Hugging Face's logo

wzhouad
/
zephyr-7b-dpo-full

Text Generation
Transformers
Safetensors
llama
trl
dpo
Generated from Trainer
conversational
Inference Endpoints
text-generation-inference
Model card Files Community
wzhouad commited on
Commit
da2a870
•
1 Parent(s): 95acbb9

Model save

Browse files
Files changed (15) hide show
  1. README.md +20 -6
  2. all_results.json +5 -5
  3. config.json +12 -10
  4. generation_config.json +5 -2
  5. model-00001-of-00004.safetensors +1 -1
  6. model-00002-of-00004.safetensors +1 -1
  7. model-00003-of-00004.safetensors +1 -1
  8. model-00004-of-00004.safetensors +1 -1
  9. model.safetensors.index.json +292 -292
  10. special_tokens_map.json +3 -21
  11. tokenizer.json +0 -0
  12. tokenizer_config.json +2039 -24
  13. train_results.json +5 -5
  14. trainer_state.json +615 -453
  15. training_args.bin +2 -2
README.md CHANGED
@@ -1,6 +1,4 @@
1
  ---
2
- license: mit
3
- base_model: HuggingFaceH4/mistral-7b-sft-beta
4
  tags:
5
  - trl
6
  - dpo
@@ -15,7 +13,17 @@ should probably proofread and complete it, then remove this comment. -->
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
 
@@ -35,12 +43,12 @@ More information needed
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: 1
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
@@ -50,6 +58,12 @@ The following hyperparameters were used during training:
50
 
51
  ### Training results
52
 
 
 
 
 
 
 
53
 
54
 
55
  ### Framework versions
 
1
  ---
 
 
2
  tags:
3
  - trl
4
  - dpo
 
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: 0.5158
19
+ - Rewards/chosen: -1.1004
20
+ - Rewards/rejected: -1.9518
21
+ - Rewards/accuracies: 0.7734
22
+ - Rewards/margins: 0.8514
23
+ - Logps/rejected: -584.4573
24
+ - Logps/chosen: -493.1730
25
+ - Logits/rejected: 0.6183
26
+ - Logits/chosen: 0.4916
27
 
28
  ## Model description
29
 
 
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
 
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
+ | 0.5824 | 0.21 | 100 | 0.5818 | -0.0931 | -0.5163 | 0.7461 | 0.4232 | -440.9000 | -392.4388 | 0.7087 | 0.6273 |
64
+ | 0.5501 | 0.42 | 200 | 0.5347 | -0.5406 | -1.2460 | 0.7773 | 0.7055 | -513.8766 | -437.1852 | 1.2047 | 1.0554 |
65
+ | 0.5149 | 0.63 | 300 | 0.5204 | -0.9040 | -1.6985 | 0.7773 | 0.7944 | -559.1196 | -473.5317 | 0.8648 | 0.7274 |
66
+ | 0.5002 | 0.84 | 400 | 0.5158 | -1.1004 | -1.9518 | 0.7734 | 0.8514 | -584.4573 | -493.1730 | 0.6183 | 0.4916 |
67
 
68
 
69
  ### Framework versions
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 1.0,
3
- "train_loss": 0.0941658933221558,
4
- "train_runtime": 3198.7545,
5
- "train_samples": 51894,
6
- "train_samples_per_second": 16.223,
7
- "train_steps_per_second": 0.127
8
  }
 
1
  {
2
  "epoch": 1.0,
3
+ "train_loss": 0.5470197245759784,
4
+ "train_runtime": 4302.1619,
5
+ "train_samples": 61134,
6
+ "train_samples_per_second": 14.21,
7
+ "train_steps_per_second": 0.111
8
  }
config.json CHANGED
@@ -1,26 +1,28 @@
1
  {
2
- "_name_or_path": "HuggingFaceH4/mistral-7b-sft-beta",
3
  "architectures": [
4
- "MistralForCausalLM"
5
  ],
 
6
  "attention_dropout": 0.0,
7
- "bos_token_id": 1,
8
- "eos_token_id": 2,
9
  "hidden_act": "silu",
10
  "hidden_size": 4096,
11
  "initializer_range": 0.02,
12
  "intermediate_size": 14336,
13
- "max_position_embeddings": 32768,
14
- "model_type": "mistral",
15
  "num_attention_heads": 32,
16
  "num_hidden_layers": 32,
17
  "num_key_value_heads": 8,
 
18
  "rms_norm_eps": 1e-05,
19
- "rope_theta": 10000.0,
20
- "sliding_window": 4096,
21
  "tie_word_embeddings": false,
22
  "torch_dtype": "bfloat16",
23
- "transformers_version": "4.41.1",
24
  "use_cache": false,
25
- "vocab_size": 32000
26
  }
 
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": 128001,
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
  }
generation_config.json CHANGED
@@ -1,6 +1,9 @@
1
  {
2
  "_from_model_config": true,
3
- "bos_token_id": 1,
4
- "eos_token_id": 2,
 
 
 
5
  "transformers_version": "4.35.2"
6
  }
 
1
  {
2
  "_from_model_config": true,
3
+ "bos_token_id": 128000,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128009
7
+ ],
8
  "transformers_version": "4.35.2"
9
  }
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4c40135c559cd509c92d1101c4af20bab36d4c580836a4981b6af93072e2bb04
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63cbba2984d9a52a527f5b739e24e1d29f4bfea5b1d5fe047236f2e5bb697ed9
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9d23d54700ec4d7fe04409e5adcd569e1ba8a83a51d001125a7005adffa3e3b0
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b319bfc010c4914566d0b6bc0c479e0aa8fb1a0c2f77e7c34c730489b5f6e08a
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4c2ee4663aa8da7aba8fac2c57a51c205569ea8d00ec184c54861d631afe50c7
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61ff394563b7dc160da54407cf9271932651f2c46162cb40a96f3c03eb714042
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3456f0da74749cf668b4f49e75f007c427425c4cde826a048702ed0bd89bc39b
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:086f60bdeaa9cbbf5a58bee5a9c486786cf5fa61d7db040a4216c6e721a6f47b
3
  size 1168138808
model.safetensors.index.json CHANGED
@@ -1,298 +1,298 @@
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
  }
 
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
  }
special_tokens_map.json CHANGED
@@ -1,35 +1,17 @@
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
  }
 
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": "<|end_of_text|>",
11
  "lstrip": false,
12
  "normalized": false,
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
+ "pad_token": "<|end_of_text|>"
 
 
 
 
 
 
 
 
 
 
 
 
 
17
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,25 +1,2047 @@
1
  {
2
- "add_bos_token": true,
3
- "add_eos_token": false,
4
  "added_tokens_decoder": {
5
- "0": {
6
- "content": "<unk>",
7
  "lstrip": false,
8
  "normalized": false,
9
  "rstrip": false,
10
  "single_word": false,
11
  "special": true
12
  },
13
- "1": {
14
- "content": "<s>",
15
  "lstrip": false,
16
  "normalized": false,
17
  "rstrip": false,
18
  "single_word": false,
19
  "special": true
20
  },
21
- "2": {
22
- "content": "</s>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
23
  "lstrip": false,
24
  "normalized": false,
25
  "rstrip": false,
@@ -27,22 +2049,15 @@
27
  "special": true
28
  }
29
  },
30
- "additional_special_tokens": [
31
- "<unk>",
32
- "<s>",
33
- "</s>"
 
 
 
34
  ],
35
- "bos_token": "<s>",
36
- "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 %}",
37
- "clean_up_tokenization_spaces": false,
38
- "eos_token": "</s>",
39
- "legacy": true,
40
  "model_max_length": 2048,
41
- "pad_token": "</s>",
42
- "sp_model_kwargs": {},
43
- "spaces_between_special_tokens": false,
44
- "tokenizer_class": "LlamaTokenizer",
45
- "truncation_side": "left",
46
- "unk_token": "<unk>",
47
- "use_default_system_prompt": true
48
  }
 
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
  "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": "<|end_of_text|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
  ],
 
 
 
 
 
2060
  "model_max_length": 2048,
2061
+ "pad_token": "<|end_of_text|>",
2062
+ "tokenizer_class": "PreTrainedTokenizerFast"
 
 
 
 
 
2063
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 1.0,
3
- "train_loss": 0.0941658933221558,
4
- "train_runtime": 3198.7545,
5
- "train_samples": 51894,
6
- "train_samples_per_second": 16.223,
7
- "train_steps_per_second": 0.127
8
  }
 
