gsmyrnis commited on
Commit
2a823ae
·
verified ·
1 Parent(s): c56547b

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/p/data1/mmlaion/dcft/hub/models--Qwen--Qwen2.5-7B-Instruct/snapshots/a09a35458c702b33eeacc393d103063234e8bc28",
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": 3584,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 18944,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 28,
15
+ "model_type": "qwen2",
16
+ "num_attention_heads": 28,
17
+ "num_hidden_layers": 28,
18
+ "num_key_value_heads": 4,
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 ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ }
latest ADDED
@@ -0,0 +1 @@
 
 
1
+ global_step343
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22a1698466739fe133ef0c0fdaeaafdf77ed5bbe0dfc41db74a82cb9fbe6a779
3
+ size 4877660776
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:368081f25355562ec0888520d0e8beaa598866497f4e3e8f5e5e924e33a4c0a1
3
+ size 4932751008
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9d3e1d3b989d180c4fd43a0072298e1173bddfc04796de61e5fca3843e5eaf4
3
+ size 4330865200
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aafba740ddd9212660e6b6b2ec589f9396caaf62dd80d08579db23e2278c13a0
3
+ size 1089994880
model.safetensors.index.json ADDED
@@ -0,0 +1,346 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 15231233024
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
17
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
19
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
26
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
27
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
28
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
29
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
30
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
31
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
32
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
38
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
41
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
43
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
50
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
53
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
55
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
62
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
65
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
67
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
74
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
77
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
79
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
86
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
89
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
91
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
98
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
101
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
103
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
110
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
113
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
115
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
117
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
118
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
119
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
120
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
121
+ "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
122
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
123
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
124
+ "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
125
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
126
+ "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
127
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
128
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
131
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
133
+ "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
134
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
135
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
136
+ "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
137
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
138
+ "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
139
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
140
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
146
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
149
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
151
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
153
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
154
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
155
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
156
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
157
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
158
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
159
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
160
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
161
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
162
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
163
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
164
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
170
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
173
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
175
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
182
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
185
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
187
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
194
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
197
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
199
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
206
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
209
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
211
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
216
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
217
+ "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
218
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
219
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
220
+ "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
221
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
222
+ "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
223
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
224
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
230
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
233
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
234
+ "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
235
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
236
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
238
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
242
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
243
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
244
+ "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
245
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
246
+ "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
247
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
248
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
249
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
250
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
251
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
252
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
253
+ "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
254
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
255
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
256
+ "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
257
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
258
+ "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
259
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
260
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
261
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
266
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
267
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
269
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
270
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
271
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
272
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
278
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
279
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
281
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
282
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
283
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
284
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
285
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
286
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
287
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
288
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
289
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
290
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
291
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
292
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
293
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
294
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
295
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
296
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
297
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
298
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
299
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
300
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
301
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
302
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
303
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
304
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
305
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
306
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
307
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
308
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
309
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
310
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
311
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
312
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
313
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
314
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
315
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
316
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
317
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
318
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
319
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
320
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
321
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
322
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
323
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
324
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
325
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
326
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
327
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
328
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
329
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
330
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
331
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
332
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
333
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
334
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
335
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
336
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
337
+ "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
338
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
339
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
340
+ "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
341
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
