,
117
- "rewards/accuracies": 0.643750011920929,
118
- "rewards/chosen": -0.002837834181264043,
119
- "rewards/margins": 0.05291702598333359,
120
- "rewards/rejected": -0.05575486272573471,
121
  "step": 70
122
  },
123
  {
124
- "epoch": 0.17,
125
- "learning_rate": 4.93167072587771e-07,
126
- "logits/chosen": 0.3232734501361847,
127
- "logits/rejected": 0.39760860800743103,
128
- "logps/chosen": -379.69671630859375,
129
- "logps/rejected": -327.80255126953125,
130
- "loss": 0.0902,
131
- "rewards/accuracies": 0.699999988079071,
132
- "rewards/chosen": -0.004514769650995731,
133
- "rewards/margins": 0.07807327061891556,
134
- "rewards/rejected": -0.08258803933858871,
135
  "step": 80
136
  },
137
  {
138
- "epoch": 0.19,
139
- "learning_rate": 4.882681251368548e-07,
140
- "logits/chosen": 0.31744256615638733,
141
- "logits/rejected": 0.42906659841537476,
142
- "logps/chosen": -394.5928039550781,
143
- "logps/rejected": -366.71978759765625,
144
- "loss": 0.0822,
145
- "rewards/accuracies": 0.7250000238418579,
146
- "rewards/chosen": -0.007822219282388687,
147
- "rewards/margins": 0.12728586792945862,
148
- "rewards/rejected": -0.135108083486557,
149
  "step": 90
150
  },
151
  {
152
- "epoch": 0.21,
153
- "learning_rate": 4.820919832540181e-07,
154
- "logits/chosen": 0.3827999532222748,
155
- "logits/rejected": 0.4694398045539856,
156
- "logps/chosen": -372.06585693359375,
157
- "logps/rejected": -365.7283630371094,
158
- "loss": 0.078,
159
- "rewards/accuracies": 0.5874999761581421,
160
- "rewards/chosen": -0.08074171096086502,
161
- "rewards/margins": 0.11391631513834,
162
- "rewards/rejected": -0.1946580410003662,
163
- "step": 100
164
- },
165
- {
166
- "epoch": 0.21,
167
- "eval_logits/chosen": 0.4690203070640564,
168
- "eval_logits/rejected": 0.5343385934829712,
169
- "eval_logps/chosen": -365.5567321777344,
170
- "eval_logps/rejected": -389.5570068359375,
171
- "eval_loss": 0.07822111248970032,
172
- "eval_rewards/accuracies": 0.6953125,
173
- "eval_rewards/chosen": -0.06105535477399826,
174
- "eval_rewards/margins": 0.1774202287197113,
175
- "eval_rewards/rejected": -0.23847556114196777,
176
- "eval_runtime": 75.6198,
177
- "eval_samples_per_second": 26.448,
178
- "eval_steps_per_second": 0.423,
179
  "step": 100
180
  },
181
  {
182
- "epoch": 0.23,
183
- "learning_rate": 4.7467175306295647e-07,
184
- "logits/chosen": 0.3686356246471405,
185
- "logits/rejected": 0.4329895079135895,
186
- "logps/chosen": -378.2501525878906,
187
- "logps/rejected": -378.30218505859375,
188
- "loss": 0.0749,
189
- "rewards/accuracies": 0.606249988079071,
190
- "rewards/chosen": -0.1465841382741928,
191
- "rewards/margins": 0.131878063082695,
192
- "rewards/rejected": -0.2784622311592102,
193
  "step": 110
194
  },
195
  {
196
- "epoch": 0.25,
197
- "learning_rate": 4.6604720940421207e-07,
198
- "logits/chosen": 0.449271023273468,
199
- "logits/rejected": 0.5487788915634155,
200
- "logps/chosen": -408.51385498046875,
201
- "logps/rejected": -415.11114501953125,
202
- "loss": 0.0747,
203
- "rewards/accuracies": 0.6625000238418579,
204
- "rewards/chosen": -0.19466131925582886,
205
- "rewards/margins": 0.15672670304775238,
206
- "rewards/rejected": -0.35138803720474243,
207
  "step": 120
208
  },
209
  {
210
- "epoch": 0.27,
211
- "learning_rate": 4.5626458262912735e-07,
212
- "logits/chosen": 0.5826891660690308,
213
- "logits/rejected": 0.6821892857551575,
214
- "logps/chosen": -420.2059020996094,
215
- "logps/rejected": -399.73004150390625,
216
- "loss": 0.0637,
217
- "rewards/accuracies": 0.606249988079071,
218
- "rewards/chosen": -0.29077965021133423,
219
- "rewards/margins": 0.15969224274158478,
220
- "rewards/rejected": -0.4504718780517578,
221
  "step": 130
222
  },
223
  {
224
- "epoch": 0.29,
225
- "learning_rate": 4.453763107901675e-07,
226
- "logits/chosen": 0.6231743693351746,
227
- "logits/rejected": 0.7450427412986755,
228
- "logps/chosen": -396.96990966796875,
229
- "logps/rejected": -391.3907470703125,
230
- "loss": 0.0583,
231
- "rewards/accuracies": 0.675000011920929,
232
- "rewards/chosen": -0.37303242087364197,
233
- "rewards/margins": 0.18951326608657837,
234
- "rewards/rejected": -0.562545657157898,
235
  "step": 140
236
  },
237
  {
238
- "epoch": 0.31,
239
- "learning_rate": 4.3344075855595097e-07,
240
- "logits/chosen": 0.6709073185920715,
241
- "logits/rejected": 0.8240610361099243,
242
- "logps/chosen": -388.2197570800781,
243
- "logps/rejected": -379.05377197265625,
244
- "loss": 0.0525,
245
- "rewards/accuracies": 0.6000000238418579,
246
- "rewards/chosen": -0.4231031835079193,
247
- "rewards/margins": 0.19369539618492126,
248
- "rewards/rejected": -0.6167985796928406,
249
  "step": 150
250
  },
251
  {
252
- "epoch": 0.33,
253
- "learning_rate": 4.2052190435769554e-07,
254
- "logits/chosen": 0.6301496624946594,
255
- "logits/rejected": 0.7768956422805786,
256
- "logps/chosen": -429.7679748535156,
257
- "logps/rejected": -451.64251708984375,
258
- "loss": 0.0505,
259
- "rewards/accuracies": 0.6875,
260
- "rewards/chosen": -0.4186778664588928,
261
- "rewards/margins": 0.28083106875419617,
262
- "rewards/rejected": -0.6995089054107666,
263
  "step": 160
264
  },
265
  {
266
- "epoch": 0.36,
267
- "learning_rate": 4.0668899744407567e-07,
268
- "logits/chosen": 0.6732593178749084,
269
- "logits/rejected": 0.8628215789794922,
270
