Hugging Face's logo

jan-hq
/
voxel-representation-gemma3-4b-cp-300

Safetensors
gemma3
Model card Files Community
jan-hq commited on
Commit
d12d58a
·
verified ·
1 Parent(s): 197c7ab

Upload checkpoint-300

Browse files
Files changed (26) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +3 -0
  3. config.json +60 -0
  4. generation_config.json +13 -0
  5. latest +1 -0
  6. model-00001-of-00002.safetensors +3 -0
  7. model-00002-of-00002.safetensors +3 -0
  8. model.safetensors.index.json +891 -0
  9. preprocessor_config.json +29 -0
  10. processor_config.json +4 -0
  11. rng_state_0.pth +3 -0
  12. rng_state_1.pth +3 -0
  13. rng_state_2.pth +3 -0
  14. rng_state_3.pth +3 -0
  15. rng_state_4.pth +3 -0
  16. rng_state_5.pth +3 -0
  17. rng_state_6.pth +3 -0
  18. rng_state_7.pth +3 -0
  19. scheduler.pt +3 -0
  20. special_tokens_map.json +42 -0
  21. tokenizer.json +3 -0
  22. tokenizer.model +3 -0
  23. tokenizer_config.json +0 -0
  24. trainer_state.json +2157 -0
  25. training_args.bin +3 -0
  26. zero_to_fp32.py +760 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<image_soft_token>": 262144
3
+ }
config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Gemma3ForConditionalGeneration"
4
+ ],
5
+ "boi_token_index": 255999,
6
+ "eoi_token_index": 256000,
7
+ "hidden_size": 2560,
8
+ "image_token_index": 262144,
9
+ "initializer_range": 0.02,
10
+ "mm_tokens_per_image": 256,
11
+ "model_type": "gemma3",
12
+ "text_config": {
13
+ "attention_bias": false,
14
+ "attention_dropout": 0.0,
15
+ "attn_logit_softcapping": null,
16
+ "cache_implementation": "hybrid",
17
+ "final_logit_softcapping": null,
18
+ "head_dim": 256,
19
+ "hidden_activation": "gelu_pytorch_tanh",
20
+ "hidden_size": 2560,
21
+ "initializer_range": 0.02,
22
+ "intermediate_size": 10240,
23
+ "max_position_embeddings": 131072,
24
+ "model_type": "gemma3_text",
25
+ "num_attention_heads": 8,
26
+ "num_hidden_layers": 34,
27
+ "num_key_value_heads": 4,
28
+ "query_pre_attn_scalar": 256,
29
+ "rms_norm_eps": 1e-06,
30
+ "rope_local_base_freq": 10000.0,
31
+ "rope_scaling": {
32
+ "factor": 8.0,
33
+ "rope_type": "linear"
34
+ },
35
+ "rope_theta": 1000000.0,
36
+ "sliding_window": 1024,
37
+ "sliding_window_pattern": 6,
38
+ "torch_dtype": "bfloat16",
39
+ "use_cache": true,
40
+ "vocab_size": 262208
41
+ },
42
+ "torch_dtype": "bfloat16",
43
+ "transformers_version": "4.50.0.dev0",
44
+ "use_cache": false,
45
+ "vision_config": {
46
+ "attention_dropout": 0.0,
47
+ "hidden_act": "gelu_pytorch_tanh",
48
+ "hidden_size": 1152,
49
+ "image_size": 896,
50
+ "intermediate_size": 4304,
51
+ "layer_norm_eps": 1e-06,
52
+ "model_type": "siglip_vision_model",
53
+ "num_attention_heads": 16,
54
+ "num_channels": 3,
55
+ "num_hidden_layers": 27,
56
+ "patch_size": 14,
57
+ "torch_dtype": "bfloat16",
58
+ "vision_use_head": false
59
+ }
60
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 2,
3
+ "cache_implementation": "hybrid",
4
+ "do_sample": true,
5
+ "eos_token_id": [
6
+ 1,
7
+ 106
8
+ ],
9
+ "pad_token_id": 0,
10
+ "top_k": 64,
11
+ "top_p": 0.95,
12
+ "transformers_version": "4.50.0.dev0"
13
+ }
latest ADDED
@@ -0,0 +1 @@
 
 
1
+ global_step300
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43b3113767bd3a2b901d3f2e73418043d1063a2fd5b72d72b73c1b68e464dc32
3
+ size 4961251752
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5b33286a295cbb40ded06eef3afed8c18e7be1bc66fbbf61e0b5bcb02aef93d
3
+ size 4981531360
model.safetensors.index.json ADDED
@@ -0,0 +1,891 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 9942663904
4
+ },
5
+ "weight_map": {
6
+ "language_model.lm_head.weight": "model-00002-of-00002.safetensors",
7
+ "language_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
+ "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
9
+ "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
10
+ "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
11
+ "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
12
+ "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
13
+ "language_model.model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
14
+ "language_model.model.layers.0.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
15
+ "language_model.model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
16
+ "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
17
+ "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
18
+ "language_model.model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
19
+ "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
20
+ "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
21
+ "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
22
+ "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
23
+ "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
24
+ "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
25
+ "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
26
+ "language_model.model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
27
+ "language_model.model.layers.1.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
28
+ "language_model.model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
29
+ "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
30
+ "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
31
+ "language_model.model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
32
+ "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
33
+ "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
34
+ "language_model.model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
35
+ "language_model.model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
36
+ "language_model.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
37
+ "language_model.model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
38
+ "language_model.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
39
+ "language_model.model.layers.10.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
40
+ "language_model.model.layers.10.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
41
+ "language_model.model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
42
+ "language_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
43
+ "language_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
44
+ "language_model.model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
45
+ "language_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
46
+ "language_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
47
+ "language_model.model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
48
+ "language_model.model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
49
+ "language_model.model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
50
+ "language_model.model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
51
+ "language_model.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
52
+ "language_model.model.layers.11.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
53
+ "language_model.model.layers.11.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
54
+ "language_model.model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
55
+ "language_model.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
56
+ "language_model.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
57
+ "language_model.model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
58
+ "language_model.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
59
+ "language_model.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
60
+ "language_model.model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
61
+ "language_model.model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
62
+ "language_model.model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
63
+ "language_model.model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
64
+ "language_model.model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
65
+ "language_model.model.layers.12.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
66
+ "language_model.model.layers.12.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
67
+ "language_model.model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
68
+ "language_model.model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
69
+ "language_model.model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
70
+ "language_model.model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
71
+ "language_model.model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
72
+ "language_model.model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
73
+ "language_model.model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
74
+ "language_model.model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
75
+ "language_model.model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
76
+ "language_model.model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
77
+ "language_model.model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
78
+ "language_model.model.layers.13.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
79
+ "language_model.model.layers.13.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
80
+ "language_model.model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
81
+ "language_model.model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
82
+ "language_model.model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
83
+ "language_model.model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
84
+ "language_model.model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
85
+ "language_model.model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
86
+ "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
87
+ "language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
88
+ "language_model.model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
89
+ "language_model.model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
90
+ "language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
91
+ "language_model.model.layers.14.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
92
+ "language_model.model.layers.14.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
93
+ "language_model.model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
94
+ "language_model.model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
95
+ "language_model.model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
96
+ "language_model.model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
97
+ "language_model.model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
98
+ "language_model.model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
99
+ "language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
100
+ "language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
101
+ "language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
102
+ "language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
103
+ "language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
104
+ "language_model.model.layers.15.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
105
+ "language_model.model.layers.15.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
106
+ "language_model.model.layers.15.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
107
+ "language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
108
+ "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
109
+ "language_model.model.layers.15.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
110
+ "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
111
+ "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
112
+ "language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
113
+ "language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
114
+ "language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
115
+ "language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
116
+ "language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
117
+ "language_model.model.layers.16.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
118
+ "language_model.model.layers.16.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
119
+ "language_model.model.layers.16.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
120
+ "language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
121
+ "language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
122
+ "language_model.model.layers.16.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
123
+ "language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
124
+ "language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
125
+ "language_model.model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
126
+ "language_model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
127
+ "language_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
128
+ "language_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
129
+ "language_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
130
+ "language_model.model.layers.17.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
131
+ "language_model.model.layers.17.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
132
+ "language_model.model.layers.17.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
133
+ "language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
134
+ "language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
135
+ "language_model.model.layers.17.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
136
+ "language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
137
+ "language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
138
+ "language_model.model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
139
+ "language_model.model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
140
+ "language_model.model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
141
+ "language_model.model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
142
+ "language_model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
143
+ "language_model.model.layers.18.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
144
+ "language_model.model.layers.18.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
145
+ "language_model.model.layers.18.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
146
+ "language_model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
147
+ "language_model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
148
+ "language_model.model.layers.18.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
149
+ "language_model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
150
+ "language_model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
151
+ "language_model.model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
152
+ "language_model.model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
153
+ "language_model.model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
154
+ "language_model.model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
155
+ "language_model.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