342
+ "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
343
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
344
+ "model.norm.weight": "model-00003-of-00004.safetensors"
345
+ }
346
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
tokenizer_config.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "padding_side": "right",
205
+ "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null
208
+ }
trainer_state.json ADDED
@@ -0,0 +1,2434 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.9934569247546348,
5
+ "eval_steps": 500,
6
+ "global_step": 343,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.008724100327153763,
13
+ "grad_norm": 6.035512972360855,
14
+ "learning_rate": 1.4035087719298246e-06,
15
+ "loss": 1.1029,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.017448200654307525,
20
+ "grad_norm": 6.042841036030158,
21
+ "learning_rate": 2.8070175438596493e-06,
22
+ "loss": 1.1024,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.026172300981461286,
27
+ "grad_norm": 5.910306635602092,
28
+ "learning_rate": 4.210526315789474e-06,
29
+ "loss": 1.0986,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.03489640130861505,
34
+ "grad_norm": 4.536951510086868,
35
+ "learning_rate": 5.6140350877192985e-06,
36
+ "loss": 1.0538,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.04362050163576881,
41
+ "grad_norm": 2.3773466328483686,
42
+ "learning_rate": 7.017543859649123e-06,
43
+ "loss": 0.9941,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.05234460196292257,
48
+ "grad_norm": 1.999261332126332,
49
+ "learning_rate": 8.421052631578948e-06,
50
+ "loss": 0.999,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.061068702290076333,
55
+ "grad_norm": 4.369629342726399,
56
+ "learning_rate": 9.824561403508772e-06,
57
+ "loss": 0.9889,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.0697928026172301,
62
+ "grad_norm": 4.899527942424933,
63
+ "learning_rate": 1.1228070175438597e-05,
64
+ "loss": 0.9631,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.07851690294438386,
69
+ "grad_norm": 5.748165018609449,
70
+ "learning_rate": 1.263157894736842e-05,
71
+ "loss": 0.9524,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.08724100327153762,
76
+ "grad_norm": 4.763126150981281,
77
+ "learning_rate": 1.4035087719298246e-05,
78
+ "loss": 0.952,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.09596510359869138,
83
+ "grad_norm": 3.167454561583767,
84
+ "learning_rate": 1.543859649122807e-05,
85
+ "loss": 0.9095,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.10468920392584515,
90
+ "grad_norm": 3.3676041736516433,
91
+ "learning_rate": 1.6842105263157896e-05,
92
+ "loss": 0.89,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.1134133042529989,
97
+ "grad_norm": 2.8110117483164676,
98
+ "learning_rate": 1.824561403508772e-05,
99
+ "loss": 0.8538,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.12213740458015267,
104
+ "grad_norm": 2.0519859086879286,
105
+ "learning_rate": 1.9649122807017544e-05,
106
+ "loss": 0.85,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.13086150490730644,
111
+ "grad_norm": 1.8373157533967603,
112
+ "learning_rate": 2.105263157894737e-05,
113
+ "loss": 0.8349,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.1395856052344602,
118
+ "grad_norm": 1.6156997409278058,
119
+ "learning_rate": 2.2456140350877194e-05,
120
+ "loss": 0.829,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.14830970556161396,
125
+ "grad_norm": 1.2400567097625959,
126
+ "learning_rate": 2.385964912280702e-05,
127
+ "loss": 0.8108,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.15703380588876772,
132
+ "grad_norm": 1.1069155525681142,
133
+ "learning_rate": 2.526315789473684e-05,
134
+ "loss": 0.8029,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.16575790621592149,
139
+ "grad_norm": 1.0769626887248518,
140
+ "learning_rate": 2.6666666666666667e-05,
141
+ "loss": 0.7858,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.17448200654307525,
146
+ "grad_norm": 0.7016586049675165,
147
+ "learning_rate": 2.8070175438596492e-05,
148
+ "loss": 0.7816,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.183206106870229,
153
+ "grad_norm": 0.8460028260574683,
154
+ "learning_rate": 2.9473684210526317e-05,
155
+ "loss": 0.7811,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.19193020719738277,
160
+ "grad_norm": 0.6598083455923888,
161
+ "learning_rate": 3.087719298245614e-05,
162
+ "loss": 0.7643,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.20065430752453653,
167
+ "grad_norm": 0.7215762522174539,
168
+ "learning_rate": 3.228070175438597e-05,
169
+ "loss": 0.7617,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.2093784078516903,
174
+ "grad_norm": 0.5554406103693584,
175
+ "learning_rate": 3.368421052631579e-05,
176
+ "loss": 0.7576,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.21810250817884405,
181
+ "grad_norm": 0.6258543895787715,
182
+ "learning_rate": 3.508771929824562e-05,
183
+ "loss": 0.7629,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.2268266085059978,
188
+ "grad_norm": 0.7676778822568288,
189
+ "learning_rate": 3.649122807017544e-05,
190
+ "loss": 0.7521,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.23555070883315157,
195
+ "grad_norm": 1.0032530689824866,
196
+ "learning_rate": 3.789473684210526e-05,
197
+ "loss": 0.7384,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.24427480916030533,
202
+ "grad_norm": 1.2535316239757839,
203
+ "learning_rate": 3.929824561403509e-05,
204
+ "loss": 0.7474,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.2529989094874591,
209
+ "grad_norm": 0.9953077887554728,
210
+ "learning_rate": 4.070175438596492e-05,
211
+ "loss": 0.7412,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.2617230098146129,
216
+ "grad_norm": 1.3600760898966002,
217
+ "learning_rate": 4.210526315789474e-05,
218
+ "loss": 0.7257,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.27044711014176664,
223
+ "grad_norm": 0.6326945767090465,
224
+ "learning_rate": 4.350877192982457e-05,
225
+ "loss": 0.7247,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.2791712104689204,
230
+ "grad_norm": 1.0488194881380388,
231
+ "learning_rate": 4.491228070175439e-05,
232
+ "loss": 0.7247,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.28789531079607417,
237
+ "grad_norm": 1.1854260719924898,
238
+ "learning_rate": 4.6315789473684214e-05,
239
+ "loss": 0.7265,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.2966194111232279,
244
+ "grad_norm": 1.231800504978088,
245
+ "learning_rate": 4.771929824561404e-05,
246
+ "loss": 0.724,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.3053435114503817,
251
+ "grad_norm": 1.1471910683800164,
252
+ "learning_rate": 4.9122807017543864e-05,
253
+ "loss": 0.7245,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.31406761177753545,
258
+ "grad_norm": 1.2650375204215663,
259
+ "learning_rate": 5.052631578947368e-05,
260
+ "loss": 0.7173,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.3227917121046892,
265
+ "grad_norm": 1.581708517443491,
266
+ "learning_rate": 5.1929824561403515e-05,
267
+ "loss": 0.7146,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.33151581243184297,
272
+ "grad_norm": 0.6899231907687099,
273
+ "learning_rate": 5.333333333333333e-05,
274
+ "loss": 0.7039,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.34023991275899673,
279
+ "grad_norm": 1.9659650918585876,
280
+ "learning_rate": 5.4736842105263165e-05,
281
+ "loss": 0.7129,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.3489640130861505,
286
+ "grad_norm": 0.9602545263207618,
287
+ "learning_rate": 5.6140350877192984e-05,
288
+ "loss": 0.7229,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.35768811341330425,
293
+ "grad_norm": 2.019396688493347,
294
+ "learning_rate": 5.7543859649122816e-05,
295
+ "loss": 0.7173,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.366412213740458,
300
+ "grad_norm": 1.3667216071947406,
301
+ "learning_rate": 5.8947368421052634e-05,
302
+ "loss": 0.7088,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.3751363140676118,
307
+ "grad_norm": 1.6739220492126983,
308
+ "learning_rate": 6.035087719298246e-05,
309
+ "loss": 0.7126,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.38386041439476554,
314
+ "grad_norm": 1.406631076781101,
315
+ "learning_rate": 6.175438596491228e-05,
316
+ "loss": 0.7211,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.3925845147219193,
321
+ "grad_norm": 1.232815581243198,
322
+ "learning_rate": 6.315789473684212e-05,
323
+ "loss": 0.7114,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.40130861504907306,
328
+ "grad_norm": 1.3716611381630202,
329
+ "learning_rate": 6.456140350877194e-05,
330
+ "loss": 0.7174,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.4100327153762268,
335
+ "grad_norm": 1.1415702503019296,
336
+ "learning_rate": 6.596491228070175e-05,
337
+ "loss": 0.7005,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.4187568157033806,
342
+ "grad_norm": 1.2074860027919303,
343
+ "learning_rate": 6.736842105263159e-05,
344
+ "loss": 0.7098,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.42748091603053434,
349
+ "grad_norm": 1.6609425790213797,
350
+ "learning_rate": 6.87719298245614e-05,
351
+ "loss": 0.7098,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.4362050163576881,
356
+ "grad_norm": 0.9769451874458346,
357
+ "learning_rate": 7.017543859649124e-05,
358
+ "loss": 0.7079,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.44492911668484186,
363
+ "grad_norm": 1.7666355593904801,
364
+ "learning_rate": 7.157894736842105e-05,
365
+ "loss": 0.6967,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.4536532170119956,
370
+ "grad_norm": 1.014343915032852,
371
+ "learning_rate": 7.298245614035087e-05,
372
+ "loss": 0.6961,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.4623773173391494,
377
+ "grad_norm": 1.292912081295997,
378
+ "learning_rate": 7.43859649122807e-05,
379
+ "loss": 0.6888,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.47110141766630315,
384
+ "grad_norm": 1.33549845587438,
385
+ "learning_rate": 7.578947368421052e-05,
386
+ "loss": 0.6989,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.4798255179934569,
391
+ "grad_norm": 1.6285853466115705,
392
+ "learning_rate": 7.719298245614036e-05,
393
+ "loss": 0.7016,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.48854961832061067,
398
+ "grad_norm": 0.9433375871219883,
399
+ "learning_rate": 7.859649122807017e-05,
400
+ "loss": 0.6824,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.49727371864776443,
405
+ "grad_norm": 1.2489894514867836,
406
+ "learning_rate": 8e-05,
407
+ "loss": 0.6898,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.5059978189749182,
412
+ "grad_norm": 1.60283780700127,
413
+ "learning_rate": 7.99992499440621e-05,
414
+ "loss": 0.7019,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.514721919302072,
419
+ "grad_norm": 1.349411337094158,
420
+ "learning_rate": 7.999699980437755e-05,
421
+ "loss": 0.692,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.5234460196292258,
426
+ "grad_norm": 1.4027794489135887,
427
+ "learning_rate": 7.999324966533291e-05,
428
+ "loss": 0.6739,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.5321701199563795,
433
+ "grad_norm": 0.8999831714962346,
434
+ "learning_rate": 7.998799966756889e-05,
435
+ "loss": 0.6925,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.5408942202835333,
440
+ "grad_norm": 1.2349556182219792,
441
+ "learning_rate": 7.998125000797506e-05,
442
+ "loss": 0.6811,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.549618320610687,
447
+ "grad_norm": 0.9953482513645127,
448
+ "learning_rate": 7.997300093968255e-05,
449
+ "loss": 0.6919,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.5583424209378408,
454
+ "grad_norm": 1.7631278928848257,
455
+ "learning_rate": 7.99632527720545e-05,
456
+ "loss": 0.7076,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.5670665212649946,
