Hugging Face's logo

NovaSky-AI
/
Sky-T1-32B-Flash

Text Generation
Transformers
Safetensors
English
qwen2
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
5
tgriggs commited on
Commit
2662b6e
·
1 Parent(s): fdf9e1e

Stopped tracking all *.json files with LFS and re-added them as regular files

Browse files
Files changed (8) hide show
  1. added_tokens.json +24 -3
  2. config.json +29 -3
  3. generation_config.json +14 -3
  4. model.safetensors.index.json +778 -3
  5. special_tokens_map.json +31 -3
  6. tokenizer_config.json +209 -3
  7. trainer_state.json +1278 -3
  8. vocab.json +0 -0
added_tokens.json CHANGED
@@ -1,3 +1,24 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:58b54bbe36fc752f79a24a271ef66a0a0830054b4dfad94bde757d851968060b
3
- size 605
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
config.json CHANGED
@@ -1,3 +1,29 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c4bbd6e80ddf9c33759ea5278457f284d90d4eb073a55d2dc7d0db8339774acf
3
- size 738
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "NovaSky-AI/Sky-T1-32B-Preview",
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 5120,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 27648,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 70,
15
+ "model_type": "qwen2",
16
+ "num_attention_heads": 40,
17
+ "num_hidden_layers": 64,
18
+ "num_key_value_heads": 8,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_scaling": null,
21
+ "rope_theta": 1000000.0,
22
+ "sliding_window": null,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.46.1",
26
+ "use_cache": false,
27
+ "use_sliding_window": false,
28
+ "vocab_size": 152064
29
+ }
generation_config.json CHANGED
@@ -1,3 +1,14 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:519a8db66fcfd0d18731eb75169ff8393a6f9c479fd50142fb5ee2580bb9ae64
3
- size 243
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.05,
10
+ "temperature": 0.7,
11
+ "top_k": 20,
12
+ "top_p": 0.8,
13
+ "transformers_version": "4.46.1"
14
+ }
model.safetensors.index.json CHANGED
@@ -1,3 +1,778 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:e6548816f7ae8cd9fc353a20737f640ad32db6eff13a8c097246084c3207300f
3
- size 63248
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 65527752704
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00014-of-00014.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00014.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
13
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
16
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
17
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
18
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
19
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
20
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors",
21
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
22
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
23
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
24
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
25
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
26
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
27
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
28
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
29
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
30
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
31
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
32
+ "model.layers.10.input_layernorm.weight": "model-00003-of-00014.safetensors",
33
+ "model.layers.10.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
34
+ "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
35
+ "model.layers.10.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
36
+ "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
37
+ "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
38
+ "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
39
+ "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
40
+ "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
41
+ "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
42
+ "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
43
+ "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
44
+ "model.layers.11.input_layernorm.weight": "model-00003-of-00014.safetensors",
45
+ "model.layers.11.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
46
+ "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
47
+ "model.layers.11.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
48
+ "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
49
+ "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
50
+ "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
51
+ "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
52
+ "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
53
+ "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
54
+ "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
55
+ "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
56
+ "model.layers.12.input_layernorm.weight": "model-00003-of-00014.safetensors",
57
+ "model.layers.12.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
58
+ "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
59
+ "model.layers.12.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
60
+ "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
61
+ "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
62
+ "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
63
+ "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
64
+ "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
65
+ "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
66
+ "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
67
+ "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
68
+ "model.layers.13.input_layernorm.weight": "model-00004-of-00014.safetensors",
69
+ "model.layers.13.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
70
+ "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
71
+ "model.layers.13.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
72
+ "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
73
+ "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
74
+ "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
75
+ "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
76
+ "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
77
+ "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
78
+ "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
79
+ "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
80
+ "model.layers.14.input_layernorm.weight": "model-00004-of-00014.safetensors",
81
+ "model.layers.14.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
82
+ "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
83
+ "model.layers.14.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
84
+ "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
85
+ "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
86
+ "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
87
+ "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
88
+ "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
89
+ "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
90
+ "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
91
+ "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
92
+ "model.layers.15.input_layernorm.weight": "model-00004-of-00014.safetensors",
93
+ "model.layers.15.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
94
+ "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
95
+ "model.layers.15.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
96
+ "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
97
+ "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
98
+ "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
99
+ "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
100
+ "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
101
+ "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
102
+ "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
103
+ "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
104
+ "model.layers.16.input_layernorm.weight": "model-00004-of-00014.safetensors",
105
+ "model.layers.16.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
106
+ "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
107
+ "model.layers.16.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
108
+ "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
109
+ "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
110
+ "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
111
+ "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
112
+ "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
113
+ "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
114
+ "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
115
+ "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
116
+ "model.layers.17.input_layernorm.weight": "model-00004-of-00014.safetensors",
117
+ "model.layers.17.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
118
+ "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
119
+ "model.layers.17.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
120
+ "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
121
+ "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
122
+ "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
123
+ "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
124
+ "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
125
+ "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
126
+ "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
127
+ "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
128
+ "model.layers.18.input_layernorm.weight": "model-00005-of-00014.safetensors",
129
+ "model.layers.18.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
130
+ "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
131
+ "model.layers.18.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
132
+ "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
133
+ "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
134
+ "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
135
+ "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
136
+ "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
137
+ "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
138
+ "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
139
+ "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
140
+ "model.layers.19.input_layernorm.weight": "model-00005-of-00014.safetensors",
141
+ "model.layers.19.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
142
+ "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
143
+ "model.layers.19.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
144
+ "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
145
+ "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
146
+ "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
147
+ "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
148
+ "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
149
+ "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
150
+ "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
151
+ "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
152
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00014.safetensors",
153
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
154
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
155
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
156
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
157
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
158
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
159
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
160
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
161
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
162
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
163
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
164
+ "model.layers.20.input_layernorm.weight": "model-00005-of-00014.safetensors",
165
+ "model.layers.20.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
166
+ "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
167
+ "model.layers.20.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
168
+ "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
169
+ "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
170
+ "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
171
+ "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
172
+ "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
173
+ "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
174
+ "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
175
+ "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
176
