tengxiao1 commited on
Commit
ae60326
1 Parent(s): 5438f51
README.md ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: llama3
3
+ base_model: meta-llama/Meta-Llama-3-8B-Instruct
4
+ tags:
5
+ - alignment_handbook-handbook
6
+ - generated_from_trainer
7
+ datasets:
8
+ - princeton-nlp/llama3-ultrafeedback
9
+ model-index:
10
+ - name: LLama-8B-Instruct-v0.1-MI-2e-5
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/tengxiao01/huggingface/runs/biqlfgyz)
18
+ # LLama-8B-Instruct-v0.1-MI-2e-5
19
+
20
+ This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the princeton-nlp/llama3-ultrafeedback dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 1.2552
23
+ - Rewards/chosen: -0.5792
24
+ - Rewards/rejected: -0.7270
25
+ - Rewards/accuracies: 0.6626
26
+ - Rewards/margins: 0.1478
27
+ - Logps/rejected: -0.7270
28
+ - Logps/chosen: -0.5792
29
+ - Logits/rejected: -0.3939
30
+ - Logits/chosen: -0.3830
31
+
32
+ ## Model description
33
+
34
+ More information needed
35
+
36
+ ## Intended uses & limitations
37
+
38
+ More information needed
39
+
40
+ ## Training and evaluation data
41
+
42
+ More information needed
43
+
44
+ ## Training procedure
45
+
46
+ ### Training hyperparameters
47
+
48
+ The following hyperparameters were used during training:
49
+ - learning_rate: 2e-05
50
+ - train_batch_size: 2
51
+ - eval_batch_size: 4
52
+ - seed: 42
53
+ - distributed_type: multi-GPU
54
+ - num_devices: 4
55
+ - gradient_accumulation_steps: 16
56
+ - total_train_batch_size: 128
57
+ - total_eval_batch_size: 16
58
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
59
+ - lr_scheduler_type: cosine
60
+ - lr_scheduler_warmup_ratio: 0.1
61
+ - num_epochs: 1
62
+
63
+ ### Training results
64
+
65
+ | Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
66
+ |:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
67
+ | 1.2571 | 0.8550 | 400 | 1.2552 | -0.5792 | -0.7270 | 0.6626 | 0.1478 | -0.7270 | -0.5792 | -0.3939 | -0.3830 |
68
+
69
+
70
+ ### Framework versions
71
+
72
+ - Transformers 4.42.0
73
+ - Pytorch 2.1.2+cu121
74
+ - Datasets 2.14.6
75
+ - Tokenizers 0.19.1
all_results.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9982631930527722,
3
+ "eval_logits/chosen": -0.3633301258087158,
4
+ "eval_logits/rejected": -0.37627702951431274,
5
+ "eval_logps/chosen": -0.5874707102775574,
6
+ "eval_logps/rejected": -0.7501260638237,
7
+ "eval_loss": 1.2528961896896362,
8
+ "eval_rewards/accuracies": 0.672764241695404,
9
+ "eval_rewards/chosen": -0.5874707102775574,
10
+ "eval_rewards/margins": 0.16265536844730377,
11
+ "eval_rewards/rejected": -0.7501260638237,
12
+ "eval_runtime": 421.6929,
13
+ "eval_samples": 1961,
14
+ "eval_samples_per_second": 4.65,
15
+ "eval_steps_per_second": 0.292,
16
+ "total_flos": 0.0,
17
+ "train_loss": 1.2796013329728513,
18
+ "train_runtime": 21025.6961,
19
+ "train_samples": 59876,
20
+ "train_samples_per_second": 2.848,
21
+ "train_steps_per_second": 0.022
22
+ }
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": 128009,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 8192,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 32,
18
+ "num_hidden_layers": 32,
19
+ "num_key_value_heads": 8,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_scaling": null,
23
+ "rope_theta": 500000.0,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "bfloat16",
26
+ "transformers_version": "4.42.0",
27
+ "use_cache": true,
28
+ "vocab_size": 128256
29
+ }
eval_results.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9982631930527722,
3
+ "eval_logits/chosen": -0.3633301258087158,
4
+ "eval_logits/rejected": -0.37627702951431274,
5
+ "eval_logps/chosen": -0.5874707102775574,
6
+ "eval_logps/rejected": -0.7501260638237,
7
+ "eval_loss": 1.2528961896896362,
8
+ "eval_rewards/accuracies": 0.672764241695404,
9
+ "eval_rewards/chosen": -0.5874707102775574,
10
+ "eval_rewards/margins": 0.16265536844730377,
11
+ "eval_rewards/rejected": -0.7501260638237,
12
+ "eval_runtime": 421.6929,
13
+ "eval_samples": 1961,
14
+ "eval_samples_per_second": 4.65,
15
+ "eval_steps_per_second": 0.292
16
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128009
7
+ ],
8
+ "max_length": 4096,
9
+ "temperature": 0.6,
10
+ "top_p": 0.9,
11
+ "transformers_version": "4.42.0"
12
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:052452a968ffde995f2420fda4c0f44219b2c5b1fd770867711046e5ab15028d
3
+ size 4976698672
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4946e35ed0478949bbbd6a5f6ac2fd1b3cefbe3b7871a59b7e9eb69fbca95782
3
+ size 4999802720
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cd1d0a6b5e0c95a75a1b6af18dea73be3aa5a4fc0454ff4f8ac2887c4fe01d5
3
+ size 4915916176
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c80f5713359a49f4205243bc450d1dbdf06e93b4832b962b6526068bd7e92596
3
+ size 1168138808
model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16060522496
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
296
+ "model.norm.weight": "model-00004-of-00004.safetensors"
297
+ }
298
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|eot_id|>"
17
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,2063 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|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,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 2048,
2061
+ "pad_token": "<|eot_id|>",
2062
+ "tokenizer_class": "PreTrainedTokenizerFast"
2063
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9982631930527722,
3
+ "total_flos": 0.0,
4
+ "train_loss": 1.2796013329728513,
5
+ "train_runtime": 21025.6961,
6
+ "train_samples": 59876,
7
+ "train_samples_per_second": 2.848,
8
+ "train_steps_per_second": 0.022
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,1453 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9982631930527722,
5
+ "eval_steps": 400,
6
+ "global_step": 467,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01068804275217101,
13
+ "grad_norm": 7.8646928358072685,
14
+ "learning_rate": 2.1276595744680853e-06,
15
+ "logits/chosen": 0.061868004500865936,
16
+ "logits/rejected": 0.03774915263056755,
17
+ "logps/chosen": -0.2700309157371521,
18
+ "logps/rejected": -0.2683418393135071,
19
+ "loss": 1.2747,
20
+ "rewards/accuracies": 0.5,
21
+ "rewards/chosen": -0.2700309157371521,
22
+ "rewards/margins": -0.0016891139093786478,
23
+ "rewards/rejected": -0.2683418393135071,
24
+ "step": 5
25
+ },
26
+ {
27
+ "epoch": 0.02137608550434202,
28
+ "grad_norm": 4.709071806627697,
29
+ "learning_rate": 4.255319148936171e-06,
30
+ "logits/chosen": -0.013552236370742321,
31
+ "logits/rejected": -0.015203881077468395,
32
+ "logps/chosen": -0.2748744487762451,
33
+ "logps/rejected": -0.28091126680374146,
34
+ "loss": 1.2665,
35
+ "rewards/accuracies": 0.518750011920929,
36
+ "rewards/chosen": -0.2748744487762451,
37
+ "rewards/margins": 0.006036859937012196,
38
+ "rewards/rejected": -0.28091126680374146,
39
+ "step": 10
40
+ },
41
+ {
42
+ "epoch": 0.03206412825651302,
43
+ "grad_norm": 6.011039832471536,
44
+ "learning_rate": 6.382978723404256e-06,
45
+ "logits/chosen": 0.003249469446018338,
46
+ "logits/rejected": 0.006007631309330463,
47
+ "logps/chosen": -0.3281441628932953,
48
+ "logps/rejected": -0.3555542826652527,
49
+ "loss": 1.2824,