- "logps/chosen": -394.9469299316406,
271
- "logps/rejected": -402.25775146484375,
272
- "loss": 0.0502,
273
- "rewards/accuracies": 0.612500011920929,
274
- "rewards/chosen": -0.49948954582214355,
275
- "rewards/margins": 0.2556792199611664,
276
- "rewards/rejected": -0.7551687955856323,
277
  "step": 170
278
  },
279
  {
280
- "epoch": 0.38,
281
- "learning_rate": 3.920161866827889e-07,
282
- "logits/chosen": 0.552297830581665,
283
- "logits/rejected": 0.6591747999191284,
284
- "logps/chosen": -382.05389404296875,
285
- "logps/rejected": -420.1329040527344,
286
- "loss": 0.0507,
287
- "rewards/accuracies": 0.6187499761581421,
288
- "rewards/chosen": -0.4803597033023834,
289
- "rewards/margins": 0.27183446288108826,
290
- "rewards/rejected": -0.7521941661834717,
291
  "step": 180
292
  },
293
  {
294
- "epoch": 0.4,
295
- "learning_rate": 3.765821230985757e-07,
296
- "logits/chosen": 0.5414701700210571,
297
- "logits/rejected": 0.6569040417671204,
298
- "logps/chosen": -383.86126708984375,
299
- "logps/rejected": -409.1890869140625,
300
- "loss": 0.0485,
301
- "rewards/accuracies": 0.643750011920929,
302
- "rewards/chosen": -0.41677427291870117,
303
- "rewards/margins": 0.29112473130226135,
304
- "rewards/rejected": -0.7078990340232849,
305
  "step": 190
306
  },
307
  {
308
- "epoch": 0.42,
309
- "learning_rate": 3.604695382782159e-07,
310
- "logits/chosen": 0.49418172240257263,
311
- "logits/rejected": 0.6003471612930298,
312
- "logps/chosen": -435.78424072265625,
313
- "logps/rejected": -454.90386962890625,
314
- "loss": 0.048,
315
- "rewards/accuracies": 0.668749988079071,
316
- "rewards/chosen": -0.4994742274284363,
317
- "rewards/margins": 0.31197983026504517,
318
- "rewards/rejected": -0.811454176902771,
319
- "step": 200
320
- },
321
- {
322
- "epoch": 0.42,
323
- "eval_logits/chosen": 0.6602794528007507,
324
- "eval_logits/rejected": 0.7802540063858032,
325
- "eval_logps/chosen": -406.2314758300781,
326
- "eval_logps/rejected": -456.2774353027344,
327
- "eval_loss": 0.047346290200948715,
328
- "eval_rewards/accuracies": 0.70703125,
329
- "eval_rewards/chosen": -0.46780261397361755,
330
- "eval_rewards/margins": 0.43787747621536255,
331
- "eval_rewards/rejected": -0.9056800603866577,
332
- "eval_runtime": 76.8794,
333
- "eval_samples_per_second": 26.015,
334
- "eval_steps_per_second": 0.416,
335
  "step": 200
336
  },
337
  {
338
- "epoch": 0.44,
339
- "learning_rate": 3.4376480090239047e-07,
340
- "logits/chosen": 0.5745345950126648,
341
- "logits/rejected": 0.6733748316764832,
342
- "logps/chosen": -444.5130920410156,
343
- "logps/rejected": -429.42315673828125,
344
- "loss": 0.0459,
345
- "rewards/accuracies": 0.6625000238418579,
346
- "rewards/chosen": -0.5921798348426819,
347
- "rewards/margins": 0.2985352873802185,
348
- "rewards/rejected": -0.8907151222229004,
349
  "step": 210
350
  },
351
  {
352
- "epoch": 0.46,
353
- "learning_rate": 3.265574537815398e-07,
354
- "logits/chosen": 0.4414284825325012,
355
- "logits/rejected": 0.6841789484024048,
356
- "logps/chosen": -426.97833251953125,
357
- "logps/rejected": -429.253173828125,
358
- "loss": 0.0464,
359
- "rewards/accuracies": 0.7250000238418579,
360
- "rewards/chosen": -0.4616759717464447,
361
- "rewards/margins": 0.4957199990749359,
362
- "rewards/rejected": -0.9573960304260254,
363
  "step": 220
364
  },
365
  {
366
- "epoch": 0.48,
367
- "learning_rate": 3.0893973387735683e-07,
368
- "logits/chosen": 0.45067548751831055,
369
- "logits/rejected": 0.6739317774772644,
370
- "logps/chosen": -460.6690368652344,
371
- "logps/rejected": -432.30584716796875,
372
- "loss": 0.0467,
373
- "rewards/accuracies": 0.706250011920929,
374
- "rewards/chosen": -0.5173887610435486,
375
- "rewards/margins": 0.4104163646697998,
376
- "rewards/rejected": -0.9278050661087036,
377
  "step": 230
378
  },
379
  {
380
- "epoch": 0.5,
381
- "learning_rate": 2.910060778827554e-07,
382
- "logits/chosen": 0.5502692461013794,
383
- "logits/rejected": 0.7323163151741028,
384
- "logps/chosen": -430.7151794433594,
385
- "logps/rejected": -443.23809814453125,
386
- "loss": 0.0492,
387
- "rewards/accuracies": 0.6937500238418579,
388
- "rewards/chosen": -0.480847030878067,
389
- "rewards/margins": 0.4605809152126312,
390
- "rewards/rejected": -0.9414278864860535,
391
  "step": 240
392
  },
393
  {
394
- "epoch": 0.52,
395
- "learning_rate": 2.7285261601056697e-07,
396
- "logits/chosen": 0.571479082107544,
397
- "logits/rejected": 0.7172135710716248,
398
- "logps/chosen": -400.7060852050781,
399
- "logps/rejected": -450.3419494628906,
400
- "loss": 0.0446,
401
- "rewards/accuracies": 0.699999988079071,
402
- "rewards/chosen": -0.5908448100090027,
403
- "rewards/margins": 0.4142588973045349,
404
- "rewards/rejected": -1.0051038265228271,
405
  "step": 250
406
  },
407
  {
408
- "epoch": 0.54,
409
- "learning_rate": 2.5457665670441937e-07,
410
- "logits/chosen": 0.5472374558448792,
411
- "logits/rejected": 0.7074090242385864,
412
- "logps/chosen": -432.8170471191406,
413
- "logps/rejected": -459.19232177734375,
414
- "loss": 0.0441,
415
- "rewards/accuracies": 0.6937500238418579,
416
- "rewards/chosen": -0.6107853055000305,
417
- "rewards/margins": 0.3663175702095032,
418
- "rewards/rejected": -0.9771028757095337,
419
  "step": 260
420
  },
421
  {
422
- "epoch": 0.57,
423
- "learning_rate": 2.3627616503391812e-07,
424