+ "model.layers.21.input_layernorm.weight": "model-00005-of-00014.safetensors",
177
+ "model.layers.21.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
178
+ "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
179
+ "model.layers.21.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
180
+ "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
181
+ "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
182
+ "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
183
+ "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
184
+ "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
185
+ "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
186
+ "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
187
+ "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
188
+ "model.layers.22.input_layernorm.weight": "model-00005-of-00014.safetensors",
189
+ "model.layers.22.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
190
+ "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
191
+ "model.layers.22.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
192
+ "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
193
+ "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
194
+ "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
195
+ "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
196
+ "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
197
+ "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
198
+ "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
199
+ "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
200
+ "model.layers.23.input_layernorm.weight": "model-00006-of-00014.safetensors",
201
+ "model.layers.23.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
202
+ "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
203
+ "model.layers.23.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
204
+ "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
205
+ "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
206
+ "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
207
+ "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
208
+ "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
209
+ "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
210
+ "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
211
+ "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
212
+ "model.layers.24.input_layernorm.weight": "model-00006-of-00014.safetensors",
213
+ "model.layers.24.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
214
+ "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
215
+ "model.layers.24.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
216
+ "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
217
+ "model.layers.24.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
218
+ "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
219
+ "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
220
+ "model.layers.24.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
221
+ "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
222
+ "model.layers.24.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
223
+ "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
224
+ "model.layers.25.input_layernorm.weight": "model-00006-of-00014.safetensors",
225
+ "model.layers.25.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
226
+ "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
227
+ "model.layers.25.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
228
+ "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
229
+ "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
230
+ "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
231
+ "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
232
+ "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
233
+ "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
234
+ "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
235
+ "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
236
+ "model.layers.26.input_layernorm.weight": "model-00006-of-00014.safetensors",
237
+ "model.layers.26.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
238
+ "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
239
+ "model.layers.26.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
240
+ "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
241
+ "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
242
+ "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
243
+ "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
244
+ "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
245
+ "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
246
+ "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
247
+ "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
248
+ "model.layers.27.input_layernorm.weight": "model-00006-of-00014.safetensors",
249
+ "model.layers.27.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
250
+ "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
251
+ "model.layers.27.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
252
+ "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
253
+ "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
254
+ "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
255
+ "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
256
+ "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
257
+ "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
258
+ "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
259
+ "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
260
+ "model.layers.28.input_layernorm.weight": "model-00007-of-00014.safetensors",
261
+ "model.layers.28.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
262
+ "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
263
+ "model.layers.28.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
264
+ "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
265
+ "model.layers.28.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
266
+ "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
267
+ "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
268
+ "model.layers.28.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
269
+ "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
270
+ "model.layers.28.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
271
+ "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
272
+ "model.layers.29.input_layernorm.weight": "model-00007-of-00014.safetensors",
273
+ "model.layers.29.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
274
+ "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
275
+ "model.layers.29.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
276
+ "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
277
+ "model.layers.29.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
278
+ "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
279
+ "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
280
+ "model.layers.29.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
281
+ "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
282
+ "model.layers.29.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
283
+ "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
284
+ "model.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors",
285
+ "model.layers.3.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
286
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
287
+ "model.layers.3.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
288
+ "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
289
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
290
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
291
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
292
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
293
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
294
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
295
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
296
+ "model.layers.30.input_layernorm.weight": "model-00007-of-00014.safetensors",
297
+ "model.layers.30.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
298
+ "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
299
+ "model.layers.30.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
300
+ "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
301
+ "model.layers.30.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
302
+ "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
303
+ "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
304
+ "model.layers.30.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
305
+ "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
306
+ "model.layers.30.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
307
+ "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
308
+ "model.layers.31.input_layernorm.weight": "model-00007-of-00014.safetensors",
309
+ "model.layers.31.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
310
+ "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
311
+ "model.layers.31.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
312
+ "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
313
+ "model.layers.31.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
314
+ "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
315
+ "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
316
+ "model.layers.31.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
317
+ "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
318
+ "model.layers.31.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
319
+ "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
320
+ "model.layers.32.input_layernorm.weight": "model-00007-of-00014.safetensors",
321
+ "model.layers.32.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
322
+ "model.layers.32.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
323
+ "model.layers.32.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
324
+ "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
325
+ "model.layers.32.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
326
+ "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
327
+ "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
328
+ "model.layers.32.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
329
+ "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
330
+ "model.layers.32.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
331
+ "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
332
+ "model.layers.33.input_layernorm.weight": "model-00008-of-00014.safetensors",
333
+ "model.layers.33.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
334
+ "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
335
+ "model.layers.33.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
336
+ "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
337
+ "model.layers.33.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
338
+ "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
339
+ "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
340
+ "model.layers.33.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
341
+ "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
342
+ "model.layers.33.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
343
+ "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
344
+ "model.layers.34.input_layernorm.weight": "model-00008-of-00014.safetensors",
345
+ "model.layers.34.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
346
+ "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
347
+ "model.layers.34.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
348
+ "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
349
+ "model.layers.34.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
350
+ "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
351
+ "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
352
+ "model.layers.34.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
353
+ "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
354
+ "model.layers.34.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
355
+ "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
356
+ "model.layers.35.input_layernorm.weight": "model-00008-of-00014.safetensors",
357
+ "model.layers.35.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
358
+ "model.layers.35.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
359
+ "model.layers.35.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
360
+ "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
361
+ "model.layers.35.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
362
+ "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
363
+ "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
364