50
+ "rewards/accuracies": 0.5062500238418579,
51
+ "rewards/chosen": -0.3281441628932953,
52
+ "rewards/margins": 0.027410129085183144,
53
+ "rewards/rejected": -0.3555542826652527,
54
+ "step": 15
55
+ },
56
+ {
57
+ "epoch": 0.04275217100868404,
58
+ "grad_norm": 6.004008006662261,
59
+ "learning_rate": 8.510638297872341e-06,
60
+ "logits/chosen": -0.01057378202676773,
61
+ "logits/rejected": -0.014622092247009277,
62
+ "logps/chosen": -0.3901517391204834,
63
+ "logps/rejected": -0.46824750304222107,
64
+ "loss": 1.2729,
65
+ "rewards/accuracies": 0.574999988079071,
66
+ "rewards/chosen": -0.3901517391204834,
67
+ "rewards/margins": 0.07809571921825409,
68
+ "rewards/rejected": -0.46824750304222107,
69
+ "step": 20
70
+ },
71
+ {
72
+ "epoch": 0.053440213760855046,
73
+ "grad_norm": 3.977322200325917,
74
+ "learning_rate": 1.0638297872340426e-05,
75
+ "logits/chosen": -0.2300865650177002,
76
+ "logits/rejected": -0.22464950382709503,
77
+ "logps/chosen": -0.3714216351509094,
78
+ "logps/rejected": -0.4496099352836609,
79
+ "loss": 1.2469,
80
+ "rewards/accuracies": 0.59375,
81
+ "rewards/chosen": -0.3714216351509094,
82
+ "rewards/margins": 0.07818831503391266,
83
+ "rewards/rejected": -0.4496099352836609,
84
+ "step": 25
85
+ },
86
+ {
87
+ "epoch": 0.06412825651302605,
88
+ "grad_norm": 3.540400129958154,
89
+ "learning_rate": 1.2765957446808513e-05,
90
+ "logits/chosen": -0.3409841060638428,
91
+ "logits/rejected": -0.3320957124233246,
92
+ "logps/chosen": -0.4569724202156067,
93
+ "logps/rejected": -0.5337254405021667,
94
+ "loss": 1.2712,
95
+ "rewards/accuracies": 0.59375,
96
+ "rewards/chosen": -0.4569724202156067,
97
+ "rewards/margins": 0.07675307244062424,
98
+ "rewards/rejected": -0.5337254405021667,
99
+ "step": 30
100
+ },
101
+ {
102
+ "epoch": 0.07481629926519706,
103
+ "grad_norm": 3.7566095401283395,
104
+ "learning_rate": 1.4893617021276596e-05,
105
+ "logits/chosen": -0.179878830909729,
106
+ "logits/rejected": -0.17120154201984406,
107
+ "logps/chosen": -0.46021848917007446,
108
+ "logps/rejected": -0.5379027128219604,
109
+ "loss": 1.2803,
110
+ "rewards/accuracies": 0.53125,
111
+ "rewards/chosen": -0.46021848917007446,
112
+ "rewards/margins": 0.0776842013001442,
113
+ "rewards/rejected": -0.5379027128219604,
114
+ "step": 35
115
+ },
116
+ {
117
+ "epoch": 0.08550434201736808,
118
+ "grad_norm": 3.1819948043330344,
119
+ "learning_rate": 1.7021276595744682e-05,
120
+ "logits/chosen": -0.007068359758704901,
121
+ "logits/rejected": -0.01693672500550747,
122
+ "logps/chosen": -0.4490579664707184,
123
+ "logps/rejected": -0.4928591251373291,
124
+ "loss": 1.2726,
125
+ "rewards/accuracies": 0.5562499761581421,
126
+ "rewards/chosen": -0.4490579664707184,
127
+ "rewards/margins": 0.04380121827125549,
128
+ "rewards/rejected": -0.4928591251373291,
129
+ "step": 40
130
+ },
131
+ {
132
+ "epoch": 0.09619238476953908,
133
+ "grad_norm": 3.2270349702087966,
134
+ "learning_rate": 1.914893617021277e-05,
135
+ "logits/chosen": -0.08650992810726166,
136
+ "logits/rejected": -0.054813969880342484,
137
+ "logps/chosen": -0.5002081990242004,
138
+ "logps/rejected": -0.5691278576850891,
139
+ "loss": 1.2871,
140
+ "rewards/accuracies": 0.5625,
141
+ "rewards/chosen": -0.5002081990242004,
142
+ "rewards/margins": 0.06891956925392151,
143
+ "rewards/rejected": -0.5691278576850891,
144
+ "step": 45
145
+ },
146
+ {
147
+ "epoch": 0.10688042752171009,
148
+ "grad_norm": 2.930228008373617,
149
+ "learning_rate": 1.999748234942507e-05,
150
+ "logits/chosen": 0.05123206228017807,
151
+ "logits/rejected": 0.0639006644487381,
152
+ "logps/chosen": -0.4998701512813568,
153
+ "logps/rejected": -0.5959991812705994,
154
+ "loss": 1.286,
155
+ "rewards/accuracies": 0.606249988079071,
156
+ "rewards/chosen": -0.4998701512813568,
157
+ "rewards/margins": 0.09612905234098434,
158
+ "rewards/rejected": -0.5959991812705994,
159
+ "step": 50
160
+ },
161
+ {
162
+ "epoch": 0.11756847027388109,
163
+ "grad_norm": 3.532397749748793,
164
+ "learning_rate": 1.998210129767735e-05,
165
+ "logits/chosen": 0.12292106449604034,
166
+ "logits/rejected": 0.11930225789546967,
167
+ "logps/chosen": -0.5049015879631042,
168
+ "logps/rejected": -0.5526176691055298,
169
+ "loss": 1.2864,
170
+ "rewards/accuracies": 0.574999988079071,
171
+ "rewards/chosen": -0.5049015879631042,
172
+ "rewards/margins": 0.0477161705493927,
173
+ "rewards/rejected": -0.5526176691055298,
174
+ "step": 55
175
+ },
176
+ {
177
+ "epoch": 0.1282565130260521,
178
+ "grad_norm": 3.727525392306118,
179
+ "learning_rate": 1.9952759374651266e-05,
180
+ "logits/chosen": 0.13513417541980743,
181
+ "logits/rejected": 0.11871670186519623,
182
+ "logps/chosen": -0.5651683807373047,
183
+ "logps/rejected": -0.629240095615387,
184
+ "loss": 1.297,
185
+ "rewards/accuracies": 0.606249988079071,
186
+ "rewards/chosen": -0.5651683807373047,
187
+ "rewards/margins": 0.06407161056995392,
188
+ "rewards/rejected": -0.629240095615387,
189
+ "step": 60
190
+ },
191
+ {
192
+ "epoch": 0.13894455577822312,
193
+ "grad_norm": 4.935532042698089,
194
+ "learning_rate": 1.990949761767935e-05,
195
+ "logits/chosen": 0.2536969482898712,
196
+ "logits/rejected": 0.29733771085739136,
197
+ "logps/chosen": -0.5493020415306091,
198
+ "logps/rejected": -0.6132219433784485,
199
+ "loss": 1.2983,
200
+ "rewards/accuracies": 0.625,
201
+ "rewards/chosen": -0.5493020415306091,
202
+ "rewards/margins": 0.06391985714435577,
203
+ "rewards/rejected": -0.6132219433784485,
204
+ "step": 65
205
+ },
206
+ {
207
+ "epoch": 0.14963259853039412,
208
+ "grad_norm": 3.295200796877631,
209
+ "learning_rate": 1.9852376532240594e-05,
210
+ "logits/chosen": 0.4693821966648102,
211
+ "logits/rejected": 0.4486643671989441,
212
+ "logps/chosen": -0.5880988836288452,
213
+ "logps/rejected": -0.6713588833808899,
214
+ "loss": 1.2884,
215
+ "rewards/accuracies": 0.574999988079071,
216
+ "rewards/chosen": -0.5880988836288452,
217
+ "rewards/margins": 0.08326009660959244,
218
+ "rewards/rejected": -0.6713588833808899,
219
+ "step": 70
220
+ },
221
+ {
222
+ "epoch": 0.16032064128256512,
223
+ "grad_norm": 3.1713468009980934,
224
+ "learning_rate": 1.9781476007338058e-05,
225
+ "logits/chosen": 0.4574071764945984,
226
+ "logits/rejected": 0.5068231225013733,
227
+ "logps/chosen": -0.5979748368263245,
228
+ "logps/rejected": -0.7264337539672852,
229
+ "loss": 1.2954,
230
+ "rewards/accuracies": 0.6000000238418579,
231
+ "rewards/chosen": -0.5979748368263245,
232
+ "rewards/margins": 0.1284589320421219,
233
+ "rewards/rejected": -0.7264337539672852,
234
+ "step": 75
235
+ },
236
+ {
237
+ "epoch": 0.17100868403473615,
238
+ "grad_norm": 3.662092336336613,
239
+ "learning_rate": 1.969689520376687e-05,
240
+ "logits/chosen": 0.4844590127468109,
241
+ "logits/rejected": 0.48810499906539917,
242
+ "logps/chosen": -0.5642470121383667,
243
+ "logps/rejected": -0.6027047038078308,
244
+ "loss": 1.3069,
245
+ "rewards/accuracies": 0.5874999761581421,
246
+ "rewards/chosen": -0.5642470121383667,
247
+ "rewards/margins": 0.038457684218883514,
248
+ "rewards/rejected": -0.6027047038078308,
249
+ "step": 80
250
+ },
251
+ {
252
+ "epoch": 0.18169672678690715,
253
+ "grad_norm": 4.707016904902269,
254