461
+ "grad_norm": 0.9802682486455654,
462
+ "learning_rate": 7.995200587067445e-05,
463
+ "loss": 0.6836,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.5757906215921483,
468
+ "grad_norm": 1.4018686830735987,
469
+ "learning_rate": 7.993926065733265e-05,
470
+ "loss": 0.6998,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.5845147219193021,
475
+ "grad_norm": 1.0081781512305683,
476
+ "learning_rate": 7.992501761001027e-05,
477
+ "loss": 0.6878,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.5932388222464559,
482
+ "grad_norm": 1.2813118135682324,
483
+ "learning_rate": 7.99092772628614e-05,
484
+ "loss": 0.6948,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.6019629225736096,
489
+ "grad_norm": 0.9281112795468938,
490
+ "learning_rate": 7.98920402061931e-05,
491
+ "loss": 0.6969,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.6106870229007634,
496
+ "grad_norm": 1.2375443626494387,
497
+ "learning_rate": 7.987330708644319e-05,
498
+ "loss": 0.6793,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.6194111232279171,
503
+ "grad_norm": 1.0863449033166035,
504
+ "learning_rate": 7.985307860615607e-05,
505
+ "loss": 0.6848,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.6281352235550709,
510
+ "grad_norm": 0.942362107324505,
511
+ "learning_rate": 7.98313555239563e-05,
512
+ "loss": 0.6862,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.6368593238822247,
517
+ "grad_norm": 1.3027161650276327,
518
+ "learning_rate": 7.980813865452026e-05,
519
+ "loss": 0.6735,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.6455834242093784,
524
+ "grad_norm": 0.7977961043410647,
525
+ "learning_rate": 7.978342886854546e-05,
526
+ "loss": 0.6787,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.6543075245365322,
531
+ "grad_norm": 1.3693856212692685,
532
+ "learning_rate": 7.975722709271799e-05,
533
+ "loss": 0.6751,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.6630316248636859,
538
+ "grad_norm": 0.7738139399748106,
539
+ "learning_rate": 7.972953430967773e-05,
540
+ "loss": 0.6726,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.6717557251908397,
545
+ "grad_norm": 0.6453937973753266,
546
+ "learning_rate": 7.97003515579815e-05,
547
+ "loss": 0.6756,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.6804798255179935,
552
+ "grad_norm": 0.7085908664971486,
553
+ "learning_rate": 7.96696799320641e-05,
554
+ "loss": 0.6774,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.6892039258451472,
559
+ "grad_norm": 0.7420105586344222,
560
+ "learning_rate": 7.96375205821973e-05,
561
+ "loss": 0.6647,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.697928026172301,
566
+ "grad_norm": 1.182903610639294,
567
+ "learning_rate": 7.960387471444666e-05,
568
+ "loss": 0.6758,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.7066521264994547,
573
+ "grad_norm": 1.305515943296027,
574
+ "learning_rate": 7.956874359062632e-05,
575
+ "loss": 0.6808,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.7153762268266085,
580
+ "grad_norm": 0.9451990102208602,
581
+ "learning_rate": 7.95321285282517e-05,
582
+ "loss": 0.6697,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.7241003271537623,
587
+ "grad_norm": 0.9432391308082473,
588
+ "learning_rate": 7.949403090049002e-05,
589
+ "loss": 0.6723,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.732824427480916,
594
+ "grad_norm": 1.1371193647756934,
595
+ "learning_rate": 7.94544521361089e-05,
596
+ "loss": 0.6773,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.7415485278080698,
601
+ "grad_norm": 1.1858932832021734,
602
+ "learning_rate": 7.941339371942269e-05,
603
+ "loss": 0.6657,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.7502726281352236,
608
+ "grad_norm": 1.165847606968587,
609
+ "learning_rate": 7.937085719023685e-05,
610
+ "loss": 0.6743,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.7589967284623773,
615
+ "grad_norm": 0.5770889497138026,
616
+ "learning_rate": 7.932684414379021e-05,
617
+ "loss": 0.668,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 0.7677208287895311,
622
+ "grad_norm": 0.925349798073699,
623
+ "learning_rate": 7.928135623069509e-05,
624
+ "loss": 0.6693,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 0.7764449291166848,
629
+ "grad_norm": 1.2265564072341149,
630
+ "learning_rate": 7.923439515687546e-05,
631
+ "loss": 0.6721,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 0.7851690294438386,
636
+ "grad_norm": 0.76774338811776,
637
+ "learning_rate": 7.918596268350296e-05,
638
+ "loss": 0.664,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 0.7938931297709924,
643
+ "grad_norm": 0.811830002272808,
644
+ "learning_rate": 7.913606062693077e-05,
645
+ "loss": 0.6674,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 0.8026172300981461,
650
+ "grad_norm": 0.7896885933612465,
651
+ "learning_rate": 7.90846908586256e-05,
652
+ "loss": 0.6603,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 0.8113413304252999,
657
+ "grad_norm": 0.6860009351157326,
658
+ "learning_rate": 7.903185530509743e-05,
659
+ "loss": 0.6541,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 0.8200654307524536,
664
+ "grad_norm": 0.7887179980130798,
665
+ "learning_rate": 7.89775559478273e-05,
666
+ "loss": 0.6719,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 0.8287895310796074,
671
+ "grad_norm": 0.6863156036434349,
672
+ "learning_rate": 7.892179482319297e-05,
673
+ "loss": 0.6712,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 0.8375136314067612,
678
+ "grad_norm": 0.612318445743932,
679
+ "learning_rate": 7.886457402239256e-05,
680
+ "loss": 0.6588,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 0.8462377317339149,
685
+ "grad_norm": 0.5266659568320967,
686
+ "learning_rate": 7.880589569136616e-05,
687
+ "loss": 0.6477,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 0.8549618320610687,
692
+ "grad_norm": 0.6815563256417184,
693
+ "learning_rate": 7.874576203071531e-05,
694
+ "loss": 0.6647,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 0.8636859323882224,
699
+ "grad_norm": 0.7021771362356389,
700
+ "learning_rate": 7.868417529562043e-05,
701
+ "loss": 0.6519,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 0.8724100327153762,
706
+ "grad_norm": 0.9537663707386643,
707
+ "learning_rate": 7.862113779575638e-05,
708
+ "loss": 0.6655,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 0.88113413304253,
713
+ "grad_norm": 1.7262458672727332,
714
+ "learning_rate": 7.85566518952057e-05,
715
+ "loss": 0.6617,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 0.8898582333696837,
720
+ "grad_norm": 0.5924197078630852,
721
+ "learning_rate": 7.849072001237001e-05,
722
+ "loss": 0.6586,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 0.8985823336968375,
727
+ "grad_norm": 1.784429399577841,
728
+ "learning_rate": 7.842334461987936e-05,
729
+ "loss": 0.6718,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 0.9073064340239912,
734
+ "grad_norm": 0.8548005705828143,
735
+ "learning_rate": 7.835452824449935e-05,
736
+ "loss": 0.6589,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 0.916030534351145,
741
+ "grad_norm": 1.5914313223828267,
742
+ "learning_rate": 7.828427346703657e-05,
743
+ "loss": 0.6639,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 0.9247546346782988,
748
+ "grad_norm": 1.1912921777513241,
749
+ "learning_rate": 7.821258292224166e-05,
750
+ "loss": 0.669,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 0.9334787350054525,
755
+ "grad_norm": 1.1951669530416693,
756
+ "learning_rate": 7.813945929871056e-05,
757
+ "loss": 0.6497,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 0.9422028353326063,
762
+ "grad_norm": 1.037062568022807,
763
+ "learning_rate": 7.806490533878368e-05,
764
+ "loss": 0.6632,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 0.95092693565976,
769
+ "grad_norm": 1.2483557427639183,
770
+ "learning_rate": 7.798892383844303e-05,
771
+ "loss": 0.658,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 0.9596510359869138,
776
+ "grad_norm": 0.8133626652288988,
777
+ "learning_rate": 7.791151764720737e-05,
778
+ "loss": 0.6571,
779
+ "step": 110
780
+ },
781
+ {
782
+ "epoch": 0.9683751363140676,
783
+ "grad_norm": 1.0059615445006975,
784
+ "learning_rate": 7.783268966802539e-05,
785
+ "loss": 0.6595,
786
+ "step": 111
787
+ },
788
+ {
789
+ "epoch": 0.9770992366412213,
790
+ "grad_norm": 0.7304172503042858,
791
+ "learning_rate": 7.775244285716679e-05,
792
+ "loss": 0.6608,
793
+ "step": 112
794
+ },
795
+ {
796
+ "epoch": 0.9858233369683751,
797
+ "grad_norm": 0.7284490288054312,
798
+ "learning_rate": 7.767078022411139e-05,
799
+ "loss": 0.6492,
800
+ "step": 113
801
+ },
802
+ {
803
+ "epoch": 0.9945474372955289,
804
+ "grad_norm": 0.5901533647047473,
805
+ "learning_rate": 7.758770483143634e-05,
806
+ "loss": 0.6642,
807
+ "step": 114
808
+ },
809
+ {
810
+ "epoch": 1.0038167938931297,
811
+ "grad_norm": 0.8414397249541458,
812
+ "learning_rate": 7.750321979470123e-05,
813
+ "loss": 0.9152,
814
+ "step": 115
815
+ },
816
+ {
817
+ "epoch": 1.0125408942202836,
818
+ "grad_norm": 1.0739193248054102,
819
+ "learning_rate": 7.741732828233124e-05,
820
+ "loss": 0.626,
821
+ "step": 116
822
+ },
823
+ {
824
+ "epoch": 1.0212649945474372,
825
+ "grad_norm": 1.1988463490729344,
826
+ "learning_rate": 7.733003351549829e-05,
827
+ "loss": 0.6393,
828
+ "step": 117
829
+ },
830
+ {
831
+ "epoch": 1.0299890948745911,
832
+ "grad_norm": 0.9606655160302263,
833
+ "learning_rate": 7.724133876800031e-05,
834
+ "loss": 0.625,
835
+ "step": 118
836
+ },
837
+ {
838
+ "epoch": 1.0387131952017448,
839
+ "grad_norm": 1.2372012961246242,
840
+ "learning_rate": 7.715124736613839e-05,
841
+ "loss": 0.6278,
842
+ "step": 119
843
+ },
844
+ {
845
+ "epoch": 1.0474372955288986,
846
+ "grad_norm": 0.86001815183547,
847
+ "learning_rate": 7.705976268859207e-05,
848
+ "loss": 0.6187,
849
+ "step": 120
850
+ },
851
+ {
852
+ "epoch": 1.0561613958560523,
853
+ "grad_norm": 1.1413833226380308,
854
+ "learning_rate": 7.696688816629266e-05,
855
+ "loss": 0.63,
856
+ "step": 121
857
+ },
858
+ {
859
+ "epoch": 1.0648854961832062,
860
+ "grad_norm": 1.2327702775009692,
861
+ "learning_rate": 7.687262728229447e-05,
862
+ "loss": 0.6205,
863
+ "step": 122
864
+ },
865
+ {
866
+ "epoch": 1.0736095965103598,
867
+ "grad_norm": 0.7767212251506833,
868
+ "learning_rate": 7.677698357164431e-05,
869
+ "loss": 0.6177,
870
+ "step": 123
871
+ },
872
+ {
873
+ "epoch": 1.0823336968375137,
874
+ "grad_norm": 1.7079661807939999,
875
+ "learning_rate": 7.667996062124884e-05,
876
+ "loss": 0.6242,
877
+ "step": 124
878
+ },
879
+ {
880
+ "epoch": 1.0910577971646673,
881
+ "grad_norm": 1.0068734700150146,
882
+ "learning_rate": 7.658156206974005e-05,
883
+ "loss": 0.6183,
884
+ "step": 125
885
+ },
886
+ {
887
+ "epoch": 1.0997818974918212,
888
+ "grad_norm": 1.8753922872596245,
889
+ "learning_rate": 7.648179160733883e-05,
890
+ "loss": 0.6337,
891
+ "step": 126
892
+ },
893
+ {
894
+ "epoch": 1.1085059978189749,
895
+ "grad_norm": 1.8578444866986128,
896
+ "learning_rate": 7.638065297571657e-05,
897
+ "loss": 0.6171,
898
+ "step": 127
899
+ },
900
+ {
901
+ "epoch": 1.1172300981461287,
902
+ "grad_norm": 0.6478551153484415,
903
+ "learning_rate": 7.627814996785484e-05,
904
+ "loss": 0.6158,
905
+ "step": 128
906
+ },
907
+ {
908
+ "epoch": 1.1259541984732824,
909
+ "grad_norm": 1.4820468569461809,
910
+ "learning_rate": 7.61742864279031e-05,
911
+ "loss": 0.6197,
912
+ "step": 129
913
+ },
914
+ {
915
+ "epoch": 1.1346782988004362,
916
+ "grad_norm": 0.7243487925020168,
917
+ "learning_rate": 7.606906625103464e-05,
918
+ "loss": 0.625,
919
+ "step": 130
920
+ },
921
+ {
922
+ "epoch": 1.14340239912759,
923
+ "grad_norm": 0.9539104928282168,
924
+ "learning_rate": 7.596249338330034e-05,
925
+ "loss": 0.6194,
926
+ "step": 131
927
+ },
928
+ {
929
+ "epoch": 1.1521264994547438,
930
+ "grad_norm": 0.8136844990028549,
931
+ "learning_rate": 7.585457182148081e-05,
932