+ "model.layers.35.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
365
+ "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
366
+ "model.layers.35.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
367
+ "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
368
+ "model.layers.36.input_layernorm.weight": "model-00008-of-00014.safetensors",
369
+ "model.layers.36.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
370
+ "model.layers.36.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
371
+ "model.layers.36.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
372
+ "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
373
+ "model.layers.36.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
374
+ "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
375
+ "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
376
+ "model.layers.36.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
377
+ "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
378
+ "model.layers.36.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
379
+ "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
380
+ "model.layers.37.input_layernorm.weight": "model-00008-of-00014.safetensors",
381
+ "model.layers.37.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
382
+ "model.layers.37.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
383
+ "model.layers.37.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
384
+ "model.layers.37.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
385
+ "model.layers.37.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
386
+ "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
387
+ "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
388
+ "model.layers.37.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
389
+ "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
390
+ "model.layers.37.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
391
+ "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
392
+ "model.layers.38.input_layernorm.weight": "model-00009-of-00014.safetensors",
393
+ "model.layers.38.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
394
+ "model.layers.38.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
395
+ "model.layers.38.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
396
+ "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
397
+ "model.layers.38.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
398
+ "model.layers.38.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
399
+ "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
400
+ "model.layers.38.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
401
+ "model.layers.38.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
402
+ "model.layers.38.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
403
+ "model.layers.38.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
404
+ "model.layers.39.input_layernorm.weight": "model-00009-of-00014.safetensors",
405
+ "model.layers.39.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
406
+ "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
407
+ "model.layers.39.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
408
+ "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
409
+ "model.layers.39.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
410
+ "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
411
+ "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
412
+ "model.layers.39.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
413
+ "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
414
+ "model.layers.39.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
415
+ "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
416
+ "model.layers.4.input_layernorm.weight": "model-00002-of-00014.safetensors",
417
+ "model.layers.4.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
418
+ "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
419
+ "model.layers.4.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
420
+ "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
421
+ "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
422
+ "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
423
+ "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
424
+ "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
425
+ "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
426
+ "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
427
+ "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
428
+ "model.layers.40.input_layernorm.weight": "model-00009-of-00014.safetensors",
429
+ "model.layers.40.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
430
+ "model.layers.40.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
431
+ "model.layers.40.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
432
+ "model.layers.40.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
433
+ "model.layers.40.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
434
+ "model.layers.40.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
435
+ "model.layers.40.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
436
+ "model.layers.40.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
437
+ "model.layers.40.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
438
+ "model.layers.40.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
439
+ "model.layers.40.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
440
+ "model.layers.41.input_layernorm.weight": "model-00009-of-00014.safetensors",
441
+ "model.layers.41.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
442
+ "model.layers.41.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
443
+ "model.layers.41.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
444
+ "model.layers.41.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
445
+ "model.layers.41.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
446
+ "model.layers.41.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
447
+ "model.layers.41.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
448
+ "model.layers.41.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
449
+ "model.layers.41.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
450
+ "model.layers.41.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
451
+ "model.layers.41.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
452
+ "model.layers.42.input_layernorm.weight": "model-00009-of-00014.safetensors",
453
+ "model.layers.42.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
454
+ "model.layers.42.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
455
+ "model.layers.42.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
456
+ "model.layers.42.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
457
+ "model.layers.42.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
458
+ "model.layers.42.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
459
+ "model.layers.42.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
460
+ "model.layers.42.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
461
+ "model.layers.42.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
462
+ "model.layers.42.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
463
+ "model.layers.42.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
464
+ "model.layers.43.input_layernorm.weight": "model-00010-of-00014.safetensors",
465
+ "model.layers.43.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
466
+ "model.layers.43.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
467
+ "model.layers.43.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
468
+ "model.layers.43.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
469
+ "model.layers.43.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
470
+ "model.layers.43.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
471
+ "model.layers.43.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
472
+ "model.layers.43.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
473
+ "model.layers.43.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
474
+ "model.layers.43.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
475
+ "model.layers.43.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
476
+ "model.layers.44.input_layernorm.weight": "model-00010-of-00014.safetensors",
477
+ "model.layers.44.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
478
+ "model.layers.44.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
479
+ "model.layers.44.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
480
+ "model.layers.44.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
481
+ "model.layers.44.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
482
+ "model.layers.44.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
483
+ "model.layers.44.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
484
+ "model.layers.44.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
485
+ "model.layers.44.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
486
+ "model.layers.44.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
487
+ "model.layers.44.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
488
+ "model.layers.45.input_layernorm.weight": "model-00010-of-00014.safetensors",
489
+ "model.layers.45.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
490
+ "model.layers.45.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
491
+ "model.layers.45.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
492
+ "model.layers.45.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
493
+ "model.layers.45.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
494
+ "model.layers.45.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
495
+ "model.layers.45.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
496
+ "model.layers.45.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
497
+ "model.layers.45.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
498
+ "model.layers.45.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
499
+ "model.layers.45.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
500
+ "model.layers.46.input_layernorm.weight": "model-00010-of-00014.safetensors",
501
+ "model.layers.46.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
502
+ "model.layers.46.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
503
+ "model.layers.46.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
504
+ "model.layers.46.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
505
+ "model.layers.46.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
506
+ "model.layers.46.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
507
+ "model.layers.46.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
508
+ "model.layers.46.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
509
+ "model.layers.46.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
510
+ "model.layers.46.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
511
+ "model.layers.46.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
512
+ "model.layers.47.input_layernorm.weight": "model-00010-of-00014.safetensors",
513
+ "model.layers.47.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
514
+ "model.layers.47.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
515
+ "model.layers.47.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
516
+ "model.layers.47.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
517
+ "model.layers.47.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
518
+ "model.layers.47.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
519
+ "model.layers.47.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
520
+ "model.layers.47.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
521
+ "model.layers.47.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
522
+ "model.layers.47.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
523
+ "model.layers.47.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
524
+ "model.layers.48.input_layernorm.weight": "model-00011-of-00014.safetensors",
525
+ "model.layers.48.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
526
+ "model.layers.48.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
527
+ "model.layers.48.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
528
+ "model.layers.48.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
529
+ "model.layers.48.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
530
+ "model.layers.48.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
531
+ "model.layers.48.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
532
+ "model.layers.48.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
533
+ "model.layers.48.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
534