+ "learning_rate": 1.9598752415428893e-05,
255
+ "logits/chosen": 0.6143449544906616,
256
+ "logits/rejected": 0.6212804317474365,
257
+ "logps/chosen": -0.5707159042358398,
258
+ "logps/rejected": -0.6457289457321167,
259
+ "loss": 1.3041,
260
+ "rewards/accuracies": 0.543749988079071,
261
+ "rewards/chosen": -0.5707159042358398,
262
+ "rewards/margins": 0.07501306384801865,
263
+ "rewards/rejected": -0.6457289457321167,
264
+ "step": 85
265
+ },
266
+ {
267
+ "epoch": 0.19238476953907815,
268
+ "grad_norm": 3.539384946251158,
269
+ "learning_rate": 1.9487184903888e-05,
270
+ "logits/chosen": 0.7592190504074097,
271
+ "logits/rejected": 0.7624388933181763,
272
+ "logps/chosen": -0.5937708616256714,
273
+ "logps/rejected": -0.7089810967445374,
274
+ "loss": 1.2995,
275
+ "rewards/accuracies": 0.606249988079071,
276
+ "rewards/chosen": -0.5937708616256714,
277
+ "rewards/margins": 0.11521027237176895,
278
+ "rewards/rejected": -0.7089810967445374,
279
+ "step": 90
280
+ },
281
+ {
282
+ "epoch": 0.20307281229124916,
283
+ "grad_norm": 3.622523084533489,
284
+ "learning_rate": 1.9362348706397374e-05,
285
+ "logits/chosen": 0.45539766550064087,
286
+ "logits/rejected": 0.439523309469223,
287
+ "logps/chosen": -0.6361597180366516,
288
+ "logps/rejected": -0.660950243473053,
289
+ "loss": 1.3105,
290
+ "rewards/accuracies": 0.512499988079071,
291
+ "rewards/chosen": -0.6361597180366516,
292
+ "rewards/margins": 0.024790499359369278,
293
+ "rewards/rejected": -0.660950243473053,
294
+ "step": 95
295
+ },
296
+ {
297
+ "epoch": 0.21376085504342018,
298
+ "grad_norm": 3.7211660011686827,
299
+ "learning_rate": 1.9224418417667295e-05,
300
+ "logits/chosen": 0.4752308428287506,
301
+ "logits/rejected": 0.4805218279361725,
302
+ "logps/chosen": -0.6078037619590759,
303
+ "logps/rejected": -0.7114612460136414,
304
+ "loss": 1.3073,
305
+ "rewards/accuracies": 0.5625,
306
+ "rewards/chosen": -0.6078037619590759,
307
+ "rewards/margins": 0.10365743935108185,
308
+ "rewards/rejected": -0.7114612460136414,
309
+ "step": 100
310
+ },
311
+ {
312
+ "epoch": 0.22444889779559118,
313
+ "grad_norm": 3.4955810534668945,
314
+ "learning_rate": 1.907358694567865e-05,
315
+ "logits/chosen": 0.4134964346885681,
316
+ "logits/rejected": 0.39591750502586365,
317
+ "logps/chosen": -0.5727143287658691,
318
+ "logps/rejected": -0.6490830183029175,
319
+ "loss": 1.2904,
320
+ "rewards/accuracies": 0.518750011920929,
321
+ "rewards/chosen": -0.5727143287658691,
322
+ "rewards/margins": 0.07636874169111252,
323
+ "rewards/rejected": -0.6490830183029175,
324
+ "step": 105
325
+ },
326
+ {
327
+ "epoch": 0.23513694054776219,
328
+ "grad_norm": 3.895186311710448,
329
+ "learning_rate": 1.891006524188368e-05,
330
+ "logits/chosen": 0.27901846170425415,
331
+ "logits/rejected": 0.267717182636261,
332
+ "logps/chosen": -0.5927436351776123,
333
+ "logps/rejected": -0.6760529279708862,
334
+ "loss": 1.2909,
335
+ "rewards/accuracies": 0.5687500238418579,
336
+ "rewards/chosen": -0.5927436351776123,
337
+ "rewards/margins": 0.08330933004617691,
338
+ "rewards/rejected": -0.6760529279708862,
339
+ "step": 110
340
+ },
341
+ {
342
+ "epoch": 0.2458249832999332,
343
+ "grad_norm": 3.2529032172381034,
344
+ "learning_rate": 1.87340820061713e-05,
345
+ "logits/chosen": 0.4828861653804779,
346
+ "logits/rejected": 0.4803077280521393,
347
+ "logps/chosen": -0.6133522391319275,
348
+ "logps/rejected": -0.6779380440711975,
349
+ "loss": 1.3193,
350
+ "rewards/accuracies": 0.5687500238418579,
351
+ "rewards/chosen": -0.6133522391319275,
352
+ "rewards/margins": 0.06458581984043121,
353
+ "rewards/rejected": -0.6779380440711975,
354
+ "step": 115
355
+ },
356
+ {
357
+ "epoch": 0.2565130260521042,
358
+ "grad_norm": 3.0442398494478504,
359
+ "learning_rate": 1.854588336700962e-05,
360
+ "logits/chosen": 0.2846220135688782,
361
+ "logits/rejected": 0.2976106107234955,
362
+ "logps/chosen": -0.6584545969963074,
363
+ "logps/rejected": -0.7402211427688599,
364
+ "loss": 1.2983,
365
+ "rewards/accuracies": 0.5562499761581421,
366
+ "rewards/chosen": -0.6584545969963074,
367
+ "rewards/margins": 0.0817665308713913,
368
+ "rewards/rejected": -0.7402211427688599,
369
+ "step": 120
370
+ },
371
+ {
372
+ "epoch": 0.26720106880427524,
373
+ "grad_norm": 2.952766609523329,
374
+ "learning_rate": 1.834573253721303e-05,
375
+ "logits/chosen": 0.16905634105205536,
376
+ "logits/rejected": 0.18389183282852173,
377
+ "logps/chosen": -0.5878621339797974,
378
+ "logps/rejected": -0.6856662034988403,
379
+ "loss": 1.2725,
380
+ "rewards/accuracies": 0.6187499761581421,
381
+ "rewards/chosen": -0.5878621339797974,
382
+ "rewards/margins": 0.097803995013237,
383
+ "rewards/rejected": -0.6856662034988403,
384
+ "step": 125
385
+ },
386
+ {
387
+ "epoch": 0.27788911155644624,
388
+ "grad_norm": 4.574556482577368,
389
+ "learning_rate": 1.8133909445815277e-05,
390
+ "logits/chosen": 0.2116955816745758,
391
+ "logits/rejected": 0.23542623221874237,
392
+ "logps/chosen": -0.6415301561355591,
393
+ "logps/rejected": -0.711525559425354,
394
+ "loss": 1.3254,
395
+ "rewards/accuracies": 0.625,
396
+ "rewards/chosen": -0.6415301561355591,
397
+ "rewards/margins": 0.06999534368515015,
398
+ "rewards/rejected": -0.711525559425354,
399
+ "step": 130
400
+ },
401
+ {
402
+ "epoch": 0.28857715430861725,
403
+ "grad_norm": 3.3299570451518163,
404
+ "learning_rate": 1.7910710346563417e-05,
405
+ "logits/chosen": 0.21890752017498016,
406
+ "logits/rejected": 0.2111731767654419,
407
+ "logps/chosen": -0.6361859440803528,
408
+ "logps/rejected": -0.7430610656738281,
409
+ "loss": 1.3005,
410
+ "rewards/accuracies": 0.574999988079071,
411
+ "rewards/chosen": -0.6361859440803528,
412
+ "rewards/margins": 0.10687508434057236,
413
+ "rewards/rejected": -0.7430610656738281,
414
+ "step": 135
415
+ },
416
+ {
417
+ "epoch": 0.29926519706078825,
418
+ "grad_norm": 4.712724056108227,
419
+ "learning_rate": 1.7676447403580114e-05,
420
+ "logits/chosen": 0.17464594542980194,
421
+ "logits/rejected": 0.15127554535865784,
422
+ "logps/chosen": -0.6231650114059448,
423
+ "logps/rejected": -0.7518295049667358,
424
+ "loss": 1.3004,
425
+ "rewards/accuracies": 0.6499999761581421,
426
+ "rewards/chosen": -0.6231650114059448,
427
+ "rewards/margins": 0.12866440415382385,
428
+ "rewards/rejected": -0.7518295049667358,
429
+ "step": 140
430
+ },
431
+ {
432
+ "epoch": 0.30995323981295925,
433
+ "grad_norm": 3.8840639264672605,
434
+ "learning_rate": 1.7431448254773943e-05,
435
+ "logits/chosen": 0.09850597381591797,
436
+ "logits/rejected": 0.06791912019252777,
437
+ "logps/chosen": -0.6357108950614929,
438
+ "logps/rejected": -0.7526232004165649,
439
+ "loss": 1.2942,
440
+ "rewards/accuracies": 0.5874999761581421,
441
+ "rewards/chosen": -0.6357108950614929,
442
+ "rewards/margins": 0.11691226810216904,
443
+ "rewards/rejected": -0.7526232004165649,
444
+ "step": 145
445
+ },
446
+ {
447
+ "epoch": 0.32064128256513025,
448
+ "grad_norm": 3.8874041876031167,
449
+ "learning_rate": 1.717605555360812e-05,
450
+ "logits/chosen": -0.051757656037807465,
451
+ "logits/rejected": -0.07511379569768906,
452
+ "logps/chosen": -0.6289964914321899,
453
+ "logps/rejected": -0.7442386746406555,
454
+ "loss": 1.3017,
455