156
+ "language_model.model.layers.19.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
157
+ "language_model.model.layers.19.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
158
+ "language_model.model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
159
+ "language_model.model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
160
+ "language_model.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
161
+ "language_model.model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
162
+ "language_model.model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
163
+ "language_model.model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
164
+ "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
165
+ "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
166
+ "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
167
+ "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
168
+ "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
169
+ "language_model.model.layers.2.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
170
+ "language_model.model.layers.2.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
171
+ "language_model.model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
172
+ "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
173
+ "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
174
+ "language_model.model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
175
+ "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
176
+ "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
177
+ "language_model.model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
178
+ "language_model.model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
179
+ "language_model.model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
180
+ "language_model.model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
181
+ "language_model.model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
182
+ "language_model.model.layers.20.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
183
+ "language_model.model.layers.20.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
184
+ "language_model.model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
185
+ "language_model.model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
186
+ "language_model.model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
187
+ "language_model.model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
188
+ "language_model.model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
189
+ "language_model.model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
190
+ "language_model.model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
191
+ "language_model.model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
192
+ "language_model.model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
193
+ "language_model.model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
194
+ "language_model.model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
195
+ "language_model.model.layers.21.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
196
+ "language_model.model.layers.21.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
197
+ "language_model.model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
198
+ "language_model.model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
199
+ "language_model.model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
200
+ "language_model.model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
201
+ "language_model.model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
202
+ "language_model.model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
203
+ "language_model.model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
204
+ "language_model.model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
205
+ "language_model.model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
206
+ "language_model.model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
207
+ "language_model.model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
208
+ "language_model.model.layers.22.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
209
+ "language_model.model.layers.22.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
210
+ "language_model.model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
211
+ "language_model.model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
212
+ "language_model.model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
213
+ "language_model.model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
214
+ "language_model.model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
215
+ "language_model.model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
216
+ "language_model.model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
217
+ "language_model.model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
218
+ "language_model.model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
219
+ "language_model.model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
220
+ "language_model.model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
221
+ "language_model.model.layers.23.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
222
+ "language_model.model.layers.23.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
223
+ "language_model.model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
224
+ "language_model.model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
225
+ "language_model.model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
226
+ "language_model.model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
227
+ "language_model.model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
228
+ "language_model.model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
229
+ "language_model.model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
230
+ "language_model.model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
231
+ "language_model.model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
232
+ "language_model.model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
233
+ "language_model.model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
234
+ "language_model.model.layers.24.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
235
+ "language_model.model.layers.24.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
236
+ "language_model.model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
237
+ "language_model.model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
238
+ "language_model.model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
239
+ "language_model.model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
240
+ "language_model.model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
241
+ "language_model.model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
242
+ "language_model.model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
243
+ "language_model.model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
244
+ "language_model.model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
245
+ "language_model.model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
246
+ "language_model.model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
247
+ "language_model.model.layers.25.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
248
+ "language_model.model.layers.25.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
249
+ "language_model.model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
250
+ "language_model.model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
251
+ "language_model.model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
252
+ "language_model.model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
253
+ "language_model.model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
254
+ "language_model.model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
255
+ "language_model.model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
256
+ "language_model.model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
257
+ "language_model.model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
258
+ "language_model.model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
259
+ "language_model.model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
260
+ "language_model.model.layers.26.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
261
+ "language_model.model.layers.26.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
262
+ "language_model.model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
263
+ "language_model.model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
264
+ "language_model.model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
265
+ "language_model.model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
266
+ "language_model.model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
267
+ "language_model.model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
268
+ "language_model.model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
269
+ "language_model.model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
270
+ "language_model.model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
271
+ "language_model.model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
272
+ "language_model.model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
273
+ "language_model.model.layers.27.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
274
+ "language_model.model.layers.27.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
275
+ "language_model.model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
276
+ "language_model.model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
277
+ "language_model.model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
278
+ "language_model.model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
279
+ "language_model.model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
280
+ "language_model.model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
281
+ "language_model.model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
282
+ "language_model.model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
283
+ "language_model.model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
284
+ "language_model.model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
285
+ "language_model.model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
286
+ "language_model.model.layers.28.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
287
+ "language_model.model.layers.28.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
288
+ "language_model.model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
289
+ "language_model.model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
290
+ "language_model.model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
291
+ "language_model.model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
292
+ "language_model.model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
293
+ "language_model.model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
294
+ "language_model.model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
295
+ "language_model.model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
296
+ "language_model.model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
297
+ "language_model.model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
298
+ "language_model.model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
299
+ "language_model.model.layers.29.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
300
+ "language_model.model.layers.29.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
301
+ "language_model.model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
302
+ "language_model.model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
303
+ "language_model.model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
304
+ "language_model.model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
305
+ "language_model.model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
306
+ "language_model.model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
307
+ "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
308
+ "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
309
+ "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
310
+ "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
311
+ "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
312
+ "language_model.model.layers.3.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
313
+ "language_model.model.layers.3.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
314
+ "language_model.model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
315
+ "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
316
+ "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
317
+ "language_model.model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
318
+ "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
319
+ "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
320
+ "language_model.model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
321
+ "language_model.model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
322
+ "language_model.model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
323
+ "language_model.model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
324
+ "language_model.model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
325
+ "language_model.model.layers.30.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
326
+ "language_model.model.layers.30.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
327
+ "language_model.model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
328
+ "language_model.model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
329
+ "language_model.model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
330
+ "language_model.model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
331
+ "language_model.model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
332
+ "language_model.model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
333
+ "language_model.model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
334
+ "language_model.model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
335
+ "language_model.model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
336
+ "language_model.model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
337
+ "language_model.model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
338
+ "language_model.model.layers.31.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
339
+ "language_model.model.layers.31.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
340
+ "language_model.model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
341
+ "language_model.model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
342
+ "language_model.model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