1
  {
2
  "epoch": 1.0,
3
+ "train_loss": 0.5470197245759784,
4
+ "train_runtime": 4302.1619,
5
+ "train_samples": 61134,
6
+ "train_samples_per_second": 14.21,
7
+ "train_steps_per_second": 0.111
8
  }
trainer_state.json CHANGED
@@ -1,21 +1,21 @@
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": -2.769179582595825,
15
- "logits/rejected": -2.6384379863739014,
16
- "logps/chosen": -511.7125244140625,
17
- "logps/rejected": -154.70135498046875,
18
- "loss": 0.404,
19
  "rewards/accuracies": 0.0,
20
  "rewards/chosen": 0.0,
21
  "rewards/margins": 0.0,
@@ -24,576 +24,738 @@
24
  },
25
  {
26
  "epoch": 0.02,
27
- "learning_rate": 1.219512195121951e-07,
28
- "logits/chosen": -2.749405860900879,
29
- "logits/rejected": -2.719856023788452,
30
- "logps/chosen": -350.1585693359375,
31
- "logps/rejected": -113.84354400634766,
32
- "loss": 0.4139,
33
- "rewards/accuracies": 0.5416666865348816,
34
- "rewards/chosen": 0.0008429777226410806,
35
- "rewards/margins": 0.0010793738765642047,
36
- "rewards/rejected": -0.00023639613937120885,
37
  "step": 10
38
  },
39
  {
40
- "epoch": 0.05,
41
- "learning_rate": 2.439024390243902e-07,
42
- "logits/chosen": -2.73571515083313,
43
- "logits/rejected": -2.6977219581604004,
44
- "logps/chosen": -417.782470703125,
45
- "logps/rejected": -126.04759216308594,
46
- "loss": 0.4049,
47
- "rewards/accuracies": 0.7875000238418579,
48
- "rewards/chosen": 0.016058258712291718,
49
- "rewards/margins": 0.03098892793059349,
50
- "rewards/rejected": -0.014930667355656624,
51
  "step": 20
52
  },
53
  {
54
- "epoch": 0.07,
55
- "learning_rate": 3.6585365853658536e-07,
56
- "logits/chosen": -2.702385663986206,
57
- "logits/rejected": -2.697525978088379,
58
- "logps/chosen": -394.1095275878906,
59
- "logps/rejected": -112.09039306640625,
60
- "loss": 0.3743,
61
- "rewards/accuracies": 0.7749999761581421,
62
- "rewards/chosen": 0.06878620386123657,
63
- "rewards/margins": 0.18365943431854248,
64
- "rewards/rejected": -0.1148732453584671,
65
  "step": 30
66
  },
67
  {
68
- "epoch": 0.1,
69
- "learning_rate": 4.878048780487804e-07,
70
- "logits/chosen": -2.5501210689544678,
71
- "logits/rejected": -2.552663564682007,
72
- "logps/chosen": -388.2345886230469,
73
- "logps/rejected": -162.63467407226562,
74
- "loss": 0.3262,
75
- "rewards/accuracies": 0.762499988079071,
76
- "rewards/chosen": 0.029630392789840698,
77
- "rewards/margins": 0.4065938889980316,
78
- "rewards/rejected": -0.3769634962081909,
79
  "step": 40
80
  },
81
  {
82
- "epoch": 0.12,
83
- "learning_rate": 4.992461696250783e-07,
84
- "logits/chosen": -2.4305217266082764,
85
- "logits/rejected": -2.392930269241333,
86
- "logps/chosen": -440.9734802246094,
87
- "logps/rejected": -206.6797637939453,
88
- "loss": 0.2285,
89
- "rewards/accuracies": 0.8187500238418579,
90
- "rewards/chosen": -0.08316043764352798,
91
- "rewards/margins": 0.8042293787002563,
92
- "rewards/rejected": -0.8873898386955261,
93
  "step": 50
94
  },
95
  {
96
- "epoch": 0.15,
97
- "learning_rate": 4.966461721767899e-07,
98
- "logits/chosen": -2.391573905944824,
99
- "logits/rejected": -2.3458428382873535,
100
- "logps/chosen": -424.9759826660156,
101
- "logps/rejected": -236.65383911132812,
102
- "loss": 0.1605,
103
- "rewards/accuracies": 0.800000011920929,
104
- "rewards/chosen": -0.31609517335891724,
105
- "rewards/margins": 1.0237308740615845,
106
- "rewards/rejected": -1.339825987815857,
107
  "step": 60
108
  },
109
  {
110
- "epoch": 0.17,
111
- "learning_rate": 4.922100518015975e-07,
112
- "logits/chosen": -2.407805919647217,
113
- "logits/rejected": -2.3776707649230957,
114
- "logps/chosen": -444.9681091308594,
115
- "logps/rejected": -296.48907470703125,
116
- "loss": 0.1412,
117
- "rewards/accuracies": 0.762499988079071,
118
- "rewards/chosen": -0.5001243948936462,
119
- "rewards/margins": 1.270570158958435,
120
- "rewards/rejected": -1.7706947326660156,
121
  "step": 70
122
  },
123
  {
124
- "epoch": 0.2,
125
- "learning_rate": 4.859708325770919e-07,
126
- "logits/chosen": -2.3743772506713867,
127
- "logits/rejected": -2.347168445587158,
128
- "logps/chosen": -486.147705078125,
129
- "logps/rejected": -377.94305419921875,
130
- "loss": 0.0952,
131
  "rewards/accuracies": 0.737500011920929,
132
- "rewards/chosen": -0.8871649503707886,
133
- "rewards/margins": 1.4962456226348877,
134
- "rewards/rejected": -2.383410692214966,
135
  "step": 80
136
  },
137
  {
138
- "epoch": 0.22,
139
- "learning_rate": 4.779749614980225e-07,
140
- "logits/chosen": -2.3625094890594482,
141
- "logits/rejected": -2.297888994216919,
142
- "logps/chosen": -548.0413818359375,
143
- "logps/rejected": -374.68414306640625,
144
- "loss": 0.0643,
145
- "rewards/accuracies": 0.8125,
146
- "rewards/chosen": -0.5059229135513306,
147
- "rewards/margins": 1.9910331964492798,
148
- "rewards/rejected": -2.4969563484191895,
149
  "step": 90
150
  },
151
  {
152
- "epoch": 0.25,
153
- "learning_rate": 4.682819627081427e-07,
154
- "logits/chosen": -2.3414599895477295,
155
- "logits/rejected": -2.235891819000244,
156
- "logps/chosen": -536.3428955078125,
157
- "logps/rejected": -393.3332214355469,
158
- "loss": 0.0729,
159
- "rewards/accuracies": 0.8187500238418579,
160
- "rewards/chosen": -0.8122690916061401,
161
- "rewards/margins": 2.01526141166687,
162
- "rewards/rejected": -2.827530860900879,
163
  "step": 100
164
  },
165
  {
166
- "epoch": 0.27,
167
- "learning_rate": 4.569639943810477e-07,
168
- "logits/chosen": -2.2909626960754395,
169
- "logits/rejected": -2.1928114891052246,
170
- "logps/chosen": -536.5721435546875,
171
- "logps/rejected": -382.51336669921875,
172
- "loss": 0.056,
173
- "rewards/accuracies": 0.78125,
174
- "rewards/chosen": -0.9610284566879272,
175
- "rewards/margins": 1.7903772592544556,
176
- "rewards/rejected": -2.7514054775238037,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
177
  "step": 110
178
  },
179
  {
180
- "epoch": 0.3,
181
- "learning_rate": 4.4410531154874543e-07,
182
- "logits/chosen": -2.2632639408111572,
183
- "logits/rejected": -2.1712543964385986,
184
- "logps/chosen": -526.7481689453125,
185
- "logps/rejected": -429.66998291015625,
186
- "loss": 0.0474,
187
- "rewards/accuracies": 0.7562500238418579,
188
- "rewards/chosen": -1.3309078216552734,
189
- "rewards/margins": 1.883313775062561,
190
- "rewards/rejected": -3.214221477508545,
191
  "step": 120
192
  },
193
  {
194
- "epoch": 0.32,
195
- "learning_rate": 4.298016388768561e-07,
196
- "logits/chosen": -2.267120599746704,
197
- "logits/rejected": -2.1491141319274902,
198
- "logps/chosen": -495.79510498046875,
199
- "logps/rejected": -405.3984375,
200
- "loss": 0.0644,
201
- "rewards/accuracies": 0.8125,
202
- "rewards/chosen": -1.2485311031341553,
203
- "rewards/margins": 1.7459933757781982,
204
- "rewards/rejected": -2.9945242404937744,