+ "rewards/accuracies": 0.612500011920929,
456
+ "rewards/chosen": -0.6289964914321899,
457
+ "rewards/margins": 0.115242138504982,
458
+ "rewards/rejected": -0.7442386746406555,
459
+ "step": 150
460
+ },
461
+ {
462
+ "epoch": 0.33132932531730125,
463
+ "grad_norm": 2.9263158094537807,
464
+ "learning_rate": 1.691062648986865e-05,
465
+ "logits/chosen": 0.0783982202410698,
466
+ "logits/rejected": 0.06652794033288956,
467
+ "logps/chosen": -0.6385728120803833,
468
+ "logps/rejected": -0.7080265283584595,
469
+ "loss": 1.2934,
470
+ "rewards/accuracies": 0.5249999761581421,
471
+ "rewards/chosen": -0.6385728120803833,
472
+ "rewards/margins": 0.06945370137691498,
473
+ "rewards/rejected": -0.7080265283584595,
474
+ "step": 155
475
+ },
476
+ {
477
+ "epoch": 0.3420173680694723,
478
+ "grad_norm": 3.7316994379774573,
479
+ "learning_rate": 1.6635532290102114e-05,
480
+ "logits/chosen": 0.100054070353508,
481
+ "logits/rejected": 0.10980580747127533,
482
+ "logps/chosen": -0.6498998403549194,
483
+ "logps/rejected": -0.7538723945617676,
484
+ "loss": 1.3188,
485
+ "rewards/accuracies": 0.550000011920929,
486
+ "rewards/chosen": -0.6498998403549194,
487
+ "rewards/margins": 0.10397255420684814,
488
+ "rewards/rejected": -0.7538723945617676,
489
+ "step": 160
490
+ },
491
+ {
492
+ "epoch": 0.3527054108216433,
493
+ "grad_norm": 3.48431507554954,
494
+ "learning_rate": 1.635115769842179e-05,
495
+ "logits/chosen": -0.07162860035896301,
496
+ "logits/rejected": -0.08312487602233887,
497
+ "logps/chosen": -0.5983825325965881,
498
+ "logps/rejected": -0.6531118750572205,
499
+ "loss": 1.3115,
500
+ "rewards/accuracies": 0.5687500238418579,
501
+ "rewards/chosen": -0.5983825325965881,
502
+ "rewards/margins": 0.0547294095158577,
503
+ "rewards/rejected": -0.6531118750572205,
504
+ "step": 165
505
+ },
506
+ {
507
+ "epoch": 0.3633934535738143,
508
+ "grad_norm": 3.1045296158878495,
509
+ "learning_rate": 1.60579004384082e-05,
510
+ "logits/chosen": -0.034972742199897766,
511
+ "logits/rejected": -0.024472128599882126,
512
+ "logps/chosen": -0.6385360956192017,
513
+ "logps/rejected": -0.7788956761360168,
514
+ "loss": 1.2984,
515
+ "rewards/accuracies": 0.6187499761581421,
516
+ "rewards/chosen": -0.6385360956192017,
517
+ "rewards/margins": 0.14035962522029877,
518
+ "rewards/rejected": -0.7788956761360168,
519
+ "step": 170
520
+ },
521
+ {
522
+ "epoch": 0.3740814963259853,
523
+ "grad_norm": 2.8548400499038884,
524
+ "learning_rate": 1.575617065685674e-05,
525
+ "logits/chosen": -0.13102661073207855,
526
+ "logits/rejected": -0.13152942061424255,
527
+ "logps/chosen": -0.6120776534080505,
528
+ "logps/rejected": -0.6730025410652161,
529
+ "loss": 1.3073,
530
+ "rewards/accuracies": 0.5874999761581421,
531
+ "rewards/chosen": -0.6120776534080505,
532
+ "rewards/margins": 0.06092479079961777,
533
+ "rewards/rejected": -0.6730025410652161,
534
+ "step": 175
535
+ },
536
+ {
537
+ "epoch": 0.3847695390781563,
538
+ "grad_norm": 5.270781840059861,
539
+ "learning_rate": 1.5446390350150272e-05,
540
+ "logits/chosen": -0.16384097933769226,
541
+ "logits/rejected": -0.16462591290473938,
542
+ "logps/chosen": -0.6268705725669861,
543
+ "logps/rejected": -0.7125908136367798,
544
+ "loss": 1.3028,
545
+ "rewards/accuracies": 0.5687500238418579,
546
+ "rewards/chosen": -0.6268705725669861,
547
+ "rewards/margins": 0.08572021126747131,
548
+ "rewards/rejected": -0.7125908136367798,
549
+ "step": 180
550
+ },
551
+ {
552
+ "epoch": 0.3954575818303273,
553
+ "grad_norm": 2.9703550953722244,
554
+ "learning_rate": 1.5128992774059063e-05,
555
+ "logits/chosen": -0.2370837926864624,
556
+ "logits/rejected": -0.2578278183937073,
557
+ "logps/chosen": -0.6618776321411133,
558
+ "logps/rejected": -0.6950840353965759,
559
+ "loss": 1.3242,
560
+ "rewards/accuracies": 0.5687500238418579,
561
+ "rewards/chosen": -0.6618776321411133,
562
+ "rewards/margins": 0.03320637717843056,
563
+ "rewards/rejected": -0.6950840353965759,
564
+ "step": 185
565
+ },
566
+ {
567
+ "epoch": 0.4061456245824983,
568
+ "grad_norm": 2.576969091118456,
569
+ "learning_rate": 1.4804421837793379e-05,
570
+ "logits/chosen": -0.31508585810661316,
571
+ "logits/rejected": -0.31256750226020813,
572
+ "logps/chosen": -0.6105505228042603,
573
+ "logps/rejected": -0.6881141066551208,
574
+ "loss": 1.2954,
575
+ "rewards/accuracies": 0.59375,
576
+ "rewards/chosen": -0.6105505228042603,
577
+ "rewards/margins": 0.07756359130144119,
578
+ "rewards/rejected": -0.6881141066551208,
579
+ "step": 190
580
+ },
581
+ {
582
+ "epoch": 0.4168336673346693,
583
+ "grad_norm": 3.796929659092338,
584
+ "learning_rate": 1.4473131483156326e-05,
585
+ "logits/chosen": -0.25943300127983093,
586
+ "logits/rejected": -0.26059621572494507,
587
+ "logps/chosen": -0.6393094062805176,
588
+ "logps/rejected": -0.7625299096107483,
589
+ "loss": 1.2856,
590
+ "rewards/accuracies": 0.6312500238418579,
591
+ "rewards/chosen": -0.6393094062805176,
592
+ "rewards/margins": 0.12322056293487549,
593
+ "rewards/rejected": -0.7625299096107483,
594
+ "step": 195
595
+ },
596
+ {
597
+ "epoch": 0.42752171008684037,
598
+ "grad_norm": 3.4441112067059683,
599
+ "learning_rate": 1.4135585049665207e-05,
600
+ "logits/chosen": -0.24460437893867493,
601
+ "logits/rejected": -0.2346183955669403,
602
+ "logps/chosen": -0.6215813755989075,
603
+ "logps/rejected": -0.7071408629417419,
604
+ "loss": 1.2968,
605
+ "rewards/accuracies": 0.6000000238418579,
606
+ "rewards/chosen": -0.6215813755989075,
607
+ "rewards/margins": 0.08555953204631805,
608
+ "rewards/rejected": -0.7071408629417419,
609
+ "step": 200
610
+ },
611
+ {
612
+ "epoch": 0.43820975283901137,
613
+ "grad_norm": 2.8503959168303465,
614
+ "learning_rate": 1.3792254626529286e-05,
615
+ "logits/chosen": -0.23945841193199158,
616
+ "logits/rejected": -0.2520154118537903,
617
+ "logps/chosen": -0.6485592722892761,
618
+ "logps/rejected": -0.7163916826248169,
619
+ "loss": 1.3058,
620
+ "rewards/accuracies": 0.59375,
621
+ "rewards/chosen": -0.6485592722892761,
622
+ "rewards/margins": 0.06783244758844376,
623
+ "rewards/rejected": -0.7163916826248169,
624
+ "step": 205
625
+ },
626
+ {
627
+ "epoch": 0.44889779559118237,
628
+ "grad_norm": 2.9623348839853323,
629
+ "learning_rate": 1.3443620392390352e-05,
630
+ "logits/chosen": -0.22061018645763397,
631
+ "logits/rejected": -0.21657535433769226,
632
+ "logps/chosen": -0.6273641586303711,
633
+ "logps/rejected": -0.7573559880256653,
634
+ "loss": 1.3037,
635
+ "rewards/accuracies": 0.6499999761581421,
636
+ "rewards/chosen": -0.6273641586303711,
637
+ "rewards/margins": 0.1299917995929718,
638
+ "rewards/rejected": -0.7573559880256653,
639
+ "step": 210
640
+ },
641
+ {
642
+ "epoch": 0.45958583834335337,
643
+ "grad_norm": 3.2413099077478713,
644
+ "learning_rate": 1.3090169943749475e-05,
645
+ "logits/chosen": -0.11810100078582764,
646
+ "logits/rejected": -0.14453695714473724,
647
+ "logps/chosen": -0.6222162246704102,
648
+ "logps/rejected": -0.7621700763702393,
649
+ "loss": 1.2812,
650
+ "rewards/accuracies": 0.7124999761581421,
651
+ "rewards/chosen": -0.6222162246704102,
652
+ "rewards/margins": 0.1399538516998291,
653
+ "rewards/rejected": -0.7621700763702393,
654
+ "step": 215
655
+ },