343
+ "language_model.model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
344
+ "language_model.model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
345
+ "language_model.model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
346
+ "language_model.model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
347
+ "language_model.model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
348
+ "language_model.model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
349
+ "language_model.model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
350
+ "language_model.model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
351
+ "language_model.model.layers.32.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
352
+ "language_model.model.layers.32.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
353
+ "language_model.model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
354
+ "language_model.model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
355
+ "language_model.model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
356
+ "language_model.model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
357
+ "language_model.model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
358
+ "language_model.model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
359
+ "language_model.model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
360
+ "language_model.model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
361
+ "language_model.model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
362
+ "language_model.model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
363
+ "language_model.model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
364
+ "language_model.model.layers.33.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
365
+ "language_model.model.layers.33.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
366
+ "language_model.model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
367
+ "language_model.model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
368
+ "language_model.model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
369
+ "language_model.model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
370
+ "language_model.model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
371
+ "language_model.model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
372
+ "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
373
+ "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
374
+ "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
375
+ "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
376
+ "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
377
+ "language_model.model.layers.4.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
378
+ "language_model.model.layers.4.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
379
+ "language_model.model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
380
+ "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
381
+ "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
382
+ "language_model.model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
383
+ "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
384
+ "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
385
+ "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
386
+ "language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
387
+ "language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
388
+ "language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
389
+ "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
390
+ "language_model.model.layers.5.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
391
+ "language_model.model.layers.5.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
392
+ "language_model.model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
393
+ "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
394
+ "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
395
+ "language_model.model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
396
+ "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
397
+ "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
398
+ "language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
399
+ "language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
400
+ "language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
401
+ "language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
402
+ "language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
403
+ "language_model.model.layers.6.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
404
+ "language_model.model.layers.6.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
405
+ "language_model.model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
406
+ "language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
407
+ "language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
408
+ "language_model.model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
409
+ "language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
410
+ "language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
411
+ "language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
412
+ "language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
413
+ "language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
414
+ "language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
415
+ "language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
416
+ "language_model.model.layers.7.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
417
+ "language_model.model.layers.7.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
418
+ "language_model.model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
419
+ "language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
420
+ "language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
421
+ "language_model.model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
422
+ "language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
423
+ "language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
424
+ "language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
425
+ "language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
426
+ "language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
427
+ "language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
428
+ "language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
429
+ "language_model.model.layers.8.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
430
+ "language_model.model.layers.8.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
431
+ "language_model.model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
432
+ "language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
433
+ "language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
434
+ "language_model.model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
435
+ "language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
436
+ "language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
437
+ "language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
438
+ "language_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
439
+ "language_model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
440
+ "language_model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
441
+ "language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
442
+ "language_model.model.layers.9.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
443
+ "language_model.model.layers.9.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
444
+ "language_model.model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
445
+ "language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
446
+ "language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
447
+ "language_model.model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
448
+ "language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
449
+ "language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
450
+ "language_model.model.norm.weight": "model-00002-of-00002.safetensors",
451
+ "multi_modal_projector.mm_input_projection_weight": "model-00001-of-00002.safetensors",
452
+ "multi_modal_projector.mm_soft_emb_norm.weight": "model-00001-of-00002.safetensors",
453
+ "vision_tower.vision_model.embeddings.patch_embedding.bias": "model-00001-of-00002.safetensors",
454
+ "vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00002.safetensors",
455
+ "vision_tower.vision_model.embeddings.position_embedding.weight": "model-00001-of-00002.safetensors",
456
+ "vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00002.safetensors",
457
+ "vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00002.safetensors",
458
+ "vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00002.safetensors",
459
+ "vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00002.safetensors",
460
+ "vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
461
+ "vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
462
+ "vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
463
+ "vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
464
+ "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
465
+ "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
466
+ "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
467
+ "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
468
+ "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
469
+ "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
470
+ "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
471
+ "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
472
+ "vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00002.safetensors",
473
+ "vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00002.safetensors",
474
+ "vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00002.safetensors",
475
+ "vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00002.safetensors",
476
+ "vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
477
+ "vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
478
+ "vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
479
+ "vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
480
+ "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
481
+ "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
482
+ "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
483
+ "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
484
+ "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
485
+ "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
486
+ "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
487
+ "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
488
+ "vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00002.safetensors",
489
+ "vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00002.safetensors",
490
+ "vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00002.safetensors",
491
+ "vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00002.safetensors",
492
+ "vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
493
+ "vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
494
+ "vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
495
+ "vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
496
+ "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
497
+ "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
498
+ "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
499
+ "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
500
+ "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
501
+ "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
502
+ "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
503
+ "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
504
+ "vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00002.safetensors",
505
+ "vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00002.safetensors",
506
+ "vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00002.safetensors",
507
+ "vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00002.safetensors",
508
+ "vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
509
+ "vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
510
+ "vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
511
+ "vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
512
+ "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
513
+ "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
514
+ "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
515
+ "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
516
+ "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
517
+ "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
518
+ "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
519
+ "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
520
+ "vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00002.safetensors",
521
+ "vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00002.safetensors",
522
+ "vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00002.safetensors",
523
+ "vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00002.safetensors",
524
+ "vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
525
+ "vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
526
+ "vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
527
+ "vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
528
+ "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
529
+ "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
530
+ "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
531
+ "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
532
+ "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
533
+ "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
534
+ "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
535
+ "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
536
+ "vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00002.safetensors",
537
+ "vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00002.safetensors",
538
+ "vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00002.safetensors",
539
+ "vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00002.safetensors",
540
+ "vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
541
+ "vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
542
+ "vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
543
+ "vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
544
+ "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
545
+ "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
546
+ "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
547
+ "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
548
+ "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
549
+ "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
550
+ "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
551
+ "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
552
+ "vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00002.safetensors",