205
  "step": 130
206
  },
207
  {
208
- "epoch": 0.35,
209
- "learning_rate": 4.1415945805573005e-07,
210
- "logits/chosen": -2.3223276138305664,
211
- "logits/rejected": -2.2502427101135254,
212
- "logps/chosen": -463.05426025390625,
213
- "logps/rejected": -332.7582092285156,
214
- "loss": 0.1066,
215
- "rewards/accuracies": 0.793749988079071,
216
- "rewards/chosen": -0.651161789894104,
217
- "rewards/margins": 1.5051846504211426,
218
- "rewards/rejected": -2.156346321105957,
219
  "step": 140
220
  },
221
  {
222
- "epoch": 0.37,
223
- "learning_rate": 3.972952151123984e-07,
224
- "logits/chosen": -2.325868844985962,
225
- "logits/rejected": -2.2392640113830566,
226
- "logps/chosen": -467.57470703125,
227
- "logps/rejected": -340.8150939941406,
228
- "loss": 0.0856,
229
- "rewards/accuracies": 0.831250011920929,
230
- "rewards/chosen": -0.8043683767318726,
231
- "rewards/margins": 1.5466692447662354,
232
- "rewards/rejected": -2.3510377407073975,
233
  "step": 150
234
  },
235
  {
236
- "epoch": 0.39,
237
- "learning_rate": 3.793344535444142e-07,
238
- "logits/chosen": -2.265021800994873,
239
- "logits/rejected": -2.1379055976867676,
240
- "logps/chosen": -543.5413208007812,
241
- "logps/rejected": -420.13189697265625,
242
- "loss": 0.0548,
243
- "rewards/accuracies": 0.8062499761581421,
244
- "rewards/chosen": -0.9391711354255676,
245
- "rewards/margins": 2.047957181930542,
246
- "rewards/rejected": -2.987128257751465,
247
  "step": 160
248
  },
249
  {
250
- "epoch": 0.42,
251
- "learning_rate": 3.604108797288461e-07,
252
- "logits/chosen": -2.2546730041503906,
253
- "logits/rejected": -2.1583638191223145,
254
- "logps/chosen": -499.3143005371094,
255
- "logps/rejected": -415.04071044921875,
256
- "loss": 0.0594,
257
- "rewards/accuracies": 0.7875000238418579,
258
- "rewards/chosen": -1.2889763116836548,
259
- "rewards/margins": 1.7566282749176025,
260
- "rewards/rejected": -3.045604705810547,
261
  "step": 170
262
  },
263
  {
264
- "epoch": 0.44,
265
- "learning_rate": 3.40665367563858e-07,
266
- "logits/chosen": -2.2694902420043945,
267
- "logits/rejected": -2.1707589626312256,
268
- "logps/chosen": -542.9236450195312,
269
- "logps/rejected": -426.84881591796875,
270
- "loss": 0.0407,
271
- "rewards/accuracies": 0.793749988079071,
272
- "rewards/chosen": -1.164052128791809,
273
- "rewards/margins": 1.9681476354599,
274
- "rewards/rejected": -3.132199764251709,
275
  "step": 180
276
  },
277
  {
278
- "epoch": 0.47,
279
- "learning_rate": 3.202449097526798e-07,
280
- "logits/chosen": -2.23583984375,
281
- "logits/rejected": -2.137115240097046,
282
- "logps/chosen": -540.4014892578125,
283
- "logps/rejected": -475.8074645996094,
284
- "loss": 0.0389,
285
- "rewards/accuracies": 0.800000011920929,
286
- "rewards/chosen": -1.6572879552841187,
287
- "rewards/margins": 1.9838402271270752,
288
- "rewards/rejected": -3.6411280632019043,
289
  "step": 190
290
  },
291
  {
292
- "epoch": 0.49,
293
- "learning_rate": 2.993015235369905e-07,
294
- "logits/chosen": -2.2069687843322754,
295
- "logits/rejected": -2.125886917114258,
296
- "logps/chosen": -560.8629150390625,
297
- "logps/rejected": -514.3555297851562,
298
- "loss": 0.0357,
299
- "rewards/accuracies": 0.762499988079071,
300
- "rewards/chosen": -1.7802679538726807,
301
- "rewards/margins": 2.1691107749938965,
302
- "rewards/rejected": -3.949378490447998,
303
  "step": 200
304
  },
305
  {
306
- "epoch": 0.52,
307
- "learning_rate": 2.7799111902582693e-07,
308
- "logits/chosen": -2.2968099117279053,
309
- "logits/rejected": -2.1844937801361084,
310
- "logps/chosen": -592.0206298828125,
311
- "logps/rejected": -486.9053649902344,
312
- "loss": 0.0469,
313
- "rewards/accuracies": 0.8500000238418579,
314
- "rewards/chosen": -1.3230507373809814,
315
- "rewards/margins": 2.3087940216064453,
316
- "rewards/rejected": -3.6318447589874268,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
317
  "step": 210
318
  },
319
  {
320
- "epoch": 0.54,
321
- "learning_rate": 2.564723385445869e-07,
322
- "logits/chosen": -2.2583115100860596,
323
- "logits/rejected": -2.193603038787842,
324
- "logps/chosen": -516.7488403320312,
325
- "logps/rejected": -438.7547302246094,
326
- "loss": 0.0487,
327
- "rewards/accuracies": 0.7749999761581421,
328
- "rewards/chosen": -1.311513900756836,
329
- "rewards/margins": 1.9017574787139893,
330
- "rewards/rejected": -3.213271379470825,
331
  "step": 220
332
  },
333
  {
334
- "epoch": 0.57,
335
- "learning_rate": 2.3490537564442845e-07,
336
- "logits/chosen": -2.2809863090515137,
337
- "logits/rejected": -2.1941916942596436,
338
- "logps/chosen": -547.8267822265625,
339
- "logps/rejected": -443.62945556640625,
340
- "loss": 0.0629,
341
- "rewards/accuracies": 0.800000011920929,
342
- "rewards/chosen": -1.1957685947418213,
343
- "rewards/margins": 2.0020644664764404,
344
- "rewards/rejected": -3.1978330612182617,
345
  "step": 230
346
  },
347
  {
348
- "epoch": 0.59,
349
- "learning_rate": 2.1345078256378801e-07,
350
- "logits/chosen": -2.280391216278076,
351
- "logits/rejected": -2.1995670795440674,
352
- "logps/chosen": -579.6043701171875,
353
- "logps/rejected": -455.45159912109375,
354
- "loss": 0.0387,
355
- "rewards/accuracies": 0.793749988079071,
356
- "rewards/chosen": -1.3387082815170288,
357
- "rewards/margins": 2.1265225410461426,
358
- "rewards/rejected": -3.465230941772461,
359
  "step": 240
360
  },
361
  {
362
- "epoch": 0.62,
363
- "learning_rate": 1.9226827501969865e-07,
364
- "logits/chosen": -2.242464542388916,
365
- "logits/rejected": -2.1263935565948486,
366
- "logps/chosen": -543.7323608398438,
367
- "logps/rejected": -453.8377990722656,
368
- "loss": 0.0431,
369
- "rewards/accuracies": 0.7875000238418579,
370
- "rewards/chosen": -1.3675382137298584,
371
- "rewards/margins": 2.0933918952941895,
372
- "rewards/rejected": -3.4609298706054688,
373
  "step": 250
374
  },
375
  {
376
- "epoch": 0.64,
377
- "learning_rate": 1.715155432264775e-07,
378
- "logits/chosen": -2.2370102405548096,
379
- "logits/rejected": -2.1484413146972656,
380
- "logps/chosen": -511.59271240234375,
381
- "logps/rejected": -461.88836669921875,
382
- "loss": 0.0486,
383
- "rewards/accuracies": 0.793749988079071,
384
- "rewards/chosen": -1.3555858135223389,
385
- "rewards/margins": 2.12691068649292,
386
- "rewards/rejected": -3.4824962615966797,
387
  "step": 260
388
  },
389
  {
390
- "epoch": 0.67,
391
- "learning_rate": 1.51347077992983e-07,
392
- "logits/chosen": -2.2585349082946777,
393
- "logits/rejected": -2.172651767730713,
394
- "logps/chosen": -555.9609985351562,
395
- "logps/rejected": -464.13201904296875,
396
- "loss": 0.0532,
397
- "rewards/accuracies": 0.887499988079071,
398
- "rewards/chosen": -1.2712557315826416,
399
- "rewards/margins": 2.206218719482422,
400