656
+ {
657
+ "epoch": 0.47027388109552437,
658
+ "grad_norm": 3.1218400805304007,
659
+ "learning_rate": 1.2732397613019203e-05,
660
+ "logits/chosen": -0.26869744062423706,
661
+ "logits/rejected": -0.277025043964386,
662
+ "logps/chosen": -0.6378098726272583,
663
+ "logps/rejected": -0.7766000628471375,
664
+ "loss": 1.281,
665
+ "rewards/accuracies": 0.643750011920929,
666
+ "rewards/chosen": -0.6378098726272583,
667
+ "rewards/margins": 0.13879024982452393,
668
+ "rewards/rejected": -0.7766000628471375,
669
+ "step": 220
670
+ },
671
+ {
672
+ "epoch": 0.48096192384769537,
673
+ "grad_norm": 3.2992783572988698,
674
+ "learning_rate": 1.2370803777154976e-05,
675
+ "logits/chosen": -0.3226834833621979,
676
+ "logits/rejected": -0.33692580461502075,
677
+ "logps/chosen": -0.6211170554161072,
678
+ "logps/rejected": -0.7601276636123657,
679
+ "loss": 1.2728,
680
+ "rewards/accuracies": 0.6625000238418579,
681
+ "rewards/chosen": -0.6211170554161072,
682
+ "rewards/margins": 0.13901060819625854,
683
+ "rewards/rejected": -0.7601276636123657,
684
+ "step": 225
685
+ },
686
+ {
687
+ "epoch": 0.4916499665998664,
688
+ "grad_norm": 2.9698612659347132,
689
+ "learning_rate": 1.200589415783273e-05,
690
+ "logits/chosen": -0.2805679142475128,
691
+ "logits/rejected": -0.3003981113433838,
692
+ "logps/chosen": -0.6456371545791626,
693
+ "logps/rejected": -0.7589985132217407,
694
+ "loss": 1.2923,
695
+ "rewards/accuracies": 0.6312500238418579,
696
+ "rewards/chosen": -0.6456371545791626,
697
+ "rewards/margins": 0.11336138099431992,
698
+ "rewards/rejected": -0.7589985132217407,
699
+ "step": 230
700
+ },
701
+ {
702
+ "epoch": 0.5023380093520374,
703
+ "grad_norm": 2.93442353979503,
704
+ "learning_rate": 1.1638179114151378e-05,
705
+ "logits/chosen": -0.2719253897666931,
706
+ "logits/rejected": -0.2693996727466583,
707
+ "logps/chosen": -0.5996414422988892,
708
+ "logps/rejected": -0.7817131876945496,
709
+ "loss": 1.2908,
710
+ "rewards/accuracies": 0.612500011920929,
711
+ "rewards/chosen": -0.5996414422988892,
712
+ "rewards/margins": 0.18207184970378876,
713
+ "rewards/rejected": -0.7817131876945496,
714
+ "step": 235
715
+ },
716
+ {
717
+ "epoch": 0.5130260521042084,
718
+ "grad_norm": 3.1656667859377405,
719
+ "learning_rate": 1.1268172928849486e-05,
720
+ "logits/chosen": -0.36759647727012634,
721
+ "logits/rejected": -0.36635178327560425,
722
+ "logps/chosen": -0.5924197435379028,
723
+ "logps/rejected": -0.7910494208335876,
724
+ "loss": 1.286,
725
+ "rewards/accuracies": 0.675000011920929,
726
+ "rewards/chosen": -0.5924197435379028,
727
+ "rewards/margins": 0.1986297070980072,
728
+ "rewards/rejected": -0.7910494208335876,
729
+ "step": 240
730
+ },
731
+ {
732
+ "epoch": 0.5237140948563794,
733
+ "grad_norm": 2.891600548101634,
734
+ "learning_rate": 1.0896393089034336e-05,
735
+ "logits/chosen": -0.3432336151599884,
736
+ "logits/rejected": -0.33940672874450684,
737
+ "logps/chosen": -0.6054046154022217,
738
+ "logps/rejected": -0.6738919615745544,
739
+ "loss": 1.2829,
740
+ "rewards/accuracies": 0.643750011920929,
741
+ "rewards/chosen": -0.6054046154022217,
742
+ "rewards/margins": 0.06848734617233276,
743
+ "rewards/rejected": -0.6738919615745544,
744
+ "step": 245
745
+ },
746
+ {
747
+ "epoch": 0.5344021376085505,
748
+ "grad_norm": 5.01628908139822,
749
+ "learning_rate": 1.0523359562429441e-05,
750
+ "logits/chosen": -0.383030503988266,
751
+ "logits/rejected": -0.399156779050827,
752
+ "logps/chosen": -0.6492289900779724,
753
+ "logps/rejected": -0.769420862197876,
754
+ "loss": 1.2834,
755
+ "rewards/accuracies": 0.625,
756
+ "rewards/chosen": -0.6492289900779724,
757
+ "rewards/margins": 0.12019187211990356,
758
+ "rewards/rejected": -0.769420862197876,
759
+ "step": 250
760
+ },
761
+ {
762
+ "epoch": 0.5450901803607214,
763
+ "grad_norm": 2.9846407948611695,
764
+ "learning_rate": 1.0149594070152638e-05,
765
+ "logits/chosen": -0.41133952140808105,
766
+ "logits/rejected": -0.41932740807533264,
767
+ "logps/chosen": -0.6495887041091919,
768
+ "logps/rejected": -0.7451075315475464,
769
+ "loss": 1.3063,
770
+ "rewards/accuracies": 0.5687500238418579,
771
+ "rewards/chosen": -0.6495887041091919,
772
+ "rewards/margins": 0.09551887214183807,
773
+ "rewards/rejected": -0.7451075315475464,
774
+ "step": 255
775
+ },
776
+ {
777
+ "epoch": 0.5557782231128925,
778
+ "grad_norm": 3.025145774637567,
779
+ "learning_rate": 9.775619357041952e-06,
780
+ "logits/chosen": -0.37427011132240295,
781
+ "logits/rejected": -0.38933342695236206,
782
+ "logps/chosen": -0.5939801931381226,
783
+ "logps/rejected": -0.7346431016921997,
784
+ "loss": 1.2816,
785
+ "rewards/accuracies": 0.643750011920929,
786
+ "rewards/chosen": -0.5939801931381226,
787
+ "rewards/margins": 0.14066289365291595,
788
+ "rewards/rejected": -0.7346431016921997,
789
+ "step": 260
790
+ },
791
+ {
792
+ "epoch": 0.5664662658650634,
793
+ "grad_norm": 3.7873867621914634,
794
+ "learning_rate": 9.401958460549658e-06,
795
+ "logits/chosen": -0.3902246356010437,
796
+ "logits/rejected": -0.39489641785621643,
797
+ "logps/chosen": -0.5874339938163757,
798
+ "logps/rejected": -0.6752017736434937,
799
+ "loss": 1.2809,
800
+ "rewards/accuracies": 0.6000000238418579,
801
+ "rewards/chosen": -0.5874339938163757,
802
+ "rewards/margins": 0.08776768296957016,
803
+ "rewards/rejected": -0.6752017736434937,
804
+ "step": 265
805
+ },
806
+ {
807
+ "epoch": 0.5771543086172345,
808
+ "grad_norm": 4.336316474366534,
809
+ "learning_rate": 9.02913397922712e-06,
810
+ "logits/chosen": -0.4125131666660309,
811
+ "logits/rejected": -0.4208359122276306,
812
+ "logps/chosen": -0.607820987701416,
813
+ "logps/rejected": -0.905206024646759,
814
+ "loss": 1.2747,
815
+ "rewards/accuracies": 0.7437499761581421,
816
+ "rewards/chosen": -0.607820987701416,
817
+ "rewards/margins": 0.29738494753837585,
818
+ "rewards/rejected": -0.905206024646759,
819
+ "step": 270
820
+ },
821
+ {
822
+ "epoch": 0.5878423513694054,
823
+ "grad_norm": 2.9455182934401654,
824
+ "learning_rate": 8.657667341823449e-06,
825
+ "logits/chosen": -0.3412848114967346,
826
+ "logits/rejected": -0.3707515597343445,
827
+ "logps/chosen": -0.6197370290756226,
828
+ "logps/rejected": -0.7178043127059937,
829
+ "loss": 1.2785,
830
+ "rewards/accuracies": 0.6000000238418579,
831
+ "rewards/chosen": -0.6197370290756226,
832
+ "rewards/margins": 0.09806738793849945,
833
+ "rewards/rejected": -0.7178043127059937,
834
+ "step": 275
835
+ },
836
+ {
837
+ "epoch": 0.5985303941215765,
838
+ "grad_norm": 3.0985019376115464,
839
+ "learning_rate": 8.28807807802025e-06,
840
+ "logits/chosen": -0.32350999116897583,
841
+ "logits/rejected": -0.3327878415584564,
842
+ "logps/chosen": -0.5803725123405457,
843
+ "logps/rejected": -0.6662936210632324,
844
+ "loss": 1.2821,
845
+ "rewards/accuracies": 0.6312500238418579,
846
+ "rewards/chosen": -0.5803725123405457,
847
+ "rewards/margins": 0.08592123538255692,
848
+ "rewards/rejected": -0.6662936210632324,
849
+ "step": 280
850
+ },
851
+ {
852
+ "epoch": 0.6092184368737475,
853
+ "grad_norm": 3.037932780161429,
854
+ "learning_rate": 7.92088309182241e-06,
855
+ "logits/chosen": -0.3814396262168884,
856
+ "logits/rejected": -0.38753852248191833,