553
+ "vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00002.safetensors",
554
+ "vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00002.safetensors",
555
+ "vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00002.safetensors",
556
+ "vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
557
+ "vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
558
+ "vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
559
+ "vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
560
+ "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
561
+ "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
562
+ "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
563
+ "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
564
+ "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
565
+ "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
566
+ "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
567
+ "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
568
+ "vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00002.safetensors",
569
+ "vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00002.safetensors",
570
+ "vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00002.safetensors",
571
+ "vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00002.safetensors",
572
+ "vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
573
+ "vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
574
+ "vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
575
+ "vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
576
+ "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
577
+ "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
578
+ "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
579
+ "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
580
+ "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
581
+ "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
582
+ "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
583
+ "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
584
+ "vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00002.safetensors",
585
+ "vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00002.safetensors",
586
+ "vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00002.safetensors",
587
+ "vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00002.safetensors",
588
+ "vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
589
+ "vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
590
+ "vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
591
+ "vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
592
+ "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
593
+ "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
594
+ "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
595
+ "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
596
+ "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
597
+ "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
598
+ "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
599
+ "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
600
+ "vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00002.safetensors",
601
+ "vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00002.safetensors",
602
+ "vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00002.safetensors",
603
+ "vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00002.safetensors",
604
+ "vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
605
+ "vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
606
+ "vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
607
+ "vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
608
+ "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
609
+ "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
610
+ "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
611
+ "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
612
+ "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
613
+ "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
614
+ "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
615
+ "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
616
+ "vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00002.safetensors",
617
+ "vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00002.safetensors",
618
+ "vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00002.safetensors",
619
+ "vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00002.safetensors",
620
+ "vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
621
+ "vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
622
+ "vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
623
+ "vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
624
+ "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
625
+ "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
626
+ "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
627
+ "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
628
+ "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
629
+ "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
630
+ "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
631
+ "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
632
+ "vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00002.safetensors",
633
+ "vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00002.safetensors",
634
+ "vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00002.safetensors",
635
+ "vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00002.safetensors",
636
+ "vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
637
+ "vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
638
+ "vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
639
+ "vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
640
+ "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
641
+ "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
642
+ "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
643
+ "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
644
+ "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
645
+ "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
646
+ "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
647
+ "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
648
+ "vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00002.safetensors",
649
+ "vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00002.safetensors",
650
+ "vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00002.safetensors",
651
+ "vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00002.safetensors",
652
+ "vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
653
+ "vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
654
+ "vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
655
+ "vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
656
+ "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
657
+ "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
658
+ "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
659
+ "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
660
+ "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
661
+ "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
662
+ "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
663
+ "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
664
+ "vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00002.safetensors",
665
+ "vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00002.safetensors",
666
+ "vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00002.safetensors",
667
+ "vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00002.safetensors",
668
+ "vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
669
+ "vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
670
+ "vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
671
+ "vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
672
+ "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
673
+ "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
674
+ "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
675
+ "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
676
+ "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
677
+ "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
678
+ "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
679
+ "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
680
+ "vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00002.safetensors",
681
+ "vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00002.safetensors",
682
+ "vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00002.safetensors",
683
+ "vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00002.safetensors",
684
+ "vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
685
+ "vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
686
+ "vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
687
+ "vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
688
+ "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
689
+ "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
690
+ "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
691
+ "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
692
+ "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
693
+ "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
694
+ "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
695
+ "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
696
+ "vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00002.safetensors",
697
+ "vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00002.safetensors",
698
+ "vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00002.safetensors",
699
+ "vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00002.safetensors",
700
+ "vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
701
+ "vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
702
+ "vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
703
+ "vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
704
+ "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
705
+ "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
706
+ "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
707
+ "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
708
+ "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
709
+ "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
710
+ "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
711
+ "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
712
+ "vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00002.safetensors",
713
+ "vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00002.safetensors",
714
+ "vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00002.safetensors",
715
+ "vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00002.safetensors",
716
+ "vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
717
+ "vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
718
+ "vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
719
+ "vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
720
+ "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
721
+ "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
722
+ "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
723
+ "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
724
+ "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
725
+ "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
726
+ "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
727
+ "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
728
+ "vision_tower.vision_model.encoder.layers.24.layer_norm1.bias": "model-00001-of-00002.safetensors",
729
+ "vision_tower.vision_model.encoder.layers.24.layer_norm1.weight": "model-00001-of-00002.safetensors",
730
+ "vision_tower.vision_model.encoder.layers.24.layer_norm2.bias": "model-00001-of-00002.safetensors",
731
+ "vision_tower.vision_model.encoder.layers.24.layer_norm2.weight": "model-00001-of-00002.safetensors",
732
+ "vision_tower.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
733
+ "vision_tower.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
734
+ "vision_tower.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
735
+ "vision_tower.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
736
+ "vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
737
+ "vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
738
+ "vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
739
+ "vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
740
+ "vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
741
+ "vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
742
+ "vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
743
+ "vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
744
+ "vision_tower.vision_model.encoder.layers.25.layer_norm1.bias": "model-00001-of-00002.safetensors",
745
+ "vision_tower.vision_model.encoder.layers.25.layer_norm1.weight": "model-00001-of-00002.safetensors",
746
+ "vision_tower.vision_model.encoder.layers.25.layer_norm2.bias": "model-00001-of-00002.safetensors",
747
+ "vision_tower.vision_model.encoder.layers.25.layer_norm2.weight": "model-00001-of-00002.safetensors",
748
+ "vision_tower.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
749
+ "vision_tower.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
750
+ "vision_tower.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
751
+ "vision_tower.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
752
+ "vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
753
+ "vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
754
+ "vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
755
+ "vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
756
+ "vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
757
+ "vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
758
+ "vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
759
+ "vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
760
+ "vision_tower.vision_model.encoder.layers.26.layer_norm1.bias": "model-00001-of-00002.safetensors",
761
+ "vision_tower.vision_model.encoder.layers.26.layer_norm1.weight": "model-00001-of-00002.safetensors",
762
+ "vision_tower.vision_model.encoder.layers.26.layer_norm2.bias": "model-00001-of-00002.safetensors",
763
+ "vision_tower.vision_model.encoder.layers.26.layer_norm2.weight": "model-00001-of-00002.safetensors",
764
+ "vision_tower.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
765
+ "vision_tower.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
766
+ "vision_tower.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
767
+ "vision_tower.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
768
+ "vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
769
+ "vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
770
+ "vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
771
+ "vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
772
+ "vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
773