- "rewards/rejected": -3.4774742126464844,
401
  "step": 270
402
  },
403
  {
404
- "epoch": 0.69,
405
- "learning_rate": 1.3191302063739906e-07,
406
- "logits/chosen": -2.3039302825927734,
407
- "logits/rejected": -2.2482986450195312,
408
- "logps/chosen": -523.7935180664062,
409
- "logps/rejected": -427.8067321777344,
410
- "loss": 0.0485,
411
- "rewards/accuracies": 0.8374999761581421,
412
- "rewards/chosen": -1.2013866901397705,
413
- "rewards/margins": 1.99883234500885,
414
- "rewards/rejected": -3.200218915939331,
415
  "step": 280
416
  },
417
  {
418
- "epoch": 0.72,
419
- "learning_rate": 1.1335804528119475e-07,
420
- "logits/chosen": -2.2729263305664062,
421
- "logits/rejected": -2.187750816345215,
422
- "logps/chosen": -562.6840209960938,
423
- "logps/rejected": -481.2604064941406,
424
- "loss": 0.0572,
425
- "rewards/accuracies": 0.824999988079071,
426
- "rewards/chosen": -1.2244867086410522,
427
- "rewards/margins": 2.2730398178100586,
428
- "rewards/rejected": -3.4975266456604004,
429
  "step": 290
430
  },
431
  {
432
- "epoch": 0.74,
433
- "learning_rate": 9.582028184286423e-08,
434
- "logits/chosen": -2.2367167472839355,
435
- "logits/rejected": -2.1695148944854736,
436
- "logps/chosen": -515.9486083984375,
437
- "logps/rejected": -450.794189453125,
438
- "loss": 0.0493,
439
- "rewards/accuracies": 0.8500000238418579,
440
- "rewards/chosen": -1.351094365119934,
441
- "rewards/margins": 2.0661861896514893,
442
- "rewards/rejected": -3.4172801971435547,
443
  "step": 300
444
  },
445
  {
446
- "epoch": 0.76,
447
- "learning_rate": 7.943028774907065e-08,
448
- "logits/chosen": -2.2783074378967285,
449
- "logits/rejected": -2.1843154430389404,
450
- "logps/chosen": -576.671875,
451
- "logps/rejected": -450.0335998535156,
452
- "loss": 0.0471,
453
- "rewards/accuracies": 0.84375,
454
- "rewards/chosen": -1.1943355798721313,
455
- "rewards/margins": 2.2165350914001465,
456
- "rewards/rejected": -3.4108707904815674,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
457
  "step": 310
458
  },
459
  {
460
- "epoch": 0.79,
461
- "learning_rate": 6.431007601814637e-08,
462
- "logits/chosen": -2.2379584312438965,
463
- "logits/rejected": -2.1469919681549072,
464
- "logps/chosen": -541.4619140625,
465
- "logps/rejected": -480.04241943359375,
466
- "loss": 0.0444,
467
- "rewards/accuracies": 0.8062499761581421,
468
- "rewards/chosen": -1.4200572967529297,
469
- "rewards/margins": 2.1396281719207764,
470
- "rewards/rejected": -3.559685468673706,
471
  "step": 320
472
  },
473
  {
474
- "epoch": 0.81,
475
- "learning_rate": 5.0572206951246e-08,
476
- "logits/chosen": -2.2664687633514404,
477
- "logits/rejected": -2.195974349975586,
478
- "logps/chosen": -502.0436096191406,
479
- "logps/rejected": -450.3854064941406,
480
- "loss": 0.0408,
481
- "rewards/accuracies": 0.793749988079071,
482
- "rewards/chosen": -1.5081156492233276,
483
- "rewards/margins": 1.8512821197509766,
484
- "rewards/rejected": -3.3593974113464355,
485
  "step": 330
486
  },
487
  {
488
- "epoch": 0.84,
489
- "learning_rate": 3.831895019292897e-08,
490
- "logits/chosen": -2.293731451034546,
491
- "logits/rejected": -2.2087788581848145,
492
- "logps/chosen": -582.9859008789062,
493
- "logps/rejected": -495.55645751953125,
494
- "loss": 0.0391,
495
- "rewards/accuracies": 0.7875000238418579,
496
- "rewards/chosen": -1.357019305229187,
497
- "rewards/margins": 2.3732104301452637,
498
- "rewards/rejected": -3.7302298545837402,
499
  "step": 340
500
  },
501
  {
502
- "epoch": 0.86,
503
- "learning_rate": 2.764152339909756e-08,
504
- "logits/chosen": -2.2799806594848633,
505
- "logits/rejected": -2.1998825073242188,
506
- "logps/chosen": -586.57421875,
507
- "logps/rejected": -479.2138671875,
508
- "loss": 0.0514,
509
- "rewards/accuracies": 0.8062499761581421,
510
- "rewards/chosen": -1.1446287631988525,
511
- "rewards/margins": 2.45401930809021,
512
- "rewards/rejected": -3.5986480712890625,
513
  "step": 350
514
  },
515
  {
516
- "epoch": 0.89,
517
- "learning_rate": 1.861941317991664e-08,
518
- "logits/chosen": -2.1908628940582275,
519
- "logits/rejected": -2.1429388523101807,
520
- "logps/chosen": -522.1634521484375,
521
- "logps/rejected": -469.70672607421875,
522
- "loss": 0.0355,
523
- "rewards/accuracies": 0.7437499761581421,
524
- "rewards/chosen": -1.5918102264404297,
525
- "rewards/margins": 1.9443706274032593,
526
- "rewards/rejected": -3.5361809730529785,
527
  "step": 360
528
  },
529
  {
530
- "epoch": 0.91,
531
- "learning_rate": 1.13197833728636e-08,
532
- "logits/chosen": -2.2668819427490234,
533
- "logits/rejected": -2.198953866958618,
534
- "logps/chosen": -554.81005859375,
535
- "logps/rejected": -480.7757873535156,
536
- "loss": 0.042,
537
- "rewards/accuracies": 0.7562500238418579,
538
- "rewards/chosen": -1.6135523319244385,
539
- "rewards/margins": 1.966012954711914,
540
- "rewards/rejected": -3.5795655250549316,
541
  "step": 370
542
  },
543
  {
544
- "epoch": 0.94,
545
- "learning_rate": 5.79697505093521e-09,
546
- "logits/chosen": -2.309338092803955,
547
- "logits/rejected": -2.209568500518799,
548
- "logps/chosen": -586.4290771484375,
549
- "logps/rejected": -495.80450439453125,
550
- "loss": 0.0402,
551
- "rewards/accuracies": 0.824999988079071,
552
- "rewards/chosen": -1.3390227556228638,
553
- "rewards/margins": 2.412290573120117,
554
- "rewards/rejected": -3.7513129711151123,
555
  "step": 380
556
  },
557
  {
558
- "epoch": 0.96,
559
- "learning_rate": 2.092101988131256e-09,
560
- "logits/chosen": -2.2840235233306885,
561
- "logits/rejected": -2.177786350250244,
562
- "logps/chosen": -575.89990234375,
563
- "logps/rejected": -463.6390686035156,
564
- "loss": 0.042,
565
- "rewards/accuracies": 0.824999988079071,
566
- "rewards/chosen": -1.4674110412597656,
567
- "rewards/margins": 2.0524630546569824,
568
- "rewards/rejected": -3.519873857498169,
569
  "step": 390
570
  },
571
  {
572
- "epoch": 0.99,
573
- "learning_rate": 2.327445937151673e-10,
574
- "logits/chosen": -2.3001909255981445,
575
- "logits/rejected": -2.200953960418701,
576
- "logps/chosen": -590.1817016601562,
577
- "logps/rejected": -487.3092346191406,
578
- "loss": 0.037,
579
- "rewards/accuracies": 0.800000011920929,
580
- "rewards/chosen": -1.4782402515411377,
581
- "rewards/margins": 2.1466498374938965,
582
- "rewards/rejected": -3.624889850616455,
583
  "step": 400
584
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
585
  {
586
  "epoch": 1.0,
587
- "step": 405,
588
  "total_flos": 0.0,
589
- "train_loss": 0.0941658933221558,
590
- "train_runtime": 3198.7545,
591
- "train_samples_per_second": 16.223,
592
- "train_steps_per_second": 0.127
593
  }
594
  ],
595
  "logging_steps": 10,
596
- "max_steps": 405,
597
  "num_train_epochs": 1,
598
  "save_steps": 1000,
599
  "total_flos": 0.0,
 