857
+ "logps/chosen": -0.5815099477767944,
858
+ "logps/rejected": -0.6666026711463928,
859
+ "loss": 1.294,
860
+ "rewards/accuracies": 0.612500011920929,
861
+ "rewards/chosen": -0.5815099477767944,
862
+ "rewards/margins": 0.0850927084684372,
863
+ "rewards/rejected": -0.6666026711463928,
864
+ "step": 285
865
+ },
866
+ {
867
+ "epoch": 0.6199064796259185,
868
+ "grad_norm": 3.0961871877321485,
869
+ "learning_rate": 7.556595938621058e-06,
870
+ "logits/chosen": -0.46853989362716675,
871
+ "logits/rejected": -0.49206361174583435,
872
+ "logps/chosen": -0.6127103567123413,
873
+ "logps/rejected": -0.7595942616462708,
874
+ "loss": 1.2796,
875
+ "rewards/accuracies": 0.643750011920929,
876
+ "rewards/chosen": -0.6127103567123413,
877
+ "rewards/margins": 0.14688387513160706,
878
+ "rewards/rejected": -0.7595942616462708,
879
+ "step": 290
880
+ },
881
+ {
882
+ "epoch": 0.6305945223780896,
883
+ "grad_norm": 2.5558798414818837,
884
+ "learning_rate": 7.1957261069399745e-06,
885
+ "logits/chosen": -0.41997450590133667,
886
+ "logits/rejected": -0.41455715894699097,
887
+ "logps/chosen": -0.5393789410591125,
888
+ "logps/rejected": -0.6705390214920044,
889
+ "loss": 1.2859,
890
+ "rewards/accuracies": 0.6937500238418579,
891
+ "rewards/chosen": -0.5393789410591125,
892
+ "rewards/margins": 0.13116006553173065,
893
+ "rewards/rejected": -0.6705390214920044,
894
+ "step": 295
895
+ },
896
+ {
897
+ "epoch": 0.6412825651302605,
898
+ "grad_norm": 4.199327343754458,
899
+ "learning_rate": 6.83877830586976e-06,
900
+ "logits/chosen": -0.4186905324459076,
901
+ "logits/rejected": -0.400879442691803,
902
+ "logps/chosen": -0.5945369601249695,
903
+ "logps/rejected": -0.8209554553031921,
904
+ "loss": 1.2546,
905
+ "rewards/accuracies": 0.6937500238418579,
906
+ "rewards/chosen": -0.5945369601249695,
907
+ "rewards/margins": 0.22641853988170624,
908
+ "rewards/rejected": -0.8209554553031921,
909
+ "step": 300
910
+ },
911
+ {
912
+ "epoch": 0.6519706078824316,
913
+ "grad_norm": 3.5426555178859074,
914
+ "learning_rate": 6.486251759186573e-06,
915
+ "logits/chosen": -0.42441505193710327,
916
+ "logits/rejected": -0.4325898587703705,
917
+ "logps/chosen": -0.6070866584777832,
918
+ "logps/rejected": -0.7520343661308289,
919
+ "loss": 1.2695,
920
+ "rewards/accuracies": 0.6937500238418579,
921
+ "rewards/chosen": -0.6070866584777832,
922
+ "rewards/margins": 0.14494772255420685,
923
+ "rewards/rejected": -0.7520343661308289,
924
+ "step": 305
925
+ },
926
+ {
927
+ "epoch": 0.6626586506346025,
928
+ "grad_norm": 3.399076738544932,
929
+ "learning_rate": 6.138639507142539e-06,
930
+ "logits/chosen": -0.40451377630233765,
931
+ "logits/rejected": -0.41942930221557617,
932
+ "logps/chosen": -0.5666729211807251,
933
+ "logps/rejected": -0.685453474521637,
934
+ "loss": 1.2546,
935
+ "rewards/accuracies": 0.6625000238418579,
936
+ "rewards/chosen": -0.5666729211807251,
937
+ "rewards/margins": 0.11878061294555664,
938
+ "rewards/rejected": -0.685453474521637,
939
+ "step": 310
940
+ },
941
+ {
942
+ "epoch": 0.6733466933867736,
943
+ "grad_norm": 3.5429592529416407,
944
+ "learning_rate": 5.796427716904347e-06,
945
+ "logits/chosen": -0.3595660328865051,
946
+ "logits/rejected": -0.3509676158428192,
947
+ "logps/chosen": -0.6435049772262573,
948
+ "logps/rejected": -0.7910181879997253,
949
+ "loss": 1.2803,
950
+ "rewards/accuracies": 0.543749988079071,
951
+ "rewards/chosen": -0.6435049772262573,
952
+ "rewards/margins": 0.14751319587230682,
953
+ "rewards/rejected": -0.7910181879997253,
954
+ "step": 315
955
+ },
956
+ {
957
+ "epoch": 0.6840347361389446,
958
+ "grad_norm": 3.6719145043569146,
959
+ "learning_rate": 5.460095002604533e-06,
960
+ "logits/chosen": -0.3422035574913025,
961
+ "logits/rejected": -0.34498724341392517,
962
+ "logps/chosen": -0.5467932224273682,
963
+ "logps/rejected": -0.6095358729362488,
964
+ "loss": 1.2877,
965
+ "rewards/accuracies": 0.581250011920929,
966
+ "rewards/chosen": -0.5467932224273682,
967
+ "rewards/margins": 0.06274259090423584,
968
+ "rewards/rejected": -0.6095358729362488,
969
+ "step": 320
970
+ },
971
+ {
972
+ "epoch": 0.6947227788911156,
973
+ "grad_norm": 3.978020135849161,
974
+ "learning_rate": 5.130111755956327e-06,
975
+ "logits/chosen": -0.3481397032737732,
976
+ "logits/rejected": -0.34341806173324585,
977
+ "logps/chosen": -0.5532098412513733,
978
+ "logps/rejected": -0.7315355539321899,
979
+ "loss": 1.2661,
980
+ "rewards/accuracies": 0.6875,
981
+ "rewards/chosen": -0.5532098412513733,
982
+ "rewards/margins": 0.17832568287849426,
983
+ "rewards/rejected": -0.7315355539321899,
984
+ "step": 325
985
+ },
986
+ {
987
+ "epoch": 0.7054108216432866,
988
+ "grad_norm": 3.442968094749812,
989
+ "learning_rate": 4.806939488368308e-06,
990
+ "logits/chosen": -0.4118443429470062,
991
+ "logits/rejected": -0.4033087193965912,
992
+ "logps/chosen": -0.5545328855514526,
993
+ "logps/rejected": -0.7638643383979797,
994
+ "loss": 1.2502,
995
+ "rewards/accuracies": 0.581250011920929,
996
+ "rewards/chosen": -0.5545328855514526,
997
+ "rewards/margins": 0.2093314677476883,
998
+ "rewards/rejected": -0.7638643383979797,
999
+ "step": 330
1000
+ },
1001
+ {
1002
+ "epoch": 0.7160988643954576,
1003
+ "grad_norm": 3.693118587496843,
1004
+ "learning_rate": 4.491030185478976e-06,
1005
+ "logits/chosen": -0.3698023855686188,
1006
+ "logits/rejected": -0.3537530303001404,
1007
+ "logps/chosen": -0.5946871042251587,
1008
+ "logps/rejected": -0.9203634262084961,
1009
+ "loss": 1.2694,
1010
+ "rewards/accuracies": 0.637499988079071,
1011
+ "rewards/chosen": -0.5946871042251587,
1012
+ "rewards/margins": 0.32567623257637024,
1013
+ "rewards/rejected": -0.9203634262084961,
1014
+ "step": 335
1015
+ },
1016
+ {
1017
+ "epoch": 0.7267869071476286,
1018
+ "grad_norm": 3.528628571085271,
1019
+ "learning_rate": 4.182825675013945e-06,
1020
+ "logits/chosen": -0.4216648042201996,
1021
+ "logits/rejected": -0.4200260639190674,
1022
+ "logps/chosen": -0.5487005710601807,
1023
+ "logps/rejected": -0.6899628639221191,
1024
+ "loss": 1.2749,
1025
+ "rewards/accuracies": 0.668749988079071,
1026
+ "rewards/chosen": -0.5487005710601807,
1027
+ "rewards/margins": 0.14126229286193848,
1028
+ "rewards/rejected": -0.6899628639221191,
1029
+ "step": 340
1030
+ },
1031
+ {
1032
+ "epoch": 0.7374749498997996,
1033
+ "grad_norm": 3.8114111942749536,
1034
+ "learning_rate": 3.882757008849936e-06,
1035
+ "logits/chosen": -0.41083043813705444,
1036
+ "logits/rejected": -0.4161206781864166,
1037
+ "logps/chosen": -0.575046181678772,
1038
+ "logps/rejected": -0.7536992430686951,
1039
+ "loss": 1.2744,
1040
+ "rewards/accuracies": 0.6875,
1041
+ "rewards/chosen": -0.575046181678772,
1042
+ "rewards/margins": 0.17865313589572906,
1043
+ "rewards/rejected": -0.7536992430686951,
1044
+ "step": 345
1045
+ },
1046
+ {
1047
+ "epoch": 0.7481629926519706,
1048
+ "grad_norm": 4.0438053008699315,
1049
+ "learning_rate": 3.591243860149759e-06,
1050
+ "logits/chosen": -0.3628717064857483,
1051
+ "logits/rejected": -0.3853951096534729,
1052
+ "logps/chosen": -0.5914100408554077,
1053
+ "logps/rejected": -0.7692973613739014,
1054
+ "loss": 1.2695,
1055
+ "rewards/accuracies": 0.6499999761581421,
1056