+ "model.layers.48.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
535
+ "model.layers.48.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
536
+ "model.layers.49.input_layernorm.weight": "model-00011-of-00014.safetensors",
537
+ "model.layers.49.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
538
+ "model.layers.49.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
539
+ "model.layers.49.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
540
+ "model.layers.49.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
541
+ "model.layers.49.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
542
+ "model.layers.49.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
543
+ "model.layers.49.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
544
+ "model.layers.49.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
545
+ "model.layers.49.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
546
+ "model.layers.49.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
547
+ "model.layers.49.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
548
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00014.safetensors",
549
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
550
+ "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
551
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
552
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
553
+ "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
554
+ "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
555
+ "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
556
+ "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
557
+ "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
558
+ "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
559
+ "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
560
+ "model.layers.50.input_layernorm.weight": "model-00011-of-00014.safetensors",
561
+ "model.layers.50.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
562
+ "model.layers.50.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
563
+ "model.layers.50.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
564
+ "model.layers.50.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
565
+ "model.layers.50.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
566
+ "model.layers.50.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
567
+ "model.layers.50.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
568
+ "model.layers.50.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
569
+ "model.layers.50.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
570
+ "model.layers.50.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
571
+ "model.layers.50.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
572
+ "model.layers.51.input_layernorm.weight": "model-00011-of-00014.safetensors",
573
+ "model.layers.51.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
574
+ "model.layers.51.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
575
+ "model.layers.51.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
576
+ "model.layers.51.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
577
+ "model.layers.51.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
578
+ "model.layers.51.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
579
+ "model.layers.51.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
580
+ "model.layers.51.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
581
+ "model.layers.51.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
582
+ "model.layers.51.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
583
+ "model.layers.51.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
584
+ "model.layers.52.input_layernorm.weight": "model-00011-of-00014.safetensors",
585
+ "model.layers.52.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
586
+ "model.layers.52.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
587
+ "model.layers.52.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
588
+ "model.layers.52.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
589
+ "model.layers.52.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
590
+ "model.layers.52.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
591
+ "model.layers.52.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
592
+ "model.layers.52.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
593
+ "model.layers.52.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
594
+ "model.layers.52.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
595
+ "model.layers.52.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
596
+ "model.layers.53.input_layernorm.weight": "model-00012-of-00014.safetensors",
597
+ "model.layers.53.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
598
+ "model.layers.53.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
599
+ "model.layers.53.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
600
+ "model.layers.53.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
601
+ "model.layers.53.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
602
+ "model.layers.53.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
603
+ "model.layers.53.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
604
+ "model.layers.53.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
605
+ "model.layers.53.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
606
+ "model.layers.53.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
607
+ "model.layers.53.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
608
+ "model.layers.54.input_layernorm.weight": "model-00012-of-00014.safetensors",
609
+ "model.layers.54.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
610
+ "model.layers.54.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
611
+ "model.layers.54.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
612
+ "model.layers.54.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
613
+ "model.layers.54.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
614
+ "model.layers.54.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
615
+ "model.layers.54.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
616
+ "model.layers.54.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
617
+ "model.layers.54.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
618
+ "model.layers.54.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
619
+ "model.layers.54.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
620
+ "model.layers.55.input_layernorm.weight": "model-00012-of-00014.safetensors",
621
+ "model.layers.55.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
622
+ "model.layers.55.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
623
+ "model.layers.55.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
624
+ "model.layers.55.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
625
+ "model.layers.55.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
626
+ "model.layers.55.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
627
+ "model.layers.55.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
628
+ "model.layers.55.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
629
+ "model.layers.55.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
630
+ "model.layers.55.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
631
+ "model.layers.55.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
632
+ "model.layers.56.input_layernorm.weight": "model-00012-of-00014.safetensors",
633
+ "model.layers.56.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
634
+ "model.layers.56.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
635
+ "model.layers.56.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
636
+ "model.layers.56.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
637
+ "model.layers.56.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
638
+ "model.layers.56.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
639
+ "model.layers.56.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
640
+ "model.layers.56.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
641
+ "model.layers.56.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
642
+ "model.layers.56.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
643
+ "model.layers.56.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
644
+ "model.layers.57.input_layernorm.weight": "model-00012-of-00014.safetensors",
645
+ "model.layers.57.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
646
+ "model.layers.57.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
647
+ "model.layers.57.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
648
+ "model.layers.57.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
649
+ "model.layers.57.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
650
+ "model.layers.57.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
651
+ "model.layers.57.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
652
+ "model.layers.57.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
653
+ "model.layers.57.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
654
+ "model.layers.57.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
655
+ "model.layers.57.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
656
+ "model.layers.58.input_layernorm.weight": "model-00013-of-00014.safetensors",
657
+ "model.layers.58.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
658
+ "model.layers.58.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
659
+ "model.layers.58.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
660
+ "model.layers.58.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
661
+ "model.layers.58.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
662
+ "model.layers.58.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
663
+ "model.layers.58.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
664
+ "model.layers.58.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
665
+ "model.layers.58.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
666
+ "model.layers.58.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
667
+ "model.layers.58.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
668
+ "model.layers.59.input_layernorm.weight": "model-00013-of-00014.safetensors",
669
+ "model.layers.59.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
670
+ "model.layers.59.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
671
+ "model.layers.59.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
672
+ "model.layers.59.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
673
+ "model.layers.59.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
674
+ "model.layers.59.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
675
+ "model.layers.59.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
676
+ "model.layers.59.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
677
+ "model.layers.59.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
678
+ "model.layers.59.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
679
+ "model.layers.59.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
680
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00014.safetensors",
681
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
682
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
683
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
684
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
685
+ "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
686
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
687
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
688
+ "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
689
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
690
+ "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
691
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
692
+ "model.layers.60.input_layernorm.weight": "model-00013-of-00014.safetensors",
693
+ "model.layers.60.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
694
+ "model.layers.60.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
695
+ "model.layers.60.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
696
+ "model.layers.60.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
697
+ "model.layers.60.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
698
+ "model.layers.60.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
699
+ "model.layers.60.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
700
+ "model.layers.60.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
701
+ "model.layers.60.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
702
+ "model.layers.60.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
703