+ "loss": 0.6172,
933
+ "step": 132
934
+ },
935
+ {
936
+ "epoch": 1.1608505997818974,
937
+ "grad_norm": 0.7125736106844306,
938
+ "learning_rate": 7.57453056129365e-05,
939
+ "loss": 0.6151,
940
+ "step": 133
941
+ },
942
+ {
943
+ "epoch": 1.1695747001090513,
944
+ "grad_norm": 0.5804990189493681,
945
+ "learning_rate": 7.56346988554558e-05,
946
+ "loss": 0.6256,
947
+ "step": 134
948
+ },
949
+ {
950
+ "epoch": 1.178298800436205,
951
+ "grad_norm": 0.6362204084540434,
952
+ "learning_rate": 7.552275569710152e-05,
953
+ "loss": 0.6184,
954
+ "step": 135
955
+ },
956
+ {
957
+ "epoch": 1.1870229007633588,
958
+ "grad_norm": 0.43420077191532125,
959
+ "learning_rate": 7.540948033605513e-05,
960
+ "loss": 0.6105,
961
+ "step": 136
962
+ },
963
+ {
964
+ "epoch": 1.1957470010905125,
965
+ "grad_norm": 0.46232316550703767,
966
+ "learning_rate": 7.529487702045953e-05,
967
+ "loss": 0.6056,
968
+ "step": 137
969
+ },
970
+ {
971
+ "epoch": 1.2044711014176663,
972
+ "grad_norm": 0.4316498267915253,
973
+ "learning_rate": 7.517895004825956e-05,
974
+ "loss": 0.6011,
975
+ "step": 138
976
+ },
977
+ {
978
+ "epoch": 1.21319520174482,
979
+ "grad_norm": 0.38696383075278273,
980
+ "learning_rate": 7.506170376704095e-05,
981
+ "loss": 0.6141,
982
+ "step": 139
983
+ },
984
+ {
985
+ "epoch": 1.2219193020719739,
986
+ "grad_norm": 0.3858939834475368,
987
+ "learning_rate": 7.494314257386715e-05,
988
+ "loss": 0.6065,
989
+ "step": 140
990
+ },
991
+ {
992
+ "epoch": 1.2306434023991275,
993
+ "grad_norm": 0.3738279653817542,
994
+ "learning_rate": 7.48232709151145e-05,
995
+ "loss": 0.6104,
996
+ "step": 141
997
+ },
998
+ {
999
+ "epoch": 1.2393675027262814,
1000
+ "grad_norm": 0.34434724315715803,
1001
+ "learning_rate": 7.470209328630548e-05,
1002
+ "loss": 0.605,
1003
+ "step": 142
1004
+ },
1005
+ {
1006
+ "epoch": 1.248091603053435,
1007
+ "grad_norm": 0.3291602472493041,
1008
+ "learning_rate": 7.457961423194011e-05,
1009
+ "loss": 0.6018,
1010
+ "step": 143
1011
+ },
1012
+ {
1013
+ "epoch": 1.256815703380589,
1014
+ "grad_norm": 0.27837095142325796,
1015
+ "learning_rate": 7.445583834532546e-05,
1016
+ "loss": 0.5993,
1017
+ "step": 144
1018
+ },
1019
+ {
1020
+ "epoch": 1.2655398037077425,
1021
+ "grad_norm": 0.31225187743500077,
1022
+ "learning_rate": 7.433077026840346e-05,
1023
+ "loss": 0.5984,
1024
+ "step": 145
1025
+ },
1026
+ {
1027
+ "epoch": 1.2742639040348964,
1028
+ "grad_norm": 0.27063932853508044,
1029
+ "learning_rate": 7.420441469157684e-05,
1030
+ "loss": 0.6048,
1031
+ "step": 146
1032
+ },
1033
+ {
1034
+ "epoch": 1.2829880043620503,
1035
+ "grad_norm": 0.28328810560800655,
1036
+ "learning_rate": 7.407677635353308e-05,
1037
+ "loss": 0.6061,
1038
+ "step": 147
1039
+ },
1040
+ {
1041
+ "epoch": 1.291712104689204,
1042
+ "grad_norm": 0.3335236260280515,
1043
+ "learning_rate": 7.39478600410669e-05,
1044
+ "loss": 0.6055,
1045
+ "step": 148
1046
+ },
1047
+ {
1048
+ "epoch": 1.3004362050163576,
1049
+ "grad_norm": 0.34277641090811606,
1050
+ "learning_rate": 7.381767058890056e-05,
1051
+ "loss": 0.5956,
1052
+ "step": 149
1053
+ },
1054
+ {
1055
+ "epoch": 1.3091603053435115,
1056
+ "grad_norm": 0.3944860323036086,
1057
+ "learning_rate": 7.368621287950264e-05,
1058
+ "loss": 0.5971,
1059
+ "step": 150
1060
+ },
1061
+ {
1062
+ "epoch": 1.3178844056706653,
1063
+ "grad_norm": 0.390412169412763,
1064
+ "learning_rate": 7.355349184290491e-05,
1065
+ "loss": 0.5991,
1066
+ "step": 151
1067
+ },
1068
+ {
1069
+ "epoch": 1.326608505997819,
1070
+ "grad_norm": 0.44167362977698205,
1071
+ "learning_rate": 7.341951245651747e-05,
1072
+ "loss": 0.5905,
1073
+ "step": 152
1074
+ },
1075
+ {
1076
+ "epoch": 1.3353326063249726,
1077
+ "grad_norm": 0.4873733423530836,
1078
+ "learning_rate": 7.328427974494201e-05,
1079
+ "loss": 0.6061,
1080
+ "step": 153
1081
+ },
1082
+ {
1083
+ "epoch": 1.3440567066521265,
1084
+ "grad_norm": 0.529005701508295,
1085
+ "learning_rate": 7.314779877978346e-05,
1086
+ "loss": 0.6038,
1087
+ "step": 154
1088
+ },
1089
+ {
1090
+ "epoch": 1.3527808069792804,
1091
+ "grad_norm": 0.5776151078666283,
1092
+ "learning_rate": 7.301007467945974e-05,
1093
+ "loss": 0.6063,
1094
+ "step": 155
1095
+ },
1096
+ {
1097
+ "epoch": 1.361504907306434,
1098
+ "grad_norm": 0.6712943884189805,
1099
+ "learning_rate": 7.28711126090098e-05,
1100
+ "loss": 0.609,
1101
+ "step": 156
1102
+ },
1103
+ {
1104
+ "epoch": 1.3702290076335877,
1105
+ "grad_norm": 0.6974077084236574,
1106
+ "learning_rate": 7.273091777989997e-05,
1107
+ "loss": 0.617,
1108
+ "step": 157
1109
+ },
1110
+ {
1111
+ "epoch": 1.3789531079607416,
1112
+ "grad_norm": 0.622800075821039,
1113
+ "learning_rate": 7.258949544982843e-05,
1114
+ "loss": 0.6012,
1115
+ "step": 158
1116
+ },
1117
+ {
1118
+ "epoch": 1.3876772082878954,
1119
+ "grad_norm": 0.6652165160394861,
1120
+ "learning_rate": 7.24468509225281e-05,
1121
+ "loss": 0.6213,
1122
+ "step": 159
1123
+ },
1124
+ {
1125
+ "epoch": 1.396401308615049,
1126
+ "grad_norm": 0.7796997637986155,
1127
+ "learning_rate": 7.230298954756772e-05,
1128
+ "loss": 0.6116,
1129
+ "step": 160
1130
+ },
1131
+ {
1132
+ "epoch": 1.4051254089422027,
1133
+ "grad_norm": 0.8050974173338423,
1134
+ "learning_rate": 7.215791672015121e-05,
1135
+ "loss": 0.6102,
1136
+ "step": 161
1137
+ },
1138
+ {
1139
+ "epoch": 1.4138495092693566,
1140
+ "grad_norm": 0.6245666904233175,
1141
+ "learning_rate": 7.201163788091536e-05,
1142
+ "loss": 0.6051,
1143
+ "step": 162
1144
+ },
1145
+ {
1146
+ "epoch": 1.4225736095965105,
1147
+ "grad_norm": 0.2791815826660419,
1148
+ "learning_rate": 7.186415851572579e-05,
1149
+ "loss": 0.5978,
1150
+ "step": 163
1151
+ },
1152
+ {
1153
+ "epoch": 1.4312977099236641,
1154
+ "grad_norm": 0.5658363527146323,
1155
+ "learning_rate": 7.171548415547114e-05,
1156
+ "loss": 0.6064,
1157
+ "step": 164
1158
+ },
1159
+ {
1160
+ "epoch": 1.4400218102508178,
1161
+ "grad_norm": 0.6010202995307374,
1162
+ "learning_rate": 7.156562037585576e-05,
1163
+ "loss": 0.6117,
1164
+ "step": 165
1165
+ },
1166
+ {
1167
+ "epoch": 1.4487459105779716,
1168
+ "grad_norm": 0.45545843396243296,
1169
+ "learning_rate": 7.141457279719053e-05,
1170
+ "loss": 0.6079,
1171
+ "step": 166
1172
+ },
1173
+ {
1174
+ "epoch": 1.4574700109051255,
1175
+ "grad_norm": 0.37879238626475686,
1176
+ "learning_rate": 7.126234708418214e-05,
1177
+ "loss": 0.5965,
1178
+ "step": 167
1179
+ },
1180
+ {
1181
+ "epoch": 1.4661941112322792,
1182
+ "grad_norm": 0.4580319723211172,
1183
+ "learning_rate": 7.110894894572056e-05,
1184
+ "loss": 0.6106,
1185
+ "step": 168
1186
+ },
1187
+ {
1188
+ "epoch": 1.4749182115594328,
1189
+ "grad_norm": 0.43310826738894753,
1190
+ "learning_rate": 7.095438413466503e-05,
1191
+ "loss": 0.6152,
1192
+ "step": 169
1193
+ },
1194
+ {
1195
+ "epoch": 1.4836423118865867,
1196
+ "grad_norm": 0.42673749198290256,
1197
+ "learning_rate": 7.079865844762829e-05,
1198
+ "loss": 0.6058,
1199
+ "step": 170
1200
+ },
1201
+ {
1202
+ "epoch": 1.4923664122137406,
1203
+ "grad_norm": 0.5356882769390818,
1204
+ "learning_rate": 7.064177772475912e-05,
1205
+ "loss": 0.6011,
1206
+ "step": 171
1207
+ },
1208
+ {
1209
+ "epoch": 1.5010905125408942,
1210
+ "grad_norm": 0.48453744479417066,
1211
+ "learning_rate": 7.048374784952343e-05,
1212
+ "loss": 0.6014,
1213
+ "step": 172
1214
+ },
1215
+ {
1216
+ "epoch": 1.5098146128680479,
1217
+ "grad_norm": 0.40573397034428954,
1218
+ "learning_rate": 7.03245747484835e-05,
1219
+ "loss": 0.6021,
1220
+ "step": 173
1221
+ },
1222
+ {
1223
+ "epoch": 1.5185387131952017,
1224
+ "grad_norm": 0.5052592973873418,
1225
+ "learning_rate": 7.016426439107586e-05,
1226
+ "loss": 0.5976,
1227
+ "step": 174
1228
+ },
1229
+ {
1230
+ "epoch": 1.5272628135223556,
1231
+ "grad_norm": 0.5640845358828827,
1232
+ "learning_rate": 7.000282278938724e-05,
1233
+ "loss": 0.6032,
1234
+ "step": 175
1235
+ },
1236
+ {
1237
+ "epoch": 1.5359869138495092,
1238
+ "grad_norm": 0.5716127749488464,
1239
+ "learning_rate": 6.984025599792926e-05,
1240
+ "loss": 0.6069,
1241
+ "step": 176
1242
+ },
1243
+ {
1244
+ "epoch": 1.544711014176663,
1245
+ "grad_norm": 0.6147245538888289,
1246
+ "learning_rate": 6.967657011341126e-05,
1247
+ "loss": 0.6017,
1248
+ "step": 177
1249
+ },
1250
+ {
1251
+ "epoch": 1.5534351145038168,
1252
+ "grad_norm": 0.5972264181543786,
1253
+ "learning_rate": 6.951177127451177e-05,
1254
+ "loss": 0.6039,
1255
+ "step": 178
1256
+ },
1257
+ {
1258
+ "epoch": 1.5621592148309706,
1259
+ "grad_norm": 0.4511378630106592,
1260
+ "learning_rate": 6.934586566164811e-05,
1261
+ "loss": 0.609,
1262
+ "step": 179
1263
+ },
1264
+ {
1265
+ "epoch": 1.5708833151581243,
1266
+ "grad_norm": 0.3324255798317227,
1267
+ "learning_rate": 6.917885949674483e-05,
1268
+ "loss": 0.6046,
1269
+ "step": 180
1270
+ },
1271
+ {
1272
+ "epoch": 1.579607415485278,
1273
+ "grad_norm": 0.3318537793653575,
1274
+ "learning_rate": 6.901075904300021e-05,
1275
+ "loss": 0.5984,
1276
+ "step": 181
1277
+ },
1278
+ {
1279
+ "epoch": 1.5883315158124318,
1280
+ "grad_norm": 0.4025671963472955,
1281
+ "learning_rate": 6.88415706046514e-05,
1282
+ "loss": 0.5991,
1283
+ "step": 182
1284
+ },
1285
+ {
1286
+ "epoch": 1.5970556161395857,
1287
+ "grad_norm": 0.4039375325984613,
1288
+ "learning_rate": 6.867130052673806e-05,
1289
+ "loss": 0.6132,
1290
+ "step": 183
1291
+ },
1292
+ {
1293
+ "epoch": 1.6057797164667393,
1294
+ "grad_norm": 0.42633324449837107,
1295
+ "learning_rate": 6.849995519486434e-05,
1296
+ "loss": 0.6112,
1297
+ "step": 184
1298
+ },
1299
+ {
1300
+ "epoch": 1.614503816793893,
1301
+ "grad_norm": 0.4031771610559183,
1302
+ "learning_rate": 6.832754103495939e-05,
1303
+ "loss": 0.5951,
1304
+ "step": 185
1305
+ },
1306
+ {
1307
+ "epoch": 1.6232279171210469,
1308
+ "grad_norm": 0.3101345676851429,
1309
+ "learning_rate": 6.815406451303647e-05,
1310
+ "loss": 0.5977,
1311
+ "step": 186
1312
+ },
1313
+ {
1314
+ "epoch": 1.6319520174482007,
1315
+ "grad_norm": 0.28180350855331504,
1316
+ "learning_rate": 6.797953213495033e-05,
1317
+ "loss": 0.6081,
1318
+ "step": 187
1319
+ },
1320
+ {
1321
+ "epoch": 1.6406761177753544,
1322
+ "grad_norm": 0.3450910788047459,
1323
+ "learning_rate": 6.780395044615329e-05,
1324
+ "loss": 0.606,
1325
+ "step": 188
1326
+ },
1327
+ {
1328
+ "epoch": 1.649400218102508,
1329
+ "grad_norm": 0.3941732240418325,
1330
+ "learning_rate": 6.762732603144978e-05,
1331
+ "loss": 0.6079,
1332
+ "step": 189
1333
+ },
1334
+ {
1335
+ "epoch": 1.658124318429662,
1336
+ "grad_norm": 0.3241938707733741,
1337
+ "learning_rate": 6.744966551474936e-05,
1338
+ "loss": 0.604,
1339
+ "step": 190
1340
+ },
1341
+ {
1342
+ "epoch": 1.6668484187568158,
1343
+ "grad_norm": 0.27804934781744717,
1344
+ "learning_rate": 6.727097555881826e-05,
1345
+ "loss": 0.595,
1346
+ "step": 191
1347
+ },
1348
+ {
1349
+ "epoch": 1.6755725190839694,
1350
+ "grad_norm": 0.25336159667743025,
1351
+ "learning_rate": 6.709126286502965e-05,
1352
+ "loss": 0.6025,
1353
+ "step": 192
1354
+ },
1355
+ {
1356
+ "epoch": 1.684296619411123,
1357
+ "grad_norm": 0.29341065316587794,
1358
+ "learning_rate": 6.691053417311216e-05,
1359
+ "loss": 0.6023,
1360
+ "step": 193
1361
+ },
1362
+ {
1363
+ "epoch": 1.693020719738277,
1364
+ "grad_norm": 0.2878985409168238,
1365
+ "learning_rate": 6.672879626089723e-05,
1366
+ "loss": 0.5949,
1367
+ "step": 194
1368
+ },
1369
+ {
1370
+ "epoch": 1.7017448200654308,
1371
+ "grad_norm": 0.26927072720134837,
1372
+ "learning_rate": 6.654605594406486e-05,
1373
+ "loss": 0.5979,
1374
+ "step": 195
1375
+ },
1376
+ {
1377
+ "epoch": 1.7104689203925845,
1378
+ "grad_norm": 0.3155329601805801,
1379
+ "learning_rate": 6.636232007588805e-05,
1380
+ "loss": 0.587,
1381
+ "step": 196
1382
+ },
1383
+ {
1384
+ "epoch": 1.7191930207197381,
1385
+ "grad_norm": 0.34847815991034525,
1386
+ "learning_rate": 6.617759554697573e-05,
1387
+ "loss": 0.5978,
1388
+ "step": 197
1389
+ },
1390
+ {
1391
+ "epoch": 1.727917121046892,
1392
+ "grad_norm": 0.28896074500408486,