+ "vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
774
+ "vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
775
+ "vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
776
+ "vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00002.safetensors",
777
+ "vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00002.safetensors",
778
+ "vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00002.safetensors",
779
+ "vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00002.safetensors",
780
+ "vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
781
+ "vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
782
+ "vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
783
+ "vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
784
+ "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
785
+ "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
786
+ "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
787
+ "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
788
+ "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
789
+ "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
790
+ "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
791
+ "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
792
+ "vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00002.safetensors",
793
+ "vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00002.safetensors",
794
+ "vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00002.safetensors",
795
+ "vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00002.safetensors",
796
+ "vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
797
+ "vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
798
+ "vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
799
+ "vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
800
+ "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
801
+ "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
802
+ "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
803
+ "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
804
+ "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
805
+ "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
806
+ "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
807
+ "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
808
+ "vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00002.safetensors",
809
+ "vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00002.safetensors",
810
+ "vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00002.safetensors",
811
+ "vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00002.safetensors",
812
+ "vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
813
+ "vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
814
+ "vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
815
+ "vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
816
+ "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
817
+ "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
818
+ "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
819
+ "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
820
+ "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
821
+ "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
822
+ "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
823
+ "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
824
+ "vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00002.safetensors",
825
+ "vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00002.safetensors",
826
+ "vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00002.safetensors",
827
+ "vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00002.safetensors",
828
+ "vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
829
+ "vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
830
+ "vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
831
+ "vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
832
+ "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
833
+ "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
834
+ "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
835
+ "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
836
+ "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
837
+ "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
838
+ "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
839
+ "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
840
+ "vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00002.safetensors",
841
+ "vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00002.safetensors",
842
+ "vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00002.safetensors",
843
+ "vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00002.safetensors",
844
+ "vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
845
+ "vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
846
+ "vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
847
+ "vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
848
+ "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
849
+ "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
850
+ "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
851
+ "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
852
+ "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
853
+ "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
854
+ "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
855
+ "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
856
+ "vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00002.safetensors",
857
+ "vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00002.safetensors",
858
+ "vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00002.safetensors",
859
+ "vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00002.safetensors",
860
+ "vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
861
+ "vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
862
+ "vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
863
+ "vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
864
+ "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
865
+ "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
866
+ "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
867
+ "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
868
+ "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
869
+ "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
870
+ "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
871
+ "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
872
+ "vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00002.safetensors",
873
+ "vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00002.safetensors",
874
+ "vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00002.safetensors",
875
+ "vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00002.safetensors",
876
+ "vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
877
+ "vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
878
+ "vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
879
+ "vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
880
+ "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
881
+ "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
882
+ "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
883
+ "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
884
+ "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
885
+ "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
886
+ "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
887
+ "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
888
+ "vision_tower.vision_model.post_layernorm.bias": "model-00001-of-00002.safetensors",
889
+ "vision_tower.vision_model.post_layernorm.weight": "model-00001-of-00002.safetensors"
890
+ }
891
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": null,
3
+ "do_normalize": true,
4
+ "do_pan_and_scan": null,
5
+ "do_rescale": true,
6
+ "do_resize": true,
7
+ "image_mean": [
8
+ 0.5,
9
+ 0.5,
10
+ 0.5
11
+ ],
12
+ "image_processor_type": "Gemma3ImageProcessor",
13
+ "image_seq_length": 256,
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "pan_and_scan_max_num_crops": null,
20
+ "pan_and_scan_min_crop_size": null,
21
+ "pan_and_scan_min_ratio_to_activate": null,
22
+ "processor_class": "Gemma3Processor",
23
+ "resample": 2,
24
+ "rescale_factor": 0.00392156862745098,
25
+ "size": {
26
+ "height": 896,
27
+ "width": 896
28
+ }
29
+ }
processor_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "image_seq_length": 256,
3
+ "processor_class": "Gemma3Processor"
4
+ }
rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a0ef6f96a48e59aa52c4b471312c2a62378c19acc7ebbae839612b03a7d775a
3
+ size 15984
rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab11d533c0fdad46ea8b8e295ba5fdb705e078eeb88cc28f37d82913508766e9
3
+ size 15984
rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:615c168147e3465ce5bfab6da2ff4afc68566ce00ec0f0c6c9fc988038a58d0a
3
+ size 15984
rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79f71e8f8674ecaef9f8cdcbf7ac457a8b8ff15b12694ba2a2fffcb4b43f0f08
3
+ size 15984
rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88cf6d674dab5545c300a55135f08ca935730a3d35e2c419fb0b333f19482c19
3
+ size 15984
rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2754f2cd8824702f027870d93748b3c0491b0ecd30f1e3d8e937116b2be6151f
3
+ size 15984
rng_state_6.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1385124ac55604598f45ea6e2d141f29456647d3e7c10d12ca64ec93d312be8d
3
+ size 15984
rng_state_7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:416538efaec7391fa8fe782fb15146b83e5612d9e1961292c34c53e964806873
3
+ size 15984
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:418a3e6896d4c0199d7c76069e3679f58f83189aac50d7100528bee633700645
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<end_of_turn>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ }
10
+ ],
11
+ "boi_token": "<start_of_image>",
12
+ "bos_token": {
13
+ "content": "<bos>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "eoi_token": "<end_of_image>",
20
+ "eos_token": {
21
+ "content": "<eos>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "image_token": "<image_soft_token>",
28
+ "pad_token": {
29
+ "content": "<pad>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ },
35
+ "unk_token": {
36
+ "content": "<unk>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false
41
+ }
42
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
3
+ size 33384568
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
3
+ size 4689074
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
trainer_state.json ADDED
@@ -0,0 +1,2157 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0101010101010102,
5
+ "eval_steps": 100,
6
+ "global_step": 300,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.003367003367003367,
13
+ "grad_norm": 190.2997283935547,
14
+ "learning_rate": 6.711409395973154e-07,
15
+ "loss": 13.9272,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.006734006734006734,
20
+ "grad_norm": 196.5933074951172,
21
+ "learning_rate": 1.3422818791946309e-06,
22
+ "loss": 14.3753,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.010101010101010102,
27
+ "grad_norm": 198.02767944335938,
28
+ "learning_rate": 2.013422818791946e-06,
29
+ "loss": 14.4143,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.013468013468013467,
34
+ "grad_norm": 186.30801391601562,
35
+ "learning_rate": 2.6845637583892617e-06,
36
+ "loss": 13.7729,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.016835016835016835,
41
+ "grad_norm": 129.32237243652344,
42
+ "learning_rate": 3.3557046979865773e-06,
43
+ "loss": 11.4082,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.020202020202020204,
48
+ "grad_norm": 123.9930191040039,
49
+ "learning_rate": 4.026845637583892e-06,
50
+ "loss": 11.5581,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.02356902356902357,
55
+ "grad_norm": 102.4565658569336,
56
+ "learning_rate": 4.697986577181209e-06,
57
+ "loss": 9.8311,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.026936026936026935,
62
+ "grad_norm": 98.7117919921875,
63
+ "learning_rate": 5.3691275167785235e-06,
64
+ "loss": 9.825,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.030303030303030304,
69
+ "grad_norm": 121.9065170288086,
70
+ "learning_rate": 6.04026845637584e-06,
71
+ "loss": 8.5157,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.03367003367003367,
76
+ "grad_norm": 93.352294921875,
77
+ "learning_rate": 6.7114093959731546e-06,
78
+ "loss": 7.6328,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.037037037037037035,
83
+ "grad_norm": 108.89420318603516,
84
+ "learning_rate": 7.382550335570471e-06,
85
+ "loss": 7.1598,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.04040404040404041,
90
+ "grad_norm": 191.65274047851562,
91
+ "learning_rate": 8.053691275167785e-06,
92
+ "loss": 6.237,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.04377104377104377,
97
+ "grad_norm": 150.62646484375,
98
+ "learning_rate": 8.724832214765101e-06,
99
+ "loss": 5.7063,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.04713804713804714,
104
+ "grad_norm": 185.48080444335938,
105
+ "learning_rate": 9.395973154362418e-06,
106
+ "loss": 5.093,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.050505050505050504,
111
+ "grad_norm": 1576.556640625,
112
+ "learning_rate": 1.006711409395973e-05,
113
+ "loss": 8.3575,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.05387205387205387,
118
+ "grad_norm": 441.4505310058594,
119
+ "learning_rate": 1.0738255033557047e-05,
120
+ "loss": 4.679,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.05723905723905724,
125
+ "grad_norm": 499.8016357421875,
126
+ "learning_rate": 1.1409395973154363e-05,
127
+ "loss": 3.1432,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.06060606060606061,
132
+ "grad_norm": 472.59747314453125,
133
+ "learning_rate": 1.208053691275168e-05,
134
+ "loss": 2.9237,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.06397306397306397,
139
+ "grad_norm": 506.6687927246094,
140
+ "learning_rate": 1.2751677852348994e-05,
141
+ "loss": 2.6882,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.06734006734006734,
146
+ "grad_norm": 494.16949462890625,
147
+ "learning_rate": 1.3422818791946309e-05,
148
+ "loss": 2.4807,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.0707070707070707,
153
+ "grad_norm": 463.3478698730469,
154
+ "learning_rate": 1.4093959731543624e-05,
155
+ "loss": 2.2508,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.07407407407407407,
160
+ "grad_norm": 422.92401123046875,
161
+ "learning_rate": 1.4765100671140942e-05,
162
+ "loss": 1.9202,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.07744107744107744,
167
+ "grad_norm": 417.1321105957031,
168
+ "learning_rate": 1.5436241610738255e-05,
169
+ "loss": 1.6106,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.08080808080808081,
174
+ "grad_norm": 360.2781677246094,
175
+ "learning_rate": 1.610738255033557e-05,
176
+ "loss": 1.2741,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.08417508417508418,