+ "model.layers.60.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
704
+ "model.layers.61.input_layernorm.weight": "model-00013-of-00014.safetensors",
705
+ "model.layers.61.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
706
+ "model.layers.61.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
707
+ "model.layers.61.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
708
+ "model.layers.61.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
709
+ "model.layers.61.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
710
+ "model.layers.61.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
711
+ "model.layers.61.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
712
+ "model.layers.61.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
713
+ "model.layers.61.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
714
+ "model.layers.61.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
715
+ "model.layers.61.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
716
+ "model.layers.62.input_layernorm.weight": "model-00013-of-00014.safetensors",
717
+ "model.layers.62.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
718
+ "model.layers.62.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
719
+ "model.layers.62.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
720
+ "model.layers.62.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
721
+ "model.layers.62.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
722
+ "model.layers.62.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
723
+ "model.layers.62.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
724
+ "model.layers.62.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
725
+ "model.layers.62.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
726
+ "model.layers.62.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
727
+ "model.layers.62.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
728
+ "model.layers.63.input_layernorm.weight": "model-00014-of-00014.safetensors",
729
+ "model.layers.63.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
730
+ "model.layers.63.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
731
+ "model.layers.63.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
732
+ "model.layers.63.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
733
+ "model.layers.63.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
734
+ "model.layers.63.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
735
+ "model.layers.63.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
736
+ "model.layers.63.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
737
+ "model.layers.63.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
738
+ "model.layers.63.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
739
+ "model.layers.63.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
740
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00014.safetensors",
741
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
742
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
743
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
744
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
745
+ "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
746
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
747
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
748
+ "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
749
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
750
+ "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
751
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
752
+ "model.layers.8.input_layernorm.weight": "model-00003-of-00014.safetensors",
753
+ "model.layers.8.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
754
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
755
+ "model.layers.8.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
756
+ "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
757
+ "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
758
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
759
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
760
+ "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
761
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
762
+ "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
763
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
764
+ "model.layers.9.input_layernorm.weight": "model-00003-of-00014.safetensors",
765
+ "model.layers.9.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
766
+ "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
767
+ "model.layers.9.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
768
+ "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
769
+ "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
770
+ "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
771
+ "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
772
+ "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
773
+ "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
774
+ "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
775
+ "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
776
+ "model.norm.weight": "model-00014-of-00014.safetensors"
777
+ }
778
+ }
special_tokens_map.json CHANGED
@@ -1,3 +1,31 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:6676f091c8bc4d1b50146427cfde92073402866b87b6e39223227931b70083e9
3
- size 616
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer_config.json CHANGED
@@ -1,3 +1,209 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:8864f53f85df92bc281866d42942bab86e7ea72c418c4de085d895ff5ff9d908
3
- size 7366
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|endoftext|>",
201
+ "errors": "replace",
202
+ "extra_special_tokens": {},
203
+ "model_max_length": 131072,
204
+ "pad_token": "<|endoftext|>",
205
+ "padding_side": "right",
206
+ "split_special_tokens": false,
207
+ "tokenizer_class": "Qwen2Tokenizer",
208
+ "unk_token": null
209
+ }
trainer_state.json CHANGED
@@ -1,3 +1,1278 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c00e426aa58231f08d12043448549b1d12ecf255452fbdb749bb49038cd6f0fd
3
- size 44244
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.996,
5
+ "eval_steps": 500,
6
+ "global_step": 83,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.012,
13
+ "grad_norm": 0.8640882968902588,
14
+ "learning_rate": 5.555555555555555e-08,
15
+ "logits/chosen": -1.495650291442871,
16
+ "logits/rejected": -1.3535889387130737,
17
+ "logps/chosen": -0.10173828899860382,
18
+ "logps/rejected": -0.08792766183614731,
19
+ "loss": 0.8717,
20
+ "rewards/accuracies": 0.3333333730697632,
21
+ "rewards/chosen": -0.20347657799720764,
22
+ "rewards/margins": -0.027621246874332428,
23
+ "rewards/rejected": -0.17585532367229462,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.024,
28
+ "grad_norm": 0.979682981967926,
29
+ "learning_rate": 1.111111111111111e-07,
30
+ "logits/chosen": -1.443913221359253,
31
+ "logits/rejected": -1.3641024827957153,
32
+ "logps/chosen": -0.10752908140420914,
33
+ "logps/rejected": -0.08240076899528503,
34
+ "loss": 0.8846,
35
+ "rewards/accuracies": 0.2187500149011612,
36
+ "rewards/chosen": -0.21505816280841827,
37
+ "rewards/margins": -0.0502566322684288,
38
+ "rewards/rejected": -0.16480153799057007,
39
+ "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.036,
43
+ "grad_norm": 0.9309831857681274,
44
+ "learning_rate": 1.6666666666666665e-07,
45
+ "logits/chosen": -1.4732969999313354,
46
+ "logits/rejected": -1.376213550567627,
47
+ "logps/chosen": -0.10481980443000793,
48
+ "logps/rejected": -0.07933054119348526,
49
+ "loss": 0.8848,
50
+ "rewards/accuracies": 0.28125,
51
+ "rewards/chosen": -0.20963960886001587,
52
+ "rewards/margins": -0.050978537648916245,
53
+ "rewards/rejected": -0.15866108238697052,
54
+ "step": 3
55
+ },
56
+ {
57
+ "epoch": 0.048,
58
+ "grad_norm": 0.9682196974754333,
59
+ "learning_rate": 2.222222222222222e-07,
60
+ "logits/chosen": -1.5285106897354126,
61
+ "logits/rejected": -1.3950246572494507,
62
+ "logps/chosen": -0.11225953698158264,
63
+ "logps/rejected": -0.08694332838058472,
64
+ "loss": 0.8849,
65
+ "rewards/accuracies": 0.3229166865348816,
66
+ "rewards/chosen": -0.22451907396316528,
67
+ "rewards/margins": -0.05063238739967346,
68
+ "rewards/rejected": -0.17388665676116943,
69
+ "step": 4
70
+ },
71
+ {
72
+ "epoch": 0.06,
73
+ "grad_norm": 1.0820338726043701,
74
+ "learning_rate": 2.7777777777777776e-07,
75
+ "logits/chosen": -1.494052767753601,
76
+ "logits/rejected": -1.3356661796569824,
77
+ "logps/chosen": -0.12428013980388641,
78
+ "logps/rejected": -0.09185128659009933,
79
+ "loss": 0.8968,
80
+ "rewards/accuracies": 0.322916716337204,
81
+ "rewards/chosen": -0.24856027960777283,
82
+ "rewards/margins": -0.06485769897699356,
83
+ "rewards/rejected": -0.18370257318019867,
84
+ "step": 5
85
+ },
86
+ {
87
+ "epoch": 0.072,
88
+ "grad_norm": 1.0573477745056152,
89
+ "learning_rate": 3.333333333333333e-07,
90
+ "logits/chosen": -1.4825295209884644,
91
+ "logits/rejected": -1.3897716999053955,
92
+ "logps/chosen": -0.11380095779895782,
93
+ "logps/rejected": -0.08133920282125473,
94
+ "loss": 0.8938,
95
+ "rewards/accuracies": 0.3020833432674408,
96
+ "rewards/chosen": -0.22760191559791565,
97
+ "rewards/margins": -0.06492353230714798,
98
+ "rewards/rejected": -0.16267840564250946,
99
+ "step": 6
100
+ },
101
+ {
102
+ "epoch": 0.084,
103
+ "grad_norm": 0.9294664263725281,
104
+ "learning_rate": 3.888888888888889e-07,
105
+ "logits/chosen": -1.5021216869354248,
106
+ "logits/rejected": -1.3295238018035889,
107
+ "logps/chosen": -0.099081851541996,
108
+ "logps/rejected": -0.08119318634271622,
109
+ "loss": 0.8761,
110
+ "rewards/accuracies": 0.2916666567325592,
111
+ "rewards/chosen": -0.198163703083992,
112
+ "rewards/margins": -0.03577733412384987,
113
+ "rewards/rejected": -0.16238637268543243,
114
+ "step": 7
115
+ },
116
+ {
117
+ "epoch": 0.096,
118
+ "grad_norm": 1.0329580307006836,
119
+ "learning_rate": 4.444444444444444e-07,
120
+ "logits/chosen": -1.5048794746398926,
121
+ "logits/rejected": -1.377795934677124,
122
+ "logps/chosen": -0.12124787271022797,
123
+ "logps/rejected": -0.08464659005403519,
124
+ "loss": 0.9015,
125
+ "rewards/accuracies": 0.3125,
126
+ "rewards/chosen": -0.24249574542045593,
127
+ "rewards/margins": -0.07320256531238556,
128
+ "rewards/rejected": -0.16929318010807037,
129
+ "step": 8
130
+ },
131
+ {
132
+ "epoch": 0.108,
133
+ "grad_norm": 0.9767515063285828,
134
+ "learning_rate": 5e-07,
135
+ "logits/chosen": -1.5186768770217896,
136
+ "logits/rejected": -1.3877286911010742,
137
+ "logps/chosen": -0.10737170279026031,
138
+ "logps/rejected": -0.0823729932308197,
139
+ "loss": 0.8847,
140
+ "rewards/accuracies": 0.3020833432674408,
141
+ "rewards/chosen": -0.21474340558052063,
142
+ "rewards/margins": -0.04999742656946182,
143
+ "rewards/rejected": -0.1647459864616394,
144
+ "step": 9
145
+ },
146
+ {
147
+ "epoch": 0.12,
148
+ "grad_norm": 0.9653743505477905,
149
+ "learning_rate": 4.997747415511704e-07,
150
+ "logits/chosen": -1.4915320873260498,
151
+ "logits/rejected": -1.3450301885604858,
152
+ "logps/chosen": -0.10813666880130768,
153
+ "logps/rejected": -0.08507634699344635,
154
+ "loss": 0.8822,
155
+ "rewards/accuracies": 0.2291666716337204,
156
+ "rewards/chosen": -0.21627333760261536,
157
+ "rewards/margins": -0.04612065851688385,
158
+ "rewards/rejected": -0.1701526939868927,
159
+ "step": 10
160
+ },
161
+ {
162
+ "epoch": 0.132,
163
+ "grad_norm": 0.9533908367156982,
164
+ "learning_rate": 4.990993721356315e-07,
165
+ "logits/chosen": -1.4848368167877197,
166
+ "logits/rejected": -1.3539990186691284,
167
+ "logps/chosen": -0.11860796809196472,
168
+ "logps/rejected": -0.08763512969017029,
169
+ "loss": 0.8931,
170
+ "rewards/accuracies": 0.25,
171
+ "rewards/chosen": -0.23721593618392944,
172
+ "rewards/margins": -0.061945684254169464,
173
+ "rewards/rejected": -0.17527025938034058,
174
+ "step": 11
175
+ },
176
+ {
177
+ "epoch": 0.144,
178
+ "grad_norm": 0.9020726084709167,
179
+ "learning_rate": 4.979751088147191e-07,
180
+ "logits/chosen": -1.4897594451904297,
181
+ "logits/rejected": -1.3646252155303955,
182
+ "logps/chosen": -0.09957993775606155,
183
+ "logps/rejected": -0.08218874782323837,
184
+ "loss": 0.8759,
185
+ "rewards/accuracies": 0.3958333432674408,
186
+ "rewards/chosen": -0.1991598755121231,
187
+ "rewards/margins": -0.034782394766807556,
188
+ "rewards/rejected": -0.16437749564647675,
189
+ "step": 12
190
+ },
191
+ {
192
+ "epoch": 0.156,
193
+ "grad_norm": 1.0148029327392578,
194
+ "learning_rate": 4.964039775869271e-07,
195
+ "logits/chosen": -1.4809292554855347,
196
+ "logits/rejected": -1.3655236959457397,
197
+ "logps/chosen": -0.11366236209869385,