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": -0.03225263953208923,
15
+ "logits/rejected": 0.06596440076828003,
16
+ "logps/chosen": -527.7545776367188,
17
+ "logps/rejected": -376.3921203613281,
18
+ "loss": 0.6931,
19
  "rewards/accuracies": 0.0,
20
  "rewards/chosen": 0.0,
21
  "rewards/margins": 0.0,
 
24
  },
25
  {
26
  "epoch": 0.02,
27
+ "learning_rate": 1.0416666666666667e-07,
28
+ "logits/chosen": 0.00588985625654459,
29
+ "logits/rejected": 0.046256858855485916,
30
+ "logps/chosen": -367.245361328125,
31
+ "logps/rejected": -368.35211181640625,
32
+ "loss": 0.693,
33
+ "rewards/accuracies": 0.4305555522441864,
34
+ "rewards/chosen": -0.00034015471464954317,
35
+ "rewards/margins": -2.4449158445349894e-05,
36
+ "rewards/rejected": -0.0003157054306939244,
37
  "step": 10
38
  },
39
  {
40
+ "epoch": 0.04,
41
+ "learning_rate": 2.0833333333333333e-07,
42
+ "logits/chosen": 0.00024093389220070094,
43
+ "logits/rejected": 0.007919400930404663,
44
+ "logps/chosen": -365.55755615234375,
45
+ "logps/rejected": -376.015625,
46
+ "loss": 0.6926,
47
+ "rewards/accuracies": 0.5625,
48
+ "rewards/chosen": -0.0012488554930314422,
49
+ "rewards/margins": 0.0011257396545261145,
50
+ "rewards/rejected": -0.0023745952639728785,
51
  "step": 20
52
  },
53
  {
54
+ "epoch": 0.06,
55
+ "learning_rate": 3.1249999999999997e-07,
56
+ "logits/chosen": -0.04148181527853012,
57
+ "logits/rejected": -0.018698781728744507,
58
+ "logps/chosen": -426.17279052734375,
59
+ "logps/rejected": -418.4230041503906,
60
+ "loss": 0.691,
61
+ "rewards/accuracies": 0.6312500238418579,
62
+ "rewards/chosen": -0.0033198825549334288,
63
+ "rewards/margins": 0.004528028424829245,
64
+ "rewards/rejected": -0.00784791074693203,
65
  "step": 30
66
  },
67
  {
68
+ "epoch": 0.08,
69
+ "learning_rate": 4.1666666666666667e-07,
70
+ "logits/chosen": 0.048020102083683014,
71
+ "logits/rejected": 0.08308018743991852,
72
+ "logps/chosen": -376.35260009765625,
73
+ "logps/rejected": -364.0716247558594,
74
+ "loss": 0.6858,
75
+ "rewards/accuracies": 0.625,
76
+ "rewards/chosen": -0.016986483708024025,
77
+ "rewards/margins": 0.010655680671334267,
78
+ "rewards/rejected": -0.02764216624200344,
79
  "step": 40
80
  },
81
  {
82
+ "epoch": 0.1,
83
+ "learning_rate": 4.999731868769026e-07,
84
+ "logits/chosen": 0.05010465532541275,
85
+ "logits/rejected": 0.09222860634326935,
86
+ "logps/chosen": -387.15533447265625,
87
+ "logps/rejected": -384.2821350097656,
88
+ "loss": 0.6778,
89
+ "rewards/accuracies": 0.7250000238418579,
90
+ "rewards/chosen": -0.012072703801095486,
91
+ "rewards/margins": 0.04466303437948227,
92
+ "rewards/rejected": -0.05673573538661003,
93
  "step": 50
94
  },
95
  {
96
+ "epoch": 0.13,
97
+ "learning_rate": 4.990353313429303e-07,
98
+ "logits/chosen": 0.18076041340827942,
99
+ "logits/rejected": 0.19874396920204163,
100
+ "logps/chosen": -359.6280517578125,
101
+ "logps/rejected": -361.45123291015625,
102
+ "loss": 0.6612,
103
+ "rewards/accuracies": 0.668749988079071,
104
+ "rewards/chosen": -0.01258832961320877,
105
+ "rewards/margins": 0.06712029874324799,
106
+ "rewards/rejected": -0.07970863580703735,
107
  "step": 60
108
  },
109
  {
110
+ "epoch": 0.15,
111
+ "learning_rate": 4.967625656594781e-07,
112
+ "logits/chosen": 0.17704300582408905,
113
+ "logits/rejected": 0.2257777899503708,
114
+ "logps/chosen": -369.0418701171875,
115
+ "logps/rejected": -331.1271057128906,
116
+ "loss": 0.6392,
117
+ "rewards/accuracies": 0.706250011920929,
118
+ "rewards/chosen": 0.052046071738004684,
119
+ "rewards/margins": 0.11003003269433975,
120
+ "rewards/rejected": -0.057983964681625366,
121
  "step": 70
122
  },
123
  {
124
+ "epoch": 0.17,
125
+ "learning_rate": 4.93167072587771e-07,
126
+ "logits/chosen": 0.3054140508174896,
127
+ "logits/rejected": 0.3581676781177521,
128
+ "logps/chosen": -399.2489318847656,
129
+ "logps/rejected": -357.3374938964844,
130
+ "loss": 0.6238,
131
  "rewards/accuracies": 0.737500011920929,
132
+ "rewards/chosen": 0.032918043434619904,
133
+ "rewards/margins": 0.1819782257080078,
134
+ "rewards/rejected": -0.1490601897239685,
135
  "step": 80
136
  },
137
  {
138
+ "epoch": 0.19,
139
+ "learning_rate": 4.882681251368548e-07,
140
+ "logits/chosen": 0.36256638169288635,
141
+ "logits/rejected": 0.4393485486507416,
142
+ "logps/chosen": -421.45233154296875,
143
+ "logps/rejected": -408.70147705078125,
144
+ "loss": 0.6031,
145
+ "rewards/accuracies": 0.75,
146
+ "rewards/chosen": -0.04092440754175186,
147
+ "rewards/margins": 0.2830551862716675,
148
+ "rewards/rejected": -0.32397955656051636,
149
  "step": 90
150
  },
151
  {
152
+ "epoch": 0.21,
153
+ "learning_rate": 4.820919832540181e-07,
154
+ "logits/chosen": 0.28381413221359253,
155
+ "logits/rejected": 0.3675808012485504,
156
+ "logps/chosen": -397.0648193359375,
157
+ "logps/rejected": -408.3998107910156,
158
+ "loss": 0.5824,
159
+ "rewards/accuracies": 0.6625000238418579,
160
+ "rewards/chosen": -0.09815987199544907,
161
+ "rewards/margins": 0.2904922068119049,
162
+ "rewards/rejected": -0.38865208625793457,
163
  "step": 100
164
  },
165
  {
166
+ "epoch": 0.21,
167
+ "eval_logits/chosen": 0.6272635459899902,
168
+ "eval_logits/rejected": 0.7087044715881348,
169
+ "eval_logps/chosen": -392.4388427734375,
170
+ "eval_logps/rejected": -440.89996337890625,
171
+ "eval_loss": 0.5817839503288269,
172
+ "eval_rewards/accuracies": 0.74609375,
173
+ "eval_rewards/chosen": -0.09309583902359009,
174
+ "eval_rewards/margins": 0.42317453026771545,
175
+ "eval_rewards/rejected": -0.5162703394889832,
176
+ "eval_runtime": 65.229,
177
+ "eval_samples_per_second": 30.661,
178
+ "eval_steps_per_second": 0.491,
179
+ "step": 100
180
+ },
181
+ {
182
+ "epoch": 0.23,
183
+ "learning_rate": 4.7467175306295647e-07,
184
+ "logits/chosen": 0.6266800165176392,
185
+ "logits/rejected": 0.7579915523529053,
186
+ "logps/chosen": -417.3716735839844,
187
+ "logps/rejected": -436.8717346191406,
188
+ "loss": 0.5545,
189
+ "rewards/accuracies": 0.65625,
190
+ "rewards/chosen": -0.30055922269821167,
191
+ "rewards/margins": 0.33543816208839417,
192
+ "rewards/rejected": -0.6359974145889282,
193
  "step": 110
194
  },
195
  {
196
+ "epoch": 0.25,
197
+ "learning_rate": 4.6604720940421207e-07,
198
+ "logits/chosen": 0.3340543508529663,
199
+ "logits/rejected": 0.4541744291782379,
200
+ "logps/chosen": -421.9034729003906,
201
+ "logps/rejected": -450.9452209472656,
202
+ "loss": 0.5738,
203