181
+ "grad_norm": 297.3291015625,
182
+ "learning_rate": 1.6778523489932888e-05,
183
+ "loss": 1.0282,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.08754208754208755,
188
+ "grad_norm": 195.75958251953125,
189
+ "learning_rate": 1.7449664429530202e-05,
190
+ "loss": 0.799,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.09090909090909091,
195
+ "grad_norm": 116.36829376220703,
196
+ "learning_rate": 1.8120805369127517e-05,
197
+ "loss": 0.6593,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.09427609427609428,
202
+ "grad_norm": 70.56578063964844,
203
+ "learning_rate": 1.8791946308724835e-05,
204
+ "loss": 0.5787,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.09764309764309764,
209
+ "grad_norm": 45.22296905517578,
210
+ "learning_rate": 1.946308724832215e-05,
211
+ "loss": 0.5196,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.10101010101010101,
216
+ "grad_norm": 20.37734603881836,
217
+ "learning_rate": 2.013422818791946e-05,
218
+ "loss": 0.4681,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.10437710437710437,
223
+ "grad_norm": 7.735367298126221,
224
+ "learning_rate": 2.080536912751678e-05,
225
+ "loss": 0.4318,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.10774410774410774,
230
+ "grad_norm": 4.360243797302246,
231
+ "learning_rate": 2.1476510067114094e-05,
232
+ "loss": 0.4276,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.1111111111111111,
237
+ "grad_norm": 4.440345287322998,
238
+ "learning_rate": 2.2147651006711412e-05,
239
+ "loss": 0.4463,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.11447811447811448,
244
+ "grad_norm": 26.992700576782227,
245
+ "learning_rate": 2.2818791946308727e-05,
246
+ "loss": 0.4394,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.11784511784511785,
251
+ "grad_norm": 33.81399917602539,
252
+ "learning_rate": 2.348993288590604e-05,
253
+ "loss": 0.6005,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.12121212121212122,
258
+ "grad_norm": 7.8905029296875,
259
+ "learning_rate": 2.416107382550336e-05,
260
+ "loss": 0.4963,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.12457912457912458,
265
+ "grad_norm": 2.6311209201812744,
266
+ "learning_rate": 2.4832214765100674e-05,
267
+ "loss": 0.39,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.12794612794612795,
272
+ "grad_norm": 2.389883041381836,
273
+ "learning_rate": 2.550335570469799e-05,
274
+ "loss": 0.3782,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.13131313131313133,
279
+ "grad_norm": 2.070525646209717,
280
+ "learning_rate": 2.6174496644295304e-05,
281
+ "loss": 0.3592,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.13468013468013468,
286
+ "grad_norm": 5.955089569091797,
287
+ "learning_rate": 2.6845637583892618e-05,
288
+ "loss": 0.3777,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.13804713804713806,
293
+ "grad_norm": 6.50673770904541,
294
+ "learning_rate": 2.7516778523489933e-05,
295
+ "loss": 0.389,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.1414141414141414,
300
+ "grad_norm": 2.0794308185577393,
301
+ "learning_rate": 2.8187919463087248e-05,
302
+ "loss": 0.3618,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.1447811447811448,
307
+ "grad_norm": 1.5477614402770996,
308
+ "learning_rate": 2.885906040268457e-05,
309
+ "loss": 0.3593,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.14814814814814814,
314
+ "grad_norm": 10.740438461303711,
315
+ "learning_rate": 2.9530201342281884e-05,
316
+ "loss": 0.3805,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.15151515151515152,
321
+ "grad_norm": 2.993213176727295,
322
+ "learning_rate": 3.02013422818792e-05,
323
+ "loss": 0.3673,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.15488215488215487,
328
+ "grad_norm": 17.512208938598633,
329
+ "learning_rate": 3.087248322147651e-05,
330
+ "loss": 0.3922,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.15824915824915825,
335
+ "grad_norm": 2.5222012996673584,
336
+ "learning_rate": 3.1543624161073825e-05,
337
+ "loss": 0.3873,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.16161616161616163,
342
+ "grad_norm": 0.8730729222297668,
343
+ "learning_rate": 3.221476510067114e-05,
344
+ "loss": 0.3593,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.16498316498316498,
349
+ "grad_norm": 0.8050268292427063,
350
+ "learning_rate": 3.288590604026846e-05,
351
+ "loss": 0.3491,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.16835016835016836,
356
+ "grad_norm": 0.7536938190460205,
357
+ "learning_rate": 3.3557046979865775e-05,
358
+ "loss": 0.3469,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.1717171717171717,
363
+ "grad_norm": 0.9090268015861511,
364
+ "learning_rate": 3.422818791946309e-05,
365
+ "loss": 0.3663,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.1750841750841751,
370
+ "grad_norm": 0.8775368928909302,
371
+ "learning_rate": 3.4899328859060405e-05,
372
+ "loss": 0.3489,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.17845117845117844,
377
+ "grad_norm": 0.5326427221298218,
378
+ "learning_rate": 3.557046979865772e-05,
379
+ "loss": 0.3466,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.18181818181818182,
384
+ "grad_norm": 0.561137318611145,
385
+ "learning_rate": 3.6241610738255034e-05,
386
+ "loss": 0.3393,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.18518518518518517,
391
+ "grad_norm": 0.8053128123283386,
392
+ "learning_rate": 3.6912751677852356e-05,
393
+ "loss": 0.352,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.18855218855218855,
398
+ "grad_norm": 0.5964087843894958,
399
+ "learning_rate": 3.758389261744967e-05,
400
+ "loss": 0.3507,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.1919191919191919,
405
+ "grad_norm": 0.5998376607894897,
406
+ "learning_rate": 3.8255033557046985e-05,
407
+ "loss": 0.3504,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.19528619528619529,
412
+ "grad_norm": 1.2634875774383545,
413
+ "learning_rate": 3.89261744966443e-05,
414
+ "loss": 0.337,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.19865319865319866,
419
+ "grad_norm": 0.5703901648521423,
420
+ "learning_rate": 3.959731543624161e-05,
421
+ "loss": 0.3408,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.20202020202020202,
426
+ "grad_norm": 0.7656762003898621,
427
+ "learning_rate": 4.026845637583892e-05,
428
+ "loss": 0.3206,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.2053872053872054,
433
+ "grad_norm": 0.6210582852363586,
434
+ "learning_rate": 4.0939597315436244e-05,
435
+ "loss": 0.354,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.20875420875420875,
440
+ "grad_norm": 0.6622840166091919,
441
+ "learning_rate": 4.161073825503356e-05,
442
+ "loss": 0.3439,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.21212121212121213,
447
+ "grad_norm": 0.46426376700401306,
448
+ "learning_rate": 4.228187919463087e-05,
449
+ "loss": 0.3434,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.21548821548821548,
454
+ "grad_norm": 0.38662126660346985,
455
+ "learning_rate": 4.295302013422819e-05,
456
+ "loss": 0.3362,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.21885521885521886,
461
+ "grad_norm": 0.5812459588050842,
462
+ "learning_rate": 4.36241610738255e-05,
463
+ "loss": 0.323,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.2222222222222222,
468
+ "grad_norm": 0.626932680606842,
469
+ "learning_rate": 4.4295302013422824e-05,
470
+ "loss": 0.3427,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.2255892255892256,
475
+ "grad_norm": 0.5491658449172974,
476
+ "learning_rate": 4.496644295302014e-05,
477
+ "loss": 0.3406,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.22895622895622897,
482
+ "grad_norm": 0.4023520052433014,
483
+ "learning_rate": 4.5637583892617453e-05,
484
+ "loss": 0.3328,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.23232323232323232,
489
+ "grad_norm": 0.478535532951355,
490
+ "learning_rate": 4.630872483221477e-05,
491
+ "loss": 0.3402,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.2356902356902357,
496
+ "grad_norm": 0.44869011640548706,
497
+ "learning_rate": 4.697986577181208e-05,
498
+ "loss": 0.3516,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.23905723905723905,
503
+ "grad_norm": 0.4810108244419098,
504
+ "learning_rate": 4.76510067114094e-05,
505
+ "loss": 0.3411,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.24242424242424243,
510
+ "grad_norm": 0.3956281542778015,
511
+ "learning_rate": 4.832214765100672e-05,
512
+ "loss": 0.3395,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.24579124579124578,
517
+ "grad_norm": 0.40301939845085144,
518
+ "learning_rate": 4.8993288590604034e-05,
519
+ "loss": 0.3217,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.24915824915824916,
524
+ "grad_norm": 0.44550034403800964,
525
+ "learning_rate": 4.966442953020135e-05,
526
+ "loss": 0.3257,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.25252525252525254,
531
+ "grad_norm": 0.5890341997146606,
532
+ "learning_rate": 5.033557046979866e-05,
533
+ "loss": 0.3335,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.2558922558922559,
538
+ "grad_norm": 0.8096022009849548,
539
+ "learning_rate": 5.100671140939598e-05,
540
+ "loss": 0.3421,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.25925925925925924,
545
+ "grad_norm": 0.6044747829437256,
546
+ "learning_rate": 5.167785234899329e-05,
547
+ "loss": 0.3266,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.26262626262626265,
552
+ "grad_norm": 0.5191451907157898,
553
+ "learning_rate": 5.234899328859061e-05,
554
+ "loss": 0.331,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.265993265993266,
559
+ "grad_norm": 1.0799261331558228,
560
+ "learning_rate": 5.302013422818792e-05,
561
+ "loss": 0.3243,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.26936026936026936,
566
+ "grad_norm": 5.513405799865723,
567
+ "learning_rate": 5.3691275167785237e-05,
568
+ "loss": 0.379,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.2727272727272727,
573
+ "grad_norm": 0.673650860786438,
574
+ "learning_rate": 5.436241610738255e-05,
575
+ "loss": 0.3482,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.2760942760942761,
580
+ "grad_norm": 1.1485897302627563,
581
+ "learning_rate": 5.5033557046979866e-05,
582
+ "loss": 0.3351,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.27946127946127947,
587
+ "grad_norm": 0.5018780827522278,
588
+ "learning_rate": 5.570469798657718e-05,
589
+ "loss": 0.3077,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.2828282828282828,
594
+ "grad_norm": 4.367802619934082,
595
+ "learning_rate": 5.6375838926174495e-05,
596
+ "loss": 0.3284,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.28619528619528617,
601
+ "grad_norm": 33.46516036987305,
602
+ "learning_rate": 5.704697986577181e-05,
603
+ "loss": 1.0651,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.2895622895622896,
608
+ "grad_norm": 91.36512756347656,
609
+ "learning_rate": 5.771812080536914e-05,
610
+ "loss": 1.7174,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.29292929292929293,
615
+ "grad_norm": 9.666085243225098,
616
+ "learning_rate": 5.838926174496645e-05,
617
+ "loss": 0.5601,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 0.2962962962962963,
622
+ "grad_norm": 8.608613967895508,
623
+ "learning_rate": 5.906040268456377e-05,
624
+ "loss": 0.3865,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 0.2996632996632997,
629
+ "grad_norm": 3.025059223175049,
630
+ "learning_rate": 5.973154362416108e-05,
631
+ "loss": 0.358,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 0.30303030303030304,
636
+ "grad_norm": 9.862916946411133,
637
+ "learning_rate": 6.04026845637584e-05,
638
+ "loss": 0.4464,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 0.3063973063973064,
643
+ "grad_norm": 11.05635929107666,
644
+ "learning_rate": 6.107382550335571e-05,
645
+ "loss": 0.3977,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 0.30976430976430974,
650
+ "grad_norm": 1.0226973295211792,
651
+ "learning_rate": 6.174496644295302e-05,
652
+ "loss": 0.3206,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 0.31313131313131315,
657
+ "grad_norm": 1.007895827293396,
658
+ "learning_rate": 6.241610738255034e-05,
659
+ "loss": 0.3355,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 0.3164983164983165,
664
+ "grad_norm": 1.5956454277038574,
665
+ "learning_rate": 6.308724832214765e-05,
666
+ "loss": 0.3408,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 0.31986531986531985,
671
+ "grad_norm": 21.75948715209961,
672
+ "learning_rate": 6.375838926174497e-05,
673
+ "loss": 0.4627,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 0.32323232323232326,
678
+ "grad_norm": 5.754608154296875,
679
+ "learning_rate": 6.442953020134228e-05,
680
+ "loss": 0.3818,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 0.3265993265993266,
685
+ "grad_norm": 3.1888318061828613,
686
+ "learning_rate": 6.51006711409396e-05,
687
+ "loss": 0.3713,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 0.32996632996632996,
692
+ "grad_norm": 4.586446762084961,
693
+ "learning_rate": 6.577181208053692e-05,
694
+ "loss": 0.3394,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 0.3333333333333333,
699
+ "grad_norm": 0.9332061409950256,
700
+ "learning_rate": 6.644295302013423e-05,
701
+ "loss": 0.3267,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 0.3367003367003367,
706
+ "grad_norm": 4.119638442993164,
707
+ "learning_rate": 6.711409395973155e-05,
708
+ "loss": 0.3825,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 0.3367003367003367,
713
+ "eval_loss": 0.16432031989097595,
714
+ "eval_runtime": 33.0116,
715
+ "eval_samples_per_second": 30.292,
716
+ "eval_steps_per_second": 1.908,
717
+ "step": 100
718
+ },
719
+ {
720
+ "epoch": 0.3400673400673401,
721
+ "grad_norm": 1.244138240814209,
722
+ "learning_rate": 6.778523489932886e-05,
723
+ "loss": 0.3191,
724
+ "step": 101
725
+ },
726
+ {
727
+ "epoch": 0.3434343434343434,
728
+ "grad_norm": 4.564449310302734,
729
+ "learning_rate": 6.845637583892618e-05,
730
+ "loss": 0.3792,
731
+ "step": 102
732
+ },
733
+ {
734
+ "epoch": 0.3468013468013468,
735
+ "grad_norm": 71.92516326904297,
736
+ "learning_rate": 6.912751677852349e-05,
737
+ "loss": 0.9526,
738
+ "step": 103
739
+ },
740
+ {
741
+ "epoch": 0.3501683501683502,
742
+ "grad_norm": 6.8141374588012695,
743
+ "learning_rate": 6.979865771812081e-05,
744
+ "loss": 0.4132,
745
+ "step": 104
746
+ },
747
+ {
748
+ "epoch": 0.35353535353535354,
749
+ "grad_norm": 4.9158616065979,
750
+ "learning_rate": 7.046979865771812e-05,
751
+ "loss": 0.3847,
752
+ "step": 105
753
+ },
754
+ {
755
+ "epoch": 0.3569023569023569,
756
+ "grad_norm": 0.9838681221008301,
757
+ "learning_rate": 7.114093959731544e-05,
758
+ "loss": 0.335,
759
+ "step": 106
760
+ },
761
+ {
762
+ "epoch": 0.3602693602693603,
763
+ "grad_norm": 0.44024720788002014,
764
+ "learning_rate": 7.181208053691275e-05,
765
+ "loss": 0.3159,
766
+ "step": 107
767
+ },
768
+ {
769
+ "epoch": 0.36363636363636365,
770
+ "grad_norm": 0.5798377394676208,
771