- "logits/chosen": 0.5463359951972961,
425
- "logits/rejected": 0.6970590353012085,
426
- "logps/chosen": -414.2933654785156,
427
- "logps/rejected": -441.50433349609375,
428
- "loss": 0.0428,
429
- "rewards/accuracies": 0.643750011920929,
430
- "rewards/chosen": -0.6104375123977661,
431
- "rewards/margins": 0.4157808721065521,
432
- "rewards/rejected": -1.0262184143066406,
433
  "step": 270
434
  },
435
  {
436
- "epoch": 0.59,
437
- "learning_rate": 2.1804923757009882e-07,
438
- "logits/chosen": 0.5769293308258057,
439
- "logits/rejected": 0.6871014833450317,
440
- "logps/chosen": -444.06341552734375,
441
- "logps/rejected": -481.1180725097656,
442
- "loss": 0.0409,
443
- "rewards/accuracies": 0.668749988079071,
444
- "rewards/chosen": -0.599878191947937,
445
- "rewards/margins": 0.4251036047935486,
446
- "rewards/rejected": -1.0249818563461304,
447
  "step": 280
448
  },
449
  {
450
- "epoch": 0.61,
451
- "learning_rate": 1.9999357655598891e-07,
452
- "logits/chosen": 0.6332536935806274,
453
- "logits/rejected": 0.8593415021896362,
454
- "logps/chosen": -447.9913024902344,
455
- "logps/rejected": -448.5614318847656,
456
- "loss": 0.0394,
457
- "rewards/accuracies": 0.637499988079071,
458
- "rewards/chosen": -0.7027456760406494,
459
- "rewards/margins": 0.4865785241127014,
460
- "rewards/rejected": -1.1893242597579956,
461
  "step": 290
462
  },
463
  {
464
- "epoch": 0.63,
465
- "learning_rate": 1.8220596619089573e-07,
466
- "logits/chosen": 0.6542817950248718,
467
- "logits/rejected": 0.8177863359451294,
468
- "logps/chosen": -440.9554748535156,
469
- "logps/rejected": -462.11328125,
470
- "loss": 0.0386,
471
- "rewards/accuracies": 0.637499988079071,
472
- "rewards/chosen": -0.7270612716674805,
473
- "rewards/margins": 0.33339208364486694,
474
- "rewards/rejected": -1.0604532957077026,
475
- "step": 300
476
- },
477
- {
478
- "epoch": 0.63,
479
- "eval_logits/chosen": 0.7596062421798706,
480
- "eval_logits/rejected": 0.8700711131095886,
481
- "eval_logps/chosen": -420.708740234375,
482
- "eval_logps/rejected": -479.3782958984375,
483
- "eval_loss": 0.040953561663627625,
484
- "eval_rewards/accuracies": 0.71875,
485
- "eval_rewards/chosen": -0.6125754117965698,
486
- "eval_rewards/margins": 0.5241137742996216,
487
- "eval_rewards/rejected": -1.136689305305481,
488
- "eval_runtime": 75.4827,
489
- "eval_samples_per_second": 26.496,
490
- "eval_steps_per_second": 0.424,
491
  "step": 300
492
  },
493
  {
494
- "epoch": 0.65,
495
- "learning_rate": 1.647817538357072e-07,
496
- "logits/chosen": 0.6124904751777649,
497
- "logits/rejected": 0.7914358973503113,
498
- "logps/chosen": -426.30755615234375,
499
- "logps/rejected": -455.01702880859375,
500
- "loss": 0.0398,
501
- "rewards/accuracies": 0.612500011920929,
502
- "rewards/chosen": -0.6258746981620789,
503
- "rewards/margins": 0.40696629881858826,
504
- "rewards/rejected": -1.0328409671783447,
505
  "step": 310
506
  },
507
  {
508
- "epoch": 0.67,
509
- "learning_rate": 1.478143389201113e-07,
510
- "logits/chosen": 0.7360497713088989,
511
- "logits/rejected": 0.9317388534545898,
512
- "logps/chosen": -454.4518127441406,
513
- "logps/rejected": -484.66339111328125,
514
- "loss": 0.0368,
515
- "rewards/accuracies": 0.731249988079071,
516
- "rewards/chosen": -0.6490928530693054,
517
- "rewards/margins": 0.4235590994358063,
518
- "rewards/rejected": -1.072651982307434,
519
  "step": 320
520
  },
521
  {
522
- "epoch": 0.69,
523
- "learning_rate": 1.3139467229135998e-07,
524
- "logits/chosen": 0.6175029873847961,
525
- "logits/rejected": 0.7568264603614807,
526
- "logps/chosen": -429.0270080566406,
527
- "logps/rejected": -479.8829040527344,
528
- "loss": 0.0387,
529
- "rewards/accuracies": 0.668749988079071,
530
- "rewards/chosen": -0.6886905431747437,
531
- "rewards/margins": 0.38589444756507874,
532
- "rewards/rejected": -1.0745849609375,
533
  "step": 330
534
  },
535
  {
536
- "epoch": 0.71,
537
- "learning_rate": 1.1561076868822755e-07,
538
- "logits/chosen": 0.532618522644043,
539
- "logits/rejected": 0.7396461367607117,
540
- "logps/chosen": -462.6270446777344,
541
- "logps/rejected": -495.7816467285156,
542
- "loss": 0.0396,
543
- "rewards/accuracies": 0.6875,
544
- "rewards/chosen": -0.6502823829650879,
545
- "rewards/margins": 0.4719853401184082,
546
- "rewards/rejected": -1.122267723083496,
547
  "step": 340
548
  },
549
  {
550
- "epoch": 0.73,
551
- "learning_rate": 1.0054723495346482e-07,
552
- "logits/chosen": 0.6981407999992371,
553
- "logits/rejected": 0.7719085812568665,
554
- "logps/chosen": -395.1247253417969,
555
- "logps/rejected": -449.11334228515625,
556
- "loss": 0.0381,
557
- "rewards/accuracies": 0.6812499761581421,
558
- "rewards/chosen": -0.6799373030662537,
559
- "rewards/margins": 0.4461960792541504,
560
- "rewards/rejected": -1.1261335611343384,
561
  "step": 350
562
  },
563
  {
564
- "epoch": 0.75,
565
- "learning_rate": 8.628481651367875e-08,
566
- "logits/chosen": 0.6425920724868774,
567
- "logits/rejected": 0.8264240026473999,
568
- "logps/chosen": -439.60101318359375,
569
- "logps/rejected": -432.4410095214844,
570
- "loss": 0.043,
571
- "rewards/accuracies": 0.6499999761581421,
572
- "rewards/chosen": -0.6968793869018555,
573
- "rewards/margins": 0.36896371841430664,
574
- "rewards/rejected": -1.065843105316162,
575
  "step": 360
576
  },
577
  {
578
- "epoch": 0.77,
579