1393
+ "learning_rate": 6.59918892850144e-05,
1394
+ "loss": 0.6069,
1395
+ "step": 198
1396
+ },
1397
+ {
1398
+ "epoch": 1.7366412213740459,
1399
+ "grad_norm": 0.2981626524269195,
1400
+ "learning_rate": 6.580520825450827e-05,
1401
+ "loss": 0.5956,
1402
+ "step": 199
1403
+ },
1404
+ {
1405
+ "epoch": 1.7453653217011995,
1406
+ "grad_norm": 0.31680273274222387,
1407
+ "learning_rate": 6.561755945651813e-05,
1408
+ "loss": 0.5907,
1409
+ "step": 200
1410
+ },
1411
+ {
1412
+ "epoch": 1.7540894220283532,
1413
+ "grad_norm": 0.2788023167998957,
1414
+ "learning_rate": 6.542894992839873e-05,
1415
+ "loss": 0.5988,
1416
+ "step": 201
1417
+ },
1418
+ {
1419
+ "epoch": 1.762813522355507,
1420
+ "grad_norm": 0.26041179212976306,
1421
+ "learning_rate": 6.52393867435349e-05,
1422
+ "loss": 0.5879,
1423
+ "step": 202
1424
+ },
1425
+ {
1426
+ "epoch": 1.771537622682661,
1427
+ "grad_norm": 0.34950012098507055,
1428
+ "learning_rate": 6.504887701107626e-05,
1429
+ "loss": 0.5933,
1430
+ "step": 203
1431
+ },
1432
+ {
1433
+ "epoch": 1.7802617230098146,
1434
+ "grad_norm": 0.5298511066656313,
1435
+ "learning_rate": 6.48574278756706e-05,
1436
+ "loss": 0.59,
1437
+ "step": 204
1438
+ },
1439
+ {
1440
+ "epoch": 1.7889858233369684,
1441
+ "grad_norm": 0.6366920336388178,
1442
+ "learning_rate": 6.466504651719598e-05,
1443
+ "loss": 0.5967,
1444
+ "step": 205
1445
+ },
1446
+ {
1447
+ "epoch": 1.7977099236641223,
1448
+ "grad_norm": 0.6299010554780248,
1449
+ "learning_rate": 6.447174015049139e-05,
1450
+ "loss": 0.5974,
1451
+ "step": 206
1452
+ },
1453
+ {
1454
+ "epoch": 1.806434023991276,
1455
+ "grad_norm": 0.562858852871968,
1456
+ "learning_rate": 6.427751602508628e-05,
1457
+ "loss": 0.6057,
1458
+ "step": 207
1459
+ },
1460
+ {
1461
+ "epoch": 1.8151581243184296,
1462
+ "grad_norm": 0.4004595325182879,
1463
+ "learning_rate": 6.408238142492855e-05,
1464
+ "loss": 0.59,
1465
+ "step": 208
1466
+ },
1467
+ {
1468
+ "epoch": 1.8238822246455835,
1469
+ "grad_norm": 0.21584901270572757,
1470
+ "learning_rate": 6.388634366811146e-05,
1471
+ "loss": 0.5943,
1472
+ "step": 209
1473
+ },
1474
+ {
1475
+ "epoch": 1.8326063249727373,
1476
+ "grad_norm": 0.37265049074019335,
1477
+ "learning_rate": 6.368941010659921e-05,
1478
+ "loss": 0.6096,
1479
+ "step": 210
1480
+ },
1481
+ {
1482
+ "epoch": 1.841330425299891,
1483
+ "grad_norm": 0.5267910816953789,
1484
+ "learning_rate": 6.349158812595116e-05,
1485
+ "loss": 0.6053,
1486
+ "step": 211
1487
+ },
1488
+ {
1489
+ "epoch": 1.8500545256270446,
1490
+ "grad_norm": 0.47801721985552514,
1491
+ "learning_rate": 6.329288514504487e-05,
1492
+ "loss": 0.5936,
1493
+ "step": 212
1494
+ },
1495
+ {
1496
+ "epoch": 1.8587786259541985,
1497
+ "grad_norm": 0.27531874942679646,
1498
+ "learning_rate": 6.309330861579786e-05,
1499
+ "loss": 0.5997,
1500
+ "step": 213
1501
+ },
1502
+ {
1503
+ "epoch": 1.8675027262813524,
1504
+ "grad_norm": 0.3657379875213062,
1505
+ "learning_rate": 6.28928660228882e-05,
1506
+ "loss": 0.5963,
1507
+ "step": 214
1508
+ },
1509
+ {
1510
+ "epoch": 1.876226826608506,
1511
+ "grad_norm": 0.3633999933893769,
1512
+ "learning_rate": 6.269156488347372e-05,
1513
+ "loss": 0.5899,
1514
+ "step": 215
1515
+ },
1516
+ {
1517
+ "epoch": 1.8849509269356597,
1518
+ "grad_norm": 0.2855859194806056,
1519
+ "learning_rate": 6.248941274691017e-05,
1520
+ "loss": 0.5963,
1521
+ "step": 216
1522
+ },
1523
+ {
1524
+ "epoch": 1.8936750272628136,
1525
+ "grad_norm": 0.26871535087996673,
1526
+ "learning_rate": 6.228641719446808e-05,
1527
+ "loss": 0.5832,
1528
+ "step": 217
1529
+ },
1530
+ {
1531
+ "epoch": 1.9023991275899674,
1532
+ "grad_norm": 0.26413333351828056,
1533
+ "learning_rate": 6.208258583904841e-05,
1534
+ "loss": 0.5913,
1535
+ "step": 218
1536
+ },
1537
+ {
1538
+ "epoch": 1.911123227917121,
1539
+ "grad_norm": 0.27861019506862306,
1540
+ "learning_rate": 6.18779263248971e-05,
1541
+ "loss": 0.6088,
1542
+ "step": 219
1543
+ },
1544
+ {
1545
+ "epoch": 1.9198473282442747,
1546
+ "grad_norm": 0.26490994643954596,
1547
+ "learning_rate": 6.16724463273183e-05,
1548
+ "loss": 0.6072,
1549
+ "step": 220
1550
+ },
1551
+ {
1552
+ "epoch": 1.9285714285714286,
1553
+ "grad_norm": 0.2464264085957813,
1554
+ "learning_rate": 6.146615355238668e-05,
1555
+ "loss": 0.5998,
1556
+ "step": 221
1557
+ },
1558
+ {
1559
+ "epoch": 1.9372955288985825,
1560
+ "grad_norm": 0.2060880785957384,
1561
+ "learning_rate": 6.125905573665824e-05,
1562
+ "loss": 0.5998,
1563
+ "step": 222
1564
+ },
1565
+ {
1566
+ "epoch": 1.9460196292257361,
1567
+ "grad_norm": 0.26971063557098873,
1568
+ "learning_rate": 6.105116064688033e-05,
1569
+ "loss": 0.6048,
1570
+ "step": 223
1571
+ },
1572
+ {
1573
+ "epoch": 1.9547437295528898,
1574
+ "grad_norm": 0.32136759035233387,
1575
+ "learning_rate": 6.0842476079700264e-05,
1576
+ "loss": 0.6019,
1577
+ "step": 224
1578
+ },
1579
+ {
1580
+ "epoch": 1.9634678298800436,
1581
+ "grad_norm": 0.23286070304886092,
1582
+ "learning_rate": 6.063300986137297e-05,
1583
+ "loss": 0.5978,
1584
+ "step": 225
1585
+ },
1586
+ {
1587
+ "epoch": 1.9721919302071975,
1588
+ "grad_norm": 0.18824642933626035,
1589
+ "learning_rate": 6.04227698474675e-05,
1590
+ "loss": 0.5853,
1591
+ "step": 226
1592
+ },
1593
+ {
1594
+ "epoch": 1.9809160305343512,
1595
+ "grad_norm": 0.21674772391599217,
1596
+ "learning_rate": 6.02117639225724e-05,
1597
+ "loss": 0.6078,
1598
+ "step": 227
1599
+ },
1600
+ {
1601
+ "epoch": 1.9896401308615048,
1602
+ "grad_norm": 0.2934361150620414,
1603
+ "learning_rate": 6.000000000000001e-05,
1604
+ "loss": 0.5984,
1605
+ "step": 228
1606
+ },
1607
+ {
1608
+ "epoch": 1.9983642311886587,
1609
+ "grad_norm": 0.44422300505199064,
1610
+ "learning_rate": 5.9787486021489705e-05,
1611
+ "loss": 0.8056,
1612
+ "step": 229
1613
+ },
1614
+ {
1615
+ "epoch": 2.0076335877862594,
1616
+ "grad_norm": 0.5875332032837016,
1617
+ "learning_rate": 5.957422995691007e-05,
1618
+ "loss": 0.6104,
1619
+ "step": 230
1620
+ },
1621
+ {
1622
+ "epoch": 2.016357688113413,
1623
+ "grad_norm": 0.7504197536874134,
1624
+ "learning_rate": 5.936023980395997e-05,
1625
+ "loss": 0.5445,
1626
+ "step": 231
1627
+ },
1628
+ {
1629
+ "epoch": 2.025081788440567,
1630
+ "grad_norm": 1.1182174595326815,
1631
+ "learning_rate": 5.914552358786864e-05,
1632
+ "loss": 0.5436,
1633
+ "step": 232
1634
+ },
1635
+ {
1636
+ "epoch": 2.033805888767721,
1637
+ "grad_norm": 0.9253408273401474,
1638
+ "learning_rate": 5.893008936109474e-05,
1639
+ "loss": 0.5517,
1640
+ "step": 233
1641
+ },
1642
+ {
1643
+ "epoch": 2.0425299890948745,
1644
+ "grad_norm": 0.6241397091570694,
1645
+ "learning_rate": 5.871394520302432e-05,
1646
+ "loss": 0.5436,
1647
+ "step": 234
1648
+ },
1649
+ {
1650
+ "epoch": 2.051254089422028,
1651
+ "grad_norm": 0.6714967761660577,
1652
+ "learning_rate": 5.8497099219667834e-05,
1653
+ "loss": 0.5513,
1654
+ "step": 235
1655
+ },
1656
+ {
1657
+ "epoch": 2.0599781897491822,
1658
+ "grad_norm": 0.6546289177103435,
1659
+ "learning_rate": 5.827955954335616e-05,
1660
+ "loss": 0.5365,
1661
+ "step": 236
1662
+ },
1663
+ {
1664
+ "epoch": 2.068702290076336,
1665
+ "grad_norm": 0.6213690775351733,
1666
+ "learning_rate": 5.806133433243558e-05,
1667
+ "loss": 0.546,
1668
+ "step": 237
1669
+ },
1670
+ {
1671
+ "epoch": 2.0774263904034895,
1672
+ "grad_norm": 0.6920575535177348,
1673
+ "learning_rate": 5.784243177096187e-05,
1674
+ "loss": 0.5433,
1675
+ "step": 238
1676
+ },
1677
+ {
1678
+ "epoch": 2.0861504907306436,
1679
+ "grad_norm": 0.4645752707045055,
1680
+ "learning_rate": 5.7622860068393334e-05,
1681
+ "loss": 0.5289,
1682
+ "step": 239
1683
+ },
1684
+ {
1685
+ "epoch": 2.0948745910577973,
1686
+ "grad_norm": 0.4731711629332615,
1687
+ "learning_rate": 5.740262745928293e-05,
1688
+ "loss": 0.5448,
1689
+ "step": 240
1690
+ },
1691
+ {
1692
+ "epoch": 2.103598691384951,
1693
+ "grad_norm": 0.5087479759223862,
1694
+ "learning_rate": 5.718174220296949e-05,
1695
+ "loss": 0.5415,
1696
+ "step": 241
1697
+ },
1698
+ {
1699
+ "epoch": 2.1123227917121046,
1700
+ "grad_norm": 0.3397004171608698,
1701
+ "learning_rate": 5.6960212583267873e-05,
1702
+ "loss": 0.5373,
1703
+ "step": 242
1704
+ },
1705
+ {
1706
+ "epoch": 2.1210468920392582,
1707
+ "grad_norm": 0.3028591738754104,
1708
+ "learning_rate": 5.673804690815845e-05,
1709
+ "loss": 0.5393,
1710
+ "step": 243
1711
+ },
1712
+ {
1713
+ "epoch": 2.1297709923664123,
1714
+ "grad_norm": 0.4035449728515965,
1715
+ "learning_rate": 5.6515253509475405e-05,
1716
+ "loss": 0.5351,
1717
+ "step": 244
1718
+ },
1719
+ {
1720
+ "epoch": 2.138495092693566,
1721
+ "grad_norm": 0.3353749295009557,
1722
+ "learning_rate": 5.6291840742594305e-05,
1723
+ "loss": 0.5365,
1724
+ "step": 245
1725
+ },
1726
+ {
1727
+ "epoch": 2.1472191930207196,
1728
+ "grad_norm": 0.2948957119809547,
1729
+ "learning_rate": 5.606781698611879e-05,
1730
+ "loss": 0.5367,
1731
+ "step": 246
1732
+ },
1733
+ {
1734
+ "epoch": 2.1559432933478737,
1735
+ "grad_norm": 0.3274847500759932,
1736
+ "learning_rate": 5.584319064156628e-05,
1737
+ "loss": 0.5343,
1738
+ "step": 247
1739
+ },
1740
+ {
1741
+ "epoch": 2.1646673936750274,
1742
+ "grad_norm": 0.27942787362736154,
1743
+ "learning_rate": 5.561797013305297e-05,
1744
+ "loss": 0.5355,
1745
+ "step": 248
1746
+ },
1747
+ {
1748
+ "epoch": 2.173391494002181,
1749
+ "grad_norm": 0.3320815797761542,
1750
+ "learning_rate": 5.5392163906977835e-05,
1751
+ "loss": 0.5324,
1752
+ "step": 249
1753
+ },
1754
+ {
1755
+ "epoch": 2.1821155943293347,
1756
+ "grad_norm": 0.2793266605014413,
1757
+ "learning_rate": 5.516578043170591e-05,
1758
+ "loss": 0.5333,
1759
+ "step": 250
1760
+ },
1761
+ {
1762
+ "epoch": 2.1908396946564888,
1763
+ "grad_norm": 0.24153435404173842,
1764
+ "learning_rate": 5.49388281972507e-05,
1765
+ "loss": 0.5403,
1766
+ "step": 251
1767
+ },
1768
+ {
1769
+ "epoch": 2.1995637949836424,
1770
+ "grad_norm": 0.29337585767480123,
1771
+ "learning_rate": 5.471131571495574e-05,
1772
+ "loss": 0.5479,
1773
+ "step": 252
1774
+ },
1775
+ {
1776
+ "epoch": 2.208287895310796,
1777
+ "grad_norm": 0.3065886341708783,
1778
+ "learning_rate": 5.4483251517175454e-05,
1779
+ "loss": 0.5274,
1780
+ "step": 253
1781
+ },
1782
+ {
1783
+ "epoch": 2.2170119956379497,
1784
+ "grad_norm": 0.2885822613470245,
1785
+ "learning_rate": 5.425464415695514e-05,
1786
+ "loss": 0.5431,
1787
+ "step": 254
1788
+ },
1789
+ {
1790
+ "epoch": 2.225736095965104,
1791
+ "grad_norm": 0.2588491126601207,
1792
+ "learning_rate": 5.4025502207710184e-05,
1793
+ "loss": 0.5336,
1794
+ "step": 255
1795
+ },
1796
+ {
1797
+ "epoch": 2.2344601962922575,
1798
+ "grad_norm": 0.26723660749591893,
1799
+ "learning_rate": 5.379583426290458e-05,
1800
+ "loss": 0.5338,
1801
+ "step": 256
1802
+ },
1803
+ {
1804
+ "epoch": 2.243184296619411,
1805
+ "grad_norm": 0.3305889777035953,
1806
+ "learning_rate": 5.356564893572859e-05,
1807
+ "loss": 0.5393,
1808
+ "step": 257
1809
+ },
1810
+ {
1811
+ "epoch": 2.2519083969465647,
1812
+ "grad_norm": 0.22453022727431107,
1813
+ "learning_rate": 5.333495485877583e-05,
1814
+ "loss": 0.5485,
1815
+ "step": 258
1816
+ },
1817
+ {
1818
+ "epoch": 2.2606324972737184,
1819
+ "grad_norm": 0.19233156617492056,
1820
+ "learning_rate": 5.310376068371938e-05,
1821
+ "loss": 0.5418,
1822
+ "step": 259
1823
+ },
1824
+ {
1825
+ "epoch": 2.2693565976008725,
1826
+ "grad_norm": 0.20527709672078884,
1827
+ "learning_rate": 5.287207508098743e-05,
1828
+ "loss": 0.5416,
1829
+ "step": 260
1830
+ },
1831
+ {
1832
+ "epoch": 2.278080697928026,
1833
+ "grad_norm": 0.2376527665778272,
1834
+ "learning_rate": 5.263990673943811e-05,
1835
+ "loss": 0.54,
1836
+ "step": 261
1837
+ },
1838
+ {
1839
+ "epoch": 2.28680479825518,
1840
+ "grad_norm": 0.2613858051995676,
1841
+ "learning_rate": 5.2407264366033555e-05,
1842
+ "loss": 0.5498,
1843
+ "step": 262
1844
+ },
1845
+ {
1846
+ "epoch": 2.295528898582334,
1847
+ "grad_norm": 0.18916730210716454,
1848
+ "learning_rate": 5.2174156685513446e-05,