+ "learning_rate": 7.248322147651007e-05,
772
+ "loss": 0.3308,
773
+ "step": 108
774
+ },
775
+ {
776
+ "epoch": 0.367003367003367,
777
+ "grad_norm": 0.5650081038475037,
778
+ "learning_rate": 7.315436241610739e-05,
779
+ "loss": 0.3161,
780
+ "step": 109
781
+ },
782
+ {
783
+ "epoch": 0.37037037037037035,
784
+ "grad_norm": 0.5149471163749695,
785
+ "learning_rate": 7.382550335570471e-05,
786
+ "loss": 0.3291,
787
+ "step": 110
788
+ },
789
+ {
790
+ "epoch": 0.37373737373737376,
791
+ "grad_norm": 0.4448802173137665,
792
+ "learning_rate": 7.449664429530202e-05,
793
+ "loss": 0.3145,
794
+ "step": 111
795
+ },
796
+ {
797
+ "epoch": 0.3771043771043771,
798
+ "grad_norm": 0.5278413891792297,
799
+ "learning_rate": 7.516778523489934e-05,
800
+ "loss": 0.3296,
801
+ "step": 112
802
+ },
803
+ {
804
+ "epoch": 0.38047138047138046,
805
+ "grad_norm": 0.455289363861084,
806
+ "learning_rate": 7.583892617449665e-05,
807
+ "loss": 0.318,
808
+ "step": 113
809
+ },
810
+ {
811
+ "epoch": 0.3838383838383838,
812
+ "grad_norm": 0.5316647291183472,
813
+ "learning_rate": 7.651006711409397e-05,
814
+ "loss": 0.3117,
815
+ "step": 114
816
+ },
817
+ {
818
+ "epoch": 0.3872053872053872,
819
+ "grad_norm": 0.43862929940223694,
820
+ "learning_rate": 7.718120805369128e-05,
821
+ "loss": 0.3062,
822
+ "step": 115
823
+ },
824
+ {
825
+ "epoch": 0.39057239057239057,
826
+ "grad_norm": 12.535127639770508,
827
+ "learning_rate": 7.78523489932886e-05,
828
+ "loss": 0.3557,
829
+ "step": 116
830
+ },
831
+ {
832
+ "epoch": 0.3939393939393939,
833
+ "grad_norm": 15.351152420043945,
834
+ "learning_rate": 7.852348993288591e-05,
835
+ "loss": 0.5181,
836
+ "step": 117
837
+ },
838
+ {
839
+ "epoch": 0.39730639730639733,
840
+ "grad_norm": 11.918878555297852,
841
+ "learning_rate": 7.919463087248322e-05,
842
+ "loss": 0.4005,
843
+ "step": 118
844
+ },
845
+ {
846
+ "epoch": 0.4006734006734007,
847
+ "grad_norm": 9.800668716430664,
848
+ "learning_rate": 7.986577181208054e-05,
849
+ "loss": 0.422,
850
+ "step": 119
851
+ },
852
+ {
853
+ "epoch": 0.40404040404040403,
854
+ "grad_norm": 16.235355377197266,
855
+ "learning_rate": 8.053691275167784e-05,
856
+ "loss": 0.4051,
857
+ "step": 120
858
+ },
859
+ {
860
+ "epoch": 0.4074074074074074,
861
+ "grad_norm": 1.8551958799362183,
862
+ "learning_rate": 8.120805369127518e-05,
863
+ "loss": 0.3506,
864
+ "step": 121
865
+ },
866
+ {
867
+ "epoch": 0.4107744107744108,
868
+ "grad_norm": 3.990302562713623,
869
+ "learning_rate": 8.187919463087249e-05,
870
+ "loss": 0.3318,
871
+ "step": 122
872
+ },
873
+ {
874
+ "epoch": 0.41414141414141414,
875
+ "grad_norm": 22.28190040588379,
876
+ "learning_rate": 8.255033557046981e-05,
877
+ "loss": 0.4316,
878
+ "step": 123
879
+ },
880
+ {
881
+ "epoch": 0.4175084175084175,
882
+ "grad_norm": 1.9532949924468994,
883
+ "learning_rate": 8.322147651006712e-05,
884
+ "loss": 0.3596,
885
+ "step": 124
886
+ },
887
+ {
888
+ "epoch": 0.4208754208754209,
889
+ "grad_norm": 0.8453232645988464,
890
+ "learning_rate": 8.389261744966444e-05,
891
+ "loss": 0.3473,
892
+ "step": 125
893
+ },
894
+ {
895
+ "epoch": 0.42424242424242425,
896
+ "grad_norm": 3.7085459232330322,
897
+ "learning_rate": 8.456375838926175e-05,
898
+ "loss": 0.3527,
899
+ "step": 126
900
+ },
901
+ {
902
+ "epoch": 0.4276094276094276,
903
+ "grad_norm": 1.9306743144989014,
904
+ "learning_rate": 8.523489932885907e-05,
905
+ "loss": 0.3415,
906
+ "step": 127
907
+ },
908
+ {
909
+ "epoch": 0.43097643097643096,
910
+ "grad_norm": 5.023862361907959,
911
+ "learning_rate": 8.590604026845638e-05,
912
+ "loss": 0.3644,
913
+ "step": 128
914
+ },
915
+ {
916
+ "epoch": 0.43434343434343436,
917
+ "grad_norm": 4.241243362426758,
918
+ "learning_rate": 8.65771812080537e-05,
919
+ "loss": 0.4321,
920
+ "step": 129
921
+ },
922
+ {
923
+ "epoch": 0.4377104377104377,
924
+ "grad_norm": 1.7396281957626343,
925
+ "learning_rate": 8.7248322147651e-05,
926
+ "loss": 0.3334,
927
+ "step": 130
928
+ },
929
+ {
930
+ "epoch": 0.44107744107744107,
931
+ "grad_norm": 8.367612838745117,
932
+ "learning_rate": 8.791946308724833e-05,
933
+ "loss": 0.3571,
934
+ "step": 131
935
+ },
936
+ {
937
+ "epoch": 0.4444444444444444,
938
+ "grad_norm": 7.692532539367676,
939
+ "learning_rate": 8.859060402684565e-05,
940
+ "loss": 0.5196,
941
+ "step": 132
942
+ },
943
+ {
944
+ "epoch": 0.4478114478114478,
945
+ "grad_norm": 12.191128730773926,
946
+ "learning_rate": 8.926174496644296e-05,
947
+ "loss": 0.6991,
948
+ "step": 133
949
+ },
950
+ {
951
+ "epoch": 0.4511784511784512,
952
+ "grad_norm": 7.570639133453369,
953
+ "learning_rate": 8.993288590604028e-05,
954
+ "loss": 0.4818,
955
+ "step": 134
956
+ },
957
+ {
958
+ "epoch": 0.45454545454545453,
959
+ "grad_norm": 1.7189193964004517,
960
+ "learning_rate": 9.060402684563759e-05,
961
+ "loss": 0.3728,
962
+ "step": 135
963
+ },
964
+ {
965
+ "epoch": 0.45791245791245794,
966
+ "grad_norm": 9.100985527038574,
967
+ "learning_rate": 9.127516778523491e-05,
968
+ "loss": 0.3869,
969
+ "step": 136
970
+ },
971
+ {
972
+ "epoch": 0.4612794612794613,
973
+ "grad_norm": 9.76489543914795,
974
+ "learning_rate": 9.194630872483221e-05,
975
+ "loss": 0.3861,
976
+ "step": 137
977
+ },
978
+ {
979
+ "epoch": 0.46464646464646464,
980
+ "grad_norm": 3.834136962890625,
981
+ "learning_rate": 9.261744966442954e-05,
982
+ "loss": 0.4222,
983
+ "step": 138
984
+ },
985
+ {
986
+ "epoch": 0.468013468013468,
987
+ "grad_norm": 22.2440242767334,
988
+ "learning_rate": 9.328859060402684e-05,
989
+ "loss": 0.7935,
990
+ "step": 139
991
+ },
992
+ {
993
+ "epoch": 0.4713804713804714,
994
+ "grad_norm": 1.4633365869522095,
995
+ "learning_rate": 9.395973154362417e-05,
996
+ "loss": 0.347,
997
+ "step": 140
998
+ },
999
+ {
1000
+ "epoch": 0.47474747474747475,
1001
+ "grad_norm": 1.9224159717559814,
1002
+ "learning_rate": 9.463087248322147e-05,
1003
+ "loss": 0.3299,
1004
+ "step": 141
1005
+ },
1006
+ {
1007
+ "epoch": 0.4781144781144781,
1008
+ "grad_norm": 3.4107277393341064,
1009
+ "learning_rate": 9.53020134228188e-05,
1010
+ "loss": 0.4199,
1011
+ "step": 142
1012
+ },
1013
+ {
1014
+ "epoch": 0.48148148148148145,
1015
+ "grad_norm": 1.4255735874176025,
1016
+ "learning_rate": 9.59731543624161e-05,
1017
+ "loss": 0.3559,
1018
+ "step": 143
1019
+ },
1020
+ {
1021
+ "epoch": 0.48484848484848486,
1022
+ "grad_norm": 1.4576934576034546,
1023
+ "learning_rate": 9.664429530201344e-05,
1024
+ "loss": 0.3274,
1025
+ "step": 144
1026
+ },
1027
+ {
1028
+ "epoch": 0.4882154882154882,
1029
+ "grad_norm": 1.3531242609024048,
1030
+ "learning_rate": 9.731543624161075e-05,
1031
+ "loss": 0.3417,
1032
+ "step": 145
1033
+ },
1034
+ {
1035
+ "epoch": 0.49158249158249157,
1036
+ "grad_norm": 13.97393798828125,
1037
+ "learning_rate": 9.798657718120807e-05,
1038
+ "loss": 0.3434,
1039
+ "step": 146
1040
+ },
1041
+ {
1042
+ "epoch": 0.494949494949495,
1043
+ "grad_norm": 0.8413457870483398,
1044
+ "learning_rate": 9.865771812080538e-05,
1045
+ "loss": 0.3224,
1046
+ "step": 147
1047
+ },
1048
+ {
1049
+ "epoch": 0.4983164983164983,
1050
+ "grad_norm": 0.41903650760650635,
1051
+ "learning_rate": 9.93288590604027e-05,
1052
+ "loss": 0.3197,
1053
+ "step": 148
1054
+ },
1055
+ {
1056
+ "epoch": 0.5016835016835017,
1057
+ "grad_norm": 1.3428220748901367,
1058
+ "learning_rate": 0.0001,
1059
+ "loss": 0.3184,
1060
+ "step": 149
1061
+ },
1062
+ {
1063
+ "epoch": 0.5050505050505051,
1064
+ "grad_norm": 0.497494637966156,
1065
+ "learning_rate": 9.9999861762256e-05,
1066
+ "loss": 0.3064,
1067
+ "step": 150
1068
+ },
1069
+ {
1070
+ "epoch": 0.5084175084175084,
1071
+ "grad_norm": 0.5110116600990295,
1072
+ "learning_rate": 9.999944704978836e-05,
1073
+ "loss": 0.3195,
1074
+ "step": 151
1075
+ },
1076
+ {
1077
+ "epoch": 0.5117845117845118,
1078
+ "grad_norm": 0.4883813261985779,
1079
+ "learning_rate": 9.999875586489024e-05,
1080
+ "loss": 0.292,
1081
+ "step": 152
1082
+ },
1083
+ {
1084
+ "epoch": 0.5151515151515151,
1085
+ "grad_norm": 0.44456565380096436,
1086
+ "learning_rate": 9.999778821138357e-05,
1087
+ "loss": 0.3084,
1088
+ "step": 153
1089
+ },
1090
+ {
1091
+ "epoch": 0.5185185185185185,
1092
+ "grad_norm": 0.5006658434867859,
1093
+ "learning_rate": 9.999654409461896e-05,
1094
+ "loss": 0.3031,
1095
+ "step": 154
1096
+ },
1097
+ {
1098
+ "epoch": 0.5218855218855218,
1099
+ "grad_norm": 0.4398713707923889,
1100
+ "learning_rate": 9.999502352147583e-05,
1101
+ "loss": 0.3178,
1102
+ "step": 155
1103
+ },
1104
+ {
1105
+ "epoch": 0.5252525252525253,
1106
+ "grad_norm": 0.4853643476963043,
1107
+ "learning_rate": 9.999322650036214e-05,
1108
+ "loss": 0.3195,
1109
+ "step": 156
1110
+ },
1111
+ {
1112
+ "epoch": 0.5286195286195287,
1113
+ "grad_norm": 0.4636339545249939,
1114
+ "learning_rate": 9.999115304121457e-05,
1115
+ "loss": 0.3052,
1116
+ "step": 157
1117
+ },
1118
+ {
1119
+ "epoch": 0.531986531986532,
1120
+ "grad_norm": 0.525205671787262,
1121
+ "learning_rate": 9.998880315549834e-05,
1122
+ "loss": 0.3133,
1123
+ "step": 158
1124
+ },
1125
+ {
1126
+ "epoch": 0.5353535353535354,
1127
+ "grad_norm": 0.40854206681251526,
1128
+ "learning_rate": 9.998617685620714e-05,
1129
+ "loss": 0.3076,
1130
+ "step": 159
1131
+ },
1132
+ {
1133
+ "epoch": 0.5387205387205387,
1134
+ "grad_norm": 0.5355719327926636,
1135
+ "learning_rate": 9.998327415786315e-05,
1136
+ "loss": 0.3052,
1137
+ "step": 160
1138
+ },
1139
+ {
1140
+ "epoch": 0.5420875420875421,
1141
+ "grad_norm": 0.3861645460128784,
1142
+ "learning_rate": 9.998009507651684e-05,
1143
+ "loss": 0.3099,
1144
+ "step": 161
1145
+ },
1146
+ {
1147
+ "epoch": 0.5454545454545454,
1148
+ "grad_norm": 0.5338487029075623,
1149
+ "learning_rate": 9.997663962974697e-05,
1150
+ "loss": 0.3052,
1151
+ "step": 162
1152
+ },
1153
+ {
1154
+ "epoch": 0.5488215488215489,
1155
+ "grad_norm": 0.45219364762306213,
1156
+ "learning_rate": 9.997290783666049e-05,
1157
+ "loss": 0.2948,
1158
+ "step": 163
1159
+ },
1160
+ {
1161
+ "epoch": 0.5521885521885522,
1162
+ "grad_norm": 0.5037462711334229,
1163
+ "learning_rate": 9.996889971789235e-05,
1164
+ "loss": 0.3019,
1165
+ "step": 164
1166
+ },
1167
+ {
1168
+ "epoch": 0.5555555555555556,
1169
+ "grad_norm": 0.3949816823005676,
1170
+ "learning_rate": 9.996461529560553e-05,
1171
+ "loss": 0.3028,
1172
+ "step": 165
1173
+ },
1174
+ {
1175
+ "epoch": 0.5589225589225589,
1176
+ "grad_norm": 0.3921789824962616,
1177
+ "learning_rate": 9.996005459349074e-05,
1178
+ "loss": 0.2982,
1179
+ "step": 166
1180
+ },
1181
+ {
1182
+ "epoch": 0.5622895622895623,
1183
+ "grad_norm": 0.4122919738292694,
1184
+ "learning_rate": 9.995521763676645e-05,
1185
+ "loss": 0.3071,
1186
+ "step": 167
1187
+ },
1188
+ {
1189
+ "epoch": 0.5656565656565656,
1190
+ "grad_norm": 0.4212525188922882,
1191
+ "learning_rate": 9.995010445217867e-05,
1192
+ "loss": 0.3086,
1193
+ "step": 168
1194
+ },
1195
+ {
1196
+ "epoch": 0.569023569023569,
1197
+ "grad_norm": 0.3997049033641815,
1198
+ "learning_rate": 9.994471506800079e-05,
1199
+ "loss": 0.2957,
1200
+ "step": 169
1201
+ },
1202
+ {
1203
+ "epoch": 0.5723905723905723,
1204
+ "grad_norm": 0.34380048513412476,
1205
+ "learning_rate": 9.993904951403344e-05,
1206
+ "loss": 0.3122,
1207
+ "step": 170
1208
+ },
1209
+ {
1210
+ "epoch": 0.5757575757575758,
1211
+ "grad_norm": 0.40532243251800537,
1212
+ "learning_rate": 9.99331078216044e-05,
1213
+ "loss": 0.3055,
1214
+ "step": 171
1215
+ },
1216
+ {
1217
+ "epoch": 0.5791245791245792,
1218
+ "grad_norm": 0.4095707833766937,
1219
+ "learning_rate": 9.992689002356828e-05,
1220
+ "loss": 0.2868,
1221
+ "step": 172
1222
+ },
1223
+ {
1224
+ "epoch": 0.5824915824915825,
1225
+ "grad_norm": 0.41159185767173767,
1226
+ "learning_rate": 9.992039615430648e-05,
1227
+ "loss": 0.318,
1228
+ "step": 173
1229
+ },
1230
+ {
1231
+ "epoch": 0.5858585858585859,
1232
+ "grad_norm": 0.3728049397468567,
1233
+ "learning_rate": 9.991362624972688e-05,
1234
+ "loss": 0.309,
1235
+ "step": 174
1236
+ },
1237
+ {
1238
+ "epoch": 0.5892255892255892,
1239
+ "grad_norm": 0.3249180018901825,
1240
+ "learning_rate": 9.990658034726379e-05,
1241
+ "loss": 0.2818,
1242
+ "step": 175
1243
+ },
1244
+ {
1245
+ "epoch": 0.5925925925925926,
1246
+ "grad_norm": 0.35090282559394836,
1247
+ "learning_rate": 9.989925848587756e-05,
1248
+ "loss": 0.2839,
1249
+ "step": 176
1250
+ },
1251
+ {
1252
+ "epoch": 0.5959595959595959,
1253
+ "grad_norm": 0.3364333212375641,
1254
+ "learning_rate": 9.989166070605447e-05,
1255
+ "loss": 0.3063,
1256
+ "step": 177
1257
+ },
1258
+ {
1259
+ "epoch": 0.5993265993265994,
1260
+ "grad_norm": 0.4135960340499878,
1261
+ "learning_rate": 9.988378704980656e-05,
1262
+ "loss": 0.3085,
1263
+ "step": 178
1264
+ },
1265
+ {
1266
+ "epoch": 0.6026936026936027,
1267
+ "grad_norm": 0.35615649819374084,
1268
+ "learning_rate": 9.987563756067129e-05,
1269
+ "loss": 0.2955,
1270
+ "step": 179
1271
+ },
1272
+ {
1273
+ "epoch": 0.6060606060606061,
1274
+ "grad_norm": 0.3038477897644043,
1275
+ "learning_rate": 9.986721228371129e-05,
1276
+ "loss": 0.291,
1277
+ "step": 180
1278
+ },
1279
+ {
1280
+ "epoch": 0.6094276094276094,
1281
+ "grad_norm": 0.4663616120815277,
1282
+ "learning_rate": 9.985851126551428e-05,
1283
+ "loss": 0.3043,
1284
+ "step": 181
1285
+ },
1286
+ {
1287
+ "epoch": 0.6127946127946128,
1288
+ "grad_norm": 0.42187029123306274,
1289
+ "learning_rate": 9.984953455419258e-05,
1290
+ "loss": 0.2747,
1291
+ "step": 182
1292
+ },
1293
+ {
1294
+ "epoch": 0.6161616161616161,
1295
+ "grad_norm": 0.4150826334953308,
1296
+ "learning_rate": 9.9840282199383e-05,
1297
+ "loss": 0.2854,
1298
+ "step": 183
1299
+ },
1300
+ {
1301
+ "epoch": 0.6195286195286195,
1302
+ "grad_norm": 0.36844050884246826,
1303
+ "learning_rate": 9.983075425224653e-05,
1304
+ "loss": 0.2848,
1305
+ "step": 184
1306
+ },
1307
+ {
1308
+ "epoch": 0.622895622895623,
1309
+ "grad_norm": 0.4171907603740692,
1310
+ "learning_rate": 9.982095076546807e-05,
1311
+ "loss": 0.3003,
1312
+ "step": 185
1313
+ },
1314
+ {
1315
+ "epoch": 0.6262626262626263,
1316
+ "grad_norm": 0.3620002269744873,
1317
+ "learning_rate": 9.981087179325608e-05,
1318
+ "loss": 0.3043,
1319
+ "step": 186
1320
+ },
1321
+ {
1322
+ "epoch": 0.6296296296296297,
1323
+ "grad_norm": 0.40760573744773865,
1324
+ "learning_rate": 9.980051739134233e-05,
1325
+ "loss": 0.3059,
1326
+ "step": 187
1327
+ },
1328
+ {
1329
+ "epoch": 0.632996632996633,
1330
+ "grad_norm": 0.32069963216781616,
1331
+ "learning_rate": 9.978988761698161e-05,
1332
+ "loss": 0.2947,
1333
+ "step": 188
1334
+ },
1335
+ {
1336
+ "epoch": 0.6363636363636364,
1337
+ "grad_norm": 0.3327488303184509,
1338
+ "learning_rate": 9.977898252895134e-05,
1339
+ "loss": 0.2805,
1340
+ "step": 189
1341
+ },
1342
+ {
1343
+ "epoch": 0.6397306397306397,
1344
+ "grad_norm": 0.3968160152435303,
1345
+ "learning_rate": 9.976780218755131e-05,
1346
+ "loss": 0.2891,
1347
+ "step": 190
1348
+ },
1349
+ {
1350
+ "epoch": 0.6430976430976431,
1351
+ "grad_norm": 0.4018626809120178,
1352
+ "learning_rate": 9.975634665460332e-05,
1353
+ "loss": 0.2965,
1354
+ "step": 191
1355
+ },
1356
+ {
1357
+ "epoch": 0.6464646464646465,
1358
+ "grad_norm": 0.37805649638175964,
1359
+ "learning_rate": 9.974461599345088e-05,
1360
+ "loss": 0.3008,
1361
+ "step": 192
1362
+ },
1363
+ {
1364
+ "epoch": 0.6498316498316499,
1365
+ "grad_norm": 0.44425806403160095,
1366
+ "learning_rate": 9.973261026895877e-05,
1367
+ "loss": 0.2921,
1368
+ "step": 193
1369
+ },
1370
+ {
1371
+ "epoch": 0.6531986531986532,
1372
+ "grad_norm": 0.375931054353714,
1373
+ "learning_rate": 9.972032954751279e-05,
1374
+ "loss": 0.296,
1375
+ "step": 194
1376
+ },
1377
+ {
1378
+ "epoch": 0.6565656565656566,
1379
+ "grad_norm": 0.44635701179504395,
1380
+ "learning_rate": 9.970777389701926e-05,
1381
+ "loss": 0.29,
1382
+ "step": 195
1383
+ },
1384
+ {
1385
+ "epoch": 0.6599326599326599,
1386
+ "grad_norm": 0.28897619247436523,
1387
+ "learning_rate": 9.969494338690481e-05,
1388
+ "loss": 0.2895,
1389
+ "step": 196
1390
+ },
1391
+ {
1392
+ "epoch": 0.6632996632996633,
1393
+ "grad_norm": 0.4542882740497589,
1394
+ "learning_rate": 9.968183808811586e-05,
1395
+ "loss": 0.2887,
1396
+ "step": 197
1397
+ },
1398
+ {
1399
+ "epoch": 0.6666666666666666,
1400
+ "grad_norm": 0.3715568780899048,
1401
+ "learning_rate": 9.966845807311829e-05,
1402
+ "loss": 0.3038,
1403
+ "step": 198
1404
+ },
1405
+ {
1406
+ "epoch": 0.67003367003367,
1407
+ "grad_norm": 0.36940261721611023,
1408
+ "learning_rate": 9.965480341589701e-05,
1409
+ "loss": 0.2934,
1410
+ "step": 199
1411
+ },
1412
+ {
1413
+ "epoch": 0.6734006734006734,
1414
+ "grad_norm": 0.43046656250953674,
1415
+ "learning_rate": 9.96408741919556e-05,
1416
+ "loss": 0.2951,
1417
+ "step": 200
1418
+ },
1419
+ {
1420
+ "epoch": 0.6734006734006734,
1421
+ "eval_loss": 0.1412619948387146,
1422
+ "eval_runtime": 32.6268,
1423
+ "eval_samples_per_second": 30.65,
1424
+ "eval_steps_per_second": 1.931,
1425
+ "step": 200
1426
+ },
1427
+ {
1428
+ "epoch": 0.6767676767676768,
1429
+ "grad_norm": 0.37590286135673523,
1430
+ "learning_rate": 9.962667047831584e-05,
1431
+ "loss": 0.2922,
1432
+ "step": 201
1433
+ },
1434
+ {
1435
+ "epoch": 0.6801346801346801,
1436
+ "grad_norm": 0.3418475389480591,
1437
+ "learning_rate": 9.961219235351729e-05,
1438
+ "loss": 0.2732,
1439
+ "step": 202
1440
+ },
1441
+ {
1442
+ "epoch": 0.6835016835016835,
1443
+ "grad_norm": 0.3605377674102783,
1444
+ "learning_rate": 9.95974398976169e-05,
1445
+ "loss": 0.2882,
1446
+ "step": 203
1447
+ },
1448
+ {
1449
+ "epoch": 0.6868686868686869,
1450
+ "grad_norm": 0.40477219223976135,
1451
+ "learning_rate": 9.958241319218848e-05,
1452
+ "loss": 0.2859,
1453
+ "step": 204
1454
+ },
1455
+ {
1456
+ "epoch": 0.6902356902356902,
1457
+ "grad_norm": 0.4034753143787384,
1458
+ "learning_rate": 9.95671123203224e-05,
1459
+ "loss": 0.2984,
1460
+ "step": 205
1461
+ },
1462
+ {
1463
+ "epoch": 0.6936026936026936,
1464
+ "grad_norm": 0.3650234043598175,
1465
+ "learning_rate": 9.955153736662493e-05,
1466
+ "loss": 0.2772,
1467
+ "step": 206
1468
+ },
1469
+ {
1470
+ "epoch": 0.696969696969697,
1471
+ "grad_norm": 0.47222810983657837,
1472
+ "learning_rate": 9.953568841721797e-05,
1473
+ "loss": 0.28,
1474
+ "step": 207
1475
+ },
1476
+ {
1477
+ "epoch": 0.7003367003367004,
1478
+ "grad_norm": 0.3858278691768646,
1479
+ "learning_rate": 9.95195655597384e-05,
1480
+ "loss": 0.2815,
1481
+ "step": 208
1482
+ },
1483
+ {
1484
+ "epoch": 0.7037037037037037,
1485
+ "grad_norm": 0.4259450435638428,
1486
+ "learning_rate": 9.950316888333775e-05,
1487
+ "loss": 0.2965,
1488
+ "step": 209
1489
+ },
1490
+ {
1491
+ "epoch": 0.7070707070707071,
1492
+ "grad_norm": 0.4309611916542053,
1493
+ "learning_rate": 9.948649847868159e-05,
1494
+ "loss": 0.2766,
1495
+ "step": 210
1496
+ },
1497
+ {
1498
+ "epoch": 0.7104377104377104,
1499
+ "grad_norm": 0.4742699861526489,
1500
+ "learning_rate": 9.946955443794908e-05,
1501
+ "loss": 0.2859,
1502
+ "step": 211
1503
+ },
1504
+ {
1505
+ "epoch": 0.7138047138047138,
1506
+ "grad_norm": 0.4079667329788208,
1507
+ "learning_rate": 9.945233685483246e-05,
1508
+ "loss": 0.283,
1509
+ "step": 212
1510
+ },
1511
+ {
1512
+ "epoch": 0.7171717171717171,
1513
+ "grad_norm": 0.42072775959968567,
1514
+ "learning_rate": 9.943484582453653e-05,
1515
+ "loss": 0.298,
1516
+ "step": 213
1517
+ },
1518
+ {
1519
+ "epoch": 0.7205387205387206,
1520
+ "grad_norm": 0.43136894702911377,
1521
+ "learning_rate": 9.941708144377813e-05,
1522
+ "loss": 0.2693,
1523
+ "step": 214
1524
+ },
1525
+ {
1526
+ "epoch": 0.7239057239057239,
1527
+ "grad_norm": 0.42598387598991394,
1528
+ "learning_rate": 9.939904381078553e-05,
1529
+ "loss": 0.2836,
1530
+ "step": 215
1531
+ },
1532
+ {
1533
+ "epoch": 0.7272727272727273,
1534
+ "grad_norm": 0.40432655811309814,
1535
+ "learning_rate": 9.938073302529804e-05,
1536
+ "loss": 0.2844,
1537
+ "step": 216
1538
+ },
1539
+ {
1540
+ "epoch": 0.7306397306397306,
1541
+ "grad_norm": 0.3417808413505554,
1542
+ "learning_rate": 9.93621491885653e-05,
1543
+ "loss": 0.2849,
1544
+ "step": 217
1545
+ },
1546
+ {
1547
+ "epoch": 0.734006734006734,
1548
+ "grad_norm": 0.35036516189575195,
1549
+ "learning_rate": 9.934329240334686e-05,
1550
+ "loss": 0.2619,
1551
+ "step": 218
1552
+ },
1553
+ {
1554
+ "epoch": 0.7373737373737373,
1555
+ "grad_norm": 0.38956964015960693,
1556
+ "learning_rate": 9.932416277391143e-05,
1557
+ "loss": 0.2802,
1558
+ "step": 219
1559
+ },
1560
+ {
1561
+ "epoch": 0.7407407407407407,
1562
+ "grad_norm": 0.36884164810180664,
1563
+ "learning_rate": 9.930476040603653e-05,
1564
+ "loss": 0.2961,
1565
+ "step": 220
1566
+ },
1567
+ {
1568
+ "epoch": 0.7441077441077442,
1569
+ "grad_norm": 0.4145122468471527,
1570
+ "learning_rate": 9.928508540700774e-05,
1571
+ "loss": 0.2789,
1572
+ "step": 221
1573
+ },
1574
+ {
1575
+ "epoch": 0.7474747474747475,
1576
+ "grad_norm": 0.36580273509025574,
1577
+ "learning_rate": 9.926513788561816e-05,
1578
+ "loss": 0.2824,
1579
+ "step": 222
1580
+ },
1581
+ {
1582
+ "epoch": 0.7508417508417509,
1583
+ "grad_norm": 0.2912370264530182,
1584
+ "learning_rate": 9.924491795216777e-05,
1585
+ "loss": 0.2811,
1586
+ "step": 223
1587
+ },
1588
+ {
1589
+ "epoch": 0.7542087542087542,
1590
+ "grad_norm": 0.480868399143219,
1591
+ "learning_rate": 9.922442571846293e-05,
1592
+ "loss": 0.2853,
1593
+ "step": 224
1594
+ },
1595
+ {
1596
+ "epoch": 0.7575757575757576,
1597
+ "grad_norm": 0.3405955135822296,
1598
+ "learning_rate": 9.920366129781564e-05,
1599
+ "loss": 0.2908,
1600
+ "step": 225
1601
+ },
1602
+ {
1603
+ "epoch": 0.7609427609427609,
1604
+ "grad_norm": 0.34814175963401794,
1605
+ "learning_rate": 9.918262480504295e-05,
1606
+ "loss": 0.2923,
1607
+ "step": 226
1608
+ },
1609
+ {
1610
+ "epoch": 0.7643097643097643,
1611
+ "grad_norm": 0.36179670691490173,
1612
+ "learning_rate": 9.916131635646635e-05,
1613
+ "loss": 0.276,
1614
+ "step": 227
1615
+ },
1616
+ {
1617
+ "epoch": 0.7676767676767676,
1618
+ "grad_norm": 0.3848663568496704,
1619
+ "learning_rate": 9.913973606991113e-05,
1620
+ "loss": 0.264,
1621
+ "step": 228
1622
+ },
1623
+ {
1624
+ "epoch": 0.7710437710437711,
1625
+ "grad_norm": 0.4516603648662567,
1626
+ "learning_rate": 9.911788406470569e-05,
1627
+ "loss": 0.2854,
1628
+ "step": 229
1629
+ },
1630
+ {
1631
+ "epoch": 0.7744107744107744,
1632
+ "grad_norm": 0.4367293119430542,
1633
+ "learning_rate": 9.90957604616809e-05,
1634
+ "loss": 0.2802,
1635
+ "step": 230
1636
+ },
1637
+ {
1638
+ "epoch": 0.7777777777777778,
1639
+ "grad_norm": 0.41222095489501953,
1640
+ "learning_rate": 9.907336538316944e-05,
1641
+ "loss": 0.275,
1642
+ "step": 231
1643
+ },
1644
+ {
1645
+ "epoch": 0.7811447811447811,
1646
+ "grad_norm": 0.4176308810710907,
1647
+ "learning_rate": 9.905069895300514e-05,
1648
+ "loss": 0.2854,
1649
+ "step": 232
1650
+ },
1651
+ {
1652
+ "epoch": 0.7845117845117845,
1653
+ "grad_norm": 0.4087597131729126,
1654
+ "learning_rate": 9.902776129652223e-05,
1655
+ "loss": 0.2868,
1656
+ "step": 233
1657
+ },
1658
+ {
1659
+ "epoch": 0.7878787878787878,
1660
+ "grad_norm": 0.41595739126205444,
1661
+ "learning_rate": 9.900455254055467e-05,
1662
+ "loss": 0.2835,
1663
+ "step": 234
1664
+ },
1665
+ {
1666
+ "epoch": 0.7912457912457912,
1667
+ "grad_norm": 0.5036376118659973,
1668
+ "learning_rate": 9.898107281343556e-05,
1669
+ "loss": 0.2775,
1670
+ "step": 235
1671
+ },
1672
+ {
1673
+ "epoch": 0.7946127946127947,
1674
+ "grad_norm": 0.46533098816871643,
1675
+ "learning_rate": 9.895732224499625e-05,
1676
+ "loss": 0.285,
1677
+ "step": 236
1678
+ },
1679
+ {
1680
+ "epoch": 0.797979797979798,
1681
+ "grad_norm": 0.4155175983905792,
1682
+ "learning_rate": 9.893330096656574e-05,
1683
+ "loss": 0.2877,
1684
+ "step": 237
1685
+ },
1686
+ {
1687
+ "epoch": 0.8013468013468014,
1688
+ "grad_norm": 0.34219178557395935,
1689
+ "learning_rate": 9.890900911096992e-05,
1690
+ "loss": 0.2751,
1691
+ "step": 238
1692
+ },
1693
+ {
1694
+ "epoch": 0.8047138047138047,
1695
+ "grad_norm": 0.39359742403030396,
1696
+ "learning_rate": 9.888444681253086e-05,
1697
+ "loss": 0.2758,
1698
+ "step": 239
1699
+ },
1700
+ {
1701
+ "epoch": 0.8080808080808081,
1702
+ "grad_norm": 0.3699426054954529,
1703
+ "learning_rate": 9.885961420706602e-05,
1704
+ "loss": 0.2758,
1705
+ "step": 240
1706
+ },
1707
+ {
1708
+ "epoch": 0.8114478114478114,
1709
+ "grad_norm": 0.3353779911994934,
1710
+ "learning_rate": 9.883451143188753e-05,
1711
+ "loss": 0.2891,
1712
+ "step": 241
1713
+ },
1714
+ {
1715
+ "epoch": 0.8148148148148148,
1716
+ "grad_norm": 0.3476376235485077,
1717
+ "learning_rate": 9.880913862580145e-05,
1718
+ "loss": 0.2699,
1719
+ "step": 242
1720
+ },
1721
+ {
1722
+ "epoch": 0.8181818181818182,
1723
+ "grad_norm": 0.37724611163139343,
1724
+ "learning_rate": 9.878349592910692e-05,
1725
+ "loss": 0.2759,
1726
+ "step": 243
1727
+ },
1728
+ {
1729
+ "epoch": 0.8215488215488216,
1730
+ "grad_norm": 0.3629307150840759,
1731
+ "learning_rate": 9.875758348359552e-05,
1732
+ "loss": 0.2741,
1733
+ "step": 244
1734
+ },
1735
+ {
1736
+ "epoch": 0.8249158249158249,
1737
+ "grad_norm": 0.35653156042099,
1738
+ "learning_rate": 9.873140143255036e-05,
1739
+ "loss": 0.2717,
1740
+ "step": 245
1741
+ },
1742
+ {
1743
+ "epoch": 0.8282828282828283,
1744
+ "grad_norm": 0.37418127059936523,
1745
+ "learning_rate": 9.870494992074533e-05,
1746
+ "loss": 0.2743,
1747
+ "step": 246
1748
+ },
1749
+ {
1750
+ "epoch": 0.8316498316498316,
1751
+ "grad_norm": 0.3299245238304138,
1752
+ "learning_rate": 9.867822909444434e-05,
1753
+ "loss": 0.2751,
1754
+ "step": 247
1755
+ },
1756
+ {
1757
+ "epoch": 0.835016835016835,
1758
+ "grad_norm": 0.3463493585586548,
1759
+ "learning_rate": 9.865123910140046e-05,
1760
+ "loss": 0.2778,
1761
+ "step": 248
1762
+ },
1763
+ {
1764
+ "epoch": 0.8383838383838383,
1765
+ "grad_norm": 0.5460504293441772,
1766
+ "learning_rate": 9.862398009085511e-05,
1767
+ "loss": 0.2799,
1768
+ "step": 249
1769
+ },
1770
+ {
1771
+ "epoch": 0.8417508417508418,
1772
+ "grad_norm": 0.3625568151473999,
1773
+ "learning_rate": 9.859645221353725e-05,
1774
+ "loss": 0.2641,
1775
+ "step": 250
1776
+ },
1777
+ {
1778
+ "epoch": 0.8451178451178452,
1779
+ "grad_norm": 0.37554433941841125,
1780
+ "learning_rate": 9.856865562166256e-05,
1781
+ "loss": 0.2625,
1782
+ "step": 251
1783
+ },
1784
+ {
1785
+ "epoch": 0.8484848484848485,
1786
+ "grad_norm": 0.4169292449951172,
1787
+ "learning_rate": 9.854059046893257e-05,
1788
+ "loss": 0.2754,
1789
+ "step": 252
1790
+ },
1791
+ {
1792
+ "epoch": 0.8518518518518519,
1793
+ "grad_norm": 0.4144760072231293,
1794
+ "learning_rate": 9.85122569105338e-05,
1795
+ "loss": 0.2764,
1796
+ "step": 253
1797
+ },
1798
+ {
1799
+ "epoch": 0.8552188552188552,
1800
+ "grad_norm": 0.3319230079650879,
1801
+ "learning_rate": 9.848365510313695e-05,
1802
+ "loss": 0.2812,
1803
+ "step": 254
1804
+ },
1805
+ {
1806
+ "epoch": 0.8585858585858586,
1807
+ "grad_norm": 0.31481847167015076,
1808
+ "learning_rate": 9.845478520489599e-05,
1809
+ "loss": 0.2534,
1810
+ "step": 255
1811
+ },
1812
+ {
1813
+ "epoch": 0.8619528619528619,
1814
+ "grad_norm": 0.37751275300979614,
1815
+ "learning_rate": 9.842564737544731e-05,
1816
+ "loss": 0.2796,
1817
+ "step": 256
1818
+ },
1819
+ {
1820
+ "epoch": 0.8653198653198653,
1821
+ "grad_norm": 0.4334275424480438,
1822
+ "learning_rate": 9.83962417759088e-05,
1823
+ "loss": 0.2829,
1824
+ "step": 257
1825
+ },
1826
+ {
1827
+ "epoch": 0.8686868686868687,
1828
+ "grad_norm": 0.4017227590084076,
1829
+ "learning_rate": 9.836656856887903e-05,
1830
+ "loss": 0.2667,
1831
+ "step": 258
1832
+ },
1833
+ {
1834
+ "epoch": 0.8720538720538721,
1835
+ "grad_norm": 0.42103585600852966,
1836
+ "learning_rate": 9.833662791843627e-05,
1837
+ "loss": 0.2631,
1838
+ "step": 259
1839
+ },
1840
+ {
1841
+ "epoch": 0.8754208754208754,
1842
+ "grad_norm": 0.34120380878448486,
1843
+ "learning_rate": 9.830641999013768e-05,
1844
+ "loss": 0.2613,
1845
+ "step": 260
1846
+ },
1847
+ {
1848
+ "epoch": 0.8787878787878788,
1849
+ "grad_norm": 0.49804946780204773,
1850
+ "learning_rate": 9.827594495101823e-05,
1851
+ "loss": 0.2675,
1852
+ "step": 261
1853
+ },
1854
+ {
1855
+ "epoch": 0.8821548821548821,
1856
+ "grad_norm": 0.3861115574836731,
1857
+ "learning_rate": 9.824520296959001e-05,
1858
+ "loss": 0.2708,
1859
+ "step": 262
1860
+ },
1861
+ {
1862
+ "epoch": 0.8855218855218855,
1863
+ "grad_norm": 0.39489248394966125,
1864
+ "learning_rate": 9.821419421584107e-05,
1865
+ "loss": 0.2831,
1866
+ "step": 263
1867
+ },
1868
+ {
1869
+ "epoch": 0.8888888888888888,
1870
+ "grad_norm": 0.3506355881690979,
1871
+ "learning_rate": 9.818291886123463e-05,
1872
+ "loss": 0.2784,
1873
+ "step": 264
1874
+ },
1875
+ {
1876
+ "epoch": 0.8922558922558923,
1877
+ "grad_norm": 0.35518354177474976,
1878
+ "learning_rate": 9.815137707870805e-05,
1879
+ "loss": 0.2671,
1880
+ "step": 265
1881
+ },
1882
+ {
1883
+ "epoch": 0.8956228956228957,
1884
+ "grad_norm": 0.35561174154281616,
1885
+ "learning_rate": 9.811956904267195e-05,
1886
+ "loss": 0.2784,
1887
+ "step": 266
1888
+ },
1889
+ {
1890
+ "epoch": 0.898989898989899,
1891
+ "grad_norm": 0.3117510974407196,
1892
+ "learning_rate": 9.808749492900918e-05,
1893
+ "loss": 0.2824,
1894
+ "step": 267
1895
+ },
1896
+ {
1897
+ "epoch": 0.9023569023569024,
1898
+ "grad_norm": 0.34295716881752014,
1899
+ "learning_rate": 9.805515491507382e-05,
1900
+ "loss": 0.2704,
1901
+ "step": 268
1902
+ },
1903
+ {
1904
+ "epoch": 0.9057239057239057,
1905
+ "grad_norm": 0.3531172275543213,
1906
+ "learning_rate": 9.802254917969032e-05,
1907
+ "loss": 0.2712,
1908
+ "step": 269
1909
+ },
1910
+ {
1911
+ "epoch": 0.9090909090909091,
1912
+ "grad_norm": 0.3834570646286011,
1913
+ "learning_rate": 9.798967790315244e-05,
1914
+ "loss": 0.285,
1915
+ "step": 270
1916
+ },
1917
+ {
1918
+ "epoch": 0.9124579124579124,
1919
+ "grad_norm": 0.2960718274116516,
1920
+ "learning_rate": 9.795654126722217e-05,
1921
+ "loss": 0.2786,
1922
+ "step": 271
1923
+ },
1924
+ {
1925
+ "epoch": 0.9158249158249159,
1926
+ "grad_norm": 0.3393447697162628,
1927
+ "learning_rate": 9.79231394