198
+ "logps/rejected": -0.0875682383775711,
199
+ "loss": 0.8868,
200
+ "rewards/accuracies": 0.3645833432674408,
201
+ "rewards/chosen": -0.2273247241973877,
202
+ "rewards/margins": -0.05218825116753578,
203
+ "rewards/rejected": -0.1751364767551422,
204
+ "step": 13
205
+ },
206
+ {
207
+ "epoch": 0.168,
208
+ "grad_norm": 1.334598422050476,
209
+ "learning_rate": 4.943888097369216e-07,
210
+ "logits/chosen": -1.4804601669311523,
211
+ "logits/rejected": -1.3518431186676025,
212
+ "logps/chosen": -0.13359910249710083,
213
+ "logps/rejected": -0.08674132823944092,
214
+ "loss": 0.9236,
215
+ "rewards/accuracies": 0.2395833432674408,
216
+ "rewards/chosen": -0.26719820499420166,
217
+ "rewards/margins": -0.09371551126241684,
218
+ "rewards/rejected": -0.17348265647888184,
219
+ "step": 14
220
+ },
221
+ {
222
+ "epoch": 0.18,
223
+ "grad_norm": 0.9834568500518799,
224
+ "learning_rate": 4.919332367333748e-07,
225
+ "logits/chosen": -1.4974645376205444,
226
+ "logits/rejected": -1.3400018215179443,
227
+ "logps/chosen": -0.10907550156116486,
228
+ "logps/rejected": -0.08122590184211731,
229
+ "loss": 0.8879,
230
+ "rewards/accuracies": 0.21875,
231
+ "rewards/chosen": -0.2181510031223297,
232
+ "rewards/margins": -0.05569921433925629,
233
+ "rewards/rejected": -0.16245180368423462,
234
+ "step": 15
235
+ },
236
+ {
237
+ "epoch": 0.192,
238
+ "grad_norm": 0.9361069798469543,
239
+ "learning_rate": 4.890416836848127e-07,
240
+ "logits/chosen": -1.4610369205474854,
241
+ "logits/rejected": -1.369497299194336,
242
+ "logps/chosen": -0.10335300862789154,
243
+ "logps/rejected": -0.08525583893060684,
244
+ "loss": 0.8765,
245
+ "rewards/accuracies": 0.3541666865348816,
246
+ "rewards/chosen": -0.20670601725578308,
247
+ "rewards/margins": -0.03619435429573059,
248
+ "rewards/rejected": -0.17051167786121368,
249
+ "step": 16
250
+ },
251
+ {
252
+ "epoch": 0.204,
253
+ "grad_norm": 0.910740077495575,
254
+ "learning_rate": 4.85719361365271e-07,
255
+ "logits/chosen": -1.5087649822235107,
256
+ "logits/rejected": -1.3652905225753784,
257
+ "logps/chosen": -0.09960392862558365,
258
+ "logps/rejected": -0.08507402241230011,
259
+ "loss": 0.8719,
260
+ "rewards/accuracies": 0.3541666865348816,
261
+ "rewards/chosen": -0.1992078572511673,
262
+ "rewards/margins": -0.029059793800115585,
263
+ "rewards/rejected": -0.17014804482460022,
264
+ "step": 17
265
+ },
266
+ {
267
+ "epoch": 0.216,
268
+ "grad_norm": 0.9233217239379883,
269
+ "learning_rate": 4.819722568241273e-07,
270
+ "logits/chosen": -1.4695565700531006,
271
+ "logits/rejected": -1.336183786392212,
272
+ "logps/chosen": -0.10343371331691742,
273
+ "logps/rejected": -0.0857667475938797,
274
+ "loss": 0.8769,
275
+ "rewards/accuracies": 0.4166666865348816,
276
+ "rewards/chosen": -0.20686742663383484,
277
+ "rewards/margins": -0.03533393144607544,
278
+ "rewards/rejected": -0.1715334951877594,
279
+ "step": 18
280
+ },
281
+ {
282
+ "epoch": 0.228,
283
+ "grad_norm": 0.8909419775009155,
284
+ "learning_rate": 4.778071225970339e-07,
285
+ "logits/chosen": -1.4759807586669922,
286
+ "logits/rejected": -1.3495370149612427,
287
+ "logps/chosen": -0.10235996544361115,
288
+ "logps/rejected": -0.0851350948214531,
289
+ "loss": 0.8757,
290
+ "rewards/accuracies": 0.3229166567325592,
291
+ "rewards/chosen": -0.2047199308872223,
292
+ "rewards/margins": -0.03444972261786461,
293
+ "rewards/rejected": -0.1702701896429062,
294
+ "step": 19
295
+ },
296
+ {
297
+ "epoch": 0.24,
298
+ "grad_norm": 0.9479613304138184,
299
+ "learning_rate": 4.732314645373921e-07,
300
+ "logits/chosen": -1.4673627614974976,
301
+ "logits/rejected": -1.3651877641677856,
302
+ "logps/chosen": -0.10552840679883957,
303
+ "logps/rejected": -0.07911674678325653,
304
+ "loss": 0.886,
305
+ "rewards/accuracies": 0.28125,
306
+ "rewards/chosen": -0.21105681359767914,
307
+ "rewards/margins": -0.05282333493232727,
308
+ "rewards/rejected": -0.15823349356651306,
309
+ "step": 20
310
+ },
311
+ {
312
+ "epoch": 0.252,
313
+ "grad_norm": 0.854266345500946,
314
+ "learning_rate": 4.68253528290297e-07,
315
+ "logits/chosen": -1.4877924919128418,
316
+ "logits/rejected": -1.324515461921692,
317
+ "logps/chosen": -0.1002732366323471,
318
+ "logps/rejected": -0.09079625457525253,
319
+ "loss": 0.8664,
320
+ "rewards/accuracies": 0.3645833432674408,
321
+ "rewards/chosen": -0.2005464732646942,
322
+ "rewards/margins": -0.018953965976834297,
323
+ "rewards/rejected": -0.18159250915050507,
324
+ "step": 21
325
+ },
326
+ {
327
+ "epoch": 0.264,
328
+ "grad_norm": 0.9627916812896729,
329
+ "learning_rate": 4.6288228443332776e-07,
330
+ "logits/chosen": -1.466447114944458,
331
+ "logits/rejected": -1.3485172986984253,
332
+ "logps/chosen": -0.10300128906965256,
333
+ "logps/rejected": -0.08484764397144318,
334
+ "loss": 0.8763,
335
+ "rewards/accuracies": 0.3333333730697632,
336
+ "rewards/chosen": -0.20600257813930511,
337
+ "rewards/margins": -0.03630730137228966,
338
+ "rewards/rejected": -0.16969528794288635,
339
+ "step": 22
340
+ },
341
+ {
342
+ "epoch": 0.276,
343
+ "grad_norm": 0.8689938187599182,
344
+ "learning_rate": 4.571274123109605e-07,
345
+ "logits/chosen": -1.4124252796173096,
346
+ "logits/rejected": -1.3001394271850586,
347
+ "logps/chosen": -0.10588695108890533,
348
+ "logps/rejected": -0.08438257873058319,
349
+ "loss": 0.8809,
350
+ "rewards/accuracies": 0.2395833283662796,
351
+ "rewards/chosen": -0.21177390217781067,
352
+ "rewards/margins": -0.043008752167224884,
353
+ "rewards/rejected": -0.16876515746116638,
354
+ "step": 23
355
+ },
356
+ {
357
+ "epoch": 0.288,
358
+ "grad_norm": 0.9801927208900452,
359
+ "learning_rate": 4.5099928259173514e-07,
360
+ "logits/chosen": -1.4522674083709717,
361
+ "logits/rejected": -1.3461543321609497,
362
+ "logps/chosen": -0.1134054884314537,
363
+ "logps/rejected": -0.08870639652013779,
364
+ "loss": 0.886,
365
+ "rewards/accuracies": 0.2499999850988388,
366
+ "rewards/chosen": -0.2268109768629074,
367
+ "rewards/margins": -0.049398161470890045,
368
+ "rewards/rejected": -0.17741279304027557,
369
+ "step": 24
370
+ },
371
+ {
372
+ "epoch": 0.3,
373
+ "grad_norm": 0.9185568690299988,
374
+ "learning_rate": 4.4450893857960984e-07,
375
+ "logits/chosen": -1.4601349830627441,
376
+ "logits/rejected": -1.273384928703308,
377
+ "logps/chosen": -0.10715562850236893,
378
+ "logps/rejected": -0.09089934825897217,
379
+ "loss": 0.8746,
380
+ "rewards/accuracies": 0.375,
381
+ "rewards/chosen": -0.21431125700473785,
382
+ "rewards/margins": -0.03251257538795471,
383
+ "rewards/rejected": -0.18179869651794434,
384
+ "step": 25
385
+ },
386
+ {
387
+ "epoch": 0.312,
388
+ "grad_norm": 0.8864983320236206,
389
+ "learning_rate": 4.3766807631318105e-07,
390
+ "logits/chosen": -1.438947081565857,
391
+ "logits/rejected": -1.3086212873458862,
392
+ "logps/chosen": -0.10850708931684494,
393
+ "logps/rejected": -0.0892128050327301,
394
+ "loss": 0.8781,
395
+ "rewards/accuracies": 0.3229166865348816,
396
+ "rewards/chosen": -0.21701417863368988,
397
+ "rewards/margins": -0.038588590919971466,
398
+ "rewards/rejected": -0.1784256100654602,
399
+ "step": 26
400
+ },
401
+ {
402
+ "epoch": 0.324,
403
+ "grad_norm": 0.9518214464187622,
404
+ "learning_rate": 4.3048902348863106e-07,
405
+ "logits/chosen": -1.4363845586776733,
406
+ "logits/rejected": -1.3129128217697144,
407
+ "logps/chosen": -0.10809854418039322,
408
+ "logps/rejected": -0.08249183744192123,
409
+ "loss": 0.885,
410
+ "rewards/accuracies": 0.2812500298023224,
411
+ "rewards/chosen": -0.21619708836078644,
412
+ "rewards/margins": -0.05121342092752457,
413
+ "rewards/rejected": -0.16498367488384247,
414
+ "step": 27
415
+ },
416
+ {
417
+ "epoch": 0.336,
418
+ "grad_norm": 0.9291889667510986,
419
+ "learning_rate": 4.2298471724438653e-07,
420
+ "logits/chosen": -1.4329116344451904,
421
+ "logits/rejected": -1.3157219886779785,
422
+ "logps/chosen": -0.10641689598560333,
423
+ "logps/rejected": -0.0836237370967865,
424
+ "loss": 0.8825,
425
+ "rewards/accuracies": 0.3541666567325592,
426
+ "rewards/chosen": -0.21283379197120667,
427
+ "rewards/margins": -0.04558631405234337,
428
+ "rewards/rejected": -0.167247474193573,
429
+ "step": 28
430
+ },
431
+ {
432
+ "epoch": 0.348,
433
+ "grad_norm": 0.8883063197135925,
434
+ "learning_rate": 4.151686808475203e-07,
435
+ "logits/chosen": -1.4277637004852295,
436
+ "logits/rejected": -1.2657394409179688,
437
+ "logps/chosen": -0.1044892817735672,
438
+ "logps/rejected": -0.08842873573303223,
439
+ "loss": 0.8741,
440
+ "rewards/accuracies": 0.34375,
441
+ "rewards/chosen": -0.2089785635471344,
442
+ "rewards/margins": -0.03212107717990875,
443
+ "rewards/rejected": -0.17685747146606445,
444
+ "step": 29
445
+ },
446
+ {
447
+ "epoch": 0.36,
448
+ "grad_norm": 0.9316148161888123,
449
+ "learning_rate": 4.070549993239106e-07,
450
+ "logits/chosen": -1.3881316184997559,
451
+ "logits/rejected": -1.2497737407684326,
452
+ "logps/chosen": -0.11017285287380219,
453
+ "logps/rejected": -0.0868031308054924,
454
+ "loss": 0.8842,
455
+ "rewards/accuracies": 0.3645833432674408,
456
+ "rewards/chosen": -0.22034570574760437,
457
+ "rewards/margins": -0.046739429235458374,
458
+ "rewards/rejected": -0.1736062616109848,
459
+ "step": 30
460
+ },
461
+ {
462
+ "epoch": 0.372,
463
+ "grad_norm": 0.8768561482429504,
464
+ "learning_rate": 3.9865829407607166e-07,
465
+ "logits/chosen": -1.4147083759307861,
466
+ "logits/rejected": -1.2981321811676025,
467
+ "logps/chosen": -0.10104362666606903,
468
+ "logps/rejected": -0.09066756814718246,
469
+ "loss": 0.8673,
470
+ "rewards/accuracies": 0.3437500298023224,
471
+ "rewards/chosen": -0.20208725333213806,
472
+ "rewards/margins": -0.020752109587192535,
473
+ "rewards/rejected": -0.18133513629436493,
474
+ "step": 31
475
+ },
476
+ {
477
+ "epoch": 0.384,
478
+ "grad_norm": 1.0077239274978638,
479
+ "learning_rate": 3.8999369653439883e-07,
480
+ "logits/chosen": -1.4155137538909912,
481
+ "logits/rejected": -1.2743993997573853,
482
+ "logps/chosen": -0.10902610421180725,
483
+ "logps/rejected": -0.0863211378455162,
484
+ "loss": 0.8827,
485
+ "rewards/accuracies": 0.3020833432674408,
486
+ "rewards/chosen": -0.2180522084236145,
487
+ "rewards/margins": -0.0454099103808403,
488
+ "rewards/rejected": -0.1726422756910324,
489
+ "step": 32
490
+ },
491
+ {
492
+ "epoch": 0.396,
493
+ "grad_norm": 0.9207706451416016,
494
+ "learning_rate": 3.810768208893079e-07,
495
+ "logits/chosen": -1.3758422136306763,
496
+ "logits/rejected": -1.2915358543395996,
497
+ "logps/chosen": -0.1034766435623169,
498
+ "logps/rejected": -0.07977995276451111,
499
+ "loss": 0.883,
500
+ "rewards/accuracies": 0.3020833432674408,
501
+ "rewards/chosen": -0.2069532871246338,
502
+ "rewards/margins": -0.047393374145030975,
503
+ "rewards/rejected": -0.15955990552902222,
504
+ "step": 33
505
+ },
506
+ {
507
+ "epoch": 0.408,
508
+ "grad_norm": 0.9844294190406799,
509
+ "learning_rate": 3.7192373595340865e-07,
510
+ "logits/chosen": -1.442295789718628,
511
+ "logits/rejected": -1.2863086462020874,
512
+ "logps/chosen": -0.10710459202528,
513
+ "logps/rejected": -0.08674141019582748,
514
+ "loss": 0.8796,
515
+ "rewards/accuracies": 0.3020833432674408,
516
+ "rewards/chosen": -0.21420918405056,
517
+ "rewards/margins": -0.04072638228535652,
518
+ "rewards/rejected": -0.17348282039165497,
519
+ "step": 34
520
+ },
521
+ {
522
+ "epoch": 0.42,
523
+ "grad_norm": 0.9682800769805908,
524
+ "learning_rate": 3.625509362044183e-07,
525
+ "logits/chosen": -1.3701705932617188,
526
+ "logits/rejected": -1.2656924724578857,
527
+ "logps/chosen": -0.11000403016805649,
528
+ "logps/rejected": -0.08980907499790192,
529
+ "loss": 0.8803,
530
+ "rewards/accuracies": 0.3854166567325592,
531
+ "rewards/chosen": -0.22000806033611298,
532
+ "rewards/margins": -0.04038992151618004,
533
+ "rewards/rejected": -0.17961814999580383,
534
+ "step": 35
535
+ },
536
+ {
537
+ "epoch": 0.432,
538
+ "grad_norm": 0.9004039168357849,
539
+ "learning_rate": 3.529753120609982e-07,
540
+ "logits/chosen": -1.4099225997924805,
541
+ "logits/rejected": -1.252682089805603,
542
+ "logps/chosen": -0.09707480669021606,
543
+ "logps/rejected": -0.08859608322381973,
544
+ "loss": 0.8653,
545
+ "rewards/accuracies": 0.4479166865348816,
546
+ "rewards/chosen": -0.19414961338043213,
547
+ "rewards/margins": -0.016957445070147514,
548
+ "rewards/rejected": -0.17719216644763947,
549
+ "step": 36
550
+ },
551
+ {
552
+ "epoch": 0.444,
553
+ "grad_norm": 0.9568714499473572,
554
+ "learning_rate": 3.4321411944507714e-07,
555
+ "logits/chosen": -1.3612836599349976,
556
+ "logits/rejected": -1.2257184982299805,
557
+ "logps/chosen": -0.10623904317617416,
558
+ "logps/rejected": -0.09100136905908585,