1849
+ "loss": 0.5364,
1850
+ "step": 263
1851
+ },
1852
+ {
1853
+ "epoch": 2.3042529989094875,
1854
+ "grad_norm": 0.19275577825236526,
1855
+ "learning_rate": 5.194059244006779e-05,
1856
+ "loss": 0.5434,
1857
+ "step": 264
1858
+ },
1859
+ {
1860
+ "epoch": 2.312977099236641,
1861
+ "grad_norm": 0.2384097782515164,
1862
+ "learning_rate": 5.170658038900904e-05,
1863
+ "loss": 0.5353,
1864
+ "step": 265
1865
+ },
1866
+ {
1867
+ "epoch": 2.321701199563795,
1868
+ "grad_norm": 0.21432203996579718,
1869
+ "learning_rate": 5.1472129308443616e-05,
1870
+ "loss": 0.537,
1871
+ "step": 266
1872
+ },
1873
+ {
1874
+ "epoch": 2.330425299890949,
1875
+ "grad_norm": 0.17783572065614472,
1876
+ "learning_rate": 5.123724799094279e-05,
1877
+ "loss": 0.5444,
1878
+ "step": 267
1879
+ },
1880
+ {
1881
+ "epoch": 2.3391494002181026,
1882
+ "grad_norm": 0.24973497434785122,
1883
+ "learning_rate": 5.1001945245212874e-05,
1884
+ "loss": 0.5404,
1885
+ "step": 268
1886
+ },
1887
+ {
1888
+ "epoch": 2.3478735005452562,
1889
+ "grad_norm": 0.2176404792941727,
1890
+ "learning_rate": 5.076622989576498e-05,
1891
+ "loss": 0.5376,
1892
+ "step": 269
1893
+ },
1894
+ {
1895
+ "epoch": 2.35659760087241,
1896
+ "grad_norm": 0.2460399652714288,
1897
+ "learning_rate": 5.053011078258397e-05,
1898
+ "loss": 0.5412,
1899
+ "step": 270
1900
+ },
1901
+ {
1902
+ "epoch": 2.365321701199564,
1903
+ "grad_norm": 0.1827234799837285,
1904
+ "learning_rate": 5.0293596760797e-05,
1905
+ "loss": 0.5394,
1906
+ "step": 271
1907
+ },
1908
+ {
1909
+ "epoch": 2.3740458015267176,
1910
+ "grad_norm": 0.21898045121125942,
1911
+ "learning_rate": 5.005669670034138e-05,
1912
+ "loss": 0.5417,
1913
+ "step": 272
1914
+ },
1915
+ {
1916
+ "epoch": 2.3827699018538713,
1917
+ "grad_norm": 0.24065391523216037,
1918
+ "learning_rate": 4.981941948563197e-05,
1919
+ "loss": 0.5425,
1920
+ "step": 273
1921
+ },
1922
+ {
1923
+ "epoch": 2.391494002181025,
1924
+ "grad_norm": 0.19964448205882962,
1925
+ "learning_rate": 4.958177401522796e-05,
1926
+ "loss": 0.5383,
1927
+ "step": 274
1928
+ },
1929
+ {
1930
+ "epoch": 2.400218102508179,
1931
+ "grad_norm": 0.2287719342097617,
1932
+ "learning_rate": 4.934376920149915e-05,
1933
+ "loss": 0.5424,
1934
+ "step": 275
1935
+ },
1936
+ {
1937
+ "epoch": 2.4089422028353327,
1938
+ "grad_norm": 0.15994920899181853,
1939
+ "learning_rate": 4.9105413970291747e-05,
1940
+ "loss": 0.5492,
1941
+ "step": 276
1942
+ },
1943
+ {
1944
+ "epoch": 2.4176663031624863,
1945
+ "grad_norm": 0.20177344996011212,
1946
+ "learning_rate": 4.886671726059355e-05,
1947
+ "loss": 0.5452,
1948
+ "step": 277
1949
+ },
1950
+ {
1951
+ "epoch": 2.42639040348964,
1952
+ "grad_norm": 0.2505950233818444,
1953
+ "learning_rate": 4.862768802419881e-05,
1954
+ "loss": 0.5355,
1955
+ "step": 278
1956
+ },
1957
+ {
1958
+ "epoch": 2.435114503816794,
1959
+ "grad_norm": 0.20877969786025213,
1960
+ "learning_rate": 4.8388335225372416e-05,
1961
+ "loss": 0.5312,
1962
+ "step": 279
1963
+ },
1964
+ {
1965
+ "epoch": 2.4438386041439477,
1966
+ "grad_norm": 0.16740200168268377,
1967
+ "learning_rate": 4.8148667840513773e-05,
1968
+ "loss": 0.536,
1969
+ "step": 280
1970
+ },
1971
+ {
1972
+ "epoch": 2.4525627044711014,
1973
+ "grad_norm": 0.1624204063771831,
1974
+ "learning_rate": 4.790869485782014e-05,
1975
+ "loss": 0.5411,
1976
+ "step": 281
1977
+ },
1978
+ {
1979
+ "epoch": 2.461286804798255,
1980
+ "grad_norm": 0.17548255884293712,
1981
+ "learning_rate": 4.7668425276949546e-05,
1982
+ "loss": 0.5377,
1983
+ "step": 282
1984
+ },
1985
+ {
1986
+ "epoch": 2.470010905125409,
1987
+ "grad_norm": 0.24425295770194558,
1988
+ "learning_rate": 4.742786810868327e-05,
1989
+ "loss": 0.5424,
1990
+ "step": 283
1991
+ },
1992
+ {
1993
+ "epoch": 2.4787350054525628,
1994
+ "grad_norm": 0.2279410111439652,
1995
+ "learning_rate": 4.7187032374587956e-05,
1996
+ "loss": 0.5408,
1997
+ "step": 284
1998
+ },
1999
+ {
2000
+ "epoch": 2.4874591057797164,
2001
+ "grad_norm": 0.18333960694349968,
2002
+ "learning_rate": 4.694592710667723e-05,
2003
+ "loss": 0.5387,
2004
+ "step": 285
2005
+ },
2006
+ {
2007
+ "epoch": 2.49618320610687,
2008
+ "grad_norm": 0.17387901999937752,
2009
+ "learning_rate": 4.670456134707294e-05,
2010
+ "loss": 0.5412,
2011
+ "step": 286
2012
+ },
2013
+ {
2014
+ "epoch": 2.504907306434024,
2015
+ "grad_norm": 0.1802799576438455,
2016
+ "learning_rate": 4.64629441476662e-05,
2017
+ "loss": 0.5358,
2018
+ "step": 287
2019
+ },
2020
+ {
2021
+ "epoch": 2.513631406761178,
2022
+ "grad_norm": 0.174702677057685,
2023
+ "learning_rate": 4.622108456977773e-05,
2024
+ "loss": 0.536,
2025
+ "step": 288
2026
+ },
2027
+ {
2028
+ "epoch": 2.5223555070883314,
2029
+ "grad_norm": 0.14211263717330275,
2030
+ "learning_rate": 4.597899168381818e-05,
2031
+ "loss": 0.5441,
2032
+ "step": 289
2033
+ },
2034
+ {
2035
+ "epoch": 2.531079607415485,
2036
+ "grad_norm": 0.1774683759788631,
2037
+ "learning_rate": 4.573667456894786e-05,
2038
+ "loss": 0.5349,
2039
+ "step": 290
2040
+ },
2041
+ {
2042
+ "epoch": 2.539803707742639,
2043
+ "grad_norm": 0.1951727957490502,
2044
+ "learning_rate": 4.549414231273633e-05,
2045
+ "loss": 0.5428,
2046
+ "step": 291
2047
+ },
2048
+ {
2049
+ "epoch": 2.548527808069793,
2050
+ "grad_norm": 0.16687560601341936,
2051
+ "learning_rate": 4.525140401082153e-05,
2052
+ "loss": 0.535,
2053
+ "step": 292
2054
+ },
2055
+ {
2056
+ "epoch": 2.5572519083969465,
2057
+ "grad_norm": 0.15616561471578494,
2058
+ "learning_rate": 4.50084687665687e-05,
2059
+ "loss": 0.5475,
2060
+ "step": 293
2061
+ },
2062
+ {
2063
+ "epoch": 2.5659760087241006,
2064
+ "grad_norm": 0.15824726116167803,
2065
+ "learning_rate": 4.476534569072895e-05,
2066
+ "loss": 0.5473,
2067
+ "step": 294
2068
+ },
2069
+ {
2070
+ "epoch": 2.5747001090512542,
2071
+ "grad_norm": 0.22356058463377537,
2072
+ "learning_rate": 4.452204390109763e-05,
2073
+ "loss": 0.5345,
2074
+ "step": 295
2075
+ },
2076
+ {
2077
+ "epoch": 2.583424209378408,
2078
+ "grad_norm": 0.21936785429021016,
2079
+ "learning_rate": 4.4278572522172336e-05,
2080
+ "loss": 0.5379,
2081
+ "step": 296
2082
+ },
2083
+ {
2084
+ "epoch": 2.5921483097055615,
2085
+ "grad_norm": 0.15224856301200368,
2086
+ "learning_rate": 4.403494068481074e-05,
2087
+ "loss": 0.5409,
2088
+ "step": 297
2089
+ },
2090
+ {
2091
+ "epoch": 2.600872410032715,
2092
+ "grad_norm": 0.19196426118514048,
2093
+ "learning_rate": 4.379115752588814e-05,
2094
+ "loss": 0.5531,
2095
+ "step": 298
2096
+ },
2097
+ {
2098
+ "epoch": 2.6095965103598693,
2099
+ "grad_norm": 0.21896927123986717,
2100
+ "learning_rate": 4.3547232187954866e-05,
2101
+ "loss": 0.5437,
2102
+ "step": 299
2103
+ },
2104
+ {
2105
+ "epoch": 2.618320610687023,
2106
+ "grad_norm": 0.187029673883834,
2107
+ "learning_rate": 4.33031738188933e-05,
2108
+ "loss": 0.5381,
2109
+ "step": 300
2110
+ },
2111
+ {
2112
+ "epoch": 2.6270447110141766,
2113
+ "grad_norm": 0.1542884550374639,
2114
+ "learning_rate": 4.3058991571574896e-05,
2115
+ "loss": 0.5421,
2116
+ "step": 301
2117
+ },
2118
+ {
2119
+ "epoch": 2.6357688113413307,
2120
+ "grad_norm": 0.2086016114061771,
2121
+ "learning_rate": 4.2814694603516876e-05,
2122
+ "loss": 0.5492,
2123
+ "step": 302
2124
+ },
2125
+ {
2126
+ "epoch": 2.6444929116684843,
2127
+ "grad_norm": 0.19799737279991564,
2128
+ "learning_rate": 4.257029207653881e-05,
2129
+ "loss": 0.5372,
2130
+ "step": 303
2131
+ },
2132
+ {
2133
+ "epoch": 2.653217011995638,
2134
+ "grad_norm": 0.16486499555492864,
2135
+ "learning_rate": 4.2325793156419035e-05,
2136
+ "loss": 0.5468,
2137
+ "step": 304
2138
+ },
2139
+ {
2140
+ "epoch": 2.6619411123227916,
2141
+ "grad_norm": 0.21172626026429878,
2142
+ "learning_rate": 4.20812070125509e-05,
2143
+ "loss": 0.5396,
2144
+ "step": 305
2145
+ },
2146
+ {
2147
+ "epoch": 2.6706652126499453,
2148
+ "grad_norm": 0.2470196212926822,
2149
+ "learning_rate": 4.183654281759888e-05,
2150
+ "loss": 0.5454,
2151
+ "step": 306
2152
+ },
2153
+ {
2154
+ "epoch": 2.6793893129770994,
2155
+ "grad_norm": 0.22097827298910216,
2156
+ "learning_rate": 4.159180974715457e-05,
2157
+ "loss": 0.5401,
2158
+ "step": 307
2159
+ },
2160
+ {
2161
+ "epoch": 2.688113413304253,
2162
+ "grad_norm": 0.15719194953902701,
2163
+ "learning_rate": 4.1347016979392626e-05,
2164
+ "loss": 0.5351,
2165
+ "step": 308
2166
+ },
2167
+ {
2168
+ "epoch": 2.6968375136314067,
2169
+ "grad_norm": 0.15729742427040297,
2170
+ "learning_rate": 4.110217369472649e-05,
2171
+ "loss": 0.5295,
2172
+ "step": 309
2173
+ },
2174
+ {
2175
+ "epoch": 2.7055616139585608,
2176
+ "grad_norm": 0.14739912075610104,
2177
+ "learning_rate": 4.085728907546413e-05,
2178
+ "loss": 0.5408,
2179
+ "step": 310
2180
+ },
2181
+ {
2182
+ "epoch": 2.7142857142857144,
2183
+ "grad_norm": 0.14793685021802994,
2184
+ "learning_rate": 4.061237230546369e-05,
2185
+ "loss": 0.5428,
2186
+ "step": 311
2187
+ },
2188
+ {
2189
+ "epoch": 2.723009814612868,
2190
+ "grad_norm": 0.16234675353976102,
2191
+ "learning_rate": 4.0367432569789065e-05,
2192
+ "loss": 0.5362,
2193
+ "step": 312
2194
+ },
2195
+ {
2196
+ "epoch": 2.7317339149400217,
2197
+ "grad_norm": 0.14302498512172665,
2198
+ "learning_rate": 4.012247905436539e-05,
2199
+ "loss": 0.5412,
2200
+ "step": 313
2201
+ },
2202
+ {
2203
+ "epoch": 2.7404580152671754,
2204
+ "grad_norm": 0.14016241879849234,
2205
+ "learning_rate": 3.987752094563462e-05,
2206
+ "loss": 0.5396,
2207
+ "step": 314
2208
+ },
2209
+ {
2210
+ "epoch": 2.7491821155943295,
2211
+ "grad_norm": 0.15182946842699183,
2212
+ "learning_rate": 3.963256743021095e-05,
2213
+ "loss": 0.54,
2214
+ "step": 315
2215
+ },
2216
+ {
2217
+ "epoch": 2.757906215921483,
2218
+ "grad_norm": 0.14224077108756453,
2219
+ "learning_rate": 3.9387627694536316e-05,
2220
+ "loss": 0.541,
2221
+ "step": 316
2222
+ },
2223
+ {
2224
+ "epoch": 2.7666303162486368,
2225
+ "grad_norm": 0.15804186928200673,
2226
+ "learning_rate": 3.914271092453589e-05,
2227
+ "loss": 0.5436,
2228
+ "step": 317
2229
+ },
2230
+ {
2231
+ "epoch": 2.775354416575791,
2232
+ "grad_norm": 0.18867349297613747,
2233
+ "learning_rate": 3.889782630527353e-05,
2234
+ "loss": 0.5303,
2235
+ "step": 318
2236
+ },
2237
+ {
2238
+ "epoch": 2.7840785169029445,
2239
+ "grad_norm": 0.14326765308764183,
2240
+ "learning_rate": 3.865298302060739e-05,
2241
+ "loss": 0.5306,
2242
+ "step": 319
2243
+ },
2244
+ {
2245
+ "epoch": 2.792802617230098,
2246
+ "grad_norm": 0.2074238009547974,
2247
+ "learning_rate": 3.8408190252845435e-05,
2248
+ "loss": 0.5372,
2249
+ "step": 320
2250
+ },
2251
+ {
2252
+ "epoch": 2.801526717557252,
2253
+ "grad_norm": 0.14034785022531543,
2254
+ "learning_rate": 3.816345718240113e-05,
2255
+ "loss": 0.5403,
2256
+ "step": 321
2257
+ },
2258
+ {
2259
+ "epoch": 2.8102508178844054,
2260
+ "grad_norm": 0.15821673087787588,
2261
+ "learning_rate": 3.791879298744911e-05,
2262
+ "loss": 0.5321,
2263
+ "step": 322
2264
+ },
2265
+ {
2266
+ "epoch": 2.8189749182115595,
2267
+ "grad_norm": 0.14024264925437085,
2268
+ "learning_rate": 3.767420684358097e-05,
2269
+ "loss": 0.5509,
2270
+ "step": 323
2271
+ },
2272
+ {
2273
+ "epoch": 2.827699018538713,
2274
+ "grad_norm": 0.14817524358908055,
2275
+ "learning_rate": 3.74297079234612e-05,
2276
+ "loss": 0.5414,
2277
+ "step": 324
2278
+ },
2279
+ {
2280
+ "epoch": 2.836423118865867,
2281
+ "grad_norm": 0.1618059561441321,
2282
+ "learning_rate": 3.7185305396483144e-05,
2283
+ "loss": 0.5435,
2284
+ "step": 325
2285
+ },
2286
+ {
2287
+ "epoch": 2.845147219193021,
2288
+ "grad_norm": 0.1463097964083179,
2289
+ "learning_rate": 3.694100842842512e-05,
2290
+ "loss": 0.5415,
2291
+ "step": 326
2292
+ },
2293
+ {
2294
+ "epoch": 2.8538713195201746,
2295
+ "grad_norm": 0.19816090369688377,
2296
+ "learning_rate": 3.669682618110671e-05,
2297
+ "loss": 0.5289,
2298
+ "step": 327
2299
+ },
2300
+ {
2301
+ "epoch": 2.8625954198473282,
2302
+ "grad_norm": 0.13008063298224137,
2303
+ "learning_rate": 3.645276781204515e-05,
2304
