Hugging Face's logo

zwcolin
/
gym

Safetensors
Model card Files
xet
Community
zwcolin commited on
Commit
74d3886
·
verified ·
1 Parent(s): 5beb0bd

Upload mixed_all_diff_v5_350k/checkpoint-2000

Browse files
Files changed (18) hide show
  1. .gitattributes +1 -0
  2. mixed_all_diff_v5_350k/checkpoint-2000/added_tokens.json +24 -0
  3. mixed_all_diff_v5_350k/checkpoint-2000/chat_template.json +3 -0
  4. mixed_all_diff_v5_350k/checkpoint-2000/config.json +65 -0
  5. mixed_all_diff_v5_350k/checkpoint-2000/generation_config.json +12 -0
  6. mixed_all_diff_v5_350k/checkpoint-2000/merges.txt +0 -0
  7. mixed_all_diff_v5_350k/checkpoint-2000/model-00001-of-00004.safetensors +3 -0
  8. mixed_all_diff_v5_350k/checkpoint-2000/model-00002-of-00004.safetensors +3 -0
  9. mixed_all_diff_v5_350k/checkpoint-2000/model-00003-of-00004.safetensors +3 -0
  10. mixed_all_diff_v5_350k/checkpoint-2000/model-00004-of-00004.safetensors +3 -0
  11. mixed_all_diff_v5_350k/checkpoint-2000/model.safetensors.index.json +736 -0
  12. mixed_all_diff_v5_350k/checkpoint-2000/preprocessor_config.json +36 -0
  13. mixed_all_diff_v5_350k/checkpoint-2000/special_tokens_map.json +31 -0
  14. mixed_all_diff_v5_350k/checkpoint-2000/tokenizer.json +3 -0
  15. mixed_all_diff_v5_350k/checkpoint-2000/tokenizer_config.json +210 -0
  16. mixed_all_diff_v5_350k/checkpoint-2000/trainer_state.json +1434 -0
  17. mixed_all_diff_v5_350k/checkpoint-2000/training_args.bin +3 -0
  18. mixed_all_diff_v5_350k/checkpoint-2000/vocab.json +0 -0
.gitattributes CHANGED
@@ -180,3 +180,4 @@ jigsaw-swap_alt_v5_100k/checkpoint-1500/tokenizer.json filter=lfs diff=lfs merge
180
  jigsaw-swap_mix_v5_100k/checkpoint-1500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
181
  mixed_all_diff_v5_350k/checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
182
  mixed_all_diff_v5_350k/checkpoint-1500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
180
  jigsaw-swap_mix_v5_100k/checkpoint-1500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
181
  mixed_all_diff_v5_350k/checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
182
  mixed_all_diff_v5_350k/checkpoint-1500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
183
+ mixed_all_diff_v5_350k/checkpoint-2000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
mixed_all_diff_v5_350k/checkpoint-2000/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
mixed_all_diff_v5_350k/checkpoint-2000/chat_template.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
3
+ }
mixed_all_diff_v5_350k/checkpoint-2000/config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2_5_VLForConditionalGeneration"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "eos_token_id": 151645,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 3584,
10
+ "image_token_id": 151655,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 18944,
13
+ "max_position_embeddings": 128000,
14
+ "max_window_layers": 28,
15
+ "model_type": "qwen2_5_vl",
16
+ "num_attention_heads": 28,
17
+ "num_hidden_layers": 28,
18
+ "num_key_value_heads": 4,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_scaling": {
21
+ "mrope_section": [
22
+ 16,
23
+ 24,
24
+ 24
25
+ ],
26
+ "rope_type": "default",
27
+ "type": "default"
28
+ },
29
+ "rope_theta": 1000000.0,
30
+ "sliding_window": 32768,
31
+ "tie_word_embeddings": false,
32
+ "torch_dtype": "bfloat16",
33
+ "transformers_version": "4.51.1",
34
+ "use_cache": false,
35
+ "use_sliding_window": false,
36
+ "video_token_id": 151656,
37
+ "vision_config": {
38
+ "depth": 32,
39
+ "fullatt_block_indexes": [
40
+ 7,
41
+ 15,
42
+ 23,
43
+ 31
44
+ ],
45
+ "hidden_act": "silu",
46
+ "hidden_size": 1280,
47
+ "in_channels": 3,
48
+ "in_chans": 3,
49
+ "intermediate_size": 3420,
50
+ "model_type": "qwen2_5_vl",
51
+ "num_heads": 16,
52
+ "out_hidden_size": 3584,
53
+ "patch_size": 14,
54
+ "spatial_merge_size": 2,
55
+ "spatial_patch_size": 14,
56
+ "temporal_patch_size": 2,
57
+ "tokens_per_second": 2,
58
+ "torch_dtype": "bfloat16",
59
+ "window_size": 112
60
+ },
61
+ "vision_end_token_id": 151653,
62
+ "vision_start_token_id": 151652,
63
+ "vision_token_id": 151654,
64
+ "vocab_size": 152064
65
+ }
mixed_all_diff_v5_350k/checkpoint-2000/generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.05,
10
+ "temperature": 1e-06,
11
+ "transformers_version": "4.51.1"
12
+ }
mixed_all_diff_v5_350k/checkpoint-2000/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
mixed_all_diff_v5_350k/checkpoint-2000/model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d596c895f7038e4ff158850ad1f66a4f4c7e5a473e237f6a7e941c8ba97ff353
3
+ size 4968243304
mixed_all_diff_v5_350k/checkpoint-2000/model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64655eba6d58ce59763bebc18174c04cd77d4becc7cdd0d126c752ba0a5a34a9
3
+ size 4991495816
mixed_all_diff_v5_350k/checkpoint-2000/model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d404a80ce7738818b58b307113878935d3a5e6f73e92aea3de2c699994012f0
3
+ size 4932751040
mixed_all_diff_v5_350k/checkpoint-2000/model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d73cab6b61fd56d2a45d71369b9c0156d03c69f0f76ca4b20753c507dd220228
3
+ size 1691924384
mixed_all_diff_v5_350k/checkpoint-2000/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.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
17
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
19
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
26
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
27
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
28
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
29
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
30
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
31
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
32
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
38
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
41
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
43
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
50
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
53
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
55
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
62
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
65
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
67
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
74
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
77
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
79
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
86
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
89
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
91
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
98
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
101
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
103
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
105
+ "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
106
+ "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
107
+ "model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
108
+ "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
109
+ "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
110
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
113
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
115
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
117
+ "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
118
+ "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
119
+ "model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
120
+ "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
121
+ "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
122
+ "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
123
+ "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
124
+ "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
125
+ "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
126
+ "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
127
+ "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
128
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
131
+ "model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
132
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
133
+ "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
134
+ "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
135
+ "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
136
+ "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
137
+ "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
138
+ "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
139
+ "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
140
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
146
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
149
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
151
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
153
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
154
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
155
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
156
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
157
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
158
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
159
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
160
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
161
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
162
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
163
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
164
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
170
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
173
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
175
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
182
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
185
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
187
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
194
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
197
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
199
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
206
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
209
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
211
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
216
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
217
+ "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
218
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
219
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
220
+ "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
221
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
222
+ "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
223
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
224
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
230
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
233
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
234
+ "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
235
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
236
+ "model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
237
+ "model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
238
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
241
+ "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
242
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
243
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
244
+ "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
245
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
246
+ "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
247
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
248
+ "model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
249
+ "model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
250
+ "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
251
+ "model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
252
+ "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
253
+ "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
254
+ "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
255
+ "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
256
+ "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
257
+ "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
258
+ "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
259
+ "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
260
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
261
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
266
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
267
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
269
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
270
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
271
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
272
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
278
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
279
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
281
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
282
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
283
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
284
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
285
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
286
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
287
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
288
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
289
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
290
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
291
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
292
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
293
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
294
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
295
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
296
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
297
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
298
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
299
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
300
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
301
+ "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
302
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
303
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
304
+ "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
305
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
306
+ "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
307
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
308
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
309
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
310
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
311
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
312
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
313
+ "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
314
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
315
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
316
+ "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
317
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
318
+ "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
319
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
320
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
321
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
322
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
323
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
324
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
325
+ "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
326
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
327
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
328
+ "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
329
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
330
+ "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
331
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
332
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
333
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
334
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
335
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
336
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
337
+ "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
338
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
339
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
340
+ "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
341
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
342
+ "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
343
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
344
+ "model.norm.weight": "model-00004-of-00004.safetensors",
345
+ "visual.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors",
346
+ "visual.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
347
+ "visual.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
348
+ "visual.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
349
+ "visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
350
+ "visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
351
+ "visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
352
+ "visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
353
+ "visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
354
+ "visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
355
+ "visual.blocks.0.norm1.weight": "model-00001-of-00004.safetensors",
356
+ "visual.blocks.0.norm2.weight": "model-00001-of-00004.safetensors",
357
+ "visual.blocks.1.attn.proj.bias": "model-00001-of-00004.safetensors",
358
+ "visual.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors",
359
+ "visual.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
360
+ "visual.blocks.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
361
+ "visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
362
+ "visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
363
+ "visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
364
+ "visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
365
+ "visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
366
+ "visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
367
+ "visual.blocks.1.norm1.weight": "model-00001-of-00004.safetensors",
368
+ "visual.blocks.1.norm2.weight": "model-00001-of-00004.safetensors",
369
+ "visual.blocks.10.attn.proj.bias": "model-00001-of-00004.safetensors",
370
+ "visual.blocks.10.attn.proj.weight": "model-00001-of-00004.safetensors",
371
+ "visual.blocks.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
372
+ "visual.blocks.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
373
+ "visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
374
+ "visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
375
+ "visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
376
+ "visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
377
+ "visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
378
+ "visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
379
+ "visual.blocks.10.norm1.weight": "model-00001-of-00004.safetensors",
380
+ "visual.blocks.10.norm2.weight": "model-00001-of-00004.safetensors",
381
+ "visual.blocks.11.attn.proj.bias": "model-00001-of-00004.safetensors",
382
+ "visual.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors",
383
+ "visual.blocks.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
384
+ "visual.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
385
+ "visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
386
+ "visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
387
+ "visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
388
+ "visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
389
+ "visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
390
+ "visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
391
+ "visual.blocks.11.norm1.weight": "model-00001-of-00004.safetensors",
392
+ "visual.blocks.11.norm2.weight": "model-00001-of-00004.safetensors",
393
+ "visual.blocks.12.attn.proj.bias": "model-00001-of-00004.safetensors",
394
+ "visual.blocks.12.attn.proj.weight": "model-00001-of-00004.safetensors",
395
+ "visual.blocks.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
396
+ "visual.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
397
+ "visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
398
+ "visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
399
+ "visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
400
+ "visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
401
+ "visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
402
+ "visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
403
+ "visual.blocks.12.norm1.weight": "model-00001-of-00004.safetensors",
404
+ "visual.blocks.12.norm2.weight": "model-00001-of-00004.safetensors",
405
+ "visual.blocks.13.attn.proj.bias": "model-00001-of-00004.safetensors",
406
+ "visual.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors",
407
+ "visual.blocks.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
408
+ "visual.blocks.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
409
+ "visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
410
+ "visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
411
+ "visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
412
+ "visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
413
+ "visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
414
+ "visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
415
+ "visual.blocks.13.norm1.weight": "model-00001-of-00004.safetensors",
416
+ "visual.blocks.13.norm2.weight": "model-00001-of-00004.safetensors",
417
+ "visual.blocks.14.attn.proj.bias": "model-00001-of-00004.safetensors",
418
+ "visual.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors",
419
+ "visual.blocks.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
420
+ "visual.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
421
+ "visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
422
+ "visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
423
+ "visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
424
+ "visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
425
+ "visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
426
+ "visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
427
+ "visual.blocks.14.norm1.weight": "model-00001-of-00004.safetensors",
428
+ "visual.blocks.14.norm2.weight": "model-00001-of-00004.safetensors",
429
+ "visual.blocks.15.attn.proj.bias": "model-00001-of-00004.safetensors",
430
+ "visual.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors",
431
+ "visual.blocks.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
432
+ "visual.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
433
+ "visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
434
+ "visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
435
+ "visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
436
+ "visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
437
+ "visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
438
+ "visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
439
+ "visual.blocks.15.norm1.weight": "model-00001-of-00004.safetensors",
440
+ "visual.blocks.15.norm2.weight": "model-00001-of-00004.safetensors",
441
+ "visual.blocks.16.attn.proj.bias": "model-00001-of-00004.safetensors",
442
+ "visual.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors",
443
+ "visual.blocks.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
444
+ "visual.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
445
+ "visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
446
+ "visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
447
+ "visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
448
+ "visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
449
+ "visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
450
+ "visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
451
+ "visual.blocks.16.norm1.weight": "model-00001-of-00004.safetensors",
452
+ "visual.blocks.16.norm2.weight": "model-00001-of-00004.safetensors",
453
+ "visual.blocks.17.attn.proj.bias": "model-00001-of-00004.safetensors",
454
+ "visual.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors",
455
+ "visual.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
456
+ "visual.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
457
+ "visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
458
+ "visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
459
+ "visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
460
+ "visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
461
+ "visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
462
+ "visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
463
+ "visual.blocks.17.norm1.weight": "model-00001-of-00004.safetensors",
464
+ "visual.blocks.17.norm2.weight": "model-00001-of-00004.safetensors",
465
+ "visual.blocks.18.attn.proj.bias": "model-00001-of-00004.safetensors",
466
+ "visual.blocks.18.attn.proj.weight": "model-00001-of-00004.safetensors",
467
+ "visual.blocks.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
468
+ "visual.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
469
+ "visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
470
+ "visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
471
+ "visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
472
+ "visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
473
+ "visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
474
+ "visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
475
+ "visual.blocks.18.norm1.weight": "model-00001-of-00004.safetensors",
476
+ "visual.blocks.18.norm2.weight": "model-00001-of-00004.safetensors",
477
+ "visual.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors",
478
+ "visual.blocks.19.attn.proj.weight": "model-00001-of-00004.safetensors",
479
+ "visual.blocks.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
480
+ "visual.blocks.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
481
+ "visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
482
+ "visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
483
+ "visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
484
+ "visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
485
+ "visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
486
+ "visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
487
+ "visual.blocks.19.norm1.weight": "model-00001-of-00004.safetensors",
488
+ "visual.blocks.19.norm2.weight": "model-00001-of-00004.safetensors",
489
+ "visual.blocks.2.attn.proj.bias": "model-00001-of-00004.safetensors",
490
+ "visual.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors",
491
+ "visual.blocks.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
492
+ "visual.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
493
+ "visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
494
+ "visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
495
+ "visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
496
+ "visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
497
+ "visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
498
+ "visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
499
+ "visual.blocks.2.norm1.weight": "model-00001-of-00004.safetensors",
500
+ "visual.blocks.2.norm2.weight": "model-00001-of-00004.safetensors",
501
+ "visual.blocks.20.attn.proj.bias": "model-00001-of-00004.safetensors",
502
+ "visual.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors",
503
+ "visual.blocks.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
504
+ "visual.blocks.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
505
+ "visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
506
+ "visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
507
+ "visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
508
+ "visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
509
+ "visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
510
+ "visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
511
+ "visual.blocks.20.norm1.weight": "model-00001-of-00004.safetensors",
512
+ "visual.blocks.20.norm2.weight": "model-00001-of-00004.safetensors",
513
+ "visual.blocks.21.attn.proj.bias": "model-00001-of-00004.safetensors",
514
+ "visual.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors",
515
+ "visual.blocks.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
516
+ "visual.blocks.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
517
+ "visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
518
+ "visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
519
+ "visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
520
+ "visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
521
+ "visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
522
+ "visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
523
+ "visual.blocks.21.norm1.weight": "model-00001-of-00004.safetensors",
524
+ "visual.blocks.21.norm2.weight": "model-00001-of-00004.safetensors",
525
+ "visual.blocks.22.attn.proj.bias": "model-00001-of-00004.safetensors",
526
+ "visual.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors",
527
+ "visual.blocks.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
528
+ "visual.blocks.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
529
+ "visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
530
+ "visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
531
+ "visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
532
+ "visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
533
+ "visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
534
+ "visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
535
+ "visual.blocks.22.norm1.weight": "model-00001-of-00004.safetensors",
536
+ "visual.blocks.22.norm2.weight": "model-00001-of-00004.safetensors",
537
+ "visual.blocks.23.attn.proj.bias": "model-00001-of-00004.safetensors",
538
+ "visual.blocks.23.attn.proj.weight": "model-00001-of-00004.safetensors",
539
+ "visual.blocks.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
540
+ "visual.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
541
+ "visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
542
+ "visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
543
+ "visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
544
+ "visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
545
+ "visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
546
+ "visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
547
+ "visual.blocks.23.norm1.weight": "model-00001-of-00004.safetensors",
548
+ "visual.blocks.23.norm2.weight": "model-00001-of-00004.safetensors",
549
+ "visual.blocks.24.attn.proj.bias": "model-00001-of-00004.safetensors",
550
+ "visual.blocks.24.attn.proj.weight": "model-00001-of-00004.safetensors",
551
+ "visual.blocks.24.attn.qkv.bias": "model-00001-of-00004.safetensors",
552
+ "visual.blocks.24.attn.qkv.weight": "model-00001-of-00004.safetensors",
553
+ "visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
554
+ "visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
555
+ "visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
556
+ "visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
557
+ "visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
558
+ "visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
559
+ "visual.blocks.24.norm1.weight": "model-00001-of-00004.safetensors",
560
+ "visual.blocks.24.norm2.weight": "model-00001-of-00004.safetensors",
561
+ "visual.blocks.25.attn.proj.bias": "model-00001-of-00004.safetensors",
562
+ "visual.blocks.25.attn.proj.weight": "model-00001-of-00004.safetensors",
563
+ "visual.blocks.25.attn.qkv.bias": "model-00001-of-00004.safetensors",
564
+ "visual.blocks.25.attn.qkv.weight": "model-00001-of-00004.safetensors",
565
+ "visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
566
+ "visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
567
+ "visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
568
+ "visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
569
+ "visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
570
+ "visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
571
+ "visual.blocks.25.norm1.weight": "model-00001-of-00004.safetensors",
572
+ "visual.blocks.25.norm2.weight": "model-00001-of-00004.safetensors",
573
+ "visual.blocks.26.attn.proj.bias": "model-00001-of-00004.safetensors",
574
+ "visual.blocks.26.attn.proj.weight": "model-00001-of-00004.safetensors",
575
+ "visual.blocks.26.attn.qkv.bias": "model-00001-of-00004.safetensors",
576
+ "visual.blocks.26.attn.qkv.weight": "model-00001-of-00004.safetensors",
577
+ "visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
578
+ "visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
579
+ "visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
580
+ "visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
581
+ "visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
582
+ "visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
583
+ "visual.blocks.26.norm1.weight": "model-00001-of-00004.safetensors",
584
+ "visual.blocks.26.norm2.weight": "model-00001-of-00004.safetensors",
585
+ "visual.blocks.27.attn.proj.bias": "model-00001-of-00004.safetensors",
586
+ "visual.blocks.27.attn.proj.weight": "model-00001-of-00004.safetensors",
587
+ "visual.blocks.27.attn.qkv.bias": "model-00001-of-00004.safetensors",
588
+ "visual.blocks.27.attn.qkv.weight": "model-00001-of-00004.safetensors",
589
+ "visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
590
+ "visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
591
+ "visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
592
+ "visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
593
+ "visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
594
+ "visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
595
+ "visual.blocks.27.norm1.weight": "model-00001-of-00004.safetensors",
596
+ "visual.blocks.27.norm2.weight": "model-00001-of-00004.safetensors",
597
+ "visual.blocks.28.attn.proj.bias": "model-00001-of-00004.safetensors",
598
+ "visual.blocks.28.attn.proj.weight": "model-00001-of-00004.safetensors",
599
+ "visual.blocks.28.attn.qkv.bias": "model-00001-of-00004.safetensors",
600
+ "visual.blocks.28.attn.qkv.weight": "model-00001-of-00004.safetensors",
601
+ "visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
602
+ "visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
603
+ "visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
604
+ "visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
605
+ "visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
606
+ "visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
607
+ "visual.blocks.28.norm1.weight": "model-00001-of-00004.safetensors",
608
+ "visual.blocks.28.norm2.weight": "model-00001-of-00004.safetensors",
609
+ "visual.blocks.29.attn.proj.bias": "model-00001-of-00004.safetensors",
610
+ "visual.blocks.29.attn.proj.weight": "model-00001-of-00004.safetensors",
611
+ "visual.blocks.29.attn.qkv.bias": "model-00001-of-00004.safetensors",
612
+ "visual.blocks.29.attn.qkv.weight": "model-00001-of-00004.safetensors",
613
+ "visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
614
+ "visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
615
+ "visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
616
+ "visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
617
+ "visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
618
+ "visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
619
+ "visual.blocks.29.norm1.weight": "model-00001-of-00004.safetensors",
620
+ "visual.blocks.29.norm2.weight": "model-00001-of-00004.safetensors",
621
+ "visual.blocks.3.attn.proj.bias": "model-00001-of-00004.safetensors",
622
+ "visual.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors",
623
+ "visual.blocks.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
624
+ "visual.blocks.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
625
+ "visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
626
+ "visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
627
+ "visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
628
+ "visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
629
+ "visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
630
+ "visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
631
+ "visual.blocks.3.norm1.weight": "model-00001-of-00004.safetensors",
632
+ "visual.blocks.3.norm2.weight": "model-00001-of-00004.safetensors",
633
+ "visual.blocks.30.attn.proj.bias": "model-00001-of-00004.safetensors",
634
+ "visual.blocks.30.attn.proj.weight": "model-00001-of-00004.safetensors",
635
+ "visual.blocks.30.attn.qkv.bias": "model-00001-of-00004.safetensors",
636
+ "visual.blocks.30.attn.qkv.weight": "model-00001-of-00004.safetensors",
637
+ "visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
638
+ "visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
639
+ "visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
640
+ "visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
641
+ "visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
642
+ "visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
643
+ "visual.blocks.30.norm1.weight": "model-00001-of-00004.safetensors",
644
+ "visual.blocks.30.norm2.weight": "model-00001-of-00004.safetensors",
645
+ "visual.blocks.31.attn.proj.bias": "model-00001-of-00004.safetensors",
646
+ "visual.blocks.31.attn.proj.weight": "model-00001-of-00004.safetensors",
647
+ "visual.blocks.31.attn.qkv.bias": "model-00001-of-00004.safetensors",
648
+ "visual.blocks.31.attn.qkv.weight": "model-00001-of-00004.safetensors",
649
+ "visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
650
+ "visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
651
+ "visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
652
+ "visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
653
+ "visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
654
+ "visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
655
+ "visual.blocks.31.norm1.weight": "model-00001-of-00004.safetensors",
656
+ "visual.blocks.31.norm2.weight": "model-00001-of-00004.safetensors",
657
+ "visual.blocks.4.attn.proj.bias": "model-00001-of-00004.safetensors",
658
+ "visual.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors",
659
+ "visual.blocks.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
660
+ "visual.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
661
+ "visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
662
+ "visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
663
+ "visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
664
+ "visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
665
+ "visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
666
+ "visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
667
+ "visual.blocks.4.norm1.weight": "model-00001-of-00004.safetensors",
668
+ "visual.blocks.4.norm2.weight": "model-00001-of-00004.safetensors",
669
+ "visual.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors",
670
+ "visual.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors",
671
+ "visual.blocks.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
672
+ "visual.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
673
+ "visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
674
+ "visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
675
+ "visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
676
+ "visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
677
+ "visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
678
+ "visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
679
+ "visual.blocks.5.norm1.weight": "model-00001-of-00004.safetensors",
680
+ "visual.blocks.5.norm2.weight": "model-00001-of-00004.safetensors",
681
+ "visual.blocks.6.attn.proj.bias": "model-00001-of-00004.safetensors",
682
+ "visual.blocks.6.attn.proj.weight": "model-00001-of-00004.safetensors",
683
+ "visual.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
684
+ "visual.blocks.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
685
+ "visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
686
+ "visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
687
+ "visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
688
+ "visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
689
+ "visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
690
+ "visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
691
+ "visual.blocks.6.norm1.weight": "model-00001-of-00004.safetensors",
692
+ "visual.blocks.6.norm2.weight": "model-00001-of-00004.safetensors",
693
+ "visual.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors",
694
+ "visual.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors",
695
+ "visual.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
696
+ "visual.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
697
+ "visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
698
+ "visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
699
+ "visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
700
+ "visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
701
+ "visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
702
+ "visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
703
+ "visual.blocks.7.norm1.weight": "model-00001-of-00004.safetensors",
704
+ "visual.blocks.7.norm2.weight": "model-00001-of-00004.safetensors",
705
+ "visual.blocks.8.attn.proj.bias": "model-00001-of-00004.safetensors",
706
+ "visual.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors",
707
+ "visual.blocks.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
708
+ "visual.blocks.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
709
+ "visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
710
+ "visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
711
+ "visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
712
+ "visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
713
+ "visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
714
+ "visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
715
+ "visual.blocks.8.norm1.weight": "model-00001-of-00004.safetensors",
716
+ "visual.blocks.8.norm2.weight": "model-00001-of-00004.safetensors",
717
+ "visual.blocks.9.attn.proj.bias": "model-00001-of-00004.safetensors",
718
+ "visual.blocks.9.attn.proj.weight": "model-00001-of-00004.safetensors",
719
+ "visual.blocks.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
720
+ "visual.blocks.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
721
+ "visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
722
+ "visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
723
+ "visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
724
+ "visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
725
+ "visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
726
+ "visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
727
+ "visual.blocks.9.norm1.weight": "model-00001-of-00004.safetensors",
728
+ "visual.blocks.9.norm2.weight": "model-00001-of-00004.safetensors",
729
+ "visual.merger.ln_q.weight": "model-00001-of-00004.safetensors",
730
+ "visual.merger.mlp.0.bias": "model-00001-of-00004.safetensors",
731
+ "visual.merger.mlp.0.weight": "model-00001-of-00004.safetensors",
732
+ "visual.merger.mlp.2.bias": "model-00001-of-00004.safetensors",
733
+ "visual.merger.mlp.2.weight": "model-00001-of-00004.safetensors",
734
+ "visual.patch_embed.proj.weight": "model-00001-of-00004.safetensors"
735
+ }
736
+ }
mixed_all_diff_v5_350k/checkpoint-2000/preprocessor_config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": null,
3
+ "data_format": "channels_first",
4
+ "default_to_square": true,
5
+ "device": null,
6
+ "do_center_crop": null,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_rescale": true,
10
+ "do_resize": true,
11
+ "image_mean": [
12
+ 0.48145466,
13
+ 0.4578275,
14
+ 0.40821073
15
+ ],
16
+ "image_processor_type": "Qwen2VLImageProcessorFast",
17
+ "image_std": [
18
+ 0.26862954,
19
+ 0.26130258,
20
+ 0.27577711
21
+ ],
22
+ "input_data_format": null,
23
+ "max_pixels": 12845056,
24
+ "merge_size": 2,
25
+ "min_pixels": 3136,
26
+ "patch_size": 14,
27
+ "processor_class": "Qwen2_5_VLProcessor",
28
+ "resample": 3,
29
+ "rescale_factor": 0.00392156862745098,
30
+ "return_tensors": null,
31
+ "size": {
32
+ "longest_edge": 12845056,
33
+ "shortest_edge": 3136
34
+ },
35
+ "temporal_patch_size": 2
36
+ }
mixed_all_diff_v5_350k/checkpoint-2000/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
+ }
mixed_all_diff_v5_350k/checkpoint-2000/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
mixed_all_diff_v5_350k/checkpoint-2000/tokenizer_config.json ADDED
@@ -0,0 +1,210 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|im_end|>",
201
+ "errors": "replace",
202
+ "extra_special_tokens": {},
203
+ "model_max_length": 131072,
204
+ "pad_token": "<|endoftext|>",
205
+ "padding_side": "right",
206
+ "processor_class": "Qwen2_5_VLProcessor",
207
+ "split_special_tokens": false,
208
+ "tokenizer_class": "Qwen2Tokenizer",
209
+ "unk_token": null
210
+ }
mixed_all_diff_v5_350k/checkpoint-2000/trainer_state.json ADDED
@@ -0,0 +1,1434 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.4,
6
+ "eval_steps": 500,
7
+ "global_step": 2000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.002,
14
+ "grad_norm": 13.095802307128906,
15
+ "learning_rate": 1.8e-07,
16
+ "loss": 0.5392,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.004,
21
+ "grad_norm": 12.536194801330566,
22
+ "learning_rate": 3.8e-07,
23
+ "loss": 0.5071,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.006,
28
+ "grad_norm": 3.061798334121704,
29
+ "learning_rate": 5.800000000000001e-07,
30
+ "loss": 0.402,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.008,
35
+ "grad_norm": 1.6354824304580688,
36
+ "learning_rate": 7.8e-07,
37
+ "loss": 0.3299,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.01,
42
+ "grad_norm": 10.905953407287598,
43
+ "learning_rate": 9.800000000000001e-07,
44
+ "loss": 0.3229,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.012,
49
+ "grad_norm": 2.0208652019500732,
50
+ "learning_rate": 1.1800000000000001e-06,
51
+ "loss": 0.2655,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.014,
56
+ "grad_norm": 2.0658318996429443,
57
+ "learning_rate": 1.3800000000000001e-06,
58
+ "loss": 0.266,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.016,
63
+ "grad_norm": 1.5789655447006226,
64
+ "learning_rate": 1.5800000000000001e-06,
65
+ "loss": 0.2769,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.018,
70
+ "grad_norm": 1.4777958393096924,
71
+ "learning_rate": 1.7800000000000001e-06,
72
+ "loss": 0.274,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.02,
77
+ "grad_norm": 1.455391764640808,
78
+ "learning_rate": 1.98e-06,
79
+ "loss": 0.25,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.022,
84
+ "grad_norm": 2.4884302616119385,
85
+ "learning_rate": 2.1800000000000003e-06,
86
+ "loss": 0.2466,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.024,
91
+ "grad_norm": 1.5171929597854614,
92
+ "learning_rate": 2.38e-06,
93
+ "loss": 0.2556,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.026,
98
+ "grad_norm": 1.3378539085388184,
99
+ "learning_rate": 2.5800000000000003e-06,
100
+ "loss": 0.2621,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.028,
105
+ "grad_norm": 1.728003978729248,
106
+ "learning_rate": 2.7800000000000005e-06,
107
+ "loss": 0.2636,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.03,
112
+ "grad_norm": 2.905702829360962,
113
+ "learning_rate": 2.9800000000000003e-06,
114
+ "loss": 0.2426,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.032,
119
+ "grad_norm": 3.693586826324463,
120
+ "learning_rate": 3.1800000000000005e-06,
121
+ "loss": 0.2505,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.034,
126
+ "grad_norm": 5.392415523529053,
127
+ "learning_rate": 3.3800000000000007e-06,
128
+ "loss": 0.2244,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.036,
133
+ "grad_norm": 1.7138640880584717,
134
+ "learning_rate": 3.58e-06,
135
+ "loss": 0.2474,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.038,
140
+ "grad_norm": 1.1188080310821533,
141
+ "learning_rate": 3.7800000000000002e-06,
142
+ "loss": 0.225,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.04,
147
+ "grad_norm": 0.9188288450241089,
148
+ "learning_rate": 3.980000000000001e-06,
149
+ "loss": 0.2397,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.042,
154
+ "grad_norm": 0.94315505027771,
155
+ "learning_rate": 4.18e-06,
156
+ "loss": 0.2471,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.044,
161
+ "grad_norm": 1.3686072826385498,
162
+ "learning_rate": 4.38e-06,
163
+ "loss": 0.258,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.046,
168
+ "grad_norm": 1.0444778203964233,
169
+ "learning_rate": 4.58e-06,
170
+ "loss": 0.2117,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.048,
175
+ "grad_norm": 1.1232186555862427,
176
+ "learning_rate": 4.78e-06,
177
+ "loss": 0.2201,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.05,
182
+ "grad_norm": 1.0262072086334229,
183
+ "learning_rate": 4.980000000000001e-06,
184
+ "loss": 0.2447,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.052,
189
+ "grad_norm": 0.8631378412246704,
190
+ "learning_rate": 5.18e-06,
191
+ "loss": 0.2259,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.054,
196
+ "grad_norm": 1.3098729848861694,
197
+ "learning_rate": 5.380000000000001e-06,
198
+ "loss": 0.2498,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.056,
203
+ "grad_norm": 1.2882674932479858,
204
+ "learning_rate": 5.580000000000001e-06,
205
+ "loss": 0.2292,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.058,
210
+ "grad_norm": 1.3000662326812744,
211
+ "learning_rate": 5.78e-06,
212
+ "loss": 0.2284,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.06,
217
+ "grad_norm": 0.9703101515769958,
218
+ "learning_rate": 5.98e-06,
219
+ "loss": 0.2064,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.062,
224
+ "grad_norm": 0.8370521664619446,
225
+ "learning_rate": 6.18e-06,
226
+ "loss": 0.2346,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.064,
231
+ "grad_norm": 1.088594913482666,
232
+ "learning_rate": 6.380000000000001e-06,
233
+ "loss": 0.2287,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.066,
238
+ "grad_norm": 1.3646186590194702,
239
+ "learning_rate": 6.5800000000000005e-06,
240
+ "loss": 0.2312,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.068,
245
+ "grad_norm": 0.9520092606544495,
246
+ "learning_rate": 6.780000000000001e-06,
247
+ "loss": 0.2217,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.07,
252
+ "grad_norm": 0.8036158084869385,
253
+ "learning_rate": 6.98e-06,
254
+ "loss": 0.256,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.072,
259
+ "grad_norm": 1.1443321704864502,
260
+ "learning_rate": 7.180000000000001e-06,
261
+ "loss": 0.2265,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.074,
266
+ "grad_norm": 1.7764973640441895,
267
+ "learning_rate": 7.3800000000000005e-06,
268
+ "loss": 0.2265,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.076,
273
+ "grad_norm": 0.7990925908088684,
274
+ "learning_rate": 7.58e-06,
275
+ "loss": 0.2279,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.078,
280
+ "grad_norm": 0.9590052366256714,
281
+ "learning_rate": 7.78e-06,
282
+ "loss": 0.2159,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.08,
287
+ "grad_norm": 0.711288332939148,
288
+ "learning_rate": 7.980000000000002e-06,
289
+ "loss": 0.2174,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.082,
294
+ "grad_norm": 1.4151089191436768,
295
+ "learning_rate": 8.18e-06,
296
+ "loss": 0.233,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.084,
301
+ "grad_norm": 0.8439831733703613,
302
+ "learning_rate": 8.380000000000001e-06,
303
+ "loss": 0.2245,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.086,
308
+ "grad_norm": 0.8315847516059875,
309
+ "learning_rate": 8.580000000000001e-06,
310
+ "loss": 0.2581,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.088,
315
+ "grad_norm": 0.7403279542922974,
316
+ "learning_rate": 8.78e-06,
317
+ "loss": 0.2342,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.09,
322
+ "grad_norm": 1.0904396772384644,
323
+ "learning_rate": 8.98e-06,
324
+ "loss": 0.2084,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.092,
329
+ "grad_norm": 0.7344077229499817,
330
+ "learning_rate": 9.180000000000002e-06,
331
+ "loss": 0.2033,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.094,
336
+ "grad_norm": 1.1634783744812012,
337
+ "learning_rate": 9.38e-06,
338
+ "loss": 0.22,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.096,
343
+ "grad_norm": 0.9504854083061218,
344
+ "learning_rate": 9.58e-06,
345
+ "loss": 0.2383,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.098,
350
+ "grad_norm": 0.9341325759887695,
351
+ "learning_rate": 9.780000000000001e-06,
352
+ "loss": 0.2273,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.1,
357
+ "grad_norm": 0.8410105109214783,
358
+ "learning_rate": 9.980000000000001e-06,
359
+ "loss": 0.2146,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 0.102,
364
+ "grad_norm": 1.1256098747253418,
365
+ "learning_rate": 9.999901304280686e-06,
366
+ "loss": 0.2205,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 0.104,
371
+ "grad_norm": 0.7720330357551575,
372
+ "learning_rate": 9.999560138895238e-06,
373
+ "loss": 0.2241,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 0.106,
378
+ "grad_norm": 0.847719669342041,
379
+ "learning_rate": 9.99897530200195e-06,
380
+ "loss": 0.2125,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 0.108,
385
+ "grad_norm": 0.5810734033584595,
386
+ "learning_rate": 9.998146822104943e-06,
387
+ "loss": 0.2257,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 0.11,
392
+ "grad_norm": 0.7734278440475464,
393
+ "learning_rate": 9.997074739583162e-06,
394
+ "loss": 0.2317,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 0.112,
399
+ "grad_norm": 2.187501907348633,
400
+ "learning_rate": 9.995759106688394e-06,
401
+ "loss": 0.2194,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 0.114,
406
+ "grad_norm": 0.8118548393249512,
407
+ "learning_rate": 9.99419998754273e-06,
408
+ "loss": 0.2295,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 0.116,
413
+ "grad_norm": 1.4760451316833496,
414
+ "learning_rate": 9.992397458135438e-06,
415
+ "loss": 0.2111,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 0.118,
420
+ "grad_norm": 2.314441204071045,
421
+ "learning_rate": 9.990351606319261e-06,
422
+ "loss": 0.2369,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 0.12,
427
+ "grad_norm": 0.6937255859375,
428
+ "learning_rate": 9.988062531806127e-06,
429
+ "loss": 0.2153,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 0.122,
434
+ "grad_norm": 1.1676185131072998,
435
+ "learning_rate": 9.9855303461623e-06,
436
+ "loss": 0.219,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 0.124,
441
+ "grad_norm": 0.693009614944458,
442
+ "learning_rate": 9.982755172802933e-06,
443
+ "loss": 0.2251,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 0.126,
448
+ "grad_norm": 0.6551271080970764,
449
+ "learning_rate": 9.979737146986064e-06,
450
+ "loss": 0.2516,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 0.128,
455
+ "grad_norm": 0.5076565146446228,
456
+ "learning_rate": 9.976476415806013e-06,
457
+ "loss": 0.2171,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 0.13,
462
+ "grad_norm": 0.7930055260658264,
463
+ "learning_rate": 9.972973138186217e-06,
464
+ "loss": 0.2292,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 0.132,
469
+ "grad_norm": 0.6024525761604309,
470
+ "learning_rate": 9.969227484871485e-06,
471
+ "loss": 0.2287,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 0.134,
476
+ "grad_norm": 0.7125842571258545,
477
+ "learning_rate": 9.965239638419673e-06,
478
+ "loss": 0.2122,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 0.136,
483
+ "grad_norm": 0.9468246698379517,
484
+ "learning_rate": 9.961009793192793e-06,
485
+ "loss": 0.2348,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 0.138,
490
+ "grad_norm": 0.4537997841835022,
491
+ "learning_rate": 9.956538155347534e-06,
492
+ "loss": 0.2103,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 0.14,
497
+ "grad_norm": 0.5157951712608337,
498
+ "learning_rate": 9.951824942825215e-06,
499
+ "loss": 0.2217,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 0.142,
504
+ "grad_norm": 4.510913372039795,
505
+ "learning_rate": 9.946870385341167e-06,
506
+ "loss": 0.2089,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 0.144,
511
+ "grad_norm": 0.5302438139915466,
512
+ "learning_rate": 9.94167472437353e-06,
513
+ "loss": 0.2382,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 0.146,
518
+ "grad_norm": 0.6763765811920166,
519
+ "learning_rate": 9.936238213151491e-06,
520
+ "loss": 0.2105,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 0.148,
525
+ "grad_norm": 0.7090476751327515,
526
+ "learning_rate": 9.930561116642936e-06,
527
+ "loss": 0.2211,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 0.15,
532
+ "grad_norm": 1.017712116241455,
533
+ "learning_rate": 9.92464371154154e-06,
534
+ "loss": 0.2129,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 0.152,
539
+ "grad_norm": 0.9004446864128113,
540
+ "learning_rate": 9.918486286253279e-06,
541
+ "loss": 0.2236,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 0.154,
546
+ "grad_norm": 0.7102458477020264,
547
+ "learning_rate": 9.912089140882377e-06,
548
+ "loss": 0.224,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 0.156,
553
+ "grad_norm": 0.46271249651908875,
554
+ "learning_rate": 9.90545258721667e-06,
555
+ "loss": 0.2064,
556
+ "step": 780
557
+ },
558
+ {
559
+ "epoch": 0.158,
560
+ "grad_norm": 0.7656673192977905,
561
+ "learning_rate": 9.898576948712427e-06,
562
+ "loss": 0.2294,
563
+ "step": 790
564
+ },
565
+ {
566
+ "epoch": 0.16,
567
+ "grad_norm": 0.6276375651359558,
568
+ "learning_rate": 9.891462560478562e-06,
569
+ "loss": 0.2167,
570
+ "step": 800
571
+ },
572
+ {
573
+ "epoch": 0.162,
574
+ "grad_norm": 0.6398945450782776,
575
+ "learning_rate": 9.884109769260326e-06,
576
+ "loss": 0.2114,
577
+ "step": 810
578
+ },
579
+ {
580
+ "epoch": 0.164,
581
+ "grad_norm": 0.6401175260543823,
582
+ "learning_rate": 9.876518933422385e-06,
583
+ "loss": 0.1955,
584
+ "step": 820
585
+ },
586
+ {
587
+ "epoch": 0.166,
588
+ "grad_norm": 0.6360971331596375,
589
+ "learning_rate": 9.868690422931372e-06,
590
+ "loss": 0.1937,
591
+ "step": 830
592
+ },
593
+ {
594
+ "epoch": 0.168,
595
+ "grad_norm": 0.6253735423088074,
596
+ "learning_rate": 9.860624619337844e-06,
597
+ "loss": 0.217,
598
+ "step": 840
599
+ },
600
+ {
601
+ "epoch": 0.17,
602
+ "grad_norm": 0.7517882585525513,
603
+ "learning_rate": 9.852321915757688e-06,
604
+ "loss": 0.2356,
605
+ "step": 850
606
+ },
607
+ {
608
+ "epoch": 0.172,
609
+ "grad_norm": 0.5675958395004272,
610
+ "learning_rate": 9.843782716852963e-06,
611
+ "loss": 0.2115,
612
+ "step": 860
613
+ },
614
+ {
615
+ "epoch": 0.174,
616
+ "grad_norm": 0.5538104176521301,
617
+ "learning_rate": 9.835007438812177e-06,
618
+ "loss": 0.2033,
619
+ "step": 870
620
+ },
621
+ {
622
+ "epoch": 0.176,
623
+ "grad_norm": 0.655990481376648,
624
+ "learning_rate": 9.825996509330001e-06,
625
+ "loss": 0.2113,
626
+ "step": 880
627
+ },
628
+ {
629
+ "epoch": 0.178,
630
+ "grad_norm": 0.7001035213470459,
631
+ "learning_rate": 9.816750367586424e-06,
632
+ "loss": 0.2196,
633
+ "step": 890
634
+ },
635
+ {
636
+ "epoch": 0.18,
637
+ "grad_norm": 0.6400002241134644,
638
+ "learning_rate": 9.807269464225355e-06,
639
+ "loss": 0.2368,
640
+ "step": 900
641
+ },
642
+ {
643
+ "epoch": 0.182,
644
+ "grad_norm": 0.42175188660621643,
645
+ "learning_rate": 9.797554261332644e-06,
646
+ "loss": 0.2153,
647
+ "step": 910
648
+ },
649
+ {
650
+ "epoch": 0.184,
651
+ "grad_norm": 0.6213666200637817,
652
+ "learning_rate": 9.787605232413575e-06,
653
+ "loss": 0.1973,
654
+ "step": 920
655
+ },
656
+ {
657
+ "epoch": 0.186,
658
+ "grad_norm": 0.6222795248031616,
659
+ "learning_rate": 9.777422862369782e-06,
660
+ "loss": 0.2277,
661
+ "step": 930
662
+ },
663
+ {
664
+ "epoch": 0.188,
665
+ "grad_norm": 0.4923384487628937,
666
+ "learning_rate": 9.767007647475618e-06,
667
+ "loss": 0.2187,
668
+ "step": 940
669
+ },
670
+ {
671
+ "epoch": 0.19,
672
+ "grad_norm": 0.5715153813362122,
673
+ "learning_rate": 9.756360095353957e-06,
674
+ "loss": 0.2179,
675
+ "step": 950
676
+ },
677
+ {
678
+ "epoch": 0.192,
679
+ "grad_norm": 0.540091872215271,
680
+ "learning_rate": 9.745480724951473e-06,
681
+ "loss": 0.2253,
682
+ "step": 960
683
+ },
684
+ {
685
+ "epoch": 0.194,
686
+ "grad_norm": 0.6585381031036377,
687
+ "learning_rate": 9.73437006651333e-06,
688
+ "loss": 0.2161,
689
+ "step": 970
690
+ },
691
+ {
692
+ "epoch": 0.196,
693
+ "grad_norm": 0.5296498537063599,
694
+ "learning_rate": 9.723028661557345e-06,
695
+ "loss": 0.2004,
696
+ "step": 980
697
+ },
698
+ {
699
+ "epoch": 0.198,
700
+ "grad_norm": 0.7658775448799133,
701
+ "learning_rate": 9.711457062847596e-06,
702
+ "loss": 0.2166,
703
+ "step": 990
704
+ },
705
+ {
706
+ "epoch": 0.2,
707
+ "grad_norm": 0.637302577495575,
708
+ "learning_rate": 9.699655834367479e-06,
709
+ "loss": 0.221,
710
+ "step": 1000
711
+ },
712
+ {
713
+ "epoch": 0.202,
714
+ "grad_norm": 0.6880996823310852,
715
+ "learning_rate": 9.687625551292219e-06,
716
+ "loss": 0.2254,
717
+ "step": 1010
718
+ },
719
+ {
720
+ "epoch": 0.204,
721
+ "grad_norm": 0.5935792326927185,
722
+ "learning_rate": 9.675366799960842e-06,
723
+ "loss": 0.1994,
724
+ "step": 1020
725
+ },
726
+ {
727
+ "epoch": 0.206,
728
+ "grad_norm": 0.6944608688354492,
729
+ "learning_rate": 9.662880177847595e-06,
730
+ "loss": 0.2095,
731
+ "step": 1030
732
+ },
733
+ {
734
+ "epoch": 0.208,
735
+ "grad_norm": 0.5425838232040405,
736
+ "learning_rate": 9.650166293532822e-06,
737
+ "loss": 0.1937,
738
+ "step": 1040
739
+ },
740
+ {
741
+ "epoch": 0.21,
742
+ "grad_norm": 0.7364100217819214,
743
+ "learning_rate": 9.637225766673309e-06,
744
+ "loss": 0.1795,
745
+ "step": 1050
746
+ },
747
+ {
748
+ "epoch": 0.212,
749
+ "grad_norm": 0.5623259544372559,
750
+ "learning_rate": 9.624059227972077e-06,
751
+ "loss": 0.2077,
752
+ "step": 1060
753
+ },
754
+ {
755
+ "epoch": 0.214,
756
+ "grad_norm": 0.5999733209609985,
757
+ "learning_rate": 9.610667319147648e-06,
758
+ "loss": 0.2013,
759
+ "step": 1070
760
+ },
761
+ {
762
+ "epoch": 0.216,
763
+ "grad_norm": 0.4067252278327942,
764
+ "learning_rate": 9.597050692902765e-06,
765
+ "loss": 0.2224,
766
+ "step": 1080
767
+ },
768
+ {
769
+ "epoch": 0.218,
770
+ "grad_norm": 0.533978283405304,
771
+ "learning_rate": 9.583210012892582e-06,
772
+ "loss": 0.2104,
773
+ "step": 1090
774
+ },
775
+ {
776
+ "epoch": 0.22,
777
+ "grad_norm": 0.42421042919158936,
778
+ "learning_rate": 9.569145953692316e-06,
779
+ "loss": 0.218,
780
+ "step": 1100
781
+ },
782
+ {
783
+ "epoch": 0.222,
784
+ "grad_norm": 0.5804603695869446,
785
+ "learning_rate": 9.554859200764371e-06,
786
+ "loss": 0.2149,
787
+ "step": 1110
788
+ },
789
+ {
790
+ "epoch": 0.224,
791
+ "grad_norm": 0.43277624249458313,
792
+ "learning_rate": 9.540350450424927e-06,
793
+ "loss": 0.2292,
794
+ "step": 1120
795
+ },
796
+ {
797
+ "epoch": 0.226,
798
+ "grad_norm": 0.8847249746322632,
799
+ "learning_rate": 9.525620409810009e-06,
800
+ "loss": 0.2106,
801
+ "step": 1130
802
+ },
803
+ {
804
+ "epoch": 0.228,
805
+ "grad_norm": 0.4747106432914734,
806
+ "learning_rate": 9.510669796841014e-06,
807
+ "loss": 0.193,
808
+ "step": 1140
809
+ },
810
+ {
811
+ "epoch": 0.23,
812
+ "grad_norm": 0.6094072461128235,
813
+ "learning_rate": 9.495499340189729e-06,
814
+ "loss": 0.2232,
815
+ "step": 1150
816
+ },
817
+ {
818
+ "epoch": 0.232,
819
+ "grad_norm": 0.4681115448474884,
820
+ "learning_rate": 9.480109779242805e-06,
821
+ "loss": 0.2151,
822
+ "step": 1160
823
+ },
824
+ {
825
+ "epoch": 0.234,
826
+ "grad_norm": 0.680808961391449,
827
+ "learning_rate": 9.464501864065735e-06,
828
+ "loss": 0.2,
829
+ "step": 1170
830
+ },
831
+ {
832
+ "epoch": 0.236,
833
+ "grad_norm": 0.7517663240432739,
834
+ "learning_rate": 9.448676355366282e-06,
835
+ "loss": 0.2237,
836
+ "step": 1180
837
+ },
838
+ {
839
+ "epoch": 0.238,
840
+ "grad_norm": 0.5416564345359802,
841
+ "learning_rate": 9.432634024457414e-06,
842
+ "loss": 0.2098,
843
+ "step": 1190
844
+ },
845
+ {
846
+ "epoch": 0.24,
847
+ "grad_norm": 0.5150811076164246,
848
+ "learning_rate": 9.41637565321971e-06,
849
+ "loss": 0.2061,
850
+ "step": 1200
851
+ },
852
+ {
853
+ "epoch": 0.242,
854
+ "grad_norm": 0.9107248783111572,
855
+ "learning_rate": 9.399902034063244e-06,
856
+ "loss": 0.2195,
857
+ "step": 1210
858
+ },
859
+ {
860
+ "epoch": 0.244,
861
+ "grad_norm": 0.6879210472106934,
862
+ "learning_rate": 9.383213969888972e-06,
863
+ "loss": 0.2038,
864
+ "step": 1220
865
+ },
866
+ {
867
+ "epoch": 0.246,
868
+ "grad_norm": 0.5012656450271606,
869
+ "learning_rate": 9.366312274049602e-06,
870
+ "loss": 0.2094,
871
+ "step": 1230
872
+ },
873
+ {
874
+ "epoch": 0.248,
875
+ "grad_norm": 0.7412648797035217,
876
+ "learning_rate": 9.349197770309942e-06,
877
+ "loss": 0.2091,
878
+ "step": 1240
879
+ },
880
+ {
881
+ "epoch": 0.25,
882
+ "grad_norm": 0.41605156660079956,
883
+ "learning_rate": 9.33187129280676e-06,
884
+ "loss": 0.2132,
885
+ "step": 1250
886
+ },
887
+ {
888
+ "epoch": 0.252,
889
+ "grad_norm": 0.4487737715244293,
890
+ "learning_rate": 9.314333686008125e-06,
891
+ "loss": 0.2101,
892
+ "step": 1260
893
+ },
894
+ {
895
+ "epoch": 0.254,
896
+ "grad_norm": 0.6217042207717896,
897
+ "learning_rate": 9.296585804672253e-06,
898
+ "loss": 0.2189,
899
+ "step": 1270
900
+ },
901
+ {
902
+ "epoch": 0.256,
903
+ "grad_norm": 0.6217819452285767,
904
+ "learning_rate": 9.278628513805838e-06,
905
+ "loss": 0.2071,
906
+ "step": 1280
907
+ },
908
+ {
909
+ "epoch": 0.258,
910
+ "grad_norm": 0.5297917127609253,
911
+ "learning_rate": 9.260462688621906e-06,
912
+ "loss": 0.1955,
913
+ "step": 1290
914
+ },
915
+ {
916
+ "epoch": 0.26,
917
+ "grad_norm": 0.9292225241661072,
918
+ "learning_rate": 9.242089214497146e-06,
919
+ "loss": 0.2235,
920
+ "step": 1300
921
+ },
922
+ {
923
+ "epoch": 0.262,
924
+ "grad_norm": 1.318722128868103,
925
+ "learning_rate": 9.223508986928766e-06,
926
+ "loss": 0.2089,
927
+ "step": 1310
928
+ },
929
+ {
930
+ "epoch": 0.264,
931
+ "grad_norm": 0.5659732818603516,
932
+ "learning_rate": 9.204722911490847e-06,
933
+ "loss": 0.2117,
934
+ "step": 1320
935
+ },
936
+ {
937
+ "epoch": 0.266,
938
+ "grad_norm": 0.6121715903282166,
939
+ "learning_rate": 9.1857319037902e-06,
940
+ "loss": 0.2219,
941
+ "step": 1330
942
+ },
943
+ {
944
+ "epoch": 0.268,
945
+ "grad_norm": 0.5208039879798889,
946
+ "learning_rate": 9.16653688942175e-06,
947
+ "loss": 0.1786,
948
+ "step": 1340
949
+ },
950
+ {
951
+ "epoch": 0.27,
952
+ "grad_norm": 0.5769920349121094,
953
+ "learning_rate": 9.147138803923417e-06,
954
+ "loss": 0.2123,
955
+ "step": 1350
956
+ },
957
+ {
958
+ "epoch": 0.272,
959
+ "grad_norm": 0.5934658646583557,
960
+ "learning_rate": 9.12753859273052e-06,
961
+ "loss": 0.2052,
962
+ "step": 1360
963
+ },
964
+ {
965
+ "epoch": 0.274,
966
+ "grad_norm": 0.5169550776481628,
967
+ "learning_rate": 9.107737211129702e-06,
968
+ "loss": 0.2033,
969
+ "step": 1370
970
+ },
971
+ {
972
+ "epoch": 0.276,
973
+ "grad_norm": 0.43102511763572693,
974
+ "learning_rate": 9.087735624212365e-06,
975
+ "loss": 0.2112,
976
+ "step": 1380
977
+ },
978
+ {
979
+ "epoch": 0.278,
980
+ "grad_norm": 0.7378923892974854,
981
+ "learning_rate": 9.06753480682764e-06,
982
+ "loss": 0.2407,
983
+ "step": 1390
984
+ },
985
+ {
986
+ "epoch": 0.28,
987
+ "grad_norm": 0.7497076988220215,
988
+ "learning_rate": 9.047135743534866e-06,
989
+ "loss": 0.2222,
990
+ "step": 1400
991
+ },
992
+ {
993
+ "epoch": 0.282,
994
+ "grad_norm": 0.5095514059066772,
995
+ "learning_rate": 9.026539428555609e-06,
996
+ "loss": 0.2226,
997
+ "step": 1410
998
+ },
999
+ {
1000
+ "epoch": 0.284,
1001
+ "grad_norm": 0.5478781461715698,
1002
+ "learning_rate": 9.005746865725206e-06,
1003
+ "loss": 0.1907,
1004
+ "step": 1420
1005
+ },
1006
+ {
1007
+ "epoch": 0.286,
1008
+ "grad_norm": 0.4810701012611389,
1009
+ "learning_rate": 8.984759068443832e-06,
1010
+ "loss": 0.1994,
1011
+ "step": 1430
1012
+ },
1013
+ {
1014
+ "epoch": 0.288,
1015
+ "grad_norm": 0.9713486433029175,
1016
+ "learning_rate": 8.963577059627117e-06,
1017
+ "loss": 0.1909,
1018
+ "step": 1440
1019
+ },
1020
+ {
1021
+ "epoch": 0.29,
1022
+ "grad_norm": 0.8102449774742126,
1023
+ "learning_rate": 8.942201871656292e-06,
1024
+ "loss": 0.2242,
1025
+ "step": 1450
1026
+ },
1027
+ {
1028
+ "epoch": 0.292,
1029
+ "grad_norm": 0.47727829217910767,
1030
+ "learning_rate": 8.920634546327857e-06,
1031
+ "loss": 0.2414,
1032
+ "step": 1460
1033
+ },
1034
+ {
1035
+ "epoch": 0.294,
1036
+ "grad_norm": 0.6131921410560608,
1037
+ "learning_rate": 8.898876134802827e-06,
1038
+ "loss": 0.2011,
1039
+ "step": 1470
1040
+ },
1041
+ {
1042
+ "epoch": 0.296,
1043
+ "grad_norm": 0.6480145454406738,
1044
+ "learning_rate": 8.87692769755548e-06,
1045
+ "loss": 0.2066,
1046
+ "step": 1480
1047
+ },
1048
+ {
1049
+ "epoch": 0.298,
1050
+ "grad_norm": 2.078758716583252,
1051
+ "learning_rate": 8.854790304321682e-06,
1052
+ "loss": 0.2173,
1053
+ "step": 1490
1054
+ },
1055
+ {
1056
+ "epoch": 0.3,
1057
+ "grad_norm": 0.40884819626808167,
1058
+ "learning_rate": 8.83246503404675e-06,
1059
+ "loss": 0.2071,
1060
+ "step": 1500
1061
+ },
1062
+ {
1063
+ "epoch": 0.302,
1064
+ "grad_norm": 0.5149683952331543,
1065
+ "learning_rate": 8.80995297483286e-06,
1066
+ "loss": 0.2102,
1067
+ "step": 1510
1068
+ },
1069
+ {
1070
+ "epoch": 0.304,
1071
+ "grad_norm": 1.1087095737457275,
1072
+ "learning_rate": 8.78725522388602e-06,
1073
+ "loss": 0.2045,
1074
+ "step": 1520
1075
+ },
1076
+ {
1077
+ "epoch": 0.306,
1078
+ "grad_norm": 0.6572810411453247,
1079
+ "learning_rate": 8.764372887462587e-06,
1080
+ "loss": 0.2223,
1081
+ "step": 1530
1082
+ },
1083
+ {
1084
+ "epoch": 0.308,
1085
+ "grad_norm": 0.6297303438186646,
1086
+ "learning_rate": 8.741307080815357e-06,
1087
+ "loss": 0.2153,
1088
+ "step": 1540
1089
+ },
1090
+ {
1091
+ "epoch": 0.31,
1092
+ "grad_norm": 0.5744212865829468,
1093
+ "learning_rate": 8.718058928139205e-06,
1094
+ "loss": 0.1852,
1095
+ "step": 1550
1096
+ },
1097
+ {
1098
+ "epoch": 0.312,
1099
+ "grad_norm": 0.5409930944442749,
1100
+ "learning_rate": 8.694629562516295e-06,
1101
+ "loss": 0.2224,
1102
+ "step": 1560
1103
+ },
1104
+ {
1105
+ "epoch": 0.314,
1106
+ "grad_norm": 1.185879111289978,
1107
+ "learning_rate": 8.671020125860851e-06,
1108
+ "loss": 0.1934,
1109
+ "step": 1570
1110
+ },
1111
+ {
1112
+ "epoch": 0.316,
1113
+ "grad_norm": 0.5738818645477295,
1114
+ "learning_rate": 8.647231768863513e-06,
1115
+ "loss": 0.1942,
1116
+ "step": 1580
1117
+ },
1118
+ {
1119
+ "epoch": 0.318,
1120
+ "grad_norm": 0.6859444975852966,
1121
+ "learning_rate": 8.623265650935233e-06,
1122
+ "loss": 0.1992,
1123
+ "step": 1590
1124
+ },
1125
+ {
1126
+ "epoch": 0.32,
1127
+ "grad_norm": 0.4545342028141022,
1128
+ "learning_rate": 8.599122940150795e-06,
1129
+ "loss": 0.1871,
1130
+ "step": 1600
1131
+ },
1132
+ {
1133
+ "epoch": 0.322,
1134
+ "grad_norm": 0.5511049032211304,
1135
+ "learning_rate": 8.574804813191859e-06,
1136
+ "loss": 0.2247,
1137
+ "step": 1610
1138
+ },
1139
+ {
1140
+ "epoch": 0.324,
1141
+ "grad_norm": 0.4010733664035797,
1142
+ "learning_rate": 8.550312455289624e-06,
1143
+ "loss": 0.2112,
1144
+ "step": 1620
1145
+ },
1146
+ {
1147
+ "epoch": 0.326,
1148
+ "grad_norm": 0.5987499952316284,
1149
+ "learning_rate": 8.525647060167063e-06,
1150
+ "loss": 0.1989,
1151
+ "step": 1630
1152
+ },
1153
+ {
1154
+ "epoch": 0.328,
1155
+ "grad_norm": 0.6073696613311768,
1156
+ "learning_rate": 8.500809829980734e-06,
1157
+ "loss": 0.1986,
1158
+ "step": 1640
1159
+ },
1160
+ {
1161
+ "epoch": 0.33,
1162
+ "grad_norm": 0.5286404490470886,
1163
+ "learning_rate": 8.4758019752622e-06,
1164
+ "loss": 0.2266,
1165
+ "step": 1650
1166
+ },
1167
+ {
1168
+ "epoch": 0.332,
1169
+ "grad_norm": 0.6704223155975342,
1170
+ "learning_rate": 8.450624714859016e-06,
1171
+ "loss": 0.2143,
1172
+ "step": 1660
1173
+ },
1174
+ {
1175
+ "epoch": 0.334,
1176
+ "grad_norm": 0.47345027327537537,
1177
+ "learning_rate": 8.425279275875336e-06,
1178
+ "loss": 0.2195,
1179
+ "step": 1670
1180
+ },
1181
+ {
1182
+ "epoch": 0.336,
1183
+ "grad_norm": 0.8093699812889099,
1184
+ "learning_rate": 8.399766893612096e-06,
1185
+ "loss": 0.1883,
1186
+ "step": 1680
1187
+ },
1188
+ {
1189
+ "epoch": 0.338,
1190
+ "grad_norm": 0.4623982310295105,
1191
+ "learning_rate": 8.374088811506819e-06,
1192
+ "loss": 0.2301,
1193
+ "step": 1690
1194
+ },
1195
+ {
1196
+ "epoch": 0.34,
1197
+ "grad_norm": 0.4242282509803772,
1198
+ "learning_rate": 8.348246281072998e-06,
1199
+ "loss": 0.213,
1200
+ "step": 1700
1201
+ },
1202
+ {
1203
+ "epoch": 0.342,
1204
+ "grad_norm": 0.5219111442565918,
1205
+ "learning_rate": 8.32224056183911e-06,
1206
+ "loss": 0.21,
1207
+ "step": 1710
1208
+ },
1209
+ {
1210
+ "epoch": 0.344,
1211
+ "grad_norm": 0.5398066639900208,
1212
+ "learning_rate": 8.296072921287217e-06,
1213
+ "loss": 0.1822,
1214
+ "step": 1720
1215
+ },
1216
+ {
1217
+ "epoch": 0.346,
1218
+ "grad_norm": 0.8422920107841492,
1219
+ "learning_rate": 8.269744634791207e-06,
1220
+ "loss": 0.1957,
1221
+ "step": 1730
1222
+ },
1223
+ {
1224
+ "epoch": 0.348,
1225
+ "grad_norm": 0.4480317533016205,
1226
+ "learning_rate": 8.243256985554622e-06,
1227
+ "loss": 0.2037,
1228
+ "step": 1740
1229
+ },
1230
+ {
1231
+ "epoch": 0.35,
1232
+ "grad_norm": 0.7563358545303345,
1233
+ "learning_rate": 8.21661126454811e-06,
1234
+ "loss": 0.2019,
1235
+ "step": 1750
1236
+ },
1237
+ {
1238
+ "epoch": 0.352,
1239
+ "grad_norm": 1.0024635791778564,
1240
+ "learning_rate": 8.189808770446528e-06,
1241
+ "loss": 0.1966,
1242
+ "step": 1760
1243
+ },
1244
+ {
1245
+ "epoch": 0.354,
1246
+ "grad_norm": 0.5437222123146057,
1247
+ "learning_rate": 8.162850809565623e-06,
1248
+ "loss": 0.2021,
1249
+ "step": 1770
1250
+ },
1251
+ {
1252
+ "epoch": 0.356,
1253
+ "grad_norm": 1.7502257823944092,
1254
+ "learning_rate": 8.135738695798377e-06,
1255
+ "loss": 0.2106,
1256
+ "step": 1780
1257
+ },
1258
+ {
1259
+ "epoch": 0.358,
1260
+ "grad_norm": 0.3269011974334717,
1261
+ "learning_rate": 8.108473750550965e-06,
1262
+ "loss": 0.188,
1263
+ "step": 1790
1264
+ },
1265
+ {
1266
+ "epoch": 0.36,
1267
+ "grad_norm": 0.49707913398742676,
1268
+ "learning_rate": 8.081057302678352e-06,
1269
+ "loss": 0.2354,
1270
+ "step": 1800
1271
+ },
1272
+ {
1273
+ "epoch": 0.362,
1274
+ "grad_norm": 0.8653764724731445,
1275
+ "learning_rate": 8.053490688419532e-06,
1276
+ "loss": 0.2325,
1277
+ "step": 1810
1278
+ },
1279
+ {
1280
+ "epoch": 0.364,
1281
+ "grad_norm": 0.7088777422904968,
1282
+ "learning_rate": 8.02577525133239e-06,
1283
+ "loss": 0.1987,
1284
+ "step": 1820
1285
+ },
1286
+ {
1287
+ "epoch": 0.366,
1288
+ "grad_norm": 0.9555034637451172,
1289
+ "learning_rate": 7.997912342228232e-06,
1290
+ "loss": 0.1952,
1291
+ "step": 1830
1292
+ },
1293
+ {
1294
+ "epoch": 0.368,
1295
+ "grad_norm": 0.4464254081249237,
1296
+ "learning_rate": 7.969903319105935e-06,
1297
+ "loss": 0.2173,
1298
+ "step": 1840
1299
+ },
1300
+ {
1301
+ "epoch": 0.37,
1302
+ "grad_norm": 0.8708261847496033,
1303
+ "learning_rate": 7.941749547085778e-06,
1304
+ "loss": 0.2115,
1305
+ "step": 1850
1306
+ },
1307
+ {
1308
+ "epoch": 0.372,
1309
+ "grad_norm": 0.47305262088775635,
1310
+ "learning_rate": 7.913452398342882e-06,
1311
+ "loss": 0.1974,
1312
+ "step": 1860
1313
+ },
1314
+ {
1315
+ "epoch": 0.374,
1316
+ "grad_norm": 0.5733006596565247,
1317
+ "learning_rate": 7.88501325204036e-06,
1318
+ "loss": 0.1877,
1319
+ "step": 1870
1320
+ },
1321
+ {
1322
+ "epoch": 0.376,
1323
+ "grad_norm": 0.7463773488998413,
1324
+ "learning_rate": 7.856433494262078e-06,
1325
+ "loss": 0.2277,
1326
+ "step": 1880
1327
+ },
1328
+ {
1329
+ "epoch": 0.378,
1330
+ "grad_norm": 0.47928038239479065,
1331
+ "learning_rate": 7.827714517945116e-06,
1332
+ "loss": 0.2225,
1333
+ "step": 1890
1334
+ },
1335
+ {
1336
+ "epoch": 0.38,
1337
+ "grad_norm": 0.8981123566627502,
1338
+ "learning_rate": 7.798857722811857e-06,
1339
+ "loss": 0.1872,
1340
+ "step": 1900
1341
+ },
1342
+ {
1343
+ "epoch": 0.382,
1344
+ "grad_norm": 0.5608500838279724,
1345
+ "learning_rate": 7.769864515301787e-06,
1346
+ "loss": 0.23,
1347
+ "step": 1910
1348
+ },
1349
+ {
1350
+ "epoch": 0.384,
1351
+ "grad_norm": 0.6065028309822083,
1352
+ "learning_rate": 7.740736308502939e-06,
1353
+ "loss": 0.2107,
1354
+ "step": 1920
1355
+ },
1356
+ {
1357
+ "epoch": 0.386,
1358
+ "grad_norm": 0.5508809685707092,
1359
+ "learning_rate": 7.711474522083015e-06,
1360
+ "loss": 0.2218,
1361
+ "step": 1930
1362
+ },
1363
+ {
1364
+ "epoch": 0.388,
1365
+ "grad_norm": 1.8120936155319214,
1366
+ "learning_rate": 7.682080582220206e-06,
1367
+ "loss": 0.2032,
1368
+ "step": 1940
1369
+ },
1370
+ {
1371
+ "epoch": 0.39,
1372
+ "grad_norm": 0.4027613401412964,
1373
+ "learning_rate": 7.652555921533671e-06,
1374
+ "loss": 0.1981,
1375
+ "step": 1950
1376
+ },
1377
+ {
1378
+ "epoch": 0.392,
1379
+ "grad_norm": 0.4585378170013428,
1380
+ "learning_rate": 7.622901979013717e-06,
1381
+ "loss": 0.1834,
1382
+ "step": 1960
1383
+ },
1384
+ {
1385
+ "epoch": 0.394,
1386
+ "grad_norm": 0.5401368141174316,
1387
+ "learning_rate": 7.5931201999516715e-06,
1388
+ "loss": 0.2236,
1389
+ "step": 1970
1390
+ },
1391
+ {
1392
+ "epoch": 0.396,
1393
+ "grad_norm": 0.5511544346809387,
1394
+ "learning_rate": 7.563212035869426e-06,
1395
+ "loss": 0.2057,
1396
+ "step": 1980
1397
+ },
1398
+ {
1399
+ "epoch": 0.398,
1400
+ "grad_norm": 0.6503185629844666,
1401
+ "learning_rate": 7.533178944448705e-06,
1402
+ "loss": 0.2298,
1403
+ "step": 1990
1404
+ },
1405
+ {
1406
+ "epoch": 0.4,
1407
+ "grad_norm": 0.49653172492980957,
1408
+ "learning_rate": 7.503022389460014e-06,
1409
+ "loss": 0.2024,
1410
+ "step": 2000
1411
+ }
1412
+ ],
1413
+ "logging_steps": 10,
1414
+ "max_steps": 5000,
1415
+ "num_input_tokens_seen": 0,
1416
+ "num_train_epochs": 9223372036854775807,
1417
+ "save_steps": 500,
1418
+ "stateful_callbacks": {
1419
+ "TrainerControl": {
1420
+ "args": {
1421
+ "should_epoch_stop": false,
1422
+ "should_evaluate": false,
1423
+ "should_log": false,
1424
+ "should_save": true,
1425
+ "should_training_stop": false
1426
+ },
1427
+ "attributes": {}
1428
+ }
1429
+ },
1430
+ "total_flos": 1.052132981104391e+19,
1431
+ "train_batch_size": 1,
1432
+ "trial_name": null,
1433
+ "trial_params": null
1434
+ }
mixed_all_diff_v5_350k/checkpoint-2000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2840099ebff8df937a59cc9c358c7cdca866a9a0799e8e4483789e8314fd4a50
3
+ size 7416
mixed_all_diff_v5_350k/checkpoint-2000/vocab.json ADDED
The diff for this file is too large to render. See raw diff