559
+ "loss": 0.8734,
560
+ "rewards/accuracies": 0.4166666567325592,
561
+ "rewards/chosen": -0.21247808635234833,
562
+ "rewards/margins": -0.030475351959466934,
563
+ "rewards/rejected": -0.1820027381181717,
564
+ "step": 37
565
+ },
566
+ {
567
+ "epoch": 0.456,
568
+ "grad_norm": 0.8658465147018433,
569
+ "learning_rate": 3.332849486855144e-07,
570
+ "logits/chosen": -1.381141185760498,
571
+ "logits/rejected": -1.2495661973953247,
572
+ "logps/chosen": -0.09047922492027283,
573
+ "logps/rejected": -0.07975338399410248,
574
+ "loss": 0.8676,
575
+ "rewards/accuracies": 0.3958333432674408,
576
+ "rewards/chosen": -0.18095844984054565,
577
+ "rewards/margins": -0.021451696753501892,
578
+ "rewards/rejected": -0.15950676798820496,
579
+ "step": 38
580
+ },
581
+ {
582
+ "epoch": 0.468,
583
+ "grad_norm": 0.9716626405715942,
584
+ "learning_rate": 3.2320569281913754e-07,
585
+ "logits/chosen": -1.3790628910064697,
586
+ "logits/rejected": -1.251636028289795,
587
+ "logps/chosen": -0.10486049205064774,
588
+ "logps/rejected": -0.08277000486850739,
589
+ "loss": 0.883,
590
+ "rewards/accuracies": 0.3437500298023224,
591
+ "rewards/chosen": -0.20972098410129547,
592
+ "rewards/margins": -0.0441809706389904,
593
+ "rewards/rejected": -0.16554000973701477,
594
+ "step": 39
595
+ },
596
+ {
597
+ "epoch": 0.48,
598
+ "grad_norm": 0.948078989982605,
599
+ "learning_rate": 3.129945153462813e-07,
600
+ "logits/chosen": -1.3937729597091675,
601
+ "logits/rejected": -1.2695637941360474,
602
+ "logps/chosen": -0.09631801396608353,
603
+ "logps/rejected": -0.08585619181394577,
604
+ "loss": 0.8673,
605
+ "rewards/accuracies": 0.3854166865348816,
606
+ "rewards/chosen": -0.19263602793216705,
607
+ "rewards/margins": -0.020923633128404617,
608
+ "rewards/rejected": -0.17171238362789154,
609
+ "step": 40
610
+ },
611
+ {
612
+ "epoch": 0.492,
613
+ "grad_norm": 0.9445565342903137,
614
+ "learning_rate": 3.0266981749893154e-07,
615
+ "logits/chosen": -1.3988057374954224,
616
+ "logits/rejected": -1.2703980207443237,
617
+ "logps/chosen": -0.09746824949979782,
618
+ "logps/rejected": -0.0910995602607727,
619
+ "loss": 0.8624,
620
+ "rewards/accuracies": 0.40625,
621
+ "rewards/chosen": -0.19493649899959564,
622
+ "rewards/margins": -0.012737366370856762,
623
+ "rewards/rejected": -0.1821991205215454,
624
+ "step": 41
625
+ },
626
+ {
627
+ "epoch": 0.504,
628
+ "grad_norm": 1.080769419670105,
629
+ "learning_rate": 2.922502050804623e-07,
630
+ "logits/chosen": -1.4094312191009521,
631
+ "logits/rejected": -1.247127890586853,
632
+ "logps/chosen": -0.09884171932935715,
633
+ "logps/rejected": -0.08831708878278732,
634
+ "loss": 0.8677,
635
+ "rewards/accuracies": 0.3958333730697632,
636
+ "rewards/chosen": -0.1976834386587143,
637
+ "rewards/margins": -0.02104926109313965,
638
+ "rewards/rejected": -0.17663417756557465,
639
+ "step": 42
640
+ },
641
+ {
642
+ "epoch": 0.516,
643
+ "grad_norm": 0.9974801540374756,
644
+ "learning_rate": 2.8175445493671966e-07,
645
+ "logits/chosen": -1.3815157413482666,
646
+ "logits/rejected": -1.2270005941390991,
647
+ "logps/chosen": -0.10922063887119293,
648
+ "logps/rejected": -0.0900418609380722,
649
+ "loss": 0.8809,
650
+ "rewards/accuracies": 0.4583333730697632,
651
+ "rewards/chosen": -0.21844127774238586,
652
+ "rewards/margins": -0.03835754841566086,
653
+ "rewards/rejected": -0.1800837218761444,
654
+ "step": 43
655
+ },
656
+ {
657
+ "epoch": 0.528,
658
+ "grad_norm": 0.9864545464515686,
659
+ "learning_rate": 2.712014811188773e-07,
660
+ "logits/chosen": -1.3654570579528809,
661
+ "logits/rejected": -1.2366658449172974,
662
+ "logps/chosen": -0.1124953106045723,
663
+ "logps/rejected": -0.0964164212346077,
664
+ "loss": 0.8745,
665
+ "rewards/accuracies": 0.375,
666
+ "rewards/chosen": -0.2249906212091446,
667
+ "rewards/margins": -0.0321577824652195,
668
+ "rewards/rejected": -0.1928328424692154,
669
+ "step": 44
670
+ },
671
+ {
672
+ "epoch": 0.54,
673
+ "grad_norm": 0.9367190599441528,
674
+ "learning_rate": 2.606103007990371e-07,
675
+ "logits/chosen": -1.3880029916763306,
676
+ "logits/rejected": -1.2659260034561157,
677
+ "logps/chosen": -0.09874889254570007,
678
+ "logps/rejected": -0.09255427867174149,
679
+ "loss": 0.8628,
680
+ "rewards/accuracies": 0.4062500298023224,
681
+ "rewards/chosen": -0.19749778509140015,
682
+ "rewards/margins": -0.012389198876917362,
683
+ "rewards/rejected": -0.18510855734348297,
684
+ "step": 45
685
+ },
686
+ {
687
+ "epoch": 0.552,
688
+ "grad_norm": 0.9902623891830444,
689
+ "learning_rate": 2.5e-07,
690
+ "logits/chosen": -1.3836193084716797,
691
+ "logits/rejected": -1.2308557033538818,
692
+ "logps/chosen": -0.09668231755495071,
693
+ "logps/rejected": -0.08627666532993317,
694
+ "loss": 0.867,
695
+ "rewards/accuracies": 0.40625,
696
+ "rewards/chosen": -0.19336463510990143,
697
+ "rewards/margins": -0.020811304450035095,
698
+ "rewards/rejected": -0.17255333065986633,
699
+ "step": 46
700
+ },
701
+ {
702
+ "epoch": 0.564,
703
+ "grad_norm": 1.0337759256362915,
704
+ "learning_rate": 2.3938969920096296e-07,
705
+ "logits/chosen": -1.3623703718185425,
706
+ "logits/rejected": -1.2246556282043457,
707
+ "logps/chosen": -0.11106079071760178,
708
+ "logps/rejected": -0.09072640538215637,
709
+ "loss": 0.8814,
710
+ "rewards/accuracies": 0.4479166865348816,
711
+ "rewards/chosen": -0.22212158143520355,
712
+ "rewards/margins": -0.040668785572052,
713
+ "rewards/rejected": -0.18145281076431274,
714
+ "step": 47
715
+ },
716
+ {
717
+ "epoch": 0.576,
718
+ "grad_norm": 0.984899640083313,
719
+ "learning_rate": 2.2879851888112278e-07,
720
+ "logits/chosen": -1.3421802520751953,
721
+ "logits/rejected": -1.198030710220337,
722
+ "logps/chosen": -0.10126922279596329,
723
+ "logps/rejected": -0.09068246185779572,
724
+ "loss": 0.8687,
725
+ "rewards/accuracies": 0.3958333730697632,
726
+ "rewards/chosen": -0.20253844559192657,
727
+ "rewards/margins": -0.021173518151044846,
728
+ "rewards/rejected": -0.18136492371559143,
729
+ "step": 48
730
+ },
731
+ {
732
+ "epoch": 0.588,
733
+ "grad_norm": 1.0588122606277466,
734
+ "learning_rate": 2.182455450632803e-07,
735
+ "logits/chosen": -1.3651273250579834,
736
+ "logits/rejected": -1.2209078073501587,
737
+ "logps/chosen": -0.10214084386825562,
738
+ "logps/rejected": -0.09154266119003296,
739
+ "loss": 0.8675,
740
+ "rewards/accuracies": 0.4166666865348816,
741
+ "rewards/chosen": -0.20428168773651123,
742
+ "rewards/margins": -0.02119637280702591,
743
+ "rewards/rejected": -0.18308532238006592,
744
+ "step": 49
745
+ },
746
+ {
747
+ "epoch": 0.6,
748
+ "grad_norm": 1.0050568580627441,
749
+ "learning_rate": 2.0774979491953776e-07,
750
+ "logits/chosen": -1.3634512424468994,
751
+ "logits/rejected": -1.1983171701431274,
752
+ "logps/chosen": -0.09622293710708618,
753
+ "logps/rejected": -0.09168636053800583,
754
+ "loss": 0.8605,
755
+ "rewards/accuracies": 0.4479166865348816,
756
+ "rewards/chosen": -0.19244587421417236,
757
+ "rewards/margins": -0.009073152206838131,
758
+ "rewards/rejected": -0.18337272107601166,
759
+ "step": 50
760
+ },
761
+ {
762
+ "epoch": 0.612,
763
+ "grad_norm": 1.003779411315918,
764
+ "learning_rate": 1.973301825010685e-07,
765
+ "logits/chosen": -1.377637267112732,
766
+ "logits/rejected": -1.2013237476348877,
767
+ "logps/chosen": -0.09089501947164536,
768
+ "logps/rejected": -0.09312086552381516,
769
+ "loss": 0.8524,
770
+ "rewards/accuracies": 0.5520833730697632,
771
+ "rewards/chosen": -0.1817900389432907,
772
+ "rewards/margins": 0.004451685585081577,
773
+ "rewards/rejected": -0.1862417310476303,
774
+ "step": 51
775
+ },
776
+ {
777
+ "epoch": 0.624,
778
+ "grad_norm": 1.0647156238555908,
779
+ "learning_rate": 1.8700548465371873e-07,
780
+ "logits/chosen": -1.3391690254211426,
781
+ "logits/rejected": -1.182291030883789,
782
+ "logps/chosen": -0.10368049144744873,
783
+ "logps/rejected": -0.09800291061401367,
784
+ "loss": 0.8624,
785
+ "rewards/accuracies": 0.4895833134651184,
786
+ "rewards/chosen": -0.20736098289489746,
787
+ "rewards/margins": -0.011355183087289333,
788
+ "rewards/rejected": -0.19600582122802734,
789
+ "step": 52
790
+ },
791
+ {
792
+ "epoch": 0.636,
793
+ "grad_norm": 1.2042913436889648,
794
+ "learning_rate": 1.767943071808624e-07,
795
+ "logits/chosen": -1.3675341606140137,
796
+ "logits/rejected": -1.2020319700241089,
797
+ "logps/chosen": -0.10732070356607437,
798
+ "logps/rejected": -0.09919053316116333,
799
+ "loss": 0.871,
800
+ "rewards/accuracies": 0.5416666865348816,
801
+ "rewards/chosen": -0.21464140713214874,
802
+ "rewards/margins": -0.01626037061214447,
803
+ "rewards/rejected": -0.19838106632232666,
804
+ "step": 53
805
+ },
806
+ {
807
+ "epoch": 0.648,
808
+ "grad_norm": 0.9795694351196289,
809
+ "learning_rate": 1.667150513144856e-07,
810
+ "logits/chosen": -1.3203659057617188,
811
+ "logits/rejected": -1.1565968990325928,
812
+ "logps/chosen": -0.09574580192565918,
813
+ "logps/rejected": -0.09623640775680542,
814
+ "loss": 0.8547,
815
+ "rewards/accuracies": 0.5520833730697632,
816
+ "rewards/chosen": -0.19149160385131836,
817
+ "rewards/margins": 0.000981215387582779,
818
+ "rewards/rejected": -0.19247281551361084,
819
+ "step": 54
820
+ },
821
+ {
822
+ "epoch": 0.66,
823
+ "grad_norm": 1.0732730627059937,
824
+ "learning_rate": 1.5678588055492286e-07,
825
+ "logits/chosen": -1.2979214191436768,
826
+ "logits/rejected": -1.150040626525879,
827
+ "logps/chosen": -0.10067766904830933,
828
+ "logps/rejected": -0.1018737256526947,
829
+ "loss": 0.8545,
830
+ "rewards/accuracies": 0.5104166865348816,
831
+ "rewards/chosen": -0.20135533809661865,
832
+ "rewards/margins": 0.0023921187967061996,
833
+ "rewards/rejected": -0.2037474513053894,
834
+ "step": 55
835
+ },
836
+ {
837
+ "epoch": 0.672,
838
+ "grad_norm": 0.9587694406509399,
839
+ "learning_rate": 1.4702468793900186e-07,
840
+ "logits/chosen": -1.3606462478637695,
841
+ "logits/rejected": -1.1573679447174072,
842
+ "logps/chosen": -0.09973961114883423,
843
+ "logps/rejected": -0.10131655633449554,
844
+ "loss": 0.8535,
845
+ "rewards/accuracies": 0.5625,
846
+ "rewards/chosen": -0.19947922229766846,
847
+ "rewards/margins": 0.003153874073177576,
848
+ "rewards/rejected": -0.2026331126689911,
849
+ "step": 56
850
+ },
851
+ {
852
+ "epoch": 0.684,
853
+ "grad_norm": 1.0398699045181274,
854
+ "learning_rate": 1.3744906379558164e-07,
855
+ "logits/chosen": -1.3375906944274902,
856
+ "logits/rejected": -1.1461068391799927,
857
+ "logps/chosen": -0.10326816886663437,
858
+ "logps/rejected": -0.10188017785549164,
859
+ "loss": 0.857,
860
+ "rewards/accuracies": 0.4687500298023224,
861
+ "rewards/chosen": -0.20653633773326874,
862
+ "rewards/margins": -0.002775975503027439,
863
+ "rewards/rejected": -0.20376035571098328,
864
+ "step": 57
865
+ },
866
+ {
867
+ "epoch": 0.696,
868
+ "grad_norm": 1.0405802726745605,
869
+ "learning_rate": 1.280762640465914e-07,
870
+ "logits/chosen": -1.3368816375732422,
871
+ "logits/rejected": -1.1643409729003906,
872
+ "logps/chosen": -0.09207028895616531,
873
+ "logps/rejected": -0.09347332268953323,
874
+ "loss": 0.8534,
875
+ "rewards/accuracies": 0.5208333134651184,
876
+ "rewards/chosen": -0.18414057791233063,
877
+ "rewards/margins": 0.002806063275784254,
878
+ "rewards/rejected": -0.18694664537906647,
879
+ "step": 58
880
+ },
881
+ {
882
+ "epoch": 0.708,
883
+ "grad_norm": 1.0253372192382812,
884
+ "learning_rate": 1.189231791106921e-07,
885
+ "logits/chosen": -1.2978026866912842,
886
+ "logits/rejected": -1.13652765750885,
887
+ "logps/chosen": -0.10593652725219727,
888
+ "logps/rejected": -0.10165742039680481,
889
+ "loss": 0.8609,
890
+ "rewards/accuracies": 0.479166716337204,
891
+ "rewards/chosen": -0.21187305450439453,
892
+ "rewards/margins": -0.008558189496397972,
893
+ "rewards/rejected": -0.20331484079360962,
894
+ "step": 59
895
+ },
896
+ {
897
+ "epoch": 0.72,
898
+ "grad_norm": 1.2529534101486206,
899
+ "learning_rate": 1.1000630346560116e-07,
900
+ "logits/chosen": -1.3010480403900146,
901
+ "logits/rejected": -1.133022665977478,
902
+ "logps/chosen": -0.11126932501792908,
903
+ "logps/rejected": -0.09786901623010635,
904
+ "loss": 0.8738,
905
+ "rewards/accuracies": 0.4895833432674408,
906
+ "rewards/chosen": -0.22253865003585815,
907
+ "rewards/margins": -0.026800617575645447,
908
+ "rewards/rejected": -0.1957380324602127,
909
+ "step": 60
910
+ },
911
+ {
912
+ "epoch": 0.732,
913
+ "grad_norm": 0.9133132696151733,
914
+ "learning_rate": 1.0134170592392836e-07,
915
+ "logits/chosen": -1.3394014835357666,
916
+ "logits/rejected": -1.1518943309783936,
917
+ "logps/chosen": -0.09960196912288666,
918
+ "logps/rejected": -0.10244160890579224,
919
+ "loss": 0.8521,
920