- "learning_rate": 7.289996455765748e-08,
580
- "logits/chosen": 0.625984787940979,
581
- "logits/rejected": 0.8757528066635132,
582
- "logps/chosen": -436.14031982421875,
583
- "logps/rejected": -427.8795471191406,
584
- "loss": 0.0353,
585
- "rewards/accuracies": 0.71875,
586
- "rewards/chosen": -0.6146796345710754,
587
- "rewards/margins": 0.46029072999954224,
588
- "rewards/rejected": -1.0749704837799072,
589
  "step": 370
590
  },
591
  {
592
- "epoch": 0.8,
593
- "learning_rate": 6.046442623320145e-08,
594
- "logits/chosen": 0.6381999254226685,
595
- "logits/rejected": 0.7063127756118774,
596
- "logps/chosen": -427.59405517578125,
597
- "logps/rejected": -458.2549743652344,
598
- "loss": 0.0412,
599
- "rewards/accuracies": 0.625,
600
- "rewards/chosen": -0.6282618641853333,
601
- "rewards/margins": 0.4091278612613678,
602
- "rewards/rejected": -1.0373896360397339,
603
  "step": 380
604
  },
605
  {
606
- "epoch": 0.82,
607
- "learning_rate": 4.904486005914027e-08,
608
- "logits/chosen": 0.5063564777374268,
609
- "logits/rejected": 0.739707887172699,
610
- "logps/chosen": -478.1827697753906,
611
- "logps/rejected": -477.25738525390625,
612
- "loss": 0.0372,
613
- "rewards/accuracies": 0.731249988079071,
614
- "rewards/chosen": -0.7358786463737488,
615
- "rewards/margins": 0.45790591835975647,
616
- "rewards/rejected": -1.1937845945358276,
617
  "step": 390
618
  },
619
  {
620
- "epoch": 0.84,
621
- "learning_rate": 3.8702478614051345e-08,
622
- "logits/chosen": 0.6090542674064636,
623
- "logits/rejected": 0.7189727425575256,
624
- "logps/chosen": -408.47076416015625,
625
- "logps/rejected": -420.4701232910156,
626
- "loss": 0.0346,
627
- "rewards/accuracies": 0.6625000238418579,
628
- "rewards/chosen": -0.6165398359298706,
629
- "rewards/margins": 0.36181989312171936,
630
- "rewards/rejected": -0.9783598184585571,
631
- "step": 400
632
- },
633
- {
634
- "epoch": 0.84,
635
- "eval_logits/chosen": 0.6971995234489441,
636
- "eval_logits/rejected": 0.8171878457069397,
637
- "eval_logps/chosen": -418.0252990722656,
638
- "eval_logps/rejected": -479.08148193359375,
639
- "eval_loss": 0.041120681911706924,
640
- "eval_rewards/accuracies": 0.73828125,
641
- "eval_rewards/chosen": -0.5857407450675964,
642
- "eval_rewards/margins": 0.547980546951294,
643
- "eval_rewards/rejected": -1.1337212324142456,
644
- "eval_runtime": 73.8954,
645
- "eval_samples_per_second": 27.065,
646
- "eval_steps_per_second": 0.433,
647
  "step": 400
648
  },
649
- {
650
- "epoch": 0.86,
651
- "learning_rate": 2.9492720416985e-08,
652
- "logits/chosen": 0.5529159903526306,
653
- "logits/rejected": 0.6982699632644653,
654
- "logps/chosen": -420.51776123046875,
655
- "logps/rejected": -412.6045837402344,
656
- "loss": 0.039,
657
- "rewards/accuracies": 0.637499988079071,
658
- "rewards/chosen": -0.6656073927879333,
659
- "rewards/margins": 0.2726648449897766,
660
- "rewards/rejected": -0.9382721781730652,
661
- "step": 410
662
- },
663
- {
664
- "epoch": 0.88,
665
- "learning_rate": 2.1464952759020856e-08,
666
- "logits/chosen": 0.5957225561141968,
667
- "logits/rejected": 0.7298467755317688,
668
- "logps/chosen": -454.47247314453125,
669
- "logps/rejected": -440.4501037597656,
670
- "loss": 0.0388,
671
- "rewards/accuracies": 0.65625,
672
- "rewards/chosen": -0.7535709142684937,
673
- "rewards/margins": 0.26328498125076294,
674
- "rewards/rejected": -1.0168558359146118,
675
- "step": 420
676
- },
677
- {
678
- "epoch": 0.9,
679
- "learning_rate": 1.4662207078575684e-08,
680
- "logits/chosen": 0.6466183662414551,
681
- "logits/rejected": 0.7053841352462769,
682
- "logps/chosen": -408.7344970703125,
683
- "logps/rejected": -474.556396484375,
684
- "loss": 0.0374,
685
- "rewards/accuracies": 0.7562500238418579,
686
- "rewards/chosen": -0.6496707201004028,
687
- "rewards/margins": 0.49481192231178284,
688
- "rewards/rejected": -1.1444827318191528,
689
- "step": 430
690
- },
691
- {
692
- "epoch": 0.92,
693
- "learning_rate": 9.12094829893642e-09,
694
- "logits/chosen": 0.7082842588424683,
695
- "logits/rejected": 0.7902501821517944,
696
- "logps/chosen": -443.640869140625,
697
- "logps/rejected": -469.3601989746094,
698
- "loss": 0.0402,
699
- "rewards/accuracies": 0.6187499761581421,
700
- "rewards/chosen": -0.7194768786430359,
701
- "rewards/margins": 0.42178624868392944,
702
- "rewards/rejected": -1.1412632465362549,
703
- "step": 440
704
- },
705
- {
706
- "epoch": 0.94,
707
- "learning_rate": 4.8708793644441086e-09,
708
- "logits/chosen": 0.6541800498962402,
709
- "logits/rejected": 0.8258839845657349,
710
- "logps/chosen": -467.66455078125,
711
- "logps/rejected": -470.41375732421875,
712
- "loss": 0.0379,
713
- "rewards/accuracies": 0.6812499761581421,
714
- "rewards/chosen": -0.6918220520019531,
715
- "rewards/margins": 0.36053839325904846,
716
- "rewards/rejected": -1.0523602962493896,
717
- "step": 450
718
- },
719
- {
720
- "epoch": 0.96,
721
- "learning_rate": 1.9347820230782295e-09,
722
- "logits/chosen": 0.7120925188064575,
723
- "logits/rejected": 0.8568435907363892,
724
- "logps/chosen": -381.9484558105469,
725
- "logps/rejected": -405.51007080078125,
726
- "loss": 0.0376,
727
- "rewards/accuracies": 0.6875,
728
- "rewards/chosen": -0.5831388235092163,
729
- "rewards/margins": 0.39855244755744934,
730
- "rewards/rejected": -0.9816913604736328,
731
- "step": 460
732
- },
733
- {
734
- "epoch": 0.98,
735
- "learning_rate": 3.2839470889836627e-10,
736
- "logits/chosen": 0.6267755627632141,
737
- "logits/rejected": 0.7731589078903198,
738
- "logps/chosen": -405.1166076660156,
739
- "logps/rejected": -455.156982421875,
740
- "loss": 0.0393,
741
- "rewards/accuracies": 0.6812499761581421,
742
- "rewards/chosen": -0.6267203092575073,
743
- "rewards/margins": 0.4798026978969574,
744
- "rewards/rejected": -1.1065229177474976,
745
- "step": 470
746
- },
747
  {
748
  "epoch": 1.0,
749
- "step": 477,
750
  "total_flos": 0.0,
751
- "train_loss": 0.05354936925432717,
752
- "train_runtime": 4393.8172,
753
- "train_samples_per_second": 13.914,
754
- "train_steps_per_second": 0.109
755
  }
756
  ],
757
  "logging_steps": 10,
758
- "max_steps": 477,
759
  "num_train_epochs": 1,
760
  "save_steps": 1000,
761
  "total_flos": 0.0,
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.998766954377312,
5
+ "eval_steps": 1000,
6
+ "global_step": 405,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
  "epoch": 0.0,
13
+ "learning_rate": 1.2195121951219512e-08,
14
+ "logits/chosen": -2.8088459968566895,
15
+ "logits/rejected": -2.7595884799957275,
16
+ "logps/chosen": -368.90777587890625,
17
+ "logps/rejected": -133.10202026367188,
18
+ "loss": 0.4054,
19
  "rewards/accuracies": 0.0,
20
  "rewards/chosen": 0.0,
21
  "rewards/margins": 0.0,
 
24
  },
25
  {
26
  "epoch": 0.02,
27
+ "learning_rate": 1.219512195121951e-07,
28
+ "logits/chosen": -2.838838815689087,
29
+ "logits/rejected": -2.8251054286956787,
30
+ "logps/chosen": -433.8114318847656,
31
+ "logps/rejected": -114.71322631835938,
32
+ "loss": 0.3815,
33
+ "rewards/accuracies": 0.5694444179534912,
34
+ "rewards/chosen": 0.0011257152073085308,
35
+ "rewards/margins": 0.0019443891942501068,
36
+ "rewards/rejected": -0.0008186736959032714,
37
  "step": 10
38
  },
39
  {
40
+ "epoch": 0.05,
41
+ "learning_rate": 2.439024390243902e-07,
42
+ "logits/chosen": -2.798201560974121,
43
+ "logits/rejected": -2.7650632858276367,
44
+ "logps/chosen": -436.72210693359375,
45
+ "logps/rejected": -109.3458023071289,
46
+ "loss": 0.3794,
47
+ "rewards/accuracies": 0.7437499761581421,
48
+ "rewards/chosen": 0.02019491419196129,
49
+ "rewards/margins": 0.03630927950143814,
50
+ "rewards/rejected": -0.016114361584186554,
51
  "step": 20
52
  },
53
  {
54
+ "epoch": 0.07,
55
+ "learning_rate": 3.6585365853658536e-07,
56
+ "logits/chosen": -2.7168636322021484,
57
+ "logits/rejected": -2.6898279190063477,
58
+ "logps/chosen": -422.3126525878906,
59
+ "logps/rejected": -128.2278289794922,
60
+ "loss": 0.3417,
61
+ "rewards/accuracies": 0.7562500238418579,
62
+ "rewards/chosen": 0.07048428058624268,
63
+ "rewards/margins": 0.20025746524333954,
64
+ "rewards/rejected": -0.12977321445941925,
65
  "step": 30
66
  },
67
  {
68
+ "epoch": 0.1,
69
+ "learning_rate": 4.878048780487804e-07,
70
+ "logits/chosen": -2.591139554977417,
71
+ "logits/rejected": -2.57306170463562,
72
+ "logps/chosen": -396.5892333984375,
73
+ "logps/rejected": -139.44308471679688,
74
+ "loss": 0.2883,
75
+ "rewards/accuracies": 0.768750011920929,
76
+ "rewards/chosen": 0.0210564024746418,
77
+ "rewards/margins": 0.42175084352493286,
78
+ "rewards/rejected": -0.40069445967674255,
79
  "step": 40
80
  },
81
  {
82
+ "epoch": 0.12,
83
+ "learning_rate": 4.992461696250783e-07,
84
+ "logits/chosen": -2.4237170219421387,
85
+ "logits/rejected": -2.397566318511963,
86
+ "logps/chosen": -446.45684814453125,
87
+ "logps/rejected": -203.3081512451172,
88
+ "loss": 0.2012,
89
+ "rewards/accuracies": 0.8125,
90
+ "rewards/chosen": -0.04143618792295456,
91
+ "rewards/margins": 0.8411922454833984,
92
+ "rewards/rejected": -0.8826284408569336,
93
  "step": 50
94
  },
95
  {
96
+ "epoch": 0.15,
97
+ "learning_rate": 4.966461721767899e-07,
98
+ "logits/chosen": -2.3991150856018066,
99
+ "logits/rejected": -2.3474137783050537,
100
+ "logps/chosen": -426.8975524902344,
101
+ "logps/rejected": -257.33331298828125,
102
+ "loss": 0.1494,
103
+ "rewards/accuracies": 0.7437499761581421,
104
+ "rewards/chosen": -0.39810866117477417,
105
+ "rewards/margins": 0.9240871667861938,
106
+ "rewards/rejected": -1.3221957683563232,
107
  "step": 60
108
  },
109
  {
110
+ "epoch": 0.17,
111
+ "learning_rate": 4.922100518015975e-07,
112
+ "logits/chosen": -2.436988592147827,
113
+ "logits/rejected": -2.3888049125671387,
114
+ "logps/chosen": -421.7872619628906,
115
+ "logps/rejected": -276.4320068359375,
116
+ "loss": 0.1308,
117
+ "rewards/accuracies": 0.78125,
118
+ "rewards/chosen": -0.37923428416252136,
119
+ "rewards/margins": 1.1982433795928955,
120
+ "rewards/rejected": -1.5774776935577393,
121
  "step": 70
122
  },
123
  {
124
+ "epoch": 0.2,
125
+ "learning_rate": 4.859708325770919e-07,
126
+ "logits/chosen": -2.3866608142852783,
127
+ "logits/rejected": -2.3412399291992188,
128
+ "logps/chosen": -472.11474609375,
129
+ "logps/rejected": -319.96246337890625,
130
+ "loss": 0.0752,
131
+ "rewards/accuracies": 0.731249988079071,
132
+ "rewards/chosen": -0.8105772733688354,
133
+ "rewards/margins": 1.3323147296905518,
134
+ "rewards/rejected": -2.1428916454315186,
135
  "step": 80
136
  },
137
  {
138
+ "epoch": 0.22,
139
+ "learning_rate": 4.779749614980225e-07,
140
+ "logits/chosen": -2.380894899368286,
141
+ "logits/rejected": -2.3338356018066406,
142
+ "logps/chosen": -545.9353637695312,
143
+ "logps/rejected": -395.8908386230469,
144
+ "loss": 0.0595,
145
+ "rewards/accuracies": 0.8374999761581421,
146
+ "rewards/chosen": -0.6987307667732239,
147
+ "rewards/margins": 1.9613780975341797,
148
+ "rewards/rejected": -2.660108804702759,
149
  "step": 90
150
  },
151
  {
152
+ "epoch": 0.25,
153
+ "learning_rate": 4.682819627081427e-07,
154
+ "logits/chosen": -2.3579602241516113,
155
+ "logits/rejected": -2.295790195465088,
156
+ "logps/chosen": -480.7085876464844,
157
+ "logps/rejected": -364.87811279296875,
158
+ "loss": 0.074,
159
+ "rewards/accuracies": 0.84375,
160
+ "rewards/chosen": -0.6792080402374268,
161
+ "rewards/margins": 1.7849966287612915,
162
+ "rewards/rejected": -2.464204788208008,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
163
  "step": 100
164
  },
165
  {
166
+ "epoch": 0.27,
167
+ "learning_rate": 4.569639943810477e-07,
168
+ "logits/chosen": -2.3346972465515137,
169
+ "logits/rejected": -2.265590190887451,
170
+ "logps/chosen": -502.68487548828125,
171
+ "logps/rejected": -394.2782287597656,
172
+ "loss": 0.0555,
173
+ "rewards/accuracies": 0.7749999761581421,
174
+ "rewards/chosen": -0.9552167654037476,
175
+ "rewards/margins": 1.8180055618286133,
176
+ "rewards/rejected": -2.7732224464416504,
177
  "step": 110
178
  },
179
  {
180
+ "epoch": 0.3,
181
+ "learning_rate": 4.4410531154874543e-07,
182
+ "logits/chosen": -2.359708547592163,
183
+ "logits/rejected": -2.275885820388794,
184
+ "logps/chosen": -540.5257568359375,
185
+ "logps/rejected": -415.78570556640625,
186
+ "loss": 0.0608,
187
+ "rewards/accuracies": 0.793749988079071,
188
+ "rewards/chosen": -0.8868741989135742,
189
+ "rewards/margins": 1.965667486190796,
190
+ "rewards/rejected": -2.852541923522949,
191
  "step": 120
192
  },
193
  {
194
+ "epoch": 0.32,
195
+ "learning_rate": 4.298016388768561e-07,
196
+ "logits/chosen": -2.431809902191162,
197
+ "logits/rejected": -2.36917781829834,
198
+ "logps/chosen": -497.15985107421875,
199
+ "logps/rejected": -360.4634094238281,
200
+ "loss": 0.0746,
201
+ "rewards/accuracies": 0.862500011920929,
202
+ "rewards/chosen": -0.3195730745792389,
203
+ "rewards/margins": 2.053260326385498,
204
+ "rewards/rejected": -2.372833251953125,
205
  "step": 130
206
  },
207
  {
208
+ "epoch": 0.35,
209
+ "learning_rate": 4.1415945805573005e-07,
210
+ "logits/chosen": -2.3186304569244385,
211
+ "logits/rejected": -2.2435660362243652,
212
+ "logps/chosen": -503.1153259277344,
213
+ "logps/rejected": -406.16278076171875,
214
+ "loss": 0.0659,
215
+ "rewards/accuracies": 0.8125,
216
+ "rewards/chosen": -0.8214370012283325,
217
+ "rewards/margins": 1.914272665977478,
218
+ "rewards/rejected": -2.7357096672058105,
219
  "step": 140
220
  },
221
  {
222
+ "epoch": 0.37,
223
+ "learning_rate": 3.972952151123984e-07,
224
+ "logits/chosen": -2.282636880874634,
225
+ "logits/rejected": -2.1880698204040527,
226
+ "logps/chosen": -486.3431091308594,
227
+ "logps/rejected": -408.52734375,
228
+ "loss": 0.0508,
229
+ "rewards/accuracies": 0.793749988079071,
230
+ "rewards/chosen": -1.11625075340271,
231
+ "rewards/margins": 1.9597688913345337,
232
+ "rewards/rejected": -3.076019287109375,
233
  "step": 150
234
  },
235
  {
236
+ "epoch": 0.39,
237
+ "learning_rate": 3.793344535444142e-07,
238
+ "logits/chosen": -2.278097629547119,
239
+ "logits/rejected": -2.1780576705932617,
240
+ "logps/chosen": -555.6715087890625,
241
+ "logps/rejected": -414.88861083984375,
242
+ "loss": 0.0418,
243
+ "rewards/accuracies": 0.824999988079071,
244
+ "rewards/chosen": -0.8848897218704224,
245
+ "rewards/margins": 2.1523947715759277,
246
+ "rewards/rejected": -3.0372846126556396,
247
  "step": 160
248
  },
249
  {
250
+ "epoch": 0.42,
251
+ "learning_rate": 3.604108797288461e-07,
252
+ "logits/chosen": -2.327190637588501,
253
+ "logits/rejected": -2.240990400314331,
254
+ "logps/chosen": -523.722900390625,
255
+ "logps/rejected": -402.6468200683594,
256
+ "loss": 0.0573,
257
+ "rewards/accuracies": 0.84375,
258
+ "rewards/chosen": -0.8474733233451843,
259
+ "rewards/margins": 2.0742928981781006,
260
+ "rewards/rejected": -2.9217662811279297,
261
  "step": 170
262
  },
263
  {
264
+ "epoch": 0.44,
265
+ "learning_rate": 3.40665367563858e-07,
266
+ "logits/chosen": -2.2963194847106934,
267
+ "logits/rejected": -2.2069220542907715,
268
+ "logps/chosen": -533.5665283203125,
269
+ "logps/rejected": -434.58074951171875,
270
+ "loss": 0.0479,
271
+ "rewards/accuracies": 0.7875000238418579,
272
+ "rewards/chosen": -1.2346763610839844,
273
+ "rewards/margins": 1.9557201862335205,
274
+ "rewards/rejected": -3.1903960704803467,
275
  "step": 180
276
  },
277
  {
278
+ "epoch": 0.47,
279
+ "learning_rate": 3.202449097526798e-07,
280
+ "logits/chosen": -2.303617000579834,
281
+ "logits/rejected": -2.2251999378204346,
282
+ "logps/chosen": -511.34063720703125,
283
+ "logps/rejected": -417.365966796875,
284
+ "loss": 0.0478,
285
+ "rewards/accuracies": 0.8125,
286
+ "rewards/chosen": -1.0919907093048096,
287
+ "rewards/margins": 2.0082223415374756,
288
+ "rewards/rejected": -3.100213050842285,
289
  "step": 190
290
  },
291
  {
292
+ "epoch": 0.49,
293
+ "learning_rate": 2.993015235369905e-07,
294
+ "logits/chosen": -2.2632386684417725,
295
+ "logits/rejected": -2.1550886631011963,
296
+ "logps/chosen": -555.7200317382812,
297
+ "logps/rejected": -457.74981689453125,
298
+ "loss": 0.0439,
299
+ "rewards/accuracies": 0.831250011920929,
300
+ "rewards/chosen": -1.16446852684021,
301
+ "rewards/margins": 2.234539270401001,
302
+ "rewards/rejected": -3.399007797241211,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
303
  "step": 200
304
  },
305
  {
306
+ "epoch": 0.52,
307
+ "learning_rate": 2.7799111902582693e-07,
308
+ "logits/chosen": -2.273411512374878,
309
+ "logits/rejected": -2.172680377960205,
310
+ "logps/chosen": -526.6717529296875,
311
+ "logps/rejected": -403.1504211425781,
312
+ "loss": 0.0448,
313
+ "rewards/accuracies": 0.731249988079071,
314
+ "rewards/chosen": -1.261858582496643,
315
+ "rewards/margins": 1.7486225366592407,
316
+ "rewards/rejected": -3.010481119155884,
317
  "step": 210
318
  },
319
  {
320
+ "epoch": 0.54,
321
+ "learning_rate": 2.564723385445869e-07,
322
+ "logits/chosen": -2.3388514518737793,
323
+ "logits/rejected": -2.263075351715088,
324
+ "logps/chosen": -517.6388549804688,
325
+ "logps/rejected": -412.77325439453125,
326
+ "loss": 0.0602,
327
+ "rewards/accuracies": 0.831250011920929,
328
+ "rewards/chosen": -1.0001862049102783,
329
+ "rewards/margins": 1.8844444751739502,
330
+ "rewards/rejected": -2.8846306800842285,
331
  "step": 220
332
  },
333
  {
334
+ "epoch": 0.57,
335
+ "learning_rate": 2.3490537564442845e-07,
336
+ "logits/chosen": -2.295351982116699,
337
+ "logits/rejected": -2.193934202194214,
338
+ "logps/chosen": -507.52520751953125,
339
+ "logps/rejected": -393.0706481933594,
340
+ "loss": 0.0637,
341
+ "rewards/accuracies": 0.7562500238418579,
342
+ "rewards/chosen": -1.1557964086532593,
343
+ "rewards/margins": 1.709519386291504,
344
+ "rewards/rejected": -2.8653159141540527,
345
  "step": 230
346
  },
347
  {
348
+ "epoch": 0.59,
349
+ "learning_rate": 2.1345078256378801e-07,
350
+ "logits/chosen": -2.326420783996582,
351
+ "logits/rejected": -2.23372220993042,
352
+ "logps/chosen": -512.0640258789062,
353
+ "logps/rejected": -428.93572998046875,
354
+ "loss": 0.051,
355
+ "rewards/accuracies": 0.800000011920929,
356
+ "rewards/chosen": -1.0325157642364502,
357
+ "rewards/margins": 2.0758230686187744,
358
+ "rewards/rejected": -3.1083388328552246,
359
  "step": 240
360
  },
361
  {
362
+ "epoch": 0.62,
363
+ "learning_rate": 1.9226827501969865e-07,
364
+ "logits/chosen": -2.324457883834839,
365
+ "logits/rejected": -2.2472641468048096,
366
+ "logps/chosen": -543.7798461914062,
367
+ "logps/rejected": -454.26043701171875,
368
+ "loss": 0.0521,
369
+ "rewards/accuracies": 0.824999988079071,
370
+ "rewards/chosen": -1.0110582113265991,
371
+ "rewards/margins": 2.3495380878448486,
372
+ "rewards/rejected": -3.360596179962158,
373
  "step": 250
374
  },
375
  {
376
+ "epoch": 0.64,
377
+ "learning_rate": 1.715155432264775e-07,
378
+ "logits/chosen": -2.316281795501709,
379
+ "logits/rejected": -2.235330581665039,
380
+ "logps/chosen": -547.55908203125,
381
+ "logps/rejected": -448.2779235839844,
382
+ "loss": 0.0399,
383
+ "rewards/accuracies": 0.8187500238418579,
384
+ "rewards/chosen": -1.1552385091781616,
385
+ "rewards/margins": 2.1640262603759766,
386
+ "rewards/rejected": -3.3192646503448486,
387
  "step": 260
388
  },
389
  {
390
+ "epoch": 0.67,
391
+ "learning_rate": 1.51347077992983e-07,
392
+ "logits/chosen": -2.301753520965576,
393
+ "logits/rejected": -2.2307753562927246,
394
+ "logps/chosen": -540.0494384765625,
395
+ "logps/rejected": -464.4815368652344,
396
+ "loss": 0.0388,
397
+ "rewards/accuracies": 0.8125,
398
+ "rewards/chosen": -1.3635069131851196,
399
+ "rewards/margins": 2.057849645614624,
400
+ "rewards/rejected": -3.421356678009033,
401
  "step": 270
402
  },
403
  {
404
+ "epoch": 0.69,
405
+ "learning_rate": 1.3191302063739906e-07,
406
+ "logits/chosen": -2.272491931915283,
407
+ "logits/rejected": -2.201686382293701,
408
+ "logps/chosen": -516.8363037109375,
409
+ "logps/rejected": -447.940185546875,
410
+ "loss": 0.0355,
411
+ "rewards/accuracies": 0.8062499761581421,
412
+ "rewards/chosen": -1.376404881477356,
413
+ "rewards/margins": 1.9720706939697266,
414
+ "rewards/rejected": -3.348475694656372,
415
  "step": 280
416
  },
417
  {
418
+ "epoch": 0.72,
419
+ "learning_rate": 1.1335804528119475e-07,
420
+ "logits/chosen": -2.3611927032470703,
421
+ "logits/rejected": -2.2538418769836426,
422
+ "logps/chosen": -550.6755981445312,
423
+ "logps/rejected": -446.7557678222656,
424
+ "loss": 0.0427,
425
+ "rewards/accuracies": 0.8125,
426
+ "rewards/chosen": -1.1491652727127075,
427
+ "rewards/margins": 2.311260461807251,
428
+ "rewards/rejected": -3.460425615310669,
429
  "step": 290
430
  },
431
  {
432
+ "epoch": 0.74,
433
+ "learning_rate": 9.582028184286423e-08,
434
+ "logits/chosen": -2.2688956260681152,
435
+ "logits/rejected": -2.2058238983154297,
436
+ "logps/chosen": -497.08392333984375,
437
+ "logps/rejected": -457.6719665527344,
438
+ "loss": 0.0469,
439
+ "rewards/accuracies": 0.762499988079071,
440
+ "rewards/chosen": -1.372286319732666,
441
+ "rewards/margins": 1.9885644912719727,
442
+ "rewards/rejected": -3.3608508110046387,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
443
  "step": 300
444
  },
445
  {
446
+ "epoch": 0.76,
447
+ "learning_rate": 7.943028774907065e-08,
448
+ "logits/chosen": -2.2832024097442627,
449
+ "logits/rejected": -2.215949535369873,
450