+ "rewards/accuracies": 0.6875,
204
+ "rewards/chosen": -0.09486015886068344,
205
+ "rewards/margins": 0.3886179029941559,
206
+ "rewards/rejected": -0.4834780693054199,
207
  "step": 120
208
  },
209
  {
210
+ "epoch": 0.27,
211
+ "learning_rate": 4.5626458262912735e-07,
212
+ "logits/chosen": 0.46364307403564453,
213
+ "logits/rejected": 0.59904944896698,
214
+ "logps/chosen": -447.900146484375,
215
+ "logps/rejected": -456.28375244140625,
216
+ "loss": 0.5497,
217
+ "rewards/accuracies": 0.699999988079071,
218
+ "rewards/chosen": -0.33782193064689636,
219
+ "rewards/margins": 0.4510591924190521,
220
+ "rewards/rejected": -0.7888811826705933,
221
  "step": 130
222
  },
223
  {
224
+ "epoch": 0.29,
225
+ "learning_rate": 4.453763107901675e-07,
226
+ "logits/chosen": 0.6642600297927856,
227
+ "logits/rejected": 0.8160743713378906,
228
+ "logps/chosen": -428.5116271972656,
229
+ "logps/rejected": -446.58514404296875,
230
+ "loss": 0.561,
231
+ "rewards/accuracies": 0.706250011920929,
232
+ "rewards/chosen": -0.4475336968898773,
233
+ "rewards/margins": 0.4344182014465332,
234
+ "rewards/rejected": -0.8819519281387329,
235
  "step": 140
236
  },
237
  {
238
+ "epoch": 0.31,
239
+ "learning_rate": 4.3344075855595097e-07,
240
+ "logits/chosen": 0.5630699992179871,
241
+ "logits/rejected": 0.6977785229682922,
242
+ "logps/chosen": -396.4422302246094,
243
+ "logps/rejected": -414.3096618652344,
244
+ "loss": 0.5533,
245
+ "rewards/accuracies": 0.7250000238418579,
246
+ "rewards/chosen": -0.2667624056339264,
247
+ "rewards/margins": 0.470877081155777,
248
+ "rewards/rejected": -0.7376395463943481,
249
  "step": 150
250
  },
251
  {
252
+ "epoch": 0.33,
253
+ "learning_rate": 4.2052190435769554e-07,
254
+ "logits/chosen": 0.7767922282218933,
255
+ "logits/rejected": 0.9524985551834106,
256
+ "logps/chosen": -433.2449645996094,
257
+ "logps/rejected": -482.81280517578125,
258
+ "loss": 0.5343,
259
+ "rewards/accuracies": 0.706250011920929,
260
+ "rewards/chosen": -0.21643297374248505,
261
+ "rewards/margins": 0.5597648024559021,
262
+ "rewards/rejected": -0.7761977910995483,
263
  "step": 160
264
  },
265
  {
266
+ "epoch": 0.36,
267
+ "learning_rate": 4.0668899744407567e-07,
268
+ "logits/chosen": 0.7099506855010986,
269
+ "logits/rejected": 0.8651117086410522,
270
+ "logps/chosen": -402.1939697265625,
271
+ "logps/rejected": -441.4981994628906,
272
+ "loss": 0.5433,
273
+ "rewards/accuracies": 0.7562500238418579,
274
+ "rewards/chosen": -0.3325835168361664,
275
+ "rewards/margins": 0.5780541896820068,
276
+ "rewards/rejected": -0.9106375575065613,
277
  "step": 170
278
  },
279
  {
280
+ "epoch": 0.38,
281
+ "learning_rate": 3.920161866827889e-07,
282
+ "logits/chosen": 0.4709444046020508,
283
+ "logits/rejected": 0.5315283536911011,
284
+ "logps/chosen": -388.9530334472656,
285
+ "logps/rejected": -453.2137756347656,
286
+ "loss": 0.5542,
287
+ "rewards/accuracies": 0.71875,
288
+ "rewards/chosen": -0.3106423020362854,
289
+ "rewards/margins": 0.5376580953598022,
290
+ "rewards/rejected": -0.8483003377914429,
291
  "step": 180
292
  },
293
  {
294
+ "epoch": 0.4,
295
+ "learning_rate": 3.765821230985757e-07,
296
+ "logits/chosen": 0.5388105511665344,
297
+ "logits/rejected": 0.6445595026016235,
298
+ "logps/chosen": -393.04718017578125,
299
+ "logps/rejected": -453.16461181640625,
300
+ "loss": 0.532,
301
+ "rewards/accuracies": 0.768750011920929,
302
+ "rewards/chosen": -0.2712288796901703,
303
+ "rewards/margins": 0.6453222036361694,
304
+ "rewards/rejected": -0.9165511131286621,
305
  "step": 190
306
  },
307
  {
308
+ "epoch": 0.42,
309
+ "learning_rate": 3.604695382782159e-07,
310
+ "logits/chosen": 0.7736464142799377,
311
+ "logits/rejected": 0.8140844106674194,
312
+ "logps/chosen": -466.62750244140625,
313
+ "logps/rejected": -507.78607177734375,
314
+ "loss": 0.5501,
315
+ "rewards/accuracies": 0.7562500238418579,
316
+ "rewards/chosen": -0.5761786103248596,
317
+ "rewards/margins": 0.5345386862754822,
318
+ "rewards/rejected": -1.1107172966003418,
319
  "step": 200
320
  },
321
  {
322
+ "epoch": 0.42,
323
+ "eval_logits/chosen": 1.055431604385376,
324
+ "eval_logits/rejected": 1.2046641111373901,
325
+ "eval_logps/chosen": -437.1852111816406,
326
+ "eval_logps/rejected": -513.8765869140625,
327
+ "eval_loss": 0.5346720218658447,
328
+ "eval_rewards/accuracies": 0.77734375,
329
+ "eval_rewards/chosen": -0.5405592918395996,
330
+ "eval_rewards/margins": 0.7054771780967712,
331
+ "eval_rewards/rejected": -1.2460365295410156,
332
+ "eval_runtime": 64.3347,
333
+ "eval_samples_per_second": 31.087,
334
+ "eval_steps_per_second": 0.497,
335
+ "step": 200
336
+ },
337
+ {
338
+ "epoch": 0.44,
339
+ "learning_rate": 3.4376480090239047e-07,
340
+ "logits/chosen": 0.890208899974823,
341
+ "logits/rejected": 1.0526978969573975,
342
+ "logps/chosen": -468.3349609375,
343
+ "logps/rejected": -481.4637145996094,
344
+ "loss": 0.5381,
345
+ "rewards/accuracies": 0.7437499761581421,
346
+ "rewards/chosen": -0.5894811749458313,
347
+ "rewards/margins": 0.5870489478111267,
348
+ "rewards/rejected": -1.176530122756958,
349
  "step": 210
350
  },
351
  {
352
+ "epoch": 0.46,
353
+ "learning_rate": 3.265574537815398e-07,
354
+ "logits/chosen": 0.693829357624054,
355
+ "logits/rejected": 0.965678870677948,
356
+ "logps/chosen": -457.4490661621094,
357
+ "logps/rejected": -490.271728515625,
358
+ "loss": 0.5182,
359
+ "rewards/accuracies": 0.78125,
360
+ "rewards/chosen": -0.5331239700317383,
361
+ "rewards/margins": 0.8056753873825073,
362
+ "rewards/rejected": -1.3387993574142456,
363
  "step": 220
364
  },
365
  {
366
+ "epoch": 0.48,
367
+ "learning_rate": 3.0893973387735683e-07,
368
+ "logits/chosen": 0.5953251123428345,
369
+ "logits/rejected": 0.8499298095703125,
370
+ "logps/chosen": -496.3831481933594,
371
+ "logps/rejected": -504.7569274902344,
372
+ "loss": 0.5216,
373
+ "rewards/accuracies": 0.737500011920929,
374
+ "rewards/chosen": -0.638763964176178,
375
+ "rewards/margins": 0.7798550724983215,
376
+ "rewards/rejected": -1.418619155883789,
377
  "step": 230
378
  },
379
  {
380
+ "epoch": 0.5,
381
+ "learning_rate": 2.910060778827554e-07,
382
+ "logits/chosen": 0.7672706842422485,
383
+ "logits/rejected": 0.9008816480636597,
384
+ "logps/chosen": -484.79803466796875,
385
+ "logps/rejected": -530.2685546875,
386
+ "loss": 0.5115,
387
+ "rewards/accuracies": 0.699999988079071,
388
+ "rewards/chosen": -0.7792438268661499,
389
+ "rewards/margins": 0.7937389612197876,
390
+ "rewards/rejected": -1.572982907295227,
391
  "step": 240
392
  },
393
  {
394
+ "epoch": 0.52,
395
+ "learning_rate": 2.7285261601056697e-07,
396
+ "logits/chosen": 0.6868101954460144,
397
+ "logits/rejected": 0.8424407243728638,
398
+ "logps/chosen": -456.3587341308594,
399
+ "logps/rejected": -537.9757080078125,
400
+ "loss": 0.5114,
401
+ "rewards/accuracies": 0.762499988079071,
402
+ "rewards/chosen": -0.9112833738327026,
403
+ "rewards/margins": 0.7427295446395874,
404
+ "rewards/rejected": -1.65401291847229,
405
  "step": 250
406
  },
407
  {
408
+ "epoch": 0.54,
409
+ "learning_rate": 2.5457665670441937e-07,
410
+ "logits/chosen": 0.5595349073410034,
411
+ "logits/rejected": 0.72369784116745,
412
+ "logps/chosen": -466.87548828125,
413
+ "logps/rejected": -528.150634765625,
414
+ "loss": 0.5036,
415
+ "rewards/accuracies": 0.762499988079071,
416
+ "rewards/chosen": -0.713230311870575,
417
+ "rewards/margins": 0.7146286368370056,
418
+ "rewards/rejected": -1.4278589487075806,
419
  "step": 260
420
  },
421
  {
422
+ "epoch": 0.57,
423
+ "learning_rate": 2.3627616503391812e-07,
424
+ "logits/chosen": 0.7341698408126831,
425
+ "logits/rejected": 0.8633677363395691,
426
+ "logps/chosen": -457.24957275390625,
427
+ "logps/rejected": -524.3684692382812,
428
+ "loss": 0.5111,
429
+ "rewards/accuracies": 0.768750011920929,
430
+ "rewards/chosen": -0.8039277195930481,
431
+ "rewards/margins": 0.8164765238761902,
432
+ "rewards/rejected": -1.6204042434692383,
433
  "step": 270
434
  },
435
  {
436
+ "epoch": 0.59,
437
+ "learning_rate": 2.1804923757009882e-07,
438
+ "logits/chosen": 0.7588011026382446,
439
+ "logits/rejected": 0.8498309254646301,
440
+ "logps/chosen": -492.8036193847656,
441
+ "logps/rejected": -563.0447998046875,
442
+ "loss": 0.5083,
443
+ "rewards/accuracies": 0.78125,
444
+ "rewards/chosen": -0.8585540652275085,
445
+ "rewards/margins": 0.759263277053833,
446
+ "rewards/rejected": -1.6178175210952759,
447
  "step": 280
448
  },
449
  {
450
+ "epoch": 0.61,
451
+ "learning_rate": 1.9999357655598891e-07,
452
+ "logits/chosen": 0.669258177280426,
453
+ "logits/rejected": 0.8894481658935547,
454
+ "logps/chosen": -498.2127380371094,
455
+ "logps/rejected": -533.4688110351562,
456
+ "loss": 0.513,
457
+ "rewards/accuracies": 0.78125,
458
+ "rewards/chosen": -0.9695415496826172,
459
+ "rewards/margins": 0.8429786562919617,
460
+ "rewards/rejected": -1.8125202655792236,
461
  "step": 290
462
  },
463
  {
464
+ "epoch": 0.63,
465
+ "learning_rate": 1.8220596619089573e-07,
466
+ "logits/chosen": 0.6566373705863953,
467
+ "logits/rejected": 0.7991911172866821,
468
+ "logps/chosen": -494.8948669433594,
469
+ "logps/rejected": -543.8385009765625,
470
+ "loss": 0.5149,
471
+ "rewards/accuracies": 0.706250011920929,
472
+ "rewards/chosen": -1.029112696647644,
473
+ "rewards/margins": 0.6092790365219116,
474
+ "rewards/rejected": -1.6383918523788452,
475
  "step": 300
476
  },
477
  {
478
+ "epoch": 0.63,
479
+ "eval_logits/chosen": 0.7274062633514404,
480
+ "eval_logits/rejected": 0.8648377656936646,
481
+ "eval_logps/chosen": -473.53173828125,
482
+ "eval_logps/rejected": -559.1195678710938,
483
+ "eval_loss": 0.5204064249992371,
484
+ "eval_rewards/accuracies": 0.77734375,
485
+ "eval_rewards/chosen": -0.9040247797966003,
486
+ "eval_rewards/margins": 0.7944413423538208,
487
+ "eval_rewards/rejected": -1.6984663009643555,
488
+ "eval_runtime": 65.8964,
489
+ "eval_samples_per_second": 30.351,
490
+ "eval_steps_per_second": 0.486,
491
+ "step": 300
492
+ },
493
+ {
494
+ "epoch": 0.65,
495
+ "learning_rate": 1.647817538357072e-07,
496
+ "logits/chosen": 0.7740650177001953,
497
+ "logits/rejected": 0.8621869087219238,
498
+ "logps/chosen": -491.20989990234375,
499
+ "logps/rejected": -546.8544921875,
500
+ "loss": 0.5039,
501
+ "rewards/accuracies": 0.7124999761581421,
502
+ "rewards/chosen": -1.0311224460601807,
503
+ "rewards/margins": 0.6867244839668274,
504
+ "rewards/rejected": -1.7178466320037842,
505
  "step": 310
506
  },
507
  {
508
+ "epoch": 0.67,
509
+ "learning_rate": 1.478143389201113e-07,
510
+ "logits/chosen": 0.7690327167510986,
511
+ "logits/rejected": 0.9306384325027466,
512
+ "logps/chosen": -519.8821411132812,
513
+ "logps/rejected": -588.0592651367188,
514
+ "loss": 0.4902,
515
+ "rewards/accuracies": 0.793749988079071,
516
+ "rewards/chosen": -1.0625598430633545,
517
+ "rewards/margins": 0.8101418614387512,
518
+ "rewards/rejected": -1.872701644897461,
519
  "step": 320
520
  },
521
  {
522
+ "epoch": 0.69,
523
+ "learning_rate": 1.3139467229135998e-07,
524
+ "logits/chosen": 0.5932360887527466,
525
+ "logits/rejected": 0.6337090730667114,
526
+ "logps/chosen": -501.433837890625,
527
+ "logps/rejected": -587.9107055664062,
528
+ "loss": 0.5005,
529
+ "rewards/accuracies": 0.768750011920929,
530
+ "rewards/chosen": -1.182588815689087,
531
+ "rewards/margins": 0.74435955286026,
532
+ "rewards/rejected": -1.9269483089447021,
533
  "step": 330
534
  },
535
  {
536
+ "epoch": 0.71,
537
+ "learning_rate": 1.1561076868822755e-07,
538
+ "logits/chosen": 0.36140671372413635,
539
+ "logits/rejected": 0.559506356716156,
540
+ "logps/chosen": -524.2594604492188,
541
+ "logps/rejected": -592.8712768554688,
542
+ "loss": 0.5141,
543
+ "rewards/accuracies": 0.731249988079071,
544
+ "rewards/chosen": -1.0356345176696777,
545
+ "rewards/margins": 0.8292257189750671,
546
+ "rewards/rejected": -1.8648601770401,
547
  "step": 340
548
  },
549
  {
550
+ "epoch": 0.73,
551
+ "learning_rate": 1.0054723495346482e-07,
552
+ "logits/chosen": 0.4322514533996582,
553
+ "logits/rejected": 0.5505155920982361,
554
+ "logps/chosen": -454.0244140625,
555
+ "logps/rejected": -545.0015258789062,
556
+ "loss": 0.4902,
557
+ "rewards/accuracies": 0.768750011920929,
558
+ "rewards/chosen": -1.0282310247421265,
559
+ "rewards/margins": 0.8233326077461243,
560
+ "rewards/rejected": -1.8515636920928955,
561
  "step": 350
562
  },
563
  {
564
+ "epoch": 0.75,
565
+ "learning_rate": 8.628481651367875e-08,
566
+ "logits/chosen": 0.40265363454818726,
567
+ "logits/rejected": 0.5925477147102356,
568
+ "logps/chosen": -503.9515686035156,
569
+ "logps/rejected": -528.5091552734375,
570
+ "loss": 0.5324,
571
+ "rewards/accuracies": 0.75,
572
+ "rewards/chosen": -1.1058452129364014,
573
+ "rewards/margins": 0.6876339316368103,
574
+ "rewards/rejected": -1.793479323387146,
575
  "step": 360
576
  },
577
  {
578