+ "rewards/chosen": -0.5914100408554077,
1057
+ "rewards/margins": 0.17788729071617126,
1058
+ "rewards/rejected": -0.7692973613739014,
1059
+ "step": 350
1060
+ },
1061
+ {
1062
+ "epoch": 0.7588510354041417,
1063
+ "grad_norm": 3.0837058616543813,
1064
+ "learning_rate": 3.308693936411421e-06,
1065
+ "logits/chosen": -0.41618281602859497,
1066
+ "logits/rejected": -0.41979169845581055,
1067
+ "logps/chosen": -0.6286286115646362,
1068
+ "logps/rejected": -0.8485868573188782,
1069
+ "loss": 1.2669,
1070
+ "rewards/accuracies": 0.6000000238418579,
1071
+ "rewards/chosen": -0.6286286115646362,
1072
+ "rewards/margins": 0.2199581414461136,
1073
+ "rewards/rejected": -0.8485868573188782,
1074
+ "step": 355
1075
+ },
1076
+ {
1077
+ "epoch": 0.7695390781563126,
1078
+ "grad_norm": 3.528809280951808,
1079
+ "learning_rate": 3.0355024092523334e-06,
1080
+ "logits/chosen": -0.38231906294822693,
1081
+ "logits/rejected": -0.40169796347618103,
1082
+ "logps/chosen": -0.5484600067138672,
1083
+ "logps/rejected": -0.6940116882324219,
1084
+ "loss": 1.2726,
1085
+ "rewards/accuracies": 0.6625000238418579,
1086
+ "rewards/chosen": -0.5484600067138672,
1087
+ "rewards/margins": 0.14555169641971588,
1088
+ "rewards/rejected": -0.6940116882324219,
1089
+ "step": 360
1090
+ },
1091
+ {
1092
+ "epoch": 0.7802271209084837,
1093
+ "grad_norm": 3.5483575752162406,
1094
+ "learning_rate": 2.7720513617260857e-06,
1095
+ "logits/chosen": -0.44837936758995056,
1096
+ "logits/rejected": -0.4736010432243347,
1097
+ "logps/chosen": -0.6057429313659668,
1098
+ "logps/rejected": -0.7651041746139526,
1099
+ "loss": 1.2659,
1100
+ "rewards/accuracies": 0.6312500238418579,
1101
+ "rewards/chosen": -0.6057429313659668,
1102
+ "rewards/margins": 0.15936115384101868,
1103
+ "rewards/rejected": -0.7651041746139526,
1104
+ "step": 365
1105
+ },
1106
+ {
1107
+ "epoch": 0.7909151636606546,
1108
+ "grad_norm": 3.7870821722349985,
1109
+ "learning_rate": 2.51870925394473e-06,
1110
+ "logits/chosen": -0.43106943368911743,
1111
+ "logits/rejected": -0.44449687004089355,
1112
+ "logps/chosen": -0.5907775163650513,
1113
+ "logps/rejected": -0.7539359331130981,
1114
+ "loss": 1.2464,
1115
+ "rewards/accuracies": 0.7250000238418579,
1116
+ "rewards/chosen": -0.5907775163650513,
1117
+ "rewards/margins": 0.1631583422422409,
1118
+ "rewards/rejected": -0.7539359331130981,
1119
+ "step": 370
1120
+ },
1121
+ {
1122
+ "epoch": 0.8016032064128257,
1123
+ "grad_norm": 3.7264373621641713,
1124
+ "learning_rate": 2.275830407754006e-06,
1125
+ "logits/chosen": -0.4176546633243561,
1126
+ "logits/rejected": -0.4209866523742676,
1127
+ "logps/chosen": -0.6014735102653503,
1128
+ "logps/rejected": -0.7754963040351868,
1129
+ "loss": 1.2615,
1130
+ "rewards/accuracies": 0.6875,
1131
+ "rewards/chosen": -0.6014735102653503,
1132
+ "rewards/margins": 0.1740228235721588,
1133
+ "rewards/rejected": -0.7754963040351868,
1134
+ "step": 375
1135
+ },
1136
+ {
1137
+ "epoch": 0.8122912491649966,
1138
+ "grad_norm": 3.211374199470538,
1139
+ "learning_rate": 2.043754511182191e-06,
1140
+ "logits/chosen": -0.42597073316574097,
1141
+ "logits/rejected": -0.4239738881587982,
1142
+ "logps/chosen": -0.5504560470581055,
1143
+ "logps/rejected": -0.7494019269943237,
1144
+ "loss": 1.2622,
1145
+ "rewards/accuracies": 0.6499999761581421,
1146
+ "rewards/chosen": -0.5504560470581055,
1147
+ "rewards/margins": 0.19894585013389587,
1148
+ "rewards/rejected": -0.7494019269943237,
1149
+ "step": 380
1150
+ },
1151
+ {
1152
+ "epoch": 0.8229792919171677,
1153
+ "grad_norm": 3.301850545380218,
1154
+ "learning_rate": 1.8228061433556866e-06,
1155
+ "logits/chosen": -0.408210426568985,
1156
+ "logits/rejected": -0.41355451941490173,
1157
+ "logps/chosen": -0.5664467811584473,
1158
+ "logps/rejected": -0.7051645517349243,
1159
+ "loss": 1.2613,
1160
+ "rewards/accuracies": 0.6812499761581421,
1161
+ "rewards/chosen": -0.5664467811584473,
1162
+ "rewards/margins": 0.13871778547763824,
1163
+ "rewards/rejected": -0.7051645517349243,
1164
+ "step": 385
1165
+ },
1166
+ {
1167
+ "epoch": 0.8336673346693386,
1168
+ "grad_norm": 3.141220152295375,
1169
+ "learning_rate": 1.6132943205457607e-06,
1170
+ "logits/chosen": -0.41336697340011597,
1171
+ "logits/rejected": -0.4139551520347595,
1172
+ "logps/chosen": -0.556975245475769,
1173
+ "logps/rejected": -0.6668010950088501,
1174
+ "loss": 1.257,
1175
+ "rewards/accuracies": 0.606249988079071,
1176
+ "rewards/chosen": -0.556975245475769,
1177
+ "rewards/margins": 0.10982589423656464,
1178
+ "rewards/rejected": -0.6668010950088501,
1179
+ "step": 390
1180
+ },
1181
+ {
1182
+ "epoch": 0.8443553774215097,
1183
+ "grad_norm": 4.402129582330891,
1184
+ "learning_rate": 1.4155120639813392e-06,
1185
+ "logits/chosen": -0.4578641355037689,
1186
+ "logits/rejected": -0.4619896411895752,
1187
+ "logps/chosen": -0.5758166909217834,
1188
+ "logps/rejected": -0.6729660630226135,
1189
+ "loss": 1.271,
1190
+ "rewards/accuracies": 0.6187499761581421,
1191
+ "rewards/chosen": -0.5758166909217834,
1192
+ "rewards/margins": 0.09714937210083008,
1193
+ "rewards/rejected": -0.6729660630226135,
1194
+ "step": 395
1195
+ },
1196
+ {
1197
+ "epoch": 0.8550434201736807,
1198
+ "grad_norm": 3.440496458892442,
1199
+ "learning_rate": 1.2297359900323346e-06,
1200
+ "logits/chosen": -0.48626774549484253,
1201
+ "logits/rejected": -0.48332077264785767,
1202
+ "logps/chosen": -0.6083348989486694,
1203
+ "logps/rejected": -0.7751791477203369,
1204
+ "loss": 1.2571,
1205
+ "rewards/accuracies": 0.6625000238418579,
1206
+ "rewards/chosen": -0.6083348989486694,
1207
+ "rewards/margins": 0.1668442189693451,
1208
+ "rewards/rejected": -0.7751791477203369,
1209
+ "step": 400
1210
+ },
1211
+ {
1212
+ "epoch": 0.8550434201736807,
1213
+ "eval_logits/chosen": -0.3830186724662781,
1214
+ "eval_logits/rejected": -0.3938583731651306,
1215
+ "eval_logps/chosen": -0.5791661143302917,
1216
+ "eval_logps/rejected": -0.7269699573516846,
1217
+ "eval_loss": 1.2552496194839478,
1218
+ "eval_rewards/accuracies": 0.6626016497612,
1219
+ "eval_rewards/chosen": -0.5791661143302917,
1220
+ "eval_rewards/margins": 0.14780384302139282,
1221
+ "eval_rewards/rejected": -0.7269699573516846,
1222
+ "eval_runtime": 426.1833,
1223
+ "eval_samples_per_second": 4.601,
1224
+ "eval_steps_per_second": 0.289,
1225
+ "step": 400
1226
+ },
1227
+ {
1228
+ "epoch": 0.8657314629258517,
1229
+ "grad_norm": 3.9745302359804944,
1230
+ "learning_rate": 1.0562259233366334e-06,
1231
+ "logits/chosen": -0.48229265213012695,
1232
+ "logits/rejected": -0.5193549394607544,
1233
+ "logps/chosen": -0.6197930574417114,
1234
+ "logps/rejected": -0.764507532119751,
1235
+ "loss": 1.2391,
1236
+ "rewards/accuracies": 0.643750011920929,
1237
+ "rewards/chosen": -0.6197930574417114,
1238
+ "rewards/margins": 0.14471451938152313,
1239
+ "rewards/rejected": -0.764507532119751,
1240
+ "step": 405
1241
+ },
1242
+ {
1243
+ "epoch": 0.8764195056780227,
1244
+ "grad_norm": 3.419466411083352,
1245
+ "learning_rate": 8.952245334118415e-07,
1246
+ "logits/chosen": -0.4593311846256256,
1247
+ "logits/rejected": -0.4776662290096283,
1248
+ "logps/chosen": -0.5977698564529419,
1249
+ "logps/rejected": -0.7118576765060425,
1250
+ "loss": 1.2719,
1251