+ "loss": 0.5409,
2305
+ "step": 328
2306
+ },
2307
+ {
2308
+ "epoch": 2.871319520174482,
2309
+ "grad_norm": 0.19611647889519343,
2310
+ "learning_rate": 3.6208842474111865e-05,
2311
+ "loss": 0.5318,
2312
+ "step": 329
2313
+ },
2314
+ {
2315
+ "epoch": 2.8800436205016355,
2316
+ "grad_norm": 0.16795674711289083,
2317
+ "learning_rate": 3.5965059315189274e-05,
2318
+ "loss": 0.5402,
2319
+ "step": 330
2320
+ },
2321
+ {
2322
+ "epoch": 2.8887677208287896,
2323
+ "grad_norm": 0.15014005665113414,
2324
+ "learning_rate": 3.572142747782768e-05,
2325
+ "loss": 0.5358,
2326
+ "step": 331
2327
+ },
2328
+ {
2329
+ "epoch": 2.8974918211559433,
2330
+ "grad_norm": 0.17800420417158852,
2331
+ "learning_rate": 3.547795609890238e-05,
2332
+ "loss": 0.5434,
2333
+ "step": 332
2334
+ },
2335
+ {
2336
+ "epoch": 2.906215921483097,
2337
+ "grad_norm": 0.15795311662461162,
2338
+ "learning_rate": 3.523465430927106e-05,
2339
+ "loss": 0.5391,
2340
+ "step": 333
2341
+ },
2342
+ {
2343
+ "epoch": 2.914940021810251,
2344
+ "grad_norm": 0.12743060334259004,
2345
+ "learning_rate": 3.499153123343131e-05,
2346
+ "loss": 0.5325,
2347
+ "step": 334
2348
+ },
2349
+ {
2350
+ "epoch": 2.9236641221374047,
2351
+ "grad_norm": 0.16855028063385719,
2352
+ "learning_rate": 3.474859598917849e-05,
2353
+ "loss": 0.5413,
2354
+ "step": 335
2355
+ },
2356
+ {
2357
+ "epoch": 2.9323882224645583,
2358
+ "grad_norm": 0.13048706187884607,
2359
+ "learning_rate": 3.4505857687263675e-05,
2360
+ "loss": 0.5424,
2361
+ "step": 336
2362
+ },
2363
+ {
2364
+ "epoch": 2.941112322791712,
2365
+ "grad_norm": 0.19367317061005948,
2366
+ "learning_rate": 3.4263325431052156e-05,
2367
+ "loss": 0.5432,
2368
+ "step": 337
2369
+ },
2370
+ {
2371
+ "epoch": 2.9498364231188656,
2372
+ "grad_norm": 0.12027268336619701,
2373
+ "learning_rate": 3.4021008316181834e-05,
2374
+ "loss": 0.5454,
2375
+ "step": 338
2376
+ },
2377
+ {
2378
+ "epoch": 2.9585605234460197,
2379
+ "grad_norm": 0.15147251810786375,
2380
+ "learning_rate": 3.377891543022229e-05,
2381
+ "loss": 0.5319,
2382
+ "step": 339
2383
+ },
2384
+ {
2385
+ "epoch": 2.9672846237731734,
2386
+ "grad_norm": 0.12811996405452336,
2387
+ "learning_rate": 3.353705585233381e-05,
2388
+ "loss": 0.544,
2389
+ "step": 340
2390
+ },
2391
+ {
2392
+ "epoch": 2.976008724100327,
2393
+ "grad_norm": 0.13491661704715102,
2394
+ "learning_rate": 3.329543865292707e-05,
2395
+ "loss": 0.5435,
2396
+ "step": 341
2397
+ },
2398
+ {
2399
+ "epoch": 2.984732824427481,
2400
+ "grad_norm": 0.15940079876011493,
2401
+ "learning_rate": 3.305407289332279e-05,
2402
+ "loss": 0.5321,
2403
+ "step": 342
2404
+ },
2405
+ {
2406
+ "epoch": 2.9934569247546348,
2407
+ "grad_norm": 0.13416535357448142,
2408
+ "learning_rate": 3.281296762541206e-05,
2409
+ "loss": 0.5555,
2410
+ "step": 343
2411
+ }
2412
+ ],
2413
+ "logging_steps": 1,
2414
+ "max_steps": 570,
2415
+ "num_input_tokens_seen": 0,
2416
+ "num_train_epochs": 5,
2417
+ "save_steps": 500,
2418
+ "stateful_callbacks": {
2419
+ "TrainerControl": {
2420
+ "args": {
2421
+ "should_epoch_stop": false,
2422
+ "should_evaluate": false,
2423
+ "should_log": false,
2424
+ "should_save": true,
2425
+ "should_training_stop": false
2426
+ },
2427
+ "attributes": {}
2428
+ }
2429
+ },
2430
+ "total_flos": 9.139303179152785e+18,
2431
+ "train_batch_size": 1,
2432
+ "trial_name": null,
2433
+ "trial_params": null
2434
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:435b09d536053faffd96cb71bfccc53874c5a49ebd38424d88f6d32884215557
3
+ size 7288
vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
zero_to_fp32.py ADDED
@@ -0,0 +1,674 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #!/usr/bin/env python
2
+
3
+ # Copyright (c) Microsoft Corporation.
4
+ # SPDX-License-Identifier: Apache-2.0
5
+
6
+ # DeepSpeed Team
7
+
8
+ # This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
9
+ # copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
10
+ # the future. Once extracted, the weights don't require DeepSpeed and can be used in any
11
+ # application.
12
+ #
13
+ # example:
14
+ # python zero_to_fp32.py . output_dir/
15
+ # or
16
+ # python zero_to_fp32.py . output_dir/ --safe_serialization
17
+
18
+ import argparse
19
+ import torch
20
+ import glob
21
+ import math
22
+ import os
23
+ import re
24
+ import json
25
+ from tqdm import tqdm
26
+ from collections import OrderedDict
27
+ from dataclasses import dataclass
28
+
29
+ # while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
30
+ # DeepSpeed data structures it has to be available in the current python environment.
31
+ from deepspeed.utils import logger
32
+ from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
33
+ FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
34
+ FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
35
+
36
+
37
+ @dataclass
38
+ class zero_model_state:
39
+ buffers: dict()
40
+ param_shapes: dict()
41
+ shared_params: list
42
+ ds_version: int
43
+ frozen_param_shapes: dict()
44
+ frozen_param_fragments: dict()
45
+
46
+
47
+ debug = 0
48
+
49
+ # load to cpu
50
+ device = torch.device('cpu')
51
+
52
+
53
+ def atoi(text):
54
+ return int(text) if text.isdigit() else text
55
+
56
+
57
+ def natural_keys(text):
58
+ '''
59
+ alist.sort(key=natural_keys) sorts in human order
60
+ http://nedbatchelder.com/blog/200712/human_sorting.html
61
+ (See Toothy's implementation in the comments)
62
+ '''
63
+ return [atoi(c) for c in re.split(r'(\d+)', text)]
64
+
65
+
66
+ def get_model_state_file(checkpoint_dir, zero_stage):
67
+ if not os.path.isdir(checkpoint_dir):
68
+ raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
69
+
70
+ # there should be only one file
71
+ if zero_stage <= 2:
72
+ file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
73
+ elif zero_stage == 3:
74
+ file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
75
+
76
+ if not os.path.exists(file):
77
+ raise FileNotFoundError(f"can't find model states file at '{file}'")
78
+
79
+ return file
80
+
81
+
82
+ def get_checkpoint_files(checkpoint_dir, glob_pattern):
83
+ # XXX: need to test that this simple glob rule works for multi-node setup too
84
+ ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
85
+
86
+ if len(ckpt_files) == 0:
87
+ raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
88
+
89
+ return ckpt_files
90
+
91
+
92
+ def get_optim_files(checkpoint_dir):
93
+ return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
94
+
95
+
96
+ def get_model_state_files(checkpoint_dir):
97
+ return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
98
+
99
+
100
+ def parse_model_states(files):
101
+ zero_model_states = []
102
+ for file in files:
103
+ state_dict = torch.load(file, map_location=device)
104
+
105
+ if BUFFER_NAMES not in state_dict:
106
+ raise ValueError(f"{file} is not a model state checkpoint")
107
+ buffer_names = state_dict[BUFFER_NAMES]
108
+ if debug:
109
+ print("Found buffers:", buffer_names)
110
+
111
+ # recover just the buffers while restoring them to fp32 if they were saved in fp16
112
+ buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
113
+ param_shapes = state_dict[PARAM_SHAPES]
114
+
115
+ # collect parameters that are included in param_shapes
116
+ param_names = []
117
+ for s in param_shapes:
118
+ for name in s.keys():
119
+ param_names.append(name)
120
+
121
+ # update with frozen parameters
122
+ frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
123
+ if frozen_param_shapes is not None:
124
+ if debug:
125
+ print(f"Found frozen_param_shapes: {frozen_param_shapes}")
126
+ param_names += list(frozen_param_shapes.keys())
127
+
128
+ # handle shared params
129
+ shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
130
+
131
+ ds_version = state_dict.get(DS_VERSION, None)
132
+
133
+ frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
134
+
135
+ z_model_state = zero_model_state(buffers=buffers,
136
+ param_shapes=param_shapes,
137
+ shared_params=shared_params,
138
+ ds_version=ds_version,
139
+ frozen_param_shapes=frozen_param_shapes,
140
+ frozen_param_fragments=frozen_param_fragments)
141
+ zero_model_states.append(z_model_state)
142
+
143
+ return zero_model_states
144
+
145
+
146
+ def parse_optim_states(files, ds_checkpoint_dir):
147
+ total_files = len(files)
148
+ state_dicts = []
149
+ for f in files:
150
+ state_dict = torch.load(f, map_location=device)
151
+ # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
152
+ # and also handle the case where it was already removed by another helper script
153
+ state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
154
+ state_dicts.append(state_dict)
155
+
156
+ if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
157
+ raise ValueError(f"{files[0]} is not a zero checkpoint")
158
+ zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
159
+ world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
160
+
161
+ # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
162
+ # parameters can be different from data parallelism for non-expert parameters. So we can just
163
+ # use the max of the partition_count to get the dp world_size.
164
+
165
+ if type(world_size) is list:
166
+ world_size = max(world_size)
167
+
168
+ if world_size != total_files:
169
+ raise ValueError(
170
+ f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
171
+ "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
172
+ )
173
+
174
+ # the groups are named differently in each stage
175
+ if zero_stage <= 2:
176
+ fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
177
+ elif zero_stage == 3:
178
+ fp32_groups_key = FP32_FLAT_GROUPS
179
+ else:
180
+ raise ValueError(f"unknown zero stage {zero_stage}")
181
+
182
+ if zero_stage <= 2:
183
+ fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
184
+ elif zero_stage == 3:
185
+ # if there is more than one param group, there will be multiple flattened tensors - one
186
+ # flattened tensor per group - for simplicity merge them into a single tensor
187
+ #
188
+ # XXX: could make the script more memory efficient for when there are multiple groups - it
189
+ # will require matching the sub-lists of param_shapes for each param group flattened tensor
190
+
191
+ fp32_flat_groups = [
192
+ torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
193
+ ]
194
+
195
+ return zero_stage, world_size, fp32_flat_groups
196
+
197
+
198
+ def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
199
+ """
200
+ Returns fp32 state_dict reconstructed from ds checkpoint
201
+
202
+ Args:
203
+ - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
204
+
205
+ """
206
+ print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
207
+
208
+ optim_files = get_optim_files(ds_checkpoint_dir)
209
+ zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
210
+ print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
211
+
212
+ model_files = get_model_state_files(ds_checkpoint_dir)
213
+
214
+ zero_model_states = parse_model_states(model_files)
215
+ print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
216
+
217
+ if zero_stage <= 2:
218
+ return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
219
+ exclude_frozen_parameters)
220
+ elif zero_stage == 3:
221
+ return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
222
+ exclude_frozen_parameters)
223
+
224
+
225
+ def _zero2_merge_frozen_params(state_dict, zero_model_states):
226
+ if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
227
+ return
228
+
229
+ frozen_param_shapes = zero_model_states[0].frozen_param_shapes
230
+ frozen_param_fragments = zero_model_states[0].frozen_param_fragments
231
+
232
+ if debug:
233
+ num_elem = sum(s.numel() for s in frozen_param_shapes.values())
234
+ print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
235
+
236
+ wanted_params = len(frozen_param_shapes)
237
+ wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
238
+ avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
239
+ print(f'Frozen params: Have {avail_numel} numels to process.')
240
+ print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
241
+
242
+ total_params = 0
243
+ total_numel = 0
244
+ for name, shape in frozen_param_shapes.items():
245
+ total_params += 1
246
+ unpartitioned_numel = shape.numel()
247
+ total_numel += unpartitioned_numel
248
+
249
+ state_dict[name] = frozen_param_fragments[name]
250
+
251
+ if debug:
252
+ print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
253
+
254
+ print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
255
+
256
+
257
+ def _has_callable(obj, fn):
258
+ attr = getattr(obj, fn, None)
259
+ return callable(attr)
260
+
261
+
262
+ def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
263
+ param_shapes = zero_model_states[0].param_shapes
264
+
265
+ # Reconstruction protocol:
266
+ #
267
+ # XXX: document this
268
+
269
+ if debug:
270
+ for i in range(world_size):
271
+ for j in range(len(fp32_flat_groups[0])):
272
+ print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
273
+
274
+ # XXX: memory usage doubles here (zero2)
275
+ num_param_groups = len(fp32_flat_groups[0])
276
+ merged_single_partition_of_fp32_groups = []
277
+ for i in range(num_param_groups):
278
+ merged_partitions = [sd[i] for sd in fp32_flat_groups]
279
+ full_single_fp32_vector = torch.cat(merged_partitions, 0)
280
+ merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
281
+ avail_numel = sum(
282
+ [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
283
+
284
+ if debug:
285
+ wanted_params = sum([len(shapes) for shapes in param_shapes])
286
+ wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
287
+ # not asserting if there is a mismatch due to possible padding
288
+ print(f"Have {avail_numel} numels to process.")
289
+ print(f"Need {wanted_numel} numels in {wanted_params} params.")
290
+
291
+ # params
292
+ # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
293
+ # out-of-core computing solution
294
+ total_numel = 0
295
+ total_params = 0
296
+ for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
297
+ offset = 0
298
+ avail_numel = full_single_fp32_vector.numel()
299
+ for name, shape in shapes.items():
300
+
301
+ unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
302
+ total_numel += unpartitioned_numel
303
+ total_params += 1
304
+
305
+ if debug:
306
+ print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
307
+ state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
308
+ offset += unpartitioned_numel
309
+
310
+ # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
311
+ # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
312
+ # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
313
+ # live optimizer object, so we are checking that the numbers are within the right range
314
+ align_to = 2 * world_size
315
+
316
+ def zero2_align(x):
317
+ return align_to * math.ceil(x / align_to)
318
+
319
+ if debug:
320
+ print(f"original offset={offset}, avail_numel={avail_numel}")
321
+
322
+ offset = zero2_align(offset)
323
+ avail_numel = zero2_align(avail_numel)
324
+
325
+ if debug:
326
+ print(f"aligned offset={offset}, avail_numel={avail_numel}")
327
+
328
+ # Sanity check
329
+ if offset != avail_numel:
330
+ raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
331
+
332
+ print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
333
+
334
+
335
+ def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
336
+ exclude_frozen_parameters):
337
+ state_dict = OrderedDict()
338
+
339
+ # buffers
340
+ buffers = zero_model_states[0].buffers
341
+ state_dict.update(buffers)
342
+ if debug:
343
+ print(f"added {len(buffers)} buffers")
344
+
345
+ if not exclude_frozen_parameters:
346
+ _zero2_merge_frozen_params(state_dict, zero_model_states)
347
+
348
+ _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
349
+
350
+ # recover shared parameters
351
+ for pair in zero_model_states[0].shared_params:
352
+ if pair[1] in state_dict:
353
+ state_dict[pair[0]] = state_dict[pair[1]]
354
+
355
+ return state_dict
356
+
357
+
358
+ def zero3_partitioned_param_info(unpartitioned_numel, world_size):
359
+ remainder = unpartitioned_numel % world_size
360
+ padding_numel = (world_size - remainder) if remainder else 0
361
+ partitioned_numel = math.ceil(unpartitioned_numel / world_size)
362
+ return partitioned_numel, padding_numel
363
+
364
+
365
+ def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
366
+ if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
367
+ return
368
+
369
+ if debug:
370
+ for i in range(world_size):
371
+ num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
372
+ print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
373
+
374
+ frozen_param_shapes = zero_model_states[0].frozen_param_shapes
375
+ wanted_params = len(frozen_param_shapes)
376
+ wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
377
+ avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
378
+ print(f'Frozen params: Have {avail_numel} numels to process.')
379
+ print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
380
+
381
+ total_params = 0
382
+ total_numel = 0
383
+ for name, shape in zero_model_states[0].frozen_param_shapes.items():
384
+ total_params += 1
385
+ unpartitioned_numel = shape.numel()
386
+ total_numel += unpartitioned_numel
387
+
388
+ param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
389
+ state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
390
+
391
+ partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
392
+
393
+ if debug:
394
+ print(
395
+ f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
396
+ )
397
+
398
+ print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
399
+
400
+
401
+ def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
402
+ param_shapes = zero_model_states[0].param_shapes
403
+ avail_numel = fp32_flat_groups[0].numel() * world_size
404
+ # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
405
+ # param, re-consolidating each param, while dealing with padding if any
406
+
407
+ # merge list of dicts, preserving order
408
+ param_shapes = {k: v for d in param_shapes for k, v in d.items()}
409
+
410
+ if debug:
411
+ for i in range(world_size):
412
+ print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
413
+
414
+ wanted_params = len(param_shapes)
415
+ wanted_numel = sum(shape.numel() for shape in param_shapes.values())
416
+ # not asserting if there is a mismatch due to possible padding
417
+ avail_numel = fp32_flat_groups[0].numel() * world_size
418
+ print(f"Trainable params: Have {avail_numel} numels to process.")
419
+ print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
420
+
421
+ # params
422
+ # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
423
+ # out-of-core computing solution
424
+ offset = 0
425
+ total_numel = 0
426
+ total_params = 0
427
+ for name, shape in tqdm(param_shapes.items(), desc='Gathering Sharded Weights'):
428
+ unpartitioned_numel = shape.numel()
429
+ total_numel += unpartitioned_numel
430
+ total_params += 1
431
+ partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
432
+
433
+ if debug:
434
+ print(
435
+ f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
436
+ )
437
+
438
+ # XXX: memory usage doubles here
439
+ state_dict[name] = torch.cat(
440
+ tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
441
+ 0).narrow(0, 0, unpartitioned_numel).view(shape)
442
+ offset += partitioned_numel
443
+
444
+ offset *= world_size
445
+
446
+ # Sanity check
447
+ if offset != avail_numel:
448
+ raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
449
+
450
+ print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
451
+
452
+
453
+ def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
454
+ exclude_frozen_parameters):
455
+ state_dict = OrderedDict()
456
+
457
+ # buffers
458
+ buffers = zero_model_states[0].buffers
459
+ state_dict.update(buffers)
460
+ if debug:
461
+ print(f"added {len(buffers)} buffers")
462
+
463
+ if not exclude_frozen_parameters:
464
+ _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
465
+
466
+ _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
467
+
468
+ # recover shared parameters
469
+ for pair in zero_model_states[0].shared_params:
470
+ if pair[1] in state_dict:
471
+ state_dict[pair[0]] = state_dict[pair[1]]
472
+
473
+ return state_dict
474
+
475
+
476
+ def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
477
+ """
478
+ Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
479
+ ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
480
+ via a model hub.
481
+
482
+ Args:
483
+ - ``checkpoint_dir``: path to the desired checkpoint folder
484
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
485
+ - ``exclude_frozen_parameters``: exclude frozen parameters
486
+
487
+ Returns:
488
+ - pytorch ``state_dict``
489
+
490
+ Note: this approach may not work if your application doesn't have sufficient free CPU memory and
491
+ you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
492
+ the checkpoint.
493
+
494
+ A typical usage might be ::
495
+
496
+ from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
497
+ # do the training and checkpoint saving
498
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
499
+ model = model.cpu() # move to cpu
500
+ model.load_state_dict(state_dict)
501
+ # submit to model hub or save the model to share with others
502
+
503
+ In this example the ``model`` will no longer be usable in the deepspeed context of the same
504
+ application. i.e. you will need to re-initialize the deepspeed engine, since
505
+ ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
506
+
507
+ If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
508
+
509
+ """
510
+ if tag is None:
511
+ latest_path = os.path.join(checkpoint_dir, 'latest')
512
+ if os.path.isfile(latest_path):
513
+ with open(latest_path, 'r') as fd:
514
+ tag = fd.read().strip()
515
+ else:
516
+ raise ValueError(f"Unable to find 'latest' file at {latest_path}")
517
+
518
+ ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
519
+
520
+ if not os.path.isdir(ds_checkpoint_dir):
521
+ raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
522
+
523
+ return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
524
+
525
+
526
+ def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
527
+ output_dir,
528
+ max_shard_size="5GB",
529
+ safe_serialization=False,
530
+ tag=None,
531
+ exclude_frozen_parameters=False):
532
+ """
533
+ Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
534
+ loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
535
+
536
+ Args:
537
+ - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
538
+ - ``output_dir``: directory to the pytorch fp32 state_dict output files
539
+ - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
540
+ - ``safe_serialization``: whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
541
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
542
+ - ``exclude_frozen_parameters``: exclude frozen parameters
543
+ """
544
+ # Dependency pre-check
545
+ if safe_serialization:
546
+ try:
547
+ from safetensors.torch import save_file
548
+ except ImportError:
549
+ print('If you want to use `safe_serialization`, please `pip install safetensors`')
550
+ raise
551
+ if max_shard_size is not None:
552
+ try:
553
+ from huggingface_hub import split_torch_state_dict_into_shards
554
+ except ImportError:
555
+ print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
556
+ raise
557
+
558
+ # Convert zero checkpoint to state_dict
559
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
560
+
561
+ # Shard the model if it is too big.
562
+ weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
563
+ if max_shard_size is not None:
564
+ filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
565
+ state_dict_split = split_torch_state_dict_into_shards(state_dict,
566
+ filename_pattern=filename_pattern,
567
+ max_shard_size=max_shard_size)
568
+ else:
569
+ from collections import namedtuple
570
+ StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
571
+ state_dict_split = StateDictSplit(is_sharded=False,
572
+ filename_to_tensors={weights_name: list(state_dict.keys())})
573
+
574
+ # Save the model
575
+ filename_to_tensors = state_dict_split.filename_to_tensors.items()
576
+ for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
577
+ shard = {tensor: state_dict[tensor].contiguous() for tensor in tensors}
578
+ output_path = os.path.join(output_dir, shard_file)
579
+ if safe_serialization:
580
+ save_file(shard, output_path, metadata={"format": "pt"})
581
+ else:
582
+ torch.save(shard, output_path)
583
+
584
+ # Save index if sharded
585
+ if state_dict_split.is_sharded:
586
+ index = {
587
+ "metadata": state_dict_split.metadata,
588
+ "weight_map": state_dict_split.tensor_to_filename,
589
+ }
590
+ save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
591
+ save_index_file = os.path.join(output_dir, save_index_file)
592
+ with open(save_index_file, "w", encoding="utf-8") as f:
593
+ content = json.dumps(index, indent=2, sort_keys=True) + "\n"
594
+ f.write(content)
595
+
596
+
597
+ def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
598
+ """
599
+ 1. Put the provided model to cpu
600
+ 2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
601
+ 3. Load it into the provided model
602
+
603
+ Args:
604
+ - ``model``: the model object to update
605
+ - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
606
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
607
+
608
+ Returns:
609
+ - ``model`: modified model
610
+
611
+ Make sure you have plenty of CPU memory available before you call this function. If you don't
612
+ have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
613
+ conveniently placed for you in the checkpoint folder.
614
+
615
+ A typical usage might be ::
616
+
617
+ from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
618
+ model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
619
+ # submit to model hub or save the model to share with others
620
+
621
+ Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
622
+ of the same application. i.e. you will need to re-initialize the deepspeed engine, since
623
+ ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
624
+
625
+ """
626
+ logger.info(f"Extracting fp32 weights")
627
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
628
+
629
+ logger.info(f"Overwriting model with fp32 weights")
630
+ model = model.cpu()
631
+ model.load_state_dict(state_dict, strict=False)
632
+
633
+ return model
634
+
635
+
636
+ if __name__ == "__main__":
637
+ parser = argparse.ArgumentParser()
638
+ parser.add_argument("checkpoint_dir",
639
+ type=str,
640
+ help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
641
+ parser.add_argument("output_dir",
642
+ type=str,
643
+ help="directory to the pytorch fp32 state_dict output files"
644
+ "(e.g. path/checkpoint-12-output/)")
645
+ parser.add_argument(
646
+ "--max_shard_size",
647
+ type=str,
648
+ default="5GB",
649
+ help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
650
+ "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
651
+ "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
652
+ "without CPU OOM issues.")
653
+ parser.add_argument(
654
+ "--safe_serialization",
655
+ default=False,
656
+ action='store_true',
657
+ help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
658
+ parser.add_argument("-t",
659
+ "--tag",
660
+ type=str,
661
+ default=None,
662
+ help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
663
+ parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
664
+ parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
665
+ args = parser.parse_args()
666
+
667
+ debug = args.debug
668
+
669
+ convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
670
+ args.output_dir,
671
+ max_shard_size=args.max_shard_size,
672
+ safe_serialization=args.safe_serialization,
673
+ tag=args.tag,
674
+ exclude_frozen_parameters=args.exclude_frozen_parameters)