+ "epoch": 0.77,
579
+ "learning_rate": 7.289996455765748e-08,
580
+ "logits/chosen": 0.4274683892726898,
581
+ "logits/rejected": 0.61224365234375,
582
+ "logps/chosen": -511.58642578125,
583
+ "logps/rejected": -554.1364135742188,
584
+ "loss": 0.5007,
585
+ "rewards/accuracies": 0.800000011920929,
586
+ "rewards/chosen": -1.1323699951171875,
587
+ "rewards/margins": 0.9710127711296082,
588
+ "rewards/rejected": -2.1033828258514404,
589
  "step": 370
590
  },
591
  {
592
+ "epoch": 0.8,
593
+ "learning_rate": 6.046442623320145e-08,
594
+ "logits/chosen": 0.40892329812049866,
595
+ "logits/rejected": 0.470926433801651,
596
+ "logps/chosen": -504.13189697265625,
597
+ "logps/rejected": -572.686279296875,
598
+ "loss": 0.503,
599
+ "rewards/accuracies": 0.7437499761581421,
600
+ "rewards/chosen": -1.1587469577789307,
601
+ "rewards/margins": 0.7905802130699158,
602
+ "rewards/rejected": -1.9493271112442017,
603
  "step": 380
604
  },
605
  {
606
+ "epoch": 0.82,
607
+ "learning_rate": 4.904486005914027e-08,
608
+ "logits/chosen": 0.40895509719848633,
609
+ "logits/rejected": 0.5847037434577942,
610
+ "logps/chosen": -547.2850952148438,
611
+ "logps/rejected": -598.1409301757812,
612
+ "loss": 0.4987,
613
+ "rewards/accuracies": 0.84375,
614
+ "rewards/chosen": -1.1907001733779907,
615
+ "rewards/margins": 0.9806511998176575,
616
+ "rewards/rejected": -2.171351194381714,
617
  "step": 390
618
  },
619
  {
620
+ "epoch": 0.84,
621
+ "learning_rate": 3.8702478614051345e-08,
622
+ "logits/chosen": 0.4281010627746582,
623
+ "logits/rejected": 0.535579264163971,
624
+ "logps/chosen": -488.087890625,
625
+ "logps/rejected": -529.5299072265625,
626
+ "loss": 0.5002,
627
+ "rewards/accuracies": 0.7437499761581421,
628
+ "rewards/chosen": -1.1802234649658203,
629
+ "rewards/margins": 0.6625608801841736,
630
+ "rewards/rejected": -1.8427842855453491,
631
  "step": 400
632
  },
633
+ {
634
+ "epoch": 0.84,
635
+ "eval_logits/chosen": 0.4915699362754822,
636
+ "eval_logits/rejected": 0.6183238625526428,
637
+ "eval_logps/chosen": -493.17303466796875,
638
+ "eval_logps/rejected": -584.4573364257812,
639
+ "eval_loss": 0.515847384929657,
640
+ "eval_rewards/accuracies": 0.7734375,
641
+ "eval_rewards/chosen": -1.1004377603530884,
642
+ "eval_rewards/margins": 0.8514068722724915,
643
+ "eval_rewards/rejected": -1.9518446922302246,
644
+ "eval_runtime": 64.7433,
645
+ "eval_samples_per_second": 30.891,
646
+ "eval_steps_per_second": 0.494,
647
+ "step": 400
648
+ },
649
+ {
650
+ "epoch": 0.86,
651
+ "learning_rate": 2.9492720416985e-08,
652
+ "logits/chosen": 0.43782034516334534,
653
+ "logits/rejected": 0.6052254438400269,
654
+ "logps/chosen": -497.4378967285156,
655
+ "logps/rejected": -523.46240234375,
656
+ "loss": 0.4953,
657
+ "rewards/accuracies": 0.7124999761581421,
658
+ "rewards/chosen": -1.195321798324585,
659
+ "rewards/margins": 0.6132557392120361,
660
+ "rewards/rejected": -1.808577537536621,
661
+ "step": 410
662
+ },
663
+ {
664
+ "epoch": 0.88,
665
+ "learning_rate": 2.1464952759020856e-08,
666
+ "logits/chosen": 0.5280969738960266,
667
+ "logits/rejected": 0.6328979730606079,
668
+ "logps/chosen": -526.4898681640625,
669
+ "logps/rejected": -548.7019653320312,
670
+ "loss": 0.5069,
671
+ "rewards/accuracies": 0.71875,
672
+ "rewards/chosen": -1.232538104057312,
673
+ "rewards/margins": 0.6250852942466736,
674
+ "rewards/rejected": -1.8576233386993408,
675
+ "step": 420
676
+ },
677
+ {
678
+ "epoch": 0.9,
679
+ "learning_rate": 1.4662207078575684e-08,
680
+ "logits/chosen": 0.47360533475875854,
681
+ "logits/rejected": 0.5836101770401001,
682
+ "logps/chosen": -488.477294921875,
683
+ "logps/rejected": -578.5478515625,
684
+ "loss": 0.4847,
685
+ "rewards/accuracies": 0.768750011920929,
686
+ "rewards/chosen": -1.2091119289398193,
687
+ "rewards/margins": 0.7417689561843872,
688
+ "rewards/rejected": -1.9508806467056274,
689
+ "step": 430
690
+ },
691
+ {
692
+ "epoch": 0.92,
693
+ "learning_rate": 9.12094829893642e-09,
694
+ "logits/chosen": 0.4982087016105652,
695
+ "logits/rejected": 0.6727950572967529,
696
+ "logps/chosen": -516.8858642578125,
697
+ "logps/rejected": -573.6490478515625,
698
+ "loss": 0.502,
699
+ "rewards/accuracies": 0.6875,
700
+ "rewards/chosen": -1.2130807638168335,
701
+ "rewards/margins": 0.7400661706924438,
702
+ "rewards/rejected": -1.9531466960906982,
703
+ "step": 440
704
+ },
705
+ {
706
+ "epoch": 0.94,
707
+ "learning_rate": 4.8708793644441086e-09,
708
+ "logits/chosen": 0.5479084849357605,
709
+ "logits/rejected": 0.7065176963806152,
710
+ "logps/chosen": -541.27880859375,
711
+ "logps/rejected": -585.5593872070312,
712
+ "loss": 0.5134,
713
+ "rewards/accuracies": 0.768750011920929,
714
+ "rewards/chosen": -1.1916383504867554,
715
+ "rewards/margins": 0.7816148400306702,
716
+ "rewards/rejected": -1.9732532501220703,
717
+ "step": 450
718
+ },
719
+ {
720
+ "epoch": 0.96,
721
+ "learning_rate": 1.9347820230782295e-09,
722
+ "logits/chosen": 0.5875118970870972,
723
+ "logits/rejected": 0.7710727453231812,
724
+ "logps/chosen": -466.2781677246094,
725
+ "logps/rejected": -524.0235595703125,
726
+ "loss": 0.5065,
727
+ "rewards/accuracies": 0.75,
728
+ "rewards/chosen": -1.1890299320220947,
729
+ "rewards/margins": 0.744467556476593,
730
+ "rewards/rejected": -1.933497667312622,
731
+ "step": 460
732
+ },
733
+ {
734
+ "epoch": 0.98,
735
+ "learning_rate": 3.2839470889836627e-10,
736
+ "logits/chosen": 0.5119856595993042,
737
+ "logits/rejected": 0.6417261958122253,
738
+ "logps/chosen": -478.779052734375,
739
+ "logps/rejected": -568.6417236328125,
740
+ "loss": 0.5098,
741
+ "rewards/accuracies": 0.768750011920929,
742
+ "rewards/chosen": -1.124279260635376,
743
+ "rewards/margins": 0.8823677897453308,
744
+ "rewards/rejected": -2.0066471099853516,
745
+ "step": 470
746
+ },
747
  {
748
  "epoch": 1.0,
749
+ "step": 477,
750
  "total_flos": 0.0,
751
+ "train_loss": 0.5470197245759784,
752
+ "train_runtime": 4302.1619,
753
+ "train_samples_per_second": 14.21,
754
+ "train_steps_per_second": 0.111
755
  }
756
  ],
757
  "logging_steps": 10,
758
+ "max_steps": 477,
759
  "num_train_epochs": 1,
760
  "save_steps": 1000,
761
  "total_flos": 0.0,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:68c47dcf14ae1af0c8de803545117dc120c7ed5cfeaa2952c21e3c73b69a22e2
3
- size 6520
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4561699df82295a24885b8c2483c644518795888c764628b73ac3934d6f0859a
3
+ size 5944