+ "logps/chosen": -493.197021484375,
451
+ "logps/rejected": -424.94073486328125,
452
+ "loss": 0.0521,
453
+ "rewards/accuracies": 0.831250011920929,
454
+ "rewards/chosen": -1.0872572660446167,
455
+ "rewards/margins": 1.9770004749298096,
456
+ "rewards/rejected": -3.0642576217651367,
457
  "step": 310
458
  },
459
  {
460
+ "epoch": 0.79,
461
+ "learning_rate": 6.431007601814637e-08,
462
+ "logits/chosen": -2.300029993057251,
463
+ "logits/rejected": -2.244724750518799,
464
+ "logps/chosen": -453.86981201171875,
465
+ "logps/rejected": -416.4488220214844,
466
+ "loss": 0.0435,
467
+ "rewards/accuracies": 0.824999988079071,
468
+ "rewards/chosen": -1.2616424560546875,
469
+ "rewards/margins": 1.8299839496612549,
470
+ "rewards/rejected": -3.0916266441345215,
471
  "step": 320
472
  },
473
  {
474
+ "epoch": 0.81,
475
+ "learning_rate": 5.0572206951246e-08,
476
+ "logits/chosen": -2.273084878921509,
477
+ "logits/rejected": -2.188479423522949,
478
+ "logps/chosen": -499.99957275390625,
479
+ "logps/rejected": -427.8397521972656,
480
+ "loss": 0.046,
481
+ "rewards/accuracies": 0.793749988079071,
482
+ "rewards/chosen": -1.324517011642456,
483
+ "rewards/margins": 1.8908493518829346,
484
+ "rewards/rejected": -3.215366840362549,
485
  "step": 330
486
  },
487
  {
488
+ "epoch": 0.84,
489
+ "learning_rate": 3.831895019292897e-08,
490
+ "logits/chosen": -2.3347887992858887,
491
+ "logits/rejected": -2.2554373741149902,
492
+ "logps/chosen": -548.2373046875,
493
+ "logps/rejected": -488.4436950683594,
494
+ "loss": 0.0447,
495
+ "rewards/accuracies": 0.831250011920929,
496
+ "rewards/chosen": -1.1382402181625366,
497
+ "rewards/margins": 2.5688745975494385,
498
+ "rewards/rejected": -3.7071146965026855,
499
  "step": 340
500
  },
501
  {
502
+ "epoch": 0.86,
503
+ "learning_rate": 2.764152339909756e-08,
504
+ "logits/chosen": -2.279545545578003,
505
+ "logits/rejected": -2.195236921310425,
506
+ "logps/chosen": -536.1104736328125,
507
+ "logps/rejected": -410.069091796875,
508
+ "loss": 0.0451,
509
+ "rewards/accuracies": 0.800000011920929,
510
+ "rewards/chosen": -1.1084119081497192,
511
+ "rewards/margins": 2.0049660205841064,
512
+ "rewards/rejected": -3.1133780479431152,
513
  "step": 350
514
  },
515
  {
516
+ "epoch": 0.89,
517
+ "learning_rate": 1.861941317991664e-08,
518
+ "logits/chosen": -2.3270392417907715,
519
+ "logits/rejected": -2.2122137546539307,
520
+ "logps/chosen": -558.4454956054688,
521
+ "logps/rejected": -451.0440979003906,
522
+ "loss": 0.0438,
523
+ "rewards/accuracies": 0.875,
524
+ "rewards/chosen": -1.0215061902999878,
525
+ "rewards/margins": 2.3432884216308594,
526
+ "rewards/rejected": -3.3647942543029785,
527
  "step": 360
528
  },
529
  {
530
+ "epoch": 0.91,
531
+ "learning_rate": 1.13197833728636e-08,
532
+ "logits/chosen": -2.287353038787842,
533
+ "logits/rejected": -2.2039966583251953,
534
+ "logps/chosen": -510.3124084472656,
535
+ "logps/rejected": -463.5337829589844,
536
+ "loss": 0.0384,
537
+ "rewards/accuracies": 0.875,
538
+ "rewards/chosen": -1.076358437538147,
539
+ "rewards/margins": 2.4394357204437256,
540
+ "rewards/rejected": -3.515794277191162,
541
  "step": 370
542
  },
543
  {
544
+ "epoch": 0.94,
545
+ "learning_rate": 5.79697505093521e-09,
546
+ "logits/chosen": -2.2827162742614746,
547
+ "logits/rejected": -2.1960558891296387,
548
+ "logps/chosen": -526.398681640625,
549
+ "logps/rejected": -435.3667907714844,
550
+ "loss": 0.0513,
551
+ "rewards/accuracies": 0.7749999761581421,
552
+ "rewards/chosen": -1.2410168647766113,
553
+ "rewards/margins": 2.0592200756073,
554
+ "rewards/rejected": -3.3002371788024902,
555
  "step": 380
556
  },
557
  {
558
+ "epoch": 0.96,
559
+ "learning_rate": 2.092101988131256e-09,
560
+ "logits/chosen": -2.332719087600708,
561
+ "logits/rejected": -2.206247568130493,
562
+ "logps/chosen": -562.2529296875,
563
+ "logps/rejected": -459.3744201660156,
564
+ "loss": 0.0425,
565
+ "rewards/accuracies": 0.856249988079071,
566
+ "rewards/chosen": -0.9911445379257202,
567
+ "rewards/margins": 2.511375665664673,
568
+ "rewards/rejected": -3.5025200843811035,
569
  "step": 390
570
  },
571
  {
572
+ "epoch": 0.99,
573
+ "learning_rate": 2.327445937151673e-10,
574
+ "logits/chosen": -2.319377899169922,
575
+ "logits/rejected": -2.2350213527679443,
576
+ "logps/chosen": -558.1907958984375,
577
+ "logps/rejected": -479.43963623046875,
578
+ "loss": 0.0443,
579
+ "rewards/accuracies": 0.831250011920929,
580
+ "rewards/chosen": -1.0957250595092773,
581
+ "rewards/margins": 2.4137606620788574,
582
+ "rewards/rejected": -3.5094857215881348,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
583
  "step": 400
584
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
585
  {
586
  "epoch": 1.0,
587
+ "step": 405,
588
  "total_flos": 0.0,
589
+ "train_loss": 0.08838768833213383,
590
+ "train_runtime": 3226.1286,
591
+ "train_samples_per_second": 16.086,
592
+ "train_steps_per_second": 0.126
593
  }
594
  ],
595
  "logging_steps": 10,
596
+ "max_steps": 405,
597
  "num_train_epochs": 1,
598
  "save_steps": 1000,
599
  "total_flos": 0.0,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:395bded4be913dd2b09c1ba28262c6a1bac69378c9457ea26d019bd947041e28
3
  size 5944
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6fdb171dbedd3c33d747caa4f7d5a15337333684182e1da435907164da14510
3
  size 5944