+ "rewards/accuracies": 0.5104166865348816,
921
+ "rewards/chosen": -0.19920393824577332,
922
+ "rewards/margins": 0.005679287016391754,
923
+ "rewards/rejected": -0.20488321781158447,
924
+ "step": 61
925
+ },
926
+ {
927
+ "epoch": 0.744,
928
+ "grad_norm": 1.0934334993362427,
929
+ "learning_rate": 9.29450006760894e-08,
930
+ "logits/chosen": -1.3294323682785034,
931
+ "logits/rejected": -1.1431366205215454,
932
+ "logps/chosen": -0.10188900679349899,
933
+ "logps/rejected": -0.09653942286968231,
934
+ "loss": 0.8616,
935
+ "rewards/accuracies": 0.5,
936
+ "rewards/chosen": -0.20377801358699799,
937
+ "rewards/margins": -0.010699168778955936,
938
+ "rewards/rejected": -0.19307884573936462,
939
+ "step": 62
940
+ },
941
+ {
942
+ "epoch": 0.756,
943
+ "grad_norm": 0.9888376593589783,
944
+ "learning_rate": 8.483131915247967e-08,
945
+ "logits/chosen": -1.3347070217132568,
946
+ "logits/rejected": -1.167306661605835,
947
+ "logps/chosen": -0.10506478697061539,
948
+ "logps/rejected": -0.1007775291800499,
949
+ "loss": 0.8603,
950
+ "rewards/accuracies": 0.5000000596046448,
951
+ "rewards/chosen": -0.21012957394123077,
952
+ "rewards/margins": -0.008574524894356728,
953
+ "rewards/rejected": -0.2015550583600998,
954
+ "step": 63
955
+ },
956
+ {
957
+ "epoch": 0.768,
958
+ "grad_norm": 0.9486240744590759,
959
+ "learning_rate": 7.701528275561347e-08,
960
+ "logits/chosen": -1.3588067293167114,
961
+ "logits/rejected": -1.1604478359222412,
962
+ "logps/chosen": -0.0977708101272583,
963
+ "logps/rejected": -0.09753303229808807,
964
+ "loss": 0.8555,
965
+ "rewards/accuracies": 0.5312500596046448,
966
+ "rewards/chosen": -0.1955416202545166,
967
+ "rewards/margins": -0.0004755451809614897,
968
+ "rewards/rejected": -0.19506606459617615,
969
+ "step": 64
970
+ },
971
+ {
972
+ "epoch": 0.78,
973
+ "grad_norm": 1.033793568611145,
974
+ "learning_rate": 6.951097651136889e-08,
975
+ "logits/chosen": -1.3951979875564575,
976
+ "logits/rejected": -1.125361680984497,
977
+ "logps/chosen": -0.10307514667510986,
978
+ "logps/rejected": -0.1052648052573204,
979
+ "loss": 0.8525,
980
+ "rewards/accuracies": 0.4895833432674408,
981
+ "rewards/chosen": -0.20615029335021973,
982
+ "rewards/margins": 0.0043793064542114735,
983
+ "rewards/rejected": -0.2105296105146408,
984
+ "step": 65
985
+ },
986
+ {
987
+ "epoch": 0.792,
988
+ "grad_norm": 1.0308159589767456,
989
+ "learning_rate": 6.233192368681889e-08,
990
+ "logits/chosen": -1.3253390789031982,
991
+ "logits/rejected": -1.1783477067947388,
992
+ "logps/chosen": -0.09217476844787598,
993
+ "logps/rejected": -0.09416632354259491,
994
+ "loss": 0.8527,
995
+ "rewards/accuracies": 0.5625,
996
+ "rewards/chosen": -0.18434953689575195,
997
+ "rewards/margins": 0.003983109723776579,
998
+ "rewards/rejected": -0.18833264708518982,
999
+ "step": 66
1000
+ },
1001
+ {
1002
+ "epoch": 0.804,
1003
+ "grad_norm": 1.1081663370132446,
1004
+ "learning_rate": 5.5491061420390174e-08,
1005
+ "logits/chosen": -1.2740880250930786,
1006
+ "logits/rejected": -1.152024269104004,
1007
+ "logps/chosen": -0.10923092067241669,
1008
+ "logps/rejected": -0.10176312923431396,
1009
+ "loss": 0.8642,
1010
+ "rewards/accuracies": 0.5104166865348816,
1011
+ "rewards/chosen": -0.21846184134483337,
1012
+ "rewards/margins": -0.01493558008223772,
1013
+ "rewards/rejected": -0.20352625846862793,
1014
+ "step": 67
1015
+ },
1016
+ {
1017
+ "epoch": 0.816,
1018
+ "grad_norm": 1.0150699615478516,
1019
+ "learning_rate": 4.900071740826489e-08,
1020
+ "logits/chosen": -1.348282814025879,
1021
+ "logits/rejected": -1.1383142471313477,
1022
+ "logps/chosen": -0.10064545273780823,
1023
+ "logps/rejected": -0.10860613733530045,
1024
+ "loss": 0.8459,
1025
+ "rewards/accuracies": 0.6041667461395264,
1026
+ "rewards/chosen": -0.20129090547561646,
1027
+ "rewards/margins": 0.01592138595879078,
1028
+ "rewards/rejected": -0.2172122746706009,
1029
+ "step": 68
1030
+ },
1031
+ {
1032
+ "epoch": 0.828,
1033
+ "grad_norm": 1.123404860496521,
1034
+ "learning_rate": 4.287258768903948e-08,
1035
+ "logits/chosen": -1.3442084789276123,
1036
+ "logits/rejected": -1.146917462348938,
1037
+ "logps/chosen": -0.10861781984567642,
1038
+ "logps/rejected": -0.10071661323308945,
1039
+ "loss": 0.8688,
1040
+ "rewards/accuracies": 0.5833333134651184,
1041
+ "rewards/chosen": -0.21723563969135284,
1042
+ "rewards/margins": -0.015802428126335144,
1043
+ "rewards/rejected": -0.2014332264661789,
1044
+ "step": 69
1045
+ },
1046
+ {
1047
+ "epoch": 0.84,
1048
+ "grad_norm": 0.9981204867362976,
1049
+ "learning_rate": 3.7117715566672176e-08,
1050
+ "logits/chosen": -1.3524047136306763,
1051
+ "logits/rejected": -1.1452308893203735,
1052
+ "logps/chosen": -0.10508691519498825,
1053
+ "logps/rejected": -0.10403452813625336,
1054
+ "loss": 0.8568,
1055
+ "rewards/accuracies": 0.5729166865348816,
1056
+ "rewards/chosen": -0.2101738303899765,
1057
+ "rewards/margins": -0.0021047808695584536,
1058
+ "rewards/rejected": -0.2080690562725067,
1059
+ "step": 70
1060
+ },
1061
+ {
1062
+ "epoch": 0.852,
1063
+ "grad_norm": 1.0365066528320312,
1064
+ "learning_rate": 3.174647170970296e-08,
1065
+ "logits/chosen": -1.3592528104782104,
1066
+ "logits/rejected": -1.1138660907745361,
1067
+ "logps/chosen": -0.10330555588006973,
1068
+ "logps/rejected": -0.1064281240105629,
1069
+ "loss": 0.8524,
1070
+ "rewards/accuracies": 0.5729166865348816,
1071
+ "rewards/chosen": -0.20661111176013947,
1072
+ "rewards/margins": 0.006245152093470097,
1073
+ "rewards/rejected": -0.2128562480211258,
1074
+ "step": 71
1075
+ },
1076
+ {
1077
+ "epoch": 0.864,
1078
+ "grad_norm": 1.076464295387268,
1079
+ "learning_rate": 2.6768535462607905e-08,
1080
+ "logits/chosen": -1.3058511018753052,
1081
+ "logits/rejected": -1.126082420349121,
1082
+ "logps/chosen": -0.10569944232702255,
1083
+ "logps/rejected": -0.11077728122472763,
1084
+ "loss": 0.8494,
1085
+ "rewards/accuracies": 0.5,
1086
+ "rewards/chosen": -0.2113988846540451,
1087
+ "rewards/margins": 0.01015565823763609,
1088
+ "rewards/rejected": -0.22155456244945526,
1089
+ "step": 72
1090
+ },
1091
+ {
1092
+ "epoch": 0.876,
1093
+ "grad_norm": 0.9264240264892578,
1094
+ "learning_rate": 2.2192877402966048e-08,
1095
+ "logits/chosen": -1.3490333557128906,
1096
+ "logits/rejected": -1.1134393215179443,
1097
+ "logps/chosen": -0.10448520630598068,
1098
+ "logps/rejected": -0.11283887922763824,
1099
+ "loss": 0.8457,
1100
+ "rewards/accuracies": 0.6145833730697632,
1101
+ "rewards/chosen": -0.20897041261196136,
1102
+ "rewards/margins": 0.016707373782992363,
1103
+ "rewards/rejected": -0.2256777584552765,
1104
+ "step": 73
1105
+ },
1106
+ {
1107
+ "epoch": 0.888,
1108
+ "grad_norm": 1.067218542098999,
1109
+ "learning_rate": 1.8027743175872662e-08,
1110
+ "logits/chosen": -1.345249891281128,
1111
+ "logits/rejected": -1.1063634157180786,
1112
+ "logps/chosen": -0.11241614818572998,
1113
+ "logps/rejected": -0.11045221984386444,
1114
+ "loss": 0.8579,
1115
+ "rewards/accuracies": 0.5104166865348816,
1116
+ "rewards/chosen": -0.22483229637145996,
1117
+ "rewards/margins": -0.003927857149392366,
1118
+ "rewards/rejected": -0.22090443968772888,
1119
+ "step": 74
1120
+ },
1121
+ {
1122
+ "epoch": 0.9,
1123
+ "grad_norm": 1.0710501670837402,
1124
+ "learning_rate": 1.4280638634728948e-08,
1125
+ "logits/chosen": -1.3244132995605469,
1126
+ "logits/rejected": -1.1485953330993652,
1127
+ "logps/chosen": -0.11838357150554657,
1128
+ "logps/rejected": -0.10926854610443115,
1129
+ "loss": 0.8683,
1130
+ "rewards/accuracies": 0.47916674613952637,
1131
+ "rewards/chosen": -0.23676714301109314,
1132
+ "rewards/margins": -0.018230034038424492,
1133
+ "rewards/rejected": -0.2185370922088623,
1134
+ "step": 75
1135
+ },
1136
+ {
1137
+ "epoch": 0.912,
1138
+ "grad_norm": 1.1065670251846313,
1139
+ "learning_rate": 1.0958316315187289e-08,
1140
+ "logits/chosen": -1.317086100578308,
1141
+ "logits/rejected": -1.1413421630859375,
1142
+ "logps/chosen": -0.10257872194051743,
1143
+ "logps/rejected": -0.10372138023376465,
1144
+ "loss": 0.8542,
1145
+ "rewards/accuracies": 0.5416666269302368,
1146
+ "rewards/chosen": -0.20515744388103485,
1147
+ "rewards/margins": 0.0022853193804621696,
1148
+ "rewards/rejected": -0.2074427604675293,
1149
+ "step": 76
1150
+ },
1151
+ {
1152
+ "epoch": 0.924,
1153
+ "grad_norm": 1.0825769901275635,
1154
+ "learning_rate": 8.066763266625282e-09,
1155
+ "logits/chosen": -1.3573386669158936,
1156
+ "logits/rejected": -1.109717607498169,
1157
+ "logps/chosen": -0.10758916288614273,
1158
+ "logps/rejected": -0.10599493980407715,
1159
+ "loss": 0.8597,
1160
+ "rewards/accuracies": 0.6250000596046448,
1161
+ "rewards/chosen": -0.21517832577228546,
1162
+ "rewards/margins": -0.0031884238123893738,
1163
+ "rewards/rejected": -0.2119898796081543,
1164
+ "step": 77
1165
+ },
1166
+ {
1167
+ "epoch": 0.936,
1168
+ "grad_norm": 0.9156083464622498,
1169
+ "learning_rate": 5.611190263078463e-09,
1170
+ "logits/chosen": -1.309991717338562,
1171
+ "logits/rejected": -1.1210401058197021,
1172
+ "logps/chosen": -0.0973024070262909,
1173
+ "logps/rejected": -0.09729278087615967,
1174
+ "loss": 0.8551,
1175
+ "rewards/accuracies": 0.4583333432674408,
1176
+ "rewards/chosen": -0.1946048140525818,
1177
+ "rewards/margins": -1.9263941794633865e-05,
1178
+ "rewards/rejected": -0.19458556175231934,
1179
+ "step": 78
1180
+ },
1181
+ {
1182
+ "epoch": 0.948,
1183
+ "grad_norm": 0.9994163513183594,
1184
+ "learning_rate": 3.5960224130728858e-09,
1185
+ "logits/chosen": -1.3023028373718262,
1186
+ "logits/rejected": -1.1124149560928345,
1187
+ "logps/chosen": -0.09809858351945877,
1188
+ "logps/rejected": -0.1080770194530487,
1189
+ "loss": 0.8436,
1190
+ "rewards/accuracies": 0.6354166865348816,
1191
+ "rewards/chosen": -0.19619716703891754,
1192
+ "rewards/margins": 0.01995689421892166,
1193
+ "rewards/rejected": -0.2161540389060974,
1194
+ "step": 79
1195
+ },
1196
+ {
1197
+ "epoch": 0.96,
1198
+ "grad_norm": 0.9938739538192749,
1199
+ "learning_rate": 2.0248911852807917e-09,
1200
+ "logits/chosen": -1.3484057188034058,
1201
+ "logits/rejected": -1.0871906280517578,
1202
+ "logps/chosen": -0.11684219539165497,
1203
+ "logps/rejected": -0.11286689341068268,
1204
+ "loss": 0.8601,
1205
+ "rewards/accuracies": 0.5104166865348816,
1206
+ "rewards/chosen": -0.23368439078330994,
1207
+ "rewards/margins": -0.007950600236654282,
1208
+ "rewards/rejected": -0.22573378682136536,
1209
+ "step": 80
1210
+ },
1211
+ {
1212
+ "epoch": 0.972,
1213
+ "grad_norm": 0.9481876492500305,
1214
+ "learning_rate": 9.006278643683696e-10,
1215
+ "logits/chosen": -1.3169337511062622,
1216
+ "logits/rejected": -1.1376291513442993,
1217
+ "logps/chosen": -0.09936561435461044,
1218
+ "logps/rejected": -0.10312428325414658,
1219
+ "loss": 0.8508,
1220
+ "rewards/accuracies": 0.5833333730697632,
1221
+ "rewards/chosen": -0.1987312287092209,
1222
+ "rewards/margins": 0.007517362013459206,
1223
+ "rewards/rejected": -0.20624856650829315,
1224
+ "step": 81
1225
+ },
1226
+ {
1227
+ "epoch": 0.984,
1228
+ "grad_norm": 1.0620635747909546,
1229
+ "learning_rate": 2.2525844882964606e-10,
1230
+ "logits/chosen": -1.3467659950256348,
1231
+ "logits/rejected": -1.1462361812591553,
1232
+ "logps/chosen": -0.10522940754890442,
1233
+ "logps/rejected": -0.10153805464506149,
1234
+ "loss": 0.8594,
1235
+ "rewards/accuracies": 0.4687500298023224,
1236
+ "rewards/chosen": -0.21045881509780884,
1237
+ "rewards/margins": -0.007382689975202084,
1238
+ "rewards/rejected": -0.20307610929012299,
1239
+ "step": 82
1240
+ },
1241
+ {
1242
+ "epoch": 0.996,
1243
+ "grad_norm": 1.0221400260925293,
1244
+ "learning_rate": 0.0,
1245
+ "logits/chosen": -1.313194751739502,
1246
+ "logits/rejected": -1.164141297340393,
1247
+ "logps/chosen": -0.10121379047632217,
1248
+ "logps/rejected": -0.1018705815076828,
1249
+ "loss": 0.8549,
1250
+ "rewards/accuracies": 0.5416666865348816,
1251
+ "rewards/chosen": -0.20242758095264435,
1252
+ "rewards/margins": 0.0013135506305843592,
1253
+ "rewards/rejected": -0.2037411630153656,
1254
+ "step": 83
1255
+ }
1256
+ ],
1257
+ "logging_steps": 1,
1258
+ "max_steps": 83,
1259
+ "num_input_tokens_seen": 0,
1260
+ "num_train_epochs": 1,
1261
+ "save_steps": 100,
1262
+ "stateful_callbacks": {
1263
+ "TrainerControl": {
1264
+ "args": {
1265
+ "should_epoch_stop": false,
1266
+ "should_evaluate": false,
1267
+ "should_log": false,
1268
+ "should_save": true,
1269
+ "should_training_stop": true
1270
+ },
1271
+ "attributes": {}
1272
+ }
1273
+ },
1274
+ "total_flos": 305651334512640.0,
1275
+ "train_batch_size": 1,
1276
+ "trial_name": null,
1277
+ "trial_params": null
1278
+ }
vocab.json CHANGED
The diff for this file is too large to render. See raw diff