+ "rewards/accuracies": 0.5625,
1252
+ "rewards/chosen": -0.5977698564529419,
1253
+ "rewards/margins": 0.11408782005310059,
1254
+ "rewards/rejected": -0.7118576765060425,
1255
+ "step": 410
1256
+ },
1257
+ {
1258
+ "epoch": 0.8871075484301937,
1259
+ "grad_norm": 3.431721917530868,
1260
+ "learning_rate": 7.46956995260033e-07,
1261
+ "logits/chosen": -0.4408165514469147,
1262
+ "logits/rejected": -0.45343226194381714,
1263
+ "logps/chosen": -0.5183443427085876,
1264
+ "logps/rejected": -0.6987067461013794,
1265
+ "loss": 1.251,
1266
+ "rewards/accuracies": 0.675000011920929,
1267
+ "rewards/chosen": -0.5183443427085876,
1268
+ "rewards/margins": 0.1803622990846634,
1269
+ "rewards/rejected": -0.6987067461013794,
1270
+ "step": 415
1271
+ },
1272
+ {
1273
+ "epoch": 0.8977955911823647,
1274
+ "grad_norm": 3.3661467211282274,
1275
+ "learning_rate": 6.116306744401391e-07,
1276
+ "logits/chosen": -0.4190942645072937,
1277
+ "logits/rejected": -0.4262022376060486,
1278
+ "logps/chosen": -0.5752037763595581,
1279
+ "logps/rejected": -0.7899097204208374,
1280
+ "loss": 1.2457,
1281
+ "rewards/accuracies": 0.668749988079071,
1282
+ "rewards/chosen": -0.5752037763595581,
1283
+ "rewards/margins": 0.2147059142589569,
1284
+ "rewards/rejected": -0.7899097204208374,
1285
+ "step": 420
1286
+ },
1287
+ {
1288
+ "epoch": 0.9084836339345357,
1289
+ "grad_norm": 3.4491228706828267,
1290
+ "learning_rate": 4.894348370484648e-07,
1291
+ "logits/chosen": -0.3854565918445587,
1292
+ "logits/rejected": -0.41155076026916504,
1293
+ "logps/chosen": -0.5380185842514038,
1294
+ "logps/rejected": -0.7508363127708435,
1295
+ "loss": 1.2377,
1296
+ "rewards/accuracies": 0.6875,
1297
+ "rewards/chosen": -0.5380185842514038,
1298
+ "rewards/margins": 0.21281783282756805,
1299
+ "rewards/rejected": -0.7508363127708435,
1300
+ "step": 425
1301
+ },
1302
+ {
1303
+ "epoch": 0.9191716766867067,
1304
+ "grad_norm": 3.846770405186625,
1305
+ "learning_rate": 3.8054038501294077e-07,
1306
+ "logits/chosen": -0.42405056953430176,
1307
+ "logits/rejected": -0.4208356738090515,
1308
+ "logps/chosen": -0.5479136109352112,
1309
+ "logps/rejected": -0.7237703204154968,
1310
+ "loss": 1.2312,
1311
+ "rewards/accuracies": 0.6499999761581421,
1312
+ "rewards/chosen": -0.5479136109352112,
1313
+ "rewards/margins": 0.17585670948028564,
1314
+ "rewards/rejected": -0.7237703204154968,
1315
+ "step": 430
1316
+ },
1317
+ {
1318
+ "epoch": 0.9298597194388778,
1319
+ "grad_norm": 3.8565624225807036,
1320
+ "learning_rate": 2.8509961707132496e-07,
1321
+ "logits/chosen": -0.4456121325492859,
1322
+ "logits/rejected": -0.4567331373691559,
1323
+ "logps/chosen": -0.6145879030227661,
1324
+ "logps/rejected": -0.7536846995353699,
1325
+ "loss": 1.2534,
1326
+ "rewards/accuracies": 0.612500011920929,
1327
+ "rewards/chosen": -0.6145879030227661,
1328
+ "rewards/margins": 0.13909675180912018,
1329
+ "rewards/rejected": -0.7536846995353699,
1330
+ "step": 435
1331
+ },
1332
+ {
1333
+ "epoch": 0.9405477621910487,
1334
+ "grad_norm": 3.992184128956239,
1335
+ "learning_rate": 2.0324601576764525e-07,
1336
+ "logits/chosen": -0.42855358123779297,
1337
+ "logits/rejected": -0.44918686151504517,
1338
+ "logps/chosen": -0.6049205660820007,
1339
+ "logps/rejected": -0.7878492474555969,
1340
+ "loss": 1.2545,
1341
+ "rewards/accuracies": 0.637499988079071,
1342
+ "rewards/chosen": -0.6049205660820007,
1343
+ "rewards/margins": 0.1829286515712738,
1344
+ "rewards/rejected": -0.7878492474555969,
1345
+ "step": 440
1346
+ },
1347
+ {
1348
+ "epoch": 0.9512358049432198,
1349
+ "grad_norm": 3.818733547378664,
1350
+ "learning_rate": 1.350940607647866e-07,
1351
+ "logits/chosen": -0.3801869750022888,
1352
+ "logits/rejected": -0.38896074891090393,
1353
+ "logps/chosen": -0.5800012350082397,
1354
+ "logps/rejected": -0.7279914617538452,
1355
+ "loss": 1.2581,
1356
+ "rewards/accuracies": 0.6187499761581421,
1357
+ "rewards/chosen": -0.5800012350082397,
1358
+ "rewards/margins": 0.14799019694328308,
1359
+ "rewards/rejected": -0.7279914617538452,
1360
+ "step": 445
1361
+ },
1362
+ {
1363
+ "epoch": 0.9619238476953907,
1364
+ "grad_norm": 3.601185509771085,
1365
+ "learning_rate": 8.07390687343379e-08,
1366
+ "logits/chosen": -0.4334098696708679,
1367
+ "logits/rejected": -0.4463852047920227,
1368
+ "logps/chosen": -0.589901864528656,
1369
+ "logps/rejected": -0.768067479133606,
1370
+ "loss": 1.2422,
1371
+ "rewards/accuracies": 0.71875,
1372
+ "rewards/chosen": -0.589901864528656,
1373
+ "rewards/margins": 0.1781655251979828,
1374
+ "rewards/rejected": -0.768067479133606,
1375
+ "step": 450
1376
+ },
1377
+ {
1378
+ "epoch": 0.9726118904475618,
1379
+ "grad_norm": 3.7947367879452023,
1380
+ "learning_rate": 4.025706004760932e-08,
1381
+ "logits/chosen": -0.39869770407676697,
1382
+ "logits/rejected": -0.39332014322280884,
1383
+ "logps/chosen": -0.6198989152908325,
1384
+ "logps/rejected": -0.8089291453361511,
1385
+ "loss": 1.2643,
1386
+ "rewards/accuracies": 0.706250011920929,
1387
+ "rewards/chosen": -0.6198989152908325,
1388
+ "rewards/margins": 0.18903018534183502,
1389
+ "rewards/rejected": -0.8089291453361511,
1390
+ "step": 455
1391
+ },
1392
+ {
1393
+ "epoch": 0.9832999331997327,
1394
+ "grad_norm": 3.5592218644016613,
1395
+ "learning_rate": 1.370465245426167e-08,
1396
+ "logits/chosen": -0.39606115221977234,
1397
+ "logits/rejected": -0.4214437007904053,
1398
+ "logps/chosen": -0.5898042917251587,
1399
+ "logps/rejected": -0.7647892832756042,
1400
+ "loss": 1.2623,
1401
+ "rewards/accuracies": 0.6937500238418579,
1402
+ "rewards/chosen": -0.5898042917251587,
1403
+ "rewards/margins": 0.17498508095741272,
1404
+ "rewards/rejected": -0.7647892832756042,
1405
+ "step": 460
1406
+ },
1407
+ {
1408
+ "epoch": 0.9939879759519038,
1409
+ "grad_norm": 3.587979644510153,
1410
+ "learning_rate": 1.1189818972656697e-09,
1411
+ "logits/chosen": -0.3767338693141937,
1412
+ "logits/rejected": -0.40465354919433594,
1413
+ "logps/chosen": -0.5555558204650879,
1414
+ "logps/rejected": -0.7796151041984558,
1415
+ "loss": 1.2483,
1416
+ "rewards/accuracies": 0.7124999761581421,
1417
+ "rewards/chosen": -0.5555558204650879,
1418
+ "rewards/margins": 0.2240593433380127,
1419
+ "rewards/rejected": -0.7796151041984558,
1420
+ "step": 465
1421
+ },
1422
+ {
1423
+ "epoch": 0.9982631930527722,
1424
+ "step": 467,
1425
+ "total_flos": 0.0,
1426
+ "train_loss": 1.2796013329728513,
1427
+ "train_runtime": 21025.6961,
1428
+ "train_samples_per_second": 2.848,
1429
+ "train_steps_per_second": 0.022
1430
+ }
1431
+ ],
1432
+ "logging_steps": 5,
1433
+ "max_steps": 467,
1434
+ "num_input_tokens_seen": 0,
1435
+ "num_train_epochs": 1,
1436
+ "save_steps": 1000000,
1437
+ "stateful_callbacks": {
1438
+ "TrainerControl": {
1439
+ "args": {
1440
+ "should_epoch_stop": false,
1441
+ "should_evaluate": false,
1442
+ "should_log": false,
1443
+ "should_save": true,
1444
+ "should_training_stop": true
1445
+ },
1446
+ "attributes": {}
1447
+ }
1448
+ },
1449
+ "total_flos": 0.0,
1450
+ "train_batch_size": 2,
1451
+ "trial_name": null,
1452
+ "trial_params": null
1453
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3313e64fc663db49c74b36235340771059d73377fb8169e19fca9242b1ec1dc
3
+ size 7416