Hugging Face's logo

SI-Lab
/
StepCount-7B-SFT-1M

Image-Text-to-Text
Transformers
Safetensors
qwen2_5_vl
llama-factory
full
qwen2.5-vl
stepcount
sft
conversational
text-generation-inference
Model card Files
xet
 Community
zhangchenhao commited on
Commit
6088da0
·
1 Parent(s): 33dc248

Upload StepCount-7B-SFT-1M checkpoint-476 remaining files

Browse files
Files changed (12) hide show
  1. .gitattributes +1 -0
  2. model-00002-of-00004.safetensors +3 -0
  3. model-00003-of-00004.safetensors +3 -0
  4. model.safetensors.index.json +736 -0
  5. preprocessor_config.json +29 -0
  6. special_tokens_map.json +31 -0
  7. tokenizer.json +3 -0
  8. tokenizer_config.json +257 -0
  9. trainer_state.json +1242 -0
  10. training_args.bin +3 -0
  11. video_preprocessor_config.json +86 -0
  12. vocab.json +0 -0
.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
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9373999662c2254d03b4fd6727504048e7fbb783dceb4b13eb70dcd3e7a894f4
3
+ size 4991497784
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c41d38dedfb8887f49db08b0569b1126f6e44a09941c9cff2b01bea37f58fd6
3
+ size 4932752872
model.safetensors.index.json ADDED
@@ -0,0 +1,736 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16584333312
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "model.language_model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
+ "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
13
+ "model.language_model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
14
+ "model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.language_model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
17
+ "model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
18
+ "model.language_model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
19
+ "model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
21
+ "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
22
+ "model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
25
+ "model.language_model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
26
+ "model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
27
+ "model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
28
+ "model.language_model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
29
+ "model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
30
+ "model.language_model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
31
+ "model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
32
+ "model.language_model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
33
+ "model.language_model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.language_model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.language_model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
36
+ "model.language_model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
37
+ "model.language_model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
38
+ "model.language_model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.language_model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
40
+ "model.language_model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
41
+ "model.language_model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.language_model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
43
+ "model.language_model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.language_model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
45
+ "model.language_model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.language_model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.language_model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.language_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
49
+ "model.language_model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
50
+ "model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.language_model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.language_model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
53
+ "model.language_model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
54
+ "model.language_model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
55
+ "model.language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.language_model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
57
+ "model.language_model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
58
+ "model.language_model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.language_model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.language_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
61
+ "model.language_model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
62
+ "model.language_model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
63
+ "model.language_model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.language_model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
65
+ "model.language_model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.language_model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
67
+ "model.language_model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.language_model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
69
+ "model.language_model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.language_model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.language_model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
72
+ "model.language_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
73
+ "model.language_model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
74
+ "model.language_model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.language_model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
76
+ "model.language_model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
77
+ "model.language_model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.language_model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
79
+ "model.language_model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.language_model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
81
+ "model.language_model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.language_model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.language_model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.language_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "model.language_model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
86
+ "model.language_model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.language_model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.language_model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
89
+ "model.language_model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
90
+ "model.language_model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
91
+ "model.language_model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.language_model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
93
+ "model.language_model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
94
+ "model.language_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.language_model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.language_model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
97
+ "model.language_model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
98
+ "model.language_model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
99
+ "model.language_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.language_model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
101
+ "model.language_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.language_model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
103
+ "model.language_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.language_model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
105
+ "model.language_model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
106
+ "model.language_model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
107
+ "model.language_model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
108
+ "model.language_model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
109
+ "model.language_model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
110
+ "model.language_model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.language_model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
112
+ "model.language_model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
113
+ "model.language_model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.language_model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
115
+ "model.language_model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.language_model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
117
+ "model.language_model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
118
+ "model.language_model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
119
+ "model.language_model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
120
+ "model.language_model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
121
+ "model.language_model.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
122
+ "model.language_model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
123
+ "model.language_model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
124
+ "model.language_model.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
125
+ "model.language_model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
126
+ "model.language_model.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
127
+ "model.language_model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
128
+ "model.language_model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
129
+ "model.language_model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
130
+ "model.language_model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
131
+ "model.language_model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
132
+ "model.language_model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
133
+ "model.language_model.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
134
+ "model.language_model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
135
+ "model.language_model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
136
+ "model.language_model.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
137
+ "model.language_model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
138
+ "model.language_model.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
139
+ "model.language_model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
140
+ "model.language_model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
141
+ "model.language_model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.language_model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.language_model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
144
+ "model.language_model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
145
+ "model.language_model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
146
+ "model.language_model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.language_model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
148
+ "model.language_model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
149
+ "model.language_model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.language_model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
151
+ "model.language_model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
152
+ "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
153
+ "model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
154
+ "model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
155
+ "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
156
+ "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
157
+ "model.language_model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
158
+ "model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
159
+ "model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
160
+ "model.language_model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
161
+ "model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
162
+ "model.language_model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
163
+ "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
164
+ "model.language_model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
165
+ "model.language_model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
166
+ "model.language_model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.language_model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.language_model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
169
+ "model.language_model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
170
+ "model.language_model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
171
+ "model.language_model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.language_model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
173
+ "model.language_model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.language_model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
175
+ "model.language_model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.language_model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
177
+ "model.language_model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.language_model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.language_model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
180
+ "model.language_model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
181
+ "model.language_model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
182
+ "model.language_model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.language_model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
184
+ "model.language_model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
185
+ "model.language_model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.language_model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
187
+ "model.language_model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.language_model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
189
+ "model.language_model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
190
+ "model.language_model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.language_model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.language_model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
193
+ "model.language_model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
194
+ "model.language_model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.language_model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.language_model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
197
+ "model.language_model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
198
+ "model.language_model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
199
+ "model.language_model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
200
+ "model.language_model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
201
+ "model.language_model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
202
+ "model.language_model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.language_model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.language_model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
205
+ "model.language_model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
206
+ "model.language_model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
207
+ "model.language_model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.language_model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
209
+ "model.language_model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.language_model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
211
+ "model.language_model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
212
+ "model.language_model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
213
+ "model.language_model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.language_model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.language_model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
216
+ "model.language_model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
217
+ "model.language_model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
218
+ "model.language_model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
219
+ "model.language_model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
220
+ "model.language_model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
221
+ "model.language_model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
222
+ "model.language_model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
223
+ "model.language_model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
224
+ "model.language_model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
225
+ "model.language_model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.language_model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.language_model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.language_model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
229
+ "model.language_model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
230
+ "model.language_model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.language_model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.language_model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
233
+ "model.language_model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
234
+ "model.language_model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
235
+ "model.language_model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
236
+ "model.language_model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
237
+ "model.language_model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
238
+ "model.language_model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.language_model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.language_model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
241
+ "model.language_model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
242
+ "model.language_model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
243
+ "model.language_model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
244
+ "model.language_model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
245
+ "model.language_model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
246
+ "model.language_model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
247
+ "model.language_model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
248
+ "model.language_model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
249
+ "model.language_model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
250
+ "model.language_model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
251
+ "model.language_model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
252
+ "model.language_model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
253
+ "model.language_model.layers.27.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
254
+ "model.language_model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
255
+ "model.language_model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
256
+ "model.language_model.layers.27.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
257
+ "model.language_model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
258
+ "model.language_model.layers.27.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
259
+ "model.language_model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
260
+ "model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
261
+ "model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
262
+ "model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
265
+ "model.language_model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
266
+ "model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
267
+ "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.language_model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
269
+ "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
270
+ "model.language_model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
271
+ "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
272
+ "model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
273
+ "model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
274
+ "model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
275
+ "model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
277
+ "model.language_model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
278
+ "model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
279
+ "model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
280
+ "model.language_model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
281
+ "model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
282
+ "model.language_model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
283
+ "model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
284
+ "model.language_model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
285
+ "model.language_model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
286
+ "model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
287
+ "model.language_model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
288
+ "model.language_model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
289
+ "model.language_model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
290
+ "model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
291
+ "model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
292
+ "model.language_model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
293
+ "model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
294
+ "model.language_model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
295
+ "model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
296
+ "model.language_model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
297
+ "model.language_model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
298
+ "model.language_model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
299
+ "model.language_model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
300
+ "model.language_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
301
+ "model.language_model.layers.6.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
302
+ "model.language_model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
303
+ "model.language_model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
304
+ "model.language_model.layers.6.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
305
+ "model.language_model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
306
+ "model.language_model.layers.6.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
307
+ "model.language_model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
308
+ "model.language_model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
309
+ "model.language_model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
310
+ "model.language_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
311
+ "model.language_model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
312
+ "model.language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
313
+ "model.language_model.layers.7.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
314
+ "model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
315
+ "model.language_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
316
+ "model.language_model.layers.7.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
317
+ "model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
318
+ "model.language_model.layers.7.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
319
+ "model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
320
+ "model.language_model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
321
+ "model.language_model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
322
+ "model.language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
323
+ "model.language_model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
324
+ "model.language_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
325
+ "model.language_model.layers.8.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
326
+ "model.language_model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
327
+ "model.language_model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
328
+ "model.language_model.layers.8.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
329
+ "model.language_model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
330
+ "model.language_model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
331
+ "model.language_model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
332
+ "model.language_model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
333
+ "model.language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
334
+ "model.language_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
335
+ "model.language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
336
+ "model.language_model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
337
+ "model.language_model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
338
+ "model.language_model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
339
+ "model.language_model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
340
+ "model.language_model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
341
+ "model.language_model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
342
+ "model.language_model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
343
+ "model.language_model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
344
+ "model.language_model.norm.weight": "model-00004-of-00004.safetensors",
345
+ "model.visual.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors",
346
+ "model.visual.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
347
+ "model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
348
+ "model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
349
+ "model.visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
350
+ "model.visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
351
+ "model.visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
352
+ "model.visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
353
+ "model.visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
354
+ "model.visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
355
+ "model.visual.blocks.0.norm1.weight": "model-00001-of-00004.safetensors",
356
+ "model.visual.blocks.0.norm2.weight": "model-00001-of-00004.safetensors",
357
+ "model.visual.blocks.1.attn.proj.bias": "model-00001-of-00004.safetensors",
358
+ "model.visual.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors",
359
+ "model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
360
+ "model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
361
+ "model.visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
362
+ "model.visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
363
+ "model.visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
364
+ "model.visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
365
+ "model.visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
366
+ "model.visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
367
+ "model.visual.blocks.1.norm1.weight": "model-00001-of-00004.safetensors",
368
+ "model.visual.blocks.1.norm2.weight": "model-00001-of-00004.safetensors",
369
+ "model.visual.blocks.10.attn.proj.bias": "model-00001-of-00004.safetensors",
370
+ "model.visual.blocks.10.attn.proj.weight": "model-00001-of-00004.safetensors",
371
+ "model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
372
+ "model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
373
+ "model.visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
374
+ "model.visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
375
+ "model.visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
376
+ "model.visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
377
+ "model.visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
378
+ "model.visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
379
+ "model.visual.blocks.10.norm1.weight": "model-00001-of-00004.safetensors",
380
+ "model.visual.blocks.10.norm2.weight": "model-00001-of-00004.safetensors",
381
+ "model.visual.blocks.11.attn.proj.bias": "model-00001-of-00004.safetensors",
382
+ "model.visual.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors",
383
+ "model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
384
+ "model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
385
+ "model.visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
386
+ "model.visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
387
+ "model.visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
388
+ "model.visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
389
+ "model.visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
390
+ "model.visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
391
+ "model.visual.blocks.11.norm1.weight": "model-00001-of-00004.safetensors",
392
+ "model.visual.blocks.11.norm2.weight": "model-00001-of-00004.safetensors",
393
+ "model.visual.blocks.12.attn.proj.bias": "model-00001-of-00004.safetensors",
394
+ "model.visual.blocks.12.attn.proj.weight": "model-00001-of-00004.safetensors",
395
+ "model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
396
+ "model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
397
+ "model.visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
398
+ "model.visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
399
+ "model.visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
400
+ "model.visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
401
+ "model.visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
402
+ "model.visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
403
+ "model.visual.blocks.12.norm1.weight": "model-00001-of-00004.safetensors",
404
+ "model.visual.blocks.12.norm2.weight": "model-00001-of-00004.safetensors",
405
+ "model.visual.blocks.13.attn.proj.bias": "model-00001-of-00004.safetensors",
406
+ "model.visual.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors",
407
+ "model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
408
+ "model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
409
+ "model.visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
410
+ "model.visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
411
+ "model.visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
412
+ "model.visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
413
+ "model.visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
414
+ "model.visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
415
+ "model.visual.blocks.13.norm1.weight": "model-00001-of-00004.safetensors",
416
+ "model.visual.blocks.13.norm2.weight": "model-00001-of-00004.safetensors",
417
+ "model.visual.blocks.14.attn.proj.bias": "model-00001-of-00004.safetensors",
418
+ "model.visual.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors",
419
+ "model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
420
+ "model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
421
+ "model.visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
422
+ "model.visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
423
+ "model.visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
424
+ "model.visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
425
+ "model.visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
426
+ "model.visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
427
+ "model.visual.blocks.14.norm1.weight": "model-00001-of-00004.safetensors",
428
+ "model.visual.blocks.14.norm2.weight": "model-00001-of-00004.safetensors",
429
+ "model.visual.blocks.15.attn.proj.bias": "model-00001-of-00004.safetensors",
430
+ "model.visual.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors",
431
+ "model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
432
+ "model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
433
+ "model.visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
434
+ "model.visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
435
+ "model.visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
436
+ "model.visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
437
+ "model.visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
438
+ "model.visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
439
+ "model.visual.blocks.15.norm1.weight": "model-00001-of-00004.safetensors",
440
+ "model.visual.blocks.15.norm2.weight": "model-00001-of-00004.safetensors",
441
+ "model.visual.blocks.16.attn.proj.bias": "model-00001-of-00004.safetensors",
442
+ "model.visual.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors",
443
+ "model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
444
+ "model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
445
+ "model.visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
446
+ "model.visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
447
+ "model.visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
448
+ "model.visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
449
+ "model.visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
450
+ "model.visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
451
+ "model.visual.blocks.16.norm1.weight": "model-00001-of-00004.safetensors",
452
+ "model.visual.blocks.16.norm2.weight": "model-00001-of-00004.safetensors",
453
+ "model.visual.blocks.17.attn.proj.bias": "model-00001-of-00004.safetensors",
454
+ "model.visual.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors",
455
+ "model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
456
+ "model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
457
+ "model.visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
458
+ "model.visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
459
+ "model.visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
460
+ "model.visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
461
+ "model.visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
462
+ "model.visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
463
+ "model.visual.blocks.17.norm1.weight": "model-00001-of-00004.safetensors",
464
+ "model.visual.blocks.17.norm2.weight": "model-00001-of-00004.safetensors",
465
+ "model.visual.blocks.18.attn.proj.bias": "model-00001-of-00004.safetensors",
466
+ "model.visual.blocks.18.attn.proj.weight": "model-00001-of-00004.safetensors",
467
+ "model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
468
+ "model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
469
+ "model.visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
470
+ "model.visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
471
+ "model.visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
472
+ "model.visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
473
+ "model.visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
474
+ "model.visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
475
+ "model.visual.blocks.18.norm1.weight": "model-00001-of-00004.safetensors",
476
+ "model.visual.blocks.18.norm2.weight": "model-00001-of-00004.safetensors",
477
+ "model.visual.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors",
478
+ "model.visual.blocks.19.attn.proj.weight": "model-00001-of-00004.safetensors",
479
+ "model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
480
+ "model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
481
+ "model.visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
482
+ "model.visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
483
+ "model.visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
484
+ "model.visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
485
+ "model.visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
486
+ "model.visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
487
+ "model.visual.blocks.19.norm1.weight": "model-00001-of-00004.safetensors",
488
+ "model.visual.blocks.19.norm2.weight": "model-00001-of-00004.safetensors",
489
+ "model.visual.blocks.2.attn.proj.bias": "model-00001-of-00004.safetensors",
490
+ "model.visual.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors",
491
+ "model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
492
+ "model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
493
+ "model.visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
494
+ "model.visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
495
+ "model.visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
496
+ "model.visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
497
+ "model.visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
498
+ "model.visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
499
+ "model.visual.blocks.2.norm1.weight": "model-00001-of-00004.safetensors",
500
+ "model.visual.blocks.2.norm2.weight": "model-00001-of-00004.safetensors",
501
+ "model.visual.blocks.20.attn.proj.bias": "model-00001-of-00004.safetensors",
502
+ "model.visual.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors",
503
+ "model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
504
+ "model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
505
+ "model.visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
506
+ "model.visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
507
+ "model.visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
508
+ "model.visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
509
+ "model.visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
510
+ "model.visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
511
+ "model.visual.blocks.20.norm1.weight": "model-00001-of-00004.safetensors",
512
+ "model.visual.blocks.20.norm2.weight": "model-00001-of-00004.safetensors",
513
+ "model.visual.blocks.21.attn.proj.bias": "model-00001-of-00004.safetensors",
514
+ "model.visual.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors",
515
+ "model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
516
+ "model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
517
+ "model.visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
518
+ "model.visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
519
+ "model.visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
520
+ "model.visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
521
+ "model.visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
522
+ "model.visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
523
+ "model.visual.blocks.21.norm1.weight": "model-00001-of-00004.safetensors",
524
+ "model.visual.blocks.21.norm2.weight": "model-00001-of-00004.safetensors",
525
+ "model.visual.blocks.22.attn.proj.bias": "model-00001-of-00004.safetensors",
526
+ "model.visual.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors",
527
+ "model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
528
+ "model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
529
+ "model.visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
530
+ "model.visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
531
+ "model.visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
532
+ "model.visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
533
+ "model.visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
534
+ "model.visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
535
+ "model.visual.blocks.22.norm1.weight": "model-00001-of-00004.safetensors",
536
+ "model.visual.blocks.22.norm2.weight": "model-00001-of-00004.safetensors",
537
+ "model.visual.blocks.23.attn.proj.bias": "model-00001-of-00004.safetensors",
538
+ "model.visual.blocks.23.attn.proj.weight": "model-00001-of-00004.safetensors",
539
+ "model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
540
+ "model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
541
+ "model.visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
542
+ "model.visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
543
+ "model.visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
544
+ "model.visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
545
+ "model.visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
546
+ "model.visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
547
+ "model.visual.blocks.23.norm1.weight": "model-00001-of-00004.safetensors",
548
+ "model.visual.blocks.23.norm2.weight": "model-00001-of-00004.safetensors",
549
+ "model.visual.blocks.24.attn.proj.bias": "model-00001-of-00004.safetensors",
550
+ "model.visual.blocks.24.attn.proj.weight": "model-00001-of-00004.safetensors",
551
+ "model.visual.blocks.24.attn.qkv.bias": "model-00001-of-00004.safetensors",
552
+ "model.visual.blocks.24.attn.qkv.weight": "model-00001-of-00004.safetensors",
553
+ "model.visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
554
+ "model.visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
555
+ "model.visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
556
+ "model.visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
557
+ "model.visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
558
+ "model.visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
559
+ "model.visual.blocks.24.norm1.weight": "model-00001-of-00004.safetensors",
560
+ "model.visual.blocks.24.norm2.weight": "model-00001-of-00004.safetensors",
561
+ "model.visual.blocks.25.attn.proj.bias": "model-00001-of-00004.safetensors",
562
+ "model.visual.blocks.25.attn.proj.weight": "model-00001-of-00004.safetensors",
563
+ "model.visual.blocks.25.attn.qkv.bias": "model-00001-of-00004.safetensors",
564
+ "model.visual.blocks.25.attn.qkv.weight": "model-00001-of-00004.safetensors",
565
+ "model.visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
566
+ "model.visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
567
+ "model.visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
568
+ "model.visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
569
+ "model.visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
570
+ "model.visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
571
+ "model.visual.blocks.25.norm1.weight": "model-00001-of-00004.safetensors",
572
+ "model.visual.blocks.25.norm2.weight": "model-00001-of-00004.safetensors",
573
+ "model.visual.blocks.26.attn.proj.bias": "model-00001-of-00004.safetensors",
574
+ "model.visual.blocks.26.attn.proj.weight": "model-00001-of-00004.safetensors",
575
+ "model.visual.blocks.26.attn.qkv.bias": "model-00001-of-00004.safetensors",
576
+ "model.visual.blocks.26.attn.qkv.weight": "model-00001-of-00004.safetensors",
577
+ "model.visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
578
+ "model.visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
579
+ "model.visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
580
+ "model.visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
581
+ "model.visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
582
+ "model.visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
583
+ "model.visual.blocks.26.norm1.weight": "model-00001-of-00004.safetensors",
584
+ "model.visual.blocks.26.norm2.weight": "model-00001-of-00004.safetensors",
585
+ "model.visual.blocks.27.attn.proj.bias": "model-00001-of-00004.safetensors",
586
+ "model.visual.blocks.27.attn.proj.weight": "model-00001-of-00004.safetensors",
587
+ "model.visual.blocks.27.attn.qkv.bias": "model-00001-of-00004.safetensors",
588
+ "model.visual.blocks.27.attn.qkv.weight": "model-00001-of-00004.safetensors",
589
+ "model.visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
590
+ "model.visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
591
+ "model.visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
592
+ "model.visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
593
+ "model.visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
594
+ "model.visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
595
+ "model.visual.blocks.27.norm1.weight": "model-00001-of-00004.safetensors",
596
+ "model.visual.blocks.27.norm2.weight": "model-00001-of-00004.safetensors",
597
+ "model.visual.blocks.28.attn.proj.bias": "model-00001-of-00004.safetensors",
598
+ "model.visual.blocks.28.attn.proj.weight": "model-00001-of-00004.safetensors",
599
+ "model.visual.blocks.28.attn.qkv.bias": "model-00001-of-00004.safetensors",
600
+ "model.visual.blocks.28.attn.qkv.weight": "model-00001-of-00004.safetensors",
601
+ "model.visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
602
+ "model.visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
603
+ "model.visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
604
+ "model.visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
605
+ "model.visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
606
+ "model.visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
607
+ "model.visual.blocks.28.norm1.weight": "model-00001-of-00004.safetensors",
608
+ "model.visual.blocks.28.norm2.weight": "model-00001-of-00004.safetensors",
609
+ "model.visual.blocks.29.attn.proj.bias": "model-00001-of-00004.safetensors",
610
+ "model.visual.blocks.29.attn.proj.weight": "model-00001-of-00004.safetensors",
611
+ "model.visual.blocks.29.attn.qkv.bias": "model-00001-of-00004.safetensors",
612
+ "model.visual.blocks.29.attn.qkv.weight": "model-00001-of-00004.safetensors",
613
+ "model.visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
614
+ "model.visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
615
+ "model.visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
616
+ "model.visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
617
+ "model.visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
618
+ "model.visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
619
+ "model.visual.blocks.29.norm1.weight": "model-00001-of-00004.safetensors",
620
+ "model.visual.blocks.29.norm2.weight": "model-00001-of-00004.safetensors",
621
+ "model.visual.blocks.3.attn.proj.bias": "model-00001-of-00004.safetensors",
622
+ "model.visual.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors",
623
+ "model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
624
+ "model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
625
+ "model.visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
626
+ "model.visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
627
+ "model.visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
628
+ "model.visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
629
+ "model.visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
630
+ "model.visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
631
+ "model.visual.blocks.3.norm1.weight": "model-00001-of-00004.safetensors",
632
+ "model.visual.blocks.3.norm2.weight": "model-00001-of-00004.safetensors",
633
+ "model.visual.blocks.30.attn.proj.bias": "model-00001-of-00004.safetensors",
634
+ "model.visual.blocks.30.attn.proj.weight": "model-00001-of-00004.safetensors",
635
+ "model.visual.blocks.30.attn.qkv.bias": "model-00001-of-00004.safetensors",
636
+ "model.visual.blocks.30.attn.qkv.weight": "model-00001-of-00004.safetensors",
637
+ "model.visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
638
+ "model.visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
639
+ "model.visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
640
+ "model.visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
641
+ "model.visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
642
+ "model.visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
643
+ "model.visual.blocks.30.norm1.weight": "model-00001-of-00004.safetensors",
644
+ "model.visual.blocks.30.norm2.weight": "model-00001-of-00004.safetensors",
645
+ "model.visual.blocks.31.attn.proj.bias": "model-00001-of-00004.safetensors",
646
+ "model.visual.blocks.31.attn.proj.weight": "model-00001-of-00004.safetensors",
647
+ "model.visual.blocks.31.attn.qkv.bias": "model-00001-of-00004.safetensors",
648
+ "model.visual.blocks.31.attn.qkv.weight": "model-00001-of-00004.safetensors",
649
+ "model.visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
650
+ "model.visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
651
+ "model.visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
652
+ "model.visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
653
+ "model.visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
654
+ "model.visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
655
+ "model.visual.blocks.31.norm1.weight": "model-00001-of-00004.safetensors",
656
+ "model.visual.blocks.31.norm2.weight": "model-00001-of-00004.safetensors",
657
+ "model.visual.blocks.4.attn.proj.bias": "model-00001-of-00004.safetensors",
658
+ "model.visual.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors",
659
+ "model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
660
+ "model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
661
+ "model.visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
662
+ "model.visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
663
+ "model.visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
664
+ "model.visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
665
+ "model.visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
666
+ "model.visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
667
+ "model.visual.blocks.4.norm1.weight": "model-00001-of-00004.safetensors",
668
+ "model.visual.blocks.4.norm2.weight": "model-00001-of-00004.safetensors",
669
+ "model.visual.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors",
670
+ "model.visual.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors",
671
+ "model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
672
+ "model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
673
+ "model.visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
674
+ "model.visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
675
+ "model.visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
676
+ "model.visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
677
+ "model.visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
678
+ "model.visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
679
+ "model.visual.blocks.5.norm1.weight": "model-00001-of-00004.safetensors",
680
+ "model.visual.blocks.5.norm2.weight": "model-00001-of-00004.safetensors",
681
+ "model.visual.blocks.6.attn.proj.bias": "model-00001-of-00004.safetensors",
682
+ "model.visual.blocks.6.attn.proj.weight": "model-00001-of-00004.safetensors",
683
+ "model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
684
+ "model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
685
+ "model.visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
686
+ "model.visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
687
+ "model.visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
688
+ "model.visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
689
+ "model.visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
690
+ "model.visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
691
+ "model.visual.blocks.6.norm1.weight": "model-00001-of-00004.safetensors",
692
+ "model.visual.blocks.6.norm2.weight": "model-00001-of-00004.safetensors",
693
+ "model.visual.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors",
694
+ "model.visual.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors",
695
+ "model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
696
+ "model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
697
+ "model.visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
698
+ "model.visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
699
+ "model.visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
700
+ "model.visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
701
+ "model.visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
702
+ "model.visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
703
+ "model.visual.blocks.7.norm1.weight": "model-00001-of-00004.safetensors",
704
+ "model.visual.blocks.7.norm2.weight": "model-00001-of-00004.safetensors",
705
+ "model.visual.blocks.8.attn.proj.bias": "model-00001-of-00004.safetensors",
706
+ "model.visual.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors",
707
+ "model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
708
+ "model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
709
+ "model.visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
710
+ "model.visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
711
+ "model.visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
712
+ "model.visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
713
+ "model.visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
714
+ "model.visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
715
+ "model.visual.blocks.8.norm1.weight": "model-00001-of-00004.safetensors",
716
+ "model.visual.blocks.8.norm2.weight": "model-00001-of-00004.safetensors",
717
+ "model.visual.blocks.9.attn.proj.bias": "model-00001-of-00004.safetensors",
718
+ "model.visual.blocks.9.attn.proj.weight": "model-00001-of-00004.safetensors",
719
+ "model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
720
+ "model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
721
+ "model.visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
722
+ "model.visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
723
+ "model.visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
724
+ "model.visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
725
+ "model.visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
726
+ "model.visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
727
+ "model.visual.blocks.9.norm1.weight": "model-00001-of-00004.safetensors",
728
+ "model.visual.blocks.9.norm2.weight": "model-00001-of-00004.safetensors",
729
+ "model.visual.merger.ln_q.weight": "model-00001-of-00004.safetensors",
730
+ "model.visual.merger.mlp.0.bias": "model-00001-of-00004.safetensors",
731
+ "model.visual.merger.mlp.0.weight": "model-00001-of-00004.safetensors",
732
+ "model.visual.merger.mlp.2.bias": "model-00001-of-00004.safetensors",
733
+ "model.visual.merger.mlp.2.weight": "model-00001-of-00004.safetensors",
734
+ "model.visual.patch_embed.proj.weight": "model-00001-of-00004.safetensors"
735
+ }
736
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": true,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.48145466,
8
+ 0.4578275,
9
+ 0.40821073
10
+ ],
11
+ "image_processor_type": "Qwen2VLImageProcessor",
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "max_pixels": 12845056,
18
+ "merge_size": 2,
19
+ "min_pixels": 3136,
20
+ "patch_size": 14,
21
+ "processor_class": "Qwen2_5_VLProcessor",
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "longest_edge": 12845056,
26
+ "shortest_edge": 3136
27
+ },
28
+ "temporal_patch_size": 2
29
+ }
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": "<|im_end|>",
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:e56e691e81e99425c4397af8539c4b79a814c331fe697d38e5fe469644d6ee71
3
+ size 11423005
tokenizer_config.json ADDED
@@ -0,0 +1,257 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "151665": {
182
+ "content": "<think>",
183
+ "lstrip": false,
184
+ "normalized": true,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</think>",
191
+ "lstrip": false,
192
+ "normalized": true,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<answer>",
199
+ "lstrip": false,
200
+ "normalized": true,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</answer>",
207
+ "lstrip": false,
208
+ "normalized": true,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ },
213
+ "151669": {
214
+ "content": "<point>",
215
+ "lstrip": false,
216
+ "normalized": true,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": false
220
+ },
221
+ "151670": {
222
+ "content": "</point>",
223
+ "lstrip": false,
224
+ "normalized": true,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": false
228
+ }
229
+ },
230
+ "additional_special_tokens": [
231
+ "<|im_start|>",
232
+ "<|im_end|>",
233
+ "<|object_ref_start|>",
234
+ "<|object_ref_end|>",
235
+ "<|box_start|>",
236
+ "<|box_end|>",
237
+ "<|quad_start|>",
238
+ "<|quad_end|>",
239
+ "<|vision_start|>",
240
+ "<|vision_end|>",
241
+ "<|vision_pad|>",
242
+ "<|image_pad|>",
243
+ "<|video_pad|>"
244
+ ],
245
+ "bos_token": null,
246
+ "clean_up_tokenization_spaces": false,
247
+ "eos_token": "<|im_end|>",
248
+ "errors": "replace",
249
+ "extra_special_tokens": {},
250
+ "model_max_length": 131072,
251
+ "pad_token": "<|endoftext|>",
252
+ "padding_side": "right",
253
+ "processor_class": "Qwen2_5_VLProcessor",
254
+ "split_special_tokens": false,
255
+ "tokenizer_class": "Qwen2Tokenizer",
256
+ "unk_token": null
257
+ }
trainer_state.json ADDED
@@ -0,0 +1,1242 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.24257867244234935,
6
+ "eval_steps": 238,
7
+ "global_step": 476,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.002038476239011339,
14
+ "grad_norm": 0.6477837651252902,
15
+ "learning_rate": 2.699735382882792e-06,
16
+ "loss": 0.5815,
17
+ "num_input_tokens_seen": 6936832,
18
+ "step": 4,
19
+ "train_runtime": 594.7401,
20
+ "train_tokens_per_second": 11663.637
21
+ },
22
+ {
23
+ "epoch": 0.004076952478022678,
24
+ "grad_norm": 0.6182898594326122,
25
+ "learning_rate": 2.698559515983203e-06,
26
+ "loss": 0.5691,
27
+ "num_input_tokens_seen": 14270848,
28
+ "step": 8,
29
+ "train_runtime": 1203.7054,
30
+ "train_tokens_per_second": 11855.764
31
+ },
32
+ {
33
+ "epoch": 0.006115428717034017,
34
+ "grad_norm": 0.6559666459303339,
35
+ "learning_rate": 2.696443816026242e-06,
36
+ "loss": 0.5597,
37
+ "num_input_tokens_seen": 21129216,
38
+ "step": 12,
39
+ "train_runtime": 1762.6999,
40
+ "train_tokens_per_second": 11986.848
41
+ },
42
+ {
43
+ "epoch": 0.008153904956045356,
44
+ "grad_norm": 0.6460312307750392,
45
+ "learning_rate": 2.693389757477617e-06,
46
+ "loss": 0.564,
47
+ "num_input_tokens_seen": 28254528,
48
+ "step": 16,
49
+ "train_runtime": 2338.7069,
50
+ "train_tokens_per_second": 12081.261
51
+ },
52
+ {
53
+ "epoch": 0.010192381195056695,
54
+ "grad_norm": 0.7820470969086647,
55
+ "learning_rate": 2.689399468760395e-06,
56
+ "loss": 0.5386,
57
+ "num_input_tokens_seen": 35623168,
58
+ "step": 20,
59
+ "train_runtime": 2958.6163,
60
+ "train_tokens_per_second": 12040.482
61
+ },
62
+ {
63
+ "epoch": 0.012230857434068034,
64
+ "grad_norm": 0.7662986210694266,
65
+ "learning_rate": 2.6844757307716743e-06,
66
+ "loss": 0.5589,
67
+ "num_input_tokens_seen": 42908288,
68
+ "step": 24,
69
+ "train_runtime": 3591.5632,
70
+ "train_tokens_per_second": 11946.967
71
+ },
72
+ {
73
+ "epoch": 0.014269333673079374,
74
+ "grad_norm": 0.7264783091425356,
75
+ "learning_rate": 2.678621974944531e-06,
76
+ "loss": 0.5349,
77
+ "num_input_tokens_seen": 49922816,
78
+ "step": 28,
79
+ "train_runtime": 4214.8304,
80
+ "train_tokens_per_second": 11844.561
81
+ },
82
+ {
83
+ "epoch": 0.01630780991209071,
84
+ "grad_norm": 0.7961355791031945,
85
+ "learning_rate": 2.6718422808565973e-06,
86
+ "loss": 0.5432,
87
+ "num_input_tokens_seen": 56972736,
88
+ "step": 32,
89
+ "train_runtime": 4806.2524,
90
+ "train_tokens_per_second": 11853.879
91
+ },
92
+ {
93
+ "epoch": 0.01834628615110205,
94
+ "grad_norm": 0.8138139768273569,
95
+ "learning_rate": 2.6641413733869353e-06,
96
+ "loss": 0.538,
97
+ "num_input_tokens_seen": 64012032,
98
+ "step": 36,
99
+ "train_runtime": 5375.3791,
100
+ "train_tokens_per_second": 11908.375
101
+ },
102
+ {
103
+ "epoch": 0.02038476239011339,
104
+ "grad_norm": 0.7766770677480328,
105
+ "learning_rate": 2.6555246194231957e-06,
106
+ "loss": 0.5368,
107
+ "num_input_tokens_seen": 71145984,
108
+ "step": 40,
109
+ "train_runtime": 5983.1229,
110
+ "train_tokens_per_second": 11891.112
111
+ },
112
+ {
113
+ "epoch": 0.02242323862912473,
114
+ "grad_norm": 0.786674093556373,
115
+ "learning_rate": 2.6459980241213444e-06,
116
+ "loss": 0.5267,
117
+ "num_input_tokens_seen": 78403392,
118
+ "step": 44,
119
+ "train_runtime": 6587.3777,
120
+ "train_tokens_per_second": 11902.064
121
+ },
122
+ {
123
+ "epoch": 0.02446171486813607,
124
+ "grad_norm": 0.895151868173495,
125
+ "learning_rate": 2.6355682267205705e-06,
126
+ "loss": 0.5334,
127
+ "num_input_tokens_seen": 85316672,
128
+ "step": 48,
129
+ "train_runtime": 7184.1032,
130
+ "train_tokens_per_second": 11875.758
131
+ },
132
+ {
133
+ "epoch": 0.02650019110714741,
134
+ "grad_norm": 0.7705686339787958,
135
+ "learning_rate": 2.6242424959162964e-06,
136
+ "loss": 0.531,
137
+ "num_input_tokens_seen": 92412736,
138
+ "step": 52,
139
+ "train_runtime": 7797.6138,
140
+ "train_tokens_per_second": 11851.412
141
+ },
142
+ {
143
+ "epoch": 0.028538667346158748,
144
+ "grad_norm": 0.819091795569789,
145
+ "learning_rate": 2.612028724794501e-06,
146
+ "loss": 0.5213,
147
+ "num_input_tokens_seen": 99543616,
148
+ "step": 56,
149
+ "train_runtime": 8349.8154,
150
+ "train_tokens_per_second": 11921.655
151
+ },
152
+ {
153
+ "epoch": 0.030577143585170087,
154
+ "grad_norm": 0.8450961282572036,
155
+ "learning_rate": 2.598935425330904e-06,
156
+ "loss": 0.5254,
157
+ "num_input_tokens_seen": 106489728,
158
+ "step": 60,
159
+ "train_runtime": 8960.4265,
160
+ "train_tokens_per_second": 11884.449
161
+ },
162
+ {
163
+ "epoch": 0.03261561982418142,
164
+ "grad_norm": 0.9361937413311264,
165
+ "learning_rate": 2.5849717224588284e-06,
166
+ "loss": 0.5376,
167
+ "num_input_tokens_seen": 113524032,
168
+ "step": 64,
169
+ "train_runtime": 9543.0991,
170
+ "train_tokens_per_second": 11895.929
171
+ },
172
+ {
173
+ "epoch": 0.034654096063192766,
174
+ "grad_norm": 0.8847320129841505,
175
+ "learning_rate": 2.5701473477098874e-06,
176
+ "loss": 0.5651,
177
+ "num_input_tokens_seen": 120475456,
178
+ "step": 68,
179
+ "train_runtime": 10086.9254,
180
+ "train_tokens_per_second": 11943.724
181
+ },
182
+ {
183
+ "epoch": 0.0366925723022041,
184
+ "grad_norm": 0.8777390400419234,
185
+ "learning_rate": 2.5544726324319225e-06,
186
+ "loss": 0.5692,
187
+ "num_input_tokens_seen": 127670080,
188
+ "step": 72,
189
+ "train_runtime": 10665.8117,
190
+ "train_tokens_per_second": 11970.029
191
+ },
192
+ {
193
+ "epoch": 0.038731048541215445,
194
+ "grad_norm": 0.9576210756092853,
195
+ "learning_rate": 2.5379585005889178e-06,
196
+ "loss": 0.5625,
197
+ "num_input_tokens_seen": 134768512,
198
+ "step": 76,
199
+ "train_runtime": 11283.1943,
200
+ "train_tokens_per_second": 11944.181
201
+ },
202
+ {
203
+ "epoch": 0.04076952478022678,
204
+ "grad_norm": 0.8753248708570508,
205
+ "learning_rate": 2.5206164611479122e-06,
206
+ "loss": 0.5805,
207
+ "num_input_tokens_seen": 141573760,
208
+ "step": 80,
209
+ "train_runtime": 11827.0251,
210
+ "train_tokens_per_second": 11970.361
211
+ },
212
+ {
213
+ "epoch": 0.042808001019238116,
214
+ "grad_norm": 0.8684000412026938,
215
+ "learning_rate": 2.502458600058214e-06,
216
+ "loss": 0.5426,
217
+ "num_input_tokens_seen": 148565440,
218
+ "step": 84,
219
+ "train_runtime": 12416.0172,
220
+ "train_tokens_per_second": 11965.628
221
+ },
222
+ {
223
+ "epoch": 0.04484647725824946,
224
+ "grad_norm": 0.7849759417456085,
225
+ "learning_rate": 2.4834975718285047e-06,
226
+ "loss": 0.5676,
227
+ "num_input_tokens_seen": 155693632,
228
+ "step": 88,
229
+ "train_runtime": 13027.3428,
230
+ "train_tokens_per_second": 11951.296
231
+ },
232
+ {
233
+ "epoch": 0.046884953497260795,
234
+ "grad_norm": 0.8527233643540989,
235
+ "learning_rate": 2.463746590707708e-06,
236
+ "loss": 0.5706,
237
+ "num_input_tokens_seen": 162884544,
238
+ "step": 92,
239
+ "train_runtime": 13621.8968,
240
+ "train_tokens_per_second": 11957.552
241
+ },
242
+ {
243
+ "epoch": 0.04892342973627214,
244
+ "grad_norm": 0.8245948514984758,
245
+ "learning_rate": 2.4432194214757634e-06,
246
+ "loss": 0.5601,
247
+ "num_input_tokens_seen": 169884480,
248
+ "step": 96,
249
+ "train_runtime": 14201.6379,
250
+ "train_tokens_per_second": 11962.316
251
+ },
252
+ {
253
+ "epoch": 0.050961905975283474,
254
+ "grad_norm": 0.9463896487710859,
255
+ "learning_rate": 2.4219303698507273e-06,
256
+ "loss": 0.578,
257
+ "num_input_tokens_seen": 177144768,
258
+ "step": 100,
259
+ "train_runtime": 14812.6402,
260
+ "train_tokens_per_second": 11959.027
261
+ },
262
+ {
263
+ "epoch": 0.05300038221429482,
264
+ "grad_norm": 0.8528440593847427,
265
+ "learning_rate": 2.399894272518887e-06,
266
+ "loss": 0.5695,
267
+ "num_input_tokens_seen": 184355904,
268
+ "step": 104,
269
+ "train_runtime": 15392.8793,
270
+ "train_tokens_per_second": 11976.7
271
+ },
272
+ {
273
+ "epoch": 0.05503885845330615,
274
+ "grad_norm": 0.8983751041750461,
275
+ "learning_rate": 2.3771264867948297e-06,
276
+ "loss": 0.5643,
277
+ "num_input_tokens_seen": 191461120,
278
+ "step": 108,
279
+ "train_runtime": 15962.3103,
280
+ "train_tokens_per_second": 11994.574
281
+ },
282
+ {
283
+ "epoch": 0.057077334692317495,
284
+ "grad_norm": 0.9738501561599475,
285
+ "learning_rate": 2.353642879918684e-06,
286
+ "loss": 0.5611,
287
+ "num_input_tokens_seen": 198512640,
288
+ "step": 112,
289
+ "train_runtime": 16542.875,
290
+ "train_tokens_per_second": 11999.888
291
+ },
292
+ {
293
+ "epoch": 0.05911581093132883,
294
+ "grad_norm": 0.9069372359842974,
295
+ "learning_rate": 2.329459817997979e-06,
296
+ "loss": 0.555,
297
+ "num_input_tokens_seen": 205184640,
298
+ "step": 116,
299
+ "train_runtime": 17132.5621,
300
+ "train_tokens_per_second": 11976.296
301
+ },
302
+ {
303
+ "epoch": 0.061154287170340174,
304
+ "grad_norm": 0.8535229191703974,
305
+ "learning_rate": 2.304594154601839e-06,
306
+ "loss": 0.5802,
307
+ "num_input_tokens_seen": 212192768,
308
+ "step": 120,
309
+ "train_runtime": 17695.1167,
310
+ "train_tokens_per_second": 11991.6
311
+ },
312
+ {
313
+ "epoch": 0.06319276340935151,
314
+ "grad_norm": 0.9235254276307827,
315
+ "learning_rate": 2.2790632190154588e-06,
316
+ "loss": 0.5602,
317
+ "num_input_tokens_seen": 219343424,
318
+ "step": 124,
319
+ "train_runtime": 18276.554,
320
+ "train_tokens_per_second": 12001.356
321
+ },
322
+ {
323
+ "epoch": 0.06523123964836285,
324
+ "grad_norm": 0.8469907739766386,
325
+ "learning_rate": 2.2528848041630394e-06,
326
+ "loss": 0.5726,
327
+ "num_input_tokens_seen": 226825024,
328
+ "step": 128,
329
+ "train_runtime": 18867.9805,
330
+ "train_tokens_per_second": 12021.691
331
+ },
332
+ {
333
+ "epoch": 0.06726971588737418,
334
+ "grad_norm": 0.863302212361952,
335
+ "learning_rate": 2.226077154207613e-06,
336
+ "loss": 0.5458,
337
+ "num_input_tokens_seen": 233873600,
338
+ "step": 132,
339
+ "train_runtime": 19428.0179,
340
+ "train_tokens_per_second": 12037.955
341
+ },
342
+ {
343
+ "epoch": 0.06930819212638553,
344
+ "grad_norm": 0.890826252542842,
345
+ "learning_rate": 2.1986589518363884e-06,
346
+ "loss": 0.5683,
347
+ "num_input_tokens_seen": 241046016,
348
+ "step": 136,
349
+ "train_runtime": 20027.9177,
350
+ "train_tokens_per_second": 12035.501
351
+ },
352
+ {
353
+ "epoch": 0.07134666836539687,
354
+ "grad_norm": 0.8897818157637029,
355
+ "learning_rate": 2.17064930524048e-06,
356
+ "loss": 0.5753,
357
+ "num_input_tokens_seen": 248445952,
358
+ "step": 140,
359
+ "train_runtime": 20655.1895,
360
+ "train_tokens_per_second": 12028.258
361
+ },
362
+ {
363
+ "epoch": 0.0733851446044082,
364
+ "grad_norm": 0.7970770860102688,
365
+ "learning_rate": 2.1420677347981022e-06,
366
+ "loss": 0.5492,
367
+ "num_input_tokens_seen": 255691072,
368
+ "step": 144,
369
+ "train_runtime": 21246.8799,
370
+ "train_tokens_per_second": 12034.288
371
+ },
372
+ {
373
+ "epoch": 0.07542362084341954,
374
+ "grad_norm": 1.114229924043429,
375
+ "learning_rate": 2.112934159470499e-06,
376
+ "loss": 0.5696,
377
+ "num_input_tokens_seen": 263081280,
378
+ "step": 148,
379
+ "train_runtime": 21841.1341,
380
+ "train_tokens_per_second": 12045.221
381
+ },
382
+ {
383
+ "epoch": 0.07746209708243089,
384
+ "grad_norm": 0.8591461034263972,
385
+ "learning_rate": 2.083268882920095e-06,
386
+ "loss": 0.5765,
387
+ "num_input_tokens_seen": 270227584,
388
+ "step": 152,
389
+ "train_runtime": 22468.8462,
390
+ "train_tokens_per_second": 12026.767
391
+ },
392
+ {
393
+ "epoch": 0.07950057332144222,
394
+ "grad_norm": 0.8676767698372961,
395
+ "learning_rate": 2.053092579360543e-06,
396
+ "loss": 0.5706,
397
+ "num_input_tokens_seen": 277353664,
398
+ "step": 156,
399
+ "train_runtime": 23053.2043,
400
+ "train_tokens_per_second": 12031.024
401
+ },
402
+ {
403
+ "epoch": 0.08153904956045356,
404
+ "grad_norm": 0.9224293367262005,
405
+ "learning_rate": 2.0224262791485315e-06,
406
+ "loss": 0.5608,
407
+ "num_input_tokens_seen": 284646784,
408
+ "step": 160,
409
+ "train_runtime": 23643.9972,
410
+ "train_tokens_per_second": 12038.86
411
+ },
412
+ {
413
+ "epoch": 0.0835775257994649,
414
+ "grad_norm": 0.887751023260673,
415
+ "learning_rate": 1.991291354127381e-06,
416
+ "loss": 0.5636,
417
+ "num_input_tokens_seen": 291840192,
418
+ "step": 164,
419
+ "train_runtime": 24251.2033,
420
+ "train_tokens_per_second": 12034.05
421
+ },
422
+ {
423
+ "epoch": 0.08561600203847623,
424
+ "grad_norm": 0.8971166373496055,
425
+ "learning_rate": 1.959709502732666e-06,
426
+ "loss": 0.5624,
427
+ "num_input_tokens_seen": 298899456,
428
+ "step": 168,
429
+ "train_runtime": 24847.2173,
430
+ "train_tokens_per_second": 12029.494
431
+ },
432
+ {
433
+ "epoch": 0.08765447827748758,
434
+ "grad_norm": 0.884570439459004,
435
+ "learning_rate": 1.927702734870216e-06,
436
+ "loss": 0.5802,
437
+ "num_input_tokens_seen": 305987520,
438
+ "step": 172,
439
+ "train_runtime": 25438.1181,
440
+ "train_tokens_per_second": 12028.701
441
+ },
442
+ {
443
+ "epoch": 0.08969295451649892,
444
+ "grad_norm": 0.7905104567457971,
445
+ "learning_rate": 1.895293356577058e-06,
446
+ "loss": 0.5557,
447
+ "num_input_tokens_seen": 312989312,
448
+ "step": 176,
449
+ "train_runtime": 26002.8183,
450
+ "train_tokens_per_second": 12036.746
451
+ },
452
+ {
453
+ "epoch": 0.09173143075551025,
454
+ "grad_norm": 0.9424718927507695,
455
+ "learning_rate": 1.8625039544759767e-06,
456
+ "loss": 0.5663,
457
+ "num_input_tokens_seen": 320097152,
458
+ "step": 180,
459
+ "train_runtime": 26586.1368,
460
+ "train_tokens_per_second": 12040.002
461
+ },
462
+ {
463
+ "epoch": 0.09376990699452159,
464
+ "grad_norm": 0.8615504446489718,
465
+ "learning_rate": 1.8293573800345261e-06,
466
+ "loss": 0.5729,
467
+ "num_input_tokens_seen": 327245696,
468
+ "step": 184,
469
+ "train_runtime": 27215.267,
470
+ "train_tokens_per_second": 12024.343
471
+ },
472
+ {
473
+ "epoch": 0.09580838323353294,
474
+ "grad_norm": 0.9699743298030914,
475
+ "learning_rate": 1.7958767336394758e-06,
476
+ "loss": 0.5737,
477
+ "num_input_tokens_seen": 334634880,
478
+ "step": 188,
479
+ "train_runtime": 27830.7489,
480
+ "train_tokens_per_second": 12023.927
481
+ },
482
+ {
483
+ "epoch": 0.09784685947254428,
484
+ "grad_norm": 0.8699479610963319,
485
+ "learning_rate": 1.7620853484977693e-06,
486
+ "loss": 0.5578,
487
+ "num_input_tokens_seen": 341804032,
488
+ "step": 192,
489
+ "train_runtime": 28418.8119,
490
+ "train_tokens_per_second": 12027.386
491
+ },
492
+ {
493
+ "epoch": 0.09988533571155561,
494
+ "grad_norm": 0.9257049516328657,
495
+ "learning_rate": 1.7280067743752384e-06,
496
+ "loss": 0.5521,
497
+ "num_input_tokens_seen": 348671424,
498
+ "step": 196,
499
+ "train_runtime": 29007.5671,
500
+ "train_tokens_per_second": 12020.016
501
+ },
502
+ {
503
+ "epoch": 0.10192381195056695,
504
+ "grad_norm": 0.9131171296688921,
505
+ "learning_rate": 1.6936647611843846e-06,
506
+ "loss": 0.5682,
507
+ "num_input_tokens_seen": 355675520,
508
+ "step": 200,
509
+ "train_runtime": 29580.1297,
510
+ "train_tokens_per_second": 12024.137
511
+ },
512
+ {
513
+ "epoch": 0.10396228818957828,
514
+ "grad_norm": 0.8769808506815606,
515
+ "learning_rate": 1.659083242432681e-06,
516
+ "loss": 0.5584,
517
+ "num_input_tokens_seen": 362651648,
518
+ "step": 204,
519
+ "train_runtime": 30152.9255,
520
+ "train_tokens_per_second": 12027.08
521
+ },
522
+ {
523
+ "epoch": 0.10600076442858963,
524
+ "grad_norm": 0.9497619416730099,
525
+ "learning_rate": 1.6242863185429212e-06,
526
+ "loss": 0.5879,
527
+ "num_input_tokens_seen": 369726720,
528
+ "step": 208,
529
+ "train_runtime": 30751.1104,
530
+ "train_tokens_per_second": 12023.199
531
+ },
532
+ {
533
+ "epoch": 0.10803924066760097,
534
+ "grad_norm": 0.9230137333974207,
535
+ "learning_rate": 1.5892982400572422e-06,
536
+ "loss": 0.5681,
537
+ "num_input_tokens_seen": 376862016,
538
+ "step": 212,
539
+ "train_runtime": 31362.1922,
540
+ "train_tokens_per_second": 12016.444
541
+ },
542
+ {
543
+ "epoch": 0.1100777169066123,
544
+ "grad_norm": 0.8995334199668418,
545
+ "learning_rate": 1.5541433907365264e-06,
546
+ "loss": 0.5455,
547
+ "num_input_tokens_seen": 383921152,
548
+ "step": 216,
549
+ "train_runtime": 31914.7502,
550
+ "train_tokens_per_second": 12029.583
551
+ },
552
+ {
553
+ "epoch": 0.11211619314562364,
554
+ "grad_norm": 0.9043735392416916,
555
+ "learning_rate": 1.5188462705669648e-06,
556
+ "loss": 0.5641,
557
+ "num_input_tokens_seen": 390988416,
558
+ "step": 220,
559
+ "train_runtime": 32509.882,
560
+ "train_tokens_per_second": 12026.756
561
+ },
562
+ {
563
+ "epoch": 0.11415466938463499,
564
+ "grad_norm": 0.9729636398442392,
565
+ "learning_rate": 1.4834314786856161e-06,
566
+ "loss": 0.5607,
567
+ "num_input_tokens_seen": 398152576,
568
+ "step": 224,
569
+ "train_runtime": 33085.7673,
570
+ "train_tokens_per_second": 12033.953
571
+ },
572
+ {
573
+ "epoch": 0.11619314562364633,
574
+ "grad_norm": 0.9539597912248131,
575
+ "learning_rate": 1.4479236962368684e-06,
576
+ "loss": 0.5589,
577
+ "num_input_tokens_seen": 405173888,
578
+ "step": 228,
579
+ "train_runtime": 33682.3182,
580
+ "train_tokens_per_second": 12029.276
581
+ },
582
+ {
583
+ "epoch": 0.11823162186265766,
584
+ "grad_norm": 0.8598081231037438,
585
+ "learning_rate": 1.4123476691717487e-06,
586
+ "loss": 0.5518,
587
+ "num_input_tokens_seen": 412070528,
588
+ "step": 232,
589
+ "train_runtime": 34252.7917,
590
+ "train_tokens_per_second": 12030.276
591
+ },
592
+ {
593
+ "epoch": 0.120270098101669,
594
+ "grad_norm": 0.8860637699401077,
595
+ "learning_rate": 1.376728191002066e-06,
596
+ "loss": 0.558,
597
+ "num_input_tokens_seen": 419423744,
598
+ "step": 236,
599
+ "train_runtime": 34844.2912,
600
+ "train_tokens_per_second": 12037.086
601
+ },
602
+ {
603
+ "epoch": 0.12128933622117467,
604
+ "eval_loss": 0.7941220998764038,
605
+ "eval_runtime": 213.2901,
606
+ "eval_samples_per_second": 4.717,
607
+ "eval_steps_per_second": 0.075,
608
+ "num_input_tokens_seen": 422911872,
609
+ "step": 238
610
+ },
611
+ {
612
+ "epoch": 0.12230857434068035,
613
+ "grad_norm": 0.9547518291189157,
614
+ "learning_rate": 1.3410900855214124e-06,
615
+ "loss": 0.5732,
616
+ "num_input_tokens_seen": 426493248,
617
+ "step": 240,
618
+ "train_runtime": 35670.5805,
619
+ "train_tokens_per_second": 11956.443
620
+ },
621
+ {
622
+ "epoch": 0.12434705057969168,
623
+ "grad_norm": 0.8725219735566059,
624
+ "learning_rate": 1.305458189505055e-06,
625
+ "loss": 0.5605,
626
+ "num_input_tokens_seen": 433674688,
627
+ "step": 244,
628
+ "train_runtime": 36270.2542,
629
+ "train_tokens_per_second": 11956.759
630
+ },
631
+ {
632
+ "epoch": 0.12638552681870302,
633
+ "grad_norm": 0.9381950485311329,
634
+ "learning_rate": 1.269857335400783e-06,
635
+ "loss": 0.5758,
636
+ "num_input_tokens_seen": 441063552,
637
+ "step": 248,
638
+ "train_runtime": 36895.0601,
639
+ "train_tokens_per_second": 11954.542
640
+ },
641
+ {
642
+ "epoch": 0.12842400305771437,
643
+ "grad_norm": 0.8095871776257958,
644
+ "learning_rate": 1.2343123340227753e-06,
645
+ "loss": 0.5682,
646
+ "num_input_tokens_seen": 448549632,
647
+ "step": 252,
648
+ "train_runtime": 37565.6709,
649
+ "train_tokens_per_second": 11940.413
650
+ },
651
+ {
652
+ "epoch": 0.1304624792967257,
653
+ "grad_norm": 0.8656130470620739,
654
+ "learning_rate": 1.1988479572605345e-06,
655
+ "loss": 0.5545,
656
+ "num_input_tokens_seen": 455502912,
657
+ "step": 256,
658
+ "train_runtime": 38151.4724,
659
+ "train_tokens_per_second": 11939.327
660
+ },
661
+ {
662
+ "epoch": 0.13250095553573704,
663
+ "grad_norm": 0.9346351864084386,
664
+ "learning_rate": 1.1634889208149594e-06,
665
+ "loss": 0.5664,
666
+ "num_input_tokens_seen": 462435200,
667
+ "step": 260,
668
+ "train_runtime": 38714.2142,
669
+ "train_tokens_per_second": 11944.843
670
+ },
671
+ {
672
+ "epoch": 0.13453943177474836,
673
+ "grad_norm": 0.899249765870996,
674
+ "learning_rate": 1.1282598669735671e-06,
675
+ "loss": 0.558,
676
+ "num_input_tokens_seen": 469336640,
677
+ "step": 264,
678
+ "train_runtime": 39254.3889,
679
+ "train_tokens_per_second": 11956.284
680
+ },
681
+ {
682
+ "epoch": 0.1365779080137597,
683
+ "grad_norm": 0.8458171655451426,
684
+ "learning_rate": 1.093185347436887e-06,
685
+ "loss": 0.5538,
686
+ "num_input_tokens_seen": 476310656,
687
+ "step": 268,
688
+ "train_runtime": 39827.3684,
689
+ "train_tokens_per_second": 11959.381
690
+ },
691
+ {
692
+ "epoch": 0.13861638425277106,
693
+ "grad_norm": 0.9179027627040293,
694
+ "learning_rate": 1.058289806207975e-06,
695
+ "loss": 0.5698,
696
+ "num_input_tokens_seen": 483771840,
697
+ "step": 272,
698
+ "train_runtime": 40459.3108,
699
+ "train_tokens_per_second": 11956.997
700
+ },
701
+ {
702
+ "epoch": 0.14065486049178239,
703
+ "grad_norm": 0.9442703488926768,
704
+ "learning_rate": 1.0235975625569967e-06,
705
+ "loss": 0.5649,
706
+ "num_input_tokens_seen": 490750336,
707
+ "step": 276,
708
+ "train_runtime": 41048.4541,
709
+ "train_tokens_per_second": 11955.391
710
+ },
711
+ {
712
+ "epoch": 0.14269333673079374,
713
+ "grad_norm": 0.8974082301624304,
714
+ "learning_rate": 9.891327940727266e-07,
715
+ "loss": 0.5657,
716
+ "num_input_tokens_seen": 497702912,
717
+ "step": 280,
718
+ "train_runtime": 41610.7519,
719
+ "train_tokens_per_second": 11960.921
720
+ },
721
+ {
722
+ "epoch": 0.14473181296980506,
723
+ "grad_norm": 0.9898213671868435,
724
+ "learning_rate": 9.549195198127994e-07,
725
+ "loss": 0.58,
726
+ "num_input_tokens_seen": 505099584,
727
+ "step": 284,
728
+ "train_runtime": 42219.4154,
729
+ "train_tokens_per_second": 11963.68
730
+ },
731
+ {
732
+ "epoch": 0.1467702892088164,
733
+ "grad_norm": 0.9363039019647847,
734
+ "learning_rate": 9.209815835644328e-07,
735
+ "loss": 0.5512,
736
+ "num_input_tokens_seen": 512152896,
737
+ "step": 288,
738
+ "train_runtime": 42766.508,
739
+ "train_tokens_per_second": 11975.56
740
+ },
741
+ {
742
+ "epoch": 0.14880876544782776,
743
+ "grad_norm": 0.9589553041250718,
744
+ "learning_rate": 8.873426372273072e-07,
745
+ "loss": 0.5747,
746
+ "num_input_tokens_seen": 519187584,
747
+ "step": 292,
748
+ "train_runtime": 43380.0418,
749
+ "train_tokens_per_second": 11968.351
750
+ },
751
+ {
752
+ "epoch": 0.15084724168683908,
753
+ "grad_norm": 0.9433972448251747,
754
+ "learning_rate": 8.540261243301721e-07,
755
+ "loss": 0.5509,
756
+ "num_input_tokens_seen": 526140736,
757
+ "step": 296,
758
+ "train_runtime": 43995.5053,
759
+ "train_tokens_per_second": 11958.966
760
+ },
761
+ {
762
+ "epoch": 0.15288571792585043,
763
+ "grad_norm": 0.9393953597111547,
764
+ "learning_rate": 8.210552636926686e-07,
765
+ "loss": 0.5629,
766
+ "num_input_tokens_seen": 532992384,
767
+ "step": 300,
768
+ "train_runtime": 44595.3555,
769
+ "train_tokens_per_second": 11951.746
770
+ },
771
+ {
772
+ "epoch": 0.15492419416486178,
773
+ "grad_norm": 0.9091057919029727,
774
+ "learning_rate": 7.884530332437565e-07,
775
+ "loss": 0.5663,
776
+ "num_input_tokens_seen": 540379392,
777
+ "step": 304,
778
+ "train_runtime": 45193.3818,
779
+ "train_tokens_per_second": 11957.047
780
+ },
781
+ {
782
+ "epoch": 0.1569626704038731,
783
+ "grad_norm": 0.8832084768576383,
784
+ "learning_rate": 7.562421540080231e-07,
785
+ "loss": 0.5613,
786
+ "num_input_tokens_seen": 547461440,
787
+ "step": 308,
788
+ "train_runtime": 45756.6672,
789
+ "train_tokens_per_second": 11964.627
790
+ },
791
+ {
792
+ "epoch": 0.15900114664288445,
793
+ "grad_norm": 0.8587618292954599,
794
+ "learning_rate": 7.244450742710321e-07,
795
+ "loss": 0.561,
796
+ "num_input_tokens_seen": 554617984,
797
+ "step": 312,
798
+ "train_runtime": 46381.4062,
799
+ "train_tokens_per_second": 11957.766
800
+ },
801
+ {
802
+ "epoch": 0.16103962288189577,
803
+ "grad_norm": 0.9446856546867352,
804
+ "learning_rate": 6.930839539347442e-07,
805
+ "loss": 0.5532,
806
+ "num_input_tokens_seen": 561693888,
807
+ "step": 316,
808
+ "train_runtime": 46994.8669,
809
+ "train_tokens_per_second": 11952.239
810
+ },
811
+ {
812
+ "epoch": 0.16307809912090712,
813
+ "grad_norm": 0.9429683753374553,
814
+ "learning_rate": 6.621806490739267e-07,
815
+ "loss": 0.5595,
816
+ "num_input_tokens_seen": 568833664,
817
+ "step": 320,
818
+ "train_runtime": 47586.3302,
819
+ "train_tokens_per_second": 11953.72
820
+ },
821
+ {
822
+ "epoch": 0.16511657535991847,
823
+ "grad_norm": 0.9035859891449433,
824
+ "learning_rate": 6.317566967042958e-07,
825
+ "loss": 0.5504,
826
+ "num_input_tokens_seen": 576161408,
827
+ "step": 324,
828
+ "train_runtime": 48187.0813,
829
+ "train_tokens_per_second": 11956.761
830
+ },
831
+ {
832
+ "epoch": 0.1671550515989298,
833
+ "grad_norm": 0.9033151093018099,
834
+ "learning_rate": 6.018332997730213e-07,
835
+ "loss": 0.5605,
836
+ "num_input_tokens_seen": 583395328,
837
+ "step": 328,
838
+ "train_runtime": 48788.5572,
839
+ "train_tokens_per_second": 11957.626
840
+ },
841
+ {
842
+ "epoch": 0.16919352783794114,
843
+ "grad_norm": 0.9609542284697502,
844
+ "learning_rate": 5.724313123820482e-07,
845
+ "loss": 0.5557,
846
+ "num_input_tokens_seen": 590636544,
847
+ "step": 332,
848
+ "train_runtime": 49400.1577,
849
+ "train_tokens_per_second": 11956.167
850
+ },
851
+ {
852
+ "epoch": 0.17123200407695247,
853
+ "grad_norm": 0.8861118611359287,
854
+ "learning_rate": 5.435712252545331e-07,
855
+ "loss": 0.5608,
856
+ "num_input_tokens_seen": 597723776,
857
+ "step": 336,
858
+ "train_runtime": 50003.6729,
859
+ "train_tokens_per_second": 11953.597
860
+ },
861
+ {
862
+ "epoch": 0.17327048031596382,
863
+ "grad_norm": 0.9761110376120566,
864
+ "learning_rate": 5.152731514545266e-07,
865
+ "loss": 0.5478,
866
+ "num_input_tokens_seen": 604770752,
867
+ "step": 340,
868
+ "train_runtime": 50553.9712,
869
+ "train_tokens_per_second": 11962.873
870
+ },
871
+ {
872
+ "epoch": 0.17530895655497516,
873
+ "grad_norm": 0.9053070583607986,
874
+ "learning_rate": 4.875568123698525e-07,
875
+ "loss": 0.55,
876
+ "num_input_tokens_seen": 612028800,
877
+ "step": 344,
878
+ "train_runtime": 51128.5271,
879
+ "train_tokens_per_second": 11970.398
880
+ },
881
+ {
882
+ "epoch": 0.1773474327939865,
883
+ "grad_norm": 0.901496752129611,
884
+ "learning_rate": 4.604415239679492e-07,
885
+ "loss": 0.5682,
886
+ "num_input_tokens_seen": 619137792,
887
+ "step": 348,
888
+ "train_runtime": 51752.3485,
889
+ "train_tokens_per_second": 11963.472
890
+ },
891
+ {
892
+ "epoch": 0.17938590903299784,
893
+ "grad_norm": 0.9438945381441597,
894
+ "learning_rate": 4.3394618333426135e-07,
895
+ "loss": 0.5652,
896
+ "num_input_tokens_seen": 625854848,
897
+ "step": 352,
898
+ "train_runtime": 52310.1207,
899
+ "train_tokens_per_second": 11964.317
900
+ },
901
+ {
902
+ "epoch": 0.1814243852720092,
903
+ "grad_norm": 0.9543610627021044,
904
+ "learning_rate": 4.080892555025522e-07,
905
+ "loss": 0.5581,
906
+ "num_input_tokens_seen": 632626752,
907
+ "step": 356,
908
+ "train_runtime": 52857.0375,
909
+ "train_tokens_per_second": 11968.638
910
+ },
911
+ {
912
+ "epoch": 0.1834628615110205,
913
+ "grad_norm": 0.9118473255578559,
914
+ "learning_rate": 3.8288876058632056e-07,
915
+ "loss": 0.56,
916
+ "num_input_tokens_seen": 639638080,
917
+ "step": 360,
918
+ "train_runtime": 53443.4994,
919
+ "train_tokens_per_second": 11968.492
920
+ },
921
+ {
922
+ "epoch": 0.18550133775003186,
923
+ "grad_norm": 0.9212497452458377,
924
+ "learning_rate": 3.5836226122029165e-07,
925
+ "loss": 0.557,
926
+ "num_input_tokens_seen": 646705152,
927
+ "step": 364,
928
+ "train_runtime": 54052.7201,
929
+ "train_tokens_per_second": 11964.341
930
+ },
931
+ {
932
+ "epoch": 0.18753981398904318,
933
+ "grad_norm": 0.9056019341991234,
934
+ "learning_rate": 3.34526850320731e-07,
935
+ "loss": 0.5602,
936
+ "num_input_tokens_seen": 653674880,
937
+ "step": 368,
938
+ "train_runtime": 54641.6155,
939
+ "train_tokens_per_second": 11962.949
940
+ },
941
+ {
942
+ "epoch": 0.18957829022805453,
943
+ "grad_norm": 1.0036743775927282,
944
+ "learning_rate": 3.1139913917311347e-07,
945
+ "loss": 0.5787,
946
+ "num_input_tokens_seen": 660674240,
947
+ "step": 372,
948
+ "train_runtime": 55222.9846,
949
+ "train_tokens_per_second": 11963.755
950
+ },
951
+ {
952
+ "epoch": 0.19161676646706588,
953
+ "grad_norm": 0.9225731699510716,
954
+ "learning_rate": 2.889952458554475e-07,
955
+ "loss": 0.5515,
956
+ "num_input_tokens_seen": 667601792,
957
+ "step": 376,
958
+ "train_runtime": 55825.7562,
959
+ "train_tokens_per_second": 11958.67
960
+ },
961
+ {
962
+ "epoch": 0.1936552427060772,
963
+ "grad_norm": 0.9067845518246624,
964
+ "learning_rate": 2.6733078400532475e-07,
965
+ "loss": 0.5621,
966
+ "num_input_tokens_seen": 674622976,
967
+ "step": 380,
968
+ "train_runtime": 56384.2096,
969
+ "train_tokens_per_second": 11964.75
970
+ },
971
+ {
972
+ "epoch": 0.19569371894508855,
973
+ "grad_norm": 0.9543732534991831,
974
+ "learning_rate": 2.464208519385228e-07,
975
+ "loss": 0.5708,
976
+ "num_input_tokens_seen": 681708672,
977
+ "step": 384,
978
+ "train_runtime": 56981.2121,
979
+ "train_tokens_per_second": 11963.745
980
+ },
981
+ {
982
+ "epoch": 0.19773219518409987,
983
+ "grad_norm": 0.8996552227811947,
984
+ "learning_rate": 2.2628002212674264e-07,
985
+ "loss": 0.5671,
986
+ "num_input_tokens_seen": 689109376,
987
+ "step": 388,
988
+ "train_runtime": 57593.2165,
989
+ "train_tokens_per_second": 11965.114
990
+ },
991
+ {
992
+ "epoch": 0.19977067142311122,
993
+ "grad_norm": 0.955255917559042,
994
+ "learning_rate": 2.0692233104181644e-07,
995
+ "loss": 0.5449,
996
+ "num_input_tokens_seen": 696091456,
997
+ "step": 392,
998
+ "train_runtime": 58166.8582,
999
+ "train_tokens_per_second": 11967.149
1000
+ },
1001
+ {
1002
+ "epoch": 0.20180914766212257,
1003
+ "grad_norm": 0.9040308153396052,
1004
+ "learning_rate": 1.8836126937346177e-07,
1005
+ "loss": 0.5618,
1006
+ "num_input_tokens_seen": 703111168,
1007
+ "step": 396,
1008
+ "train_runtime": 58738.4377,
1009
+ "train_tokens_per_second": 11970.205
1010
+ },
1011
+ {
1012
+ "epoch": 0.2038476239011339,
1013
+ "grad_norm": 0.97944459658204,
1014
+ "learning_rate": 1.706097726274012e-07,
1015
+ "loss": 0.5622,
1016
+ "num_input_tokens_seen": 710207168,
1017
+ "step": 400,
1018
+ "train_runtime": 59356.9508,
1019
+ "train_tokens_per_second": 11965.021
1020
+ },
1021
+ {
1022
+ "epoch": 0.20588610014014525,
1023
+ "grad_norm": 0.9381590971188796,
1024
+ "learning_rate": 1.5368021211039678e-07,
1025
+ "loss": 0.5411,
1026
+ "num_input_tokens_seen": 717098944,
1027
+ "step": 404,
1028
+ "train_runtime": 59911.4198,
1029
+ "train_tokens_per_second": 11969.32
1030
+ },
1031
+ {
1032
+ "epoch": 0.20792457637915657,
1033
+ "grad_norm": 0.8878878520807448,
1034
+ "learning_rate": 1.3758438630848725e-07,
1035
+ "loss": 0.5585,
1036
+ "num_input_tokens_seen": 723993152,
1037
+ "step": 408,
1038
+ "train_runtime": 60475.8972,
1039
+ "train_tokens_per_second": 11971.598
1040
+ },
1041
+ {
1042
+ "epoch": 0.20996305261816792,
1043
+ "grad_norm": 0.8806187323037155,
1044
+ "learning_rate": 1.2233351266442794e-07,
1045
+ "loss": 0.5541,
1046
+ "num_input_tokens_seen": 731057472,
1047
+ "step": 412,
1048
+ "train_runtime": 61037.4217,
1049
+ "train_tokens_per_second": 11977.201
1050
+ },
1051
+ {
1052
+ "epoch": 0.21200152885717927,
1053
+ "grad_norm": 0.9150900155470338,
1054
+ "learning_rate": 1.0793821976007693e-07,
1055
+ "loss": 0.566,
1056
+ "num_input_tokens_seen": 737872960,
1057
+ "step": 416,
1058
+ "train_runtime": 61615.4698,
1059
+ "train_tokens_per_second": 11975.45
1060
+ },
1061
+ {
1062
+ "epoch": 0.2140400050961906,
1063
+ "grad_norm": 0.9022599301148059,
1064
+ "learning_rate": 9.440853990915897e-08,
1065
+ "loss": 0.5454,
1066
+ "num_input_tokens_seen": 744627648,
1067
+ "step": 420,
1068
+ "train_runtime": 62161.1667,
1069
+ "train_tokens_per_second": 11978.984
1070
+ },
1071
+ {
1072
+ "epoch": 0.21607848133520194,
1073
+ "grad_norm": 0.9035906517868586,
1074
+ "learning_rate": 8.17539021655864e-08,
1075
+ "loss": 0.5571,
1076
+ "num_input_tokens_seen": 751584960,
1077
+ "step": 424,
1078
+ "train_runtime": 62697.4235,
1079
+ "train_tokens_per_second": 11987.494
1080
+ },
1081
+ {
1082
+ "epoch": 0.2181169575742133,
1083
+ "grad_norm": 0.8993779939634194,
1084
+ "learning_rate": 6.99831257521961e-08,
1085
+ "loss": 0.5444,
1086
+ "num_input_tokens_seen": 758504960,
1087
+ "step": 428,
1088
+ "train_runtime": 63274.1778,
1089
+ "train_tokens_per_second": 11987.591
1090
+ },
1091
+ {
1092
+ "epoch": 0.2201554338132246,
1093
+ "grad_norm": 0.9210930898367543,
1094
+ "learning_rate": 5.9104413914490546e-08,
1095
+ "loss": 0.5625,
1096
+ "num_input_tokens_seen": 765707712,
1097
+ "step": 432,
1098
+ "train_runtime": 63862.7303,
1099
+ "train_tokens_per_second": 11989.899
1100
+ },
1101
+ {
1102
+ "epoch": 0.22219391005223596,
1103
+ "grad_norm": 0.9280791017512283,
1104
+ "learning_rate": 4.912534820366224e-08,
1105
+ "loss": 0.5613,
1106
+ "num_input_tokens_seen": 772952256,
1107
+ "step": 436,
1108
+ "train_runtime": 64479.6745,
1109
+ "train_tokens_per_second": 11987.533
1110
+ },
1111
+ {
1112
+ "epoch": 0.22423238629124728,
1113
+ "grad_norm": 0.907069920744252,
1114
+ "learning_rate": 4.005288319288777e-08,
1115
+ "loss": 0.566,
1116
+ "num_input_tokens_seen": 780056832,
1117
+ "step": 440,
1118
+ "train_runtime": 65078.7995,
1119
+ "train_tokens_per_second": 11986.343
1120
+ },
1121
+ {
1122
+ "epoch": 0.22627086253025863,
1123
+ "grad_norm": 0.9315099081560159,
1124
+ "learning_rate": 3.189334163057219e-08,
1125
+ "loss": 0.5666,
1126
+ "num_input_tokens_seen": 786978752,
1127
+ "step": 444,
1128
+ "train_runtime": 65667.9097,
1129
+ "train_tokens_per_second": 11984.221
1130
+ },
1131
+ {
1132
+ "epoch": 0.22830933876926998,
1133
+ "grad_norm": 0.9383224396822377,
1134
+ "learning_rate": 2.4652410033923543e-08,
1135
+ "loss": 0.5541,
1136
+ "num_input_tokens_seen": 793887616,
1137
+ "step": 448,
1138
+ "train_runtime": 66257.6668,
1139
+ "train_tokens_per_second": 11981.823
1140
+ },
1141
+ {
1142
+ "epoch": 0.2303478150082813,
1143
+ "grad_norm": 0.8944859848575912,
1144
+ "learning_rate": 1.8335134725925177e-08,
1145
+ "loss": 0.5526,
1146
+ "num_input_tokens_seen": 800645760,
1147
+ "step": 452,
1148
+ "train_runtime": 66822.0683,
1149
+ "train_tokens_per_second": 11981.757
1150
+ },
1151
+ {
1152
+ "epoch": 0.23238629124729265,
1153
+ "grad_norm": 0.9050253510819353,
1154
+ "learning_rate": 1.2945918318473138e-08,
1155
+ "loss": 0.5634,
1156
+ "num_input_tokens_seen": 807760064,
1157
+ "step": 456,
1158
+ "train_runtime": 67425.8238,
1159
+ "train_tokens_per_second": 11979.981
1160
+ },
1161
+ {
1162
+ "epoch": 0.23442476748630398,
1163
+ "grad_norm": 0.9352706962645487,
1164
+ "learning_rate": 8.488516644122484e-09,
1165
+ "loss": 0.5618,
1166
+ "num_input_tokens_seen": 814702080,
1167
+ "step": 460,
1168
+ "train_runtime": 67994.9171,
1169
+ "train_tokens_per_second": 11981.809
1170
+ },
1171
+ {
1172
+ "epoch": 0.23646324372531533,
1173
+ "grad_norm": 0.8645415996226098,
1174
+ "learning_rate": 4.966036138587982e-09,
1175
+ "loss": 0.5553,
1176
+ "num_input_tokens_seen": 821691008,
1177
+ "step": 464,
1178
+ "train_runtime": 68583.3469,
1179
+ "train_tokens_per_second": 11980.911
1180
+ },
1181
+ {
1182
+ "epoch": 0.23850171996432667,
1183
+ "grad_norm": 0.9706971370356248,
1184
+ "learning_rate": 2.380931675817649e-09,
1185
+ "loss": 0.5601,
1186
+ "num_input_tokens_seen": 828902464,
1187
+ "step": 468,
1188
+ "train_runtime": 69210.2105,
1189
+ "train_tokens_per_second": 11976.592
1190
+ },
1191
+ {
1192
+ "epoch": 0.240540196203338,
1193
+ "grad_norm": 0.9160395400629753,
1194
+ "learning_rate": 7.350048571510504e-10,
1195
+ "loss": 0.5567,
1196
+ "num_input_tokens_seen": 835703232,
1197
+ "step": 472,
1198
+ "train_runtime": 69768.608,
1199
+ "train_tokens_per_second": 11978.213
1200
+ },
1201
+ {
1202
+ "epoch": 0.24257867244234935,
1203
+ "grad_norm": 0.839011112693872,
1204
+ "learning_rate": 2.9402755754737166e-11,
1205
+ "loss": 0.5519,
1206
+ "num_input_tokens_seen": 842742656,
1207
+ "step": 476,
1208
+ "train_runtime": 70378.9536,
1209
+ "train_tokens_per_second": 11974.356
1210
+ },
1211
+ {
1212
+ "epoch": 0.24257867244234935,
1213
+ "eval_loss": 0.7951585054397583,
1214
+ "eval_runtime": 212.309,
1215
+ "eval_samples_per_second": 4.738,
1216
+ "eval_steps_per_second": 0.075,
1217
+ "num_input_tokens_seen": 842742656,
1218
+ "step": 476
1219
+ }
1220
+ ],
1221
+ "logging_steps": 4,
1222
+ "max_steps": 476,
1223
+ "num_input_tokens_seen": 842742656,
1224
+ "num_train_epochs": 1,
1225
+ "save_steps": 238,
1226
+ "stateful_callbacks": {
1227
+ "TrainerControl": {
1228
+ "args": {
1229
+ "should_epoch_stop": false,
1230
+ "should_evaluate": false,
1231
+ "should_log": false,
1232
+ "should_save": true,
1233
+ "should_training_stop": true
1234
+ },
1235
+ "attributes": {}
1236
+ }
1237
+ },
1238
+ "total_flos": 4291443279527936.0,
1239
+ "train_batch_size": 8,
1240
+ "trial_name": null,
1241
+ "trial_params": null
1242
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21fafa26013586fcab9820ef53339974b114413e48e07ce89bb8b6ec750aec34
3
+ size 7800
video_preprocessor_config.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_valid_kwargs_names": [
3
+ "do_convert_rgb",
4
+ "do_resize",
5
+ "size",
6
+ "size_divisor",
7
+ "default_to_square",
8
+ "resample",
9
+ "do_rescale",
10
+ "rescale_factor",
11
+ "do_normalize",
12
+ "image_mean",
13
+ "image_std",
14
+ "do_pad",
15
+ "do_center_crop",
16
+ "crop_size",
17
+ "data_format",
18
+ "input_data_format",
19
+ "device",
20
+ "min_pixels",
21
+ "max_pixels",
22
+ "patch_size",
23
+ "temporal_patch_size",
24
+ "merge_size"
25
+ ],
26
+ "crop_size": null,
27
+ "data_format": "channels_first",
28
+ "default_to_square": true,
29
+ "device": null,
30
+ "do_center_crop": null,
31
+ "do_convert_rgb": true,
32
+ "do_normalize": true,
33
+ "do_pad": null,
34
+ "do_rescale": true,
35
+ "do_resize": true,
36
+ "image_mean": [
37
+ 0.48145466,
38
+ 0.4578275,
39
+ 0.40821073
40
+ ],
41
+ "image_processor_type": "Qwen2VLImageProcessor",
42
+ "image_std": [
43
+ 0.26862954,
44
+ 0.26130258,
45
+ 0.27577711
46
+ ],
47
+ "input_data_format": null,
48
+ "max_pixels": 12845056,
49
+ "merge_size": 2,
50
+ "min_pixels": 3136,
51
+ "model_valid_processing_keys": [
52
+ "do_convert_rgb",
53
+ "do_resize",
54
+ "size",
55
+ "size_divisor",
56
+ "default_to_square",
57
+ "resample",
58
+ "do_rescale",
59
+ "rescale_factor",
60
+ "do_normalize",
61
+ "image_mean",
62
+ "image_std",
63
+ "do_pad",
64
+ "do_center_crop",
65
+ "crop_size",
66
+ "data_format",
67
+ "input_data_format",
68
+ "device",
69
+ "min_pixels",
70
+ "max_pixels",
71
+ "patch_size",
72
+ "temporal_patch_size",
73
+ "merge_size"
74
+ ],
75
+ "patch_size": 14,
76
+ "processor_class": "Qwen2_5_VLProcessor",
77
+ "resample": 3,
78
+ "rescale_factor": 0.00392156862745098,
79
+ "size": {
80
+ "longest_edge": 12845056,
81
+ "shortest_edge": 3136
82
+ },
83
+ "size_divisor": null,
84
+ "temporal_patch_size": 2,
85
+ "video_processor_type": "Qwen2VLVideoProcessor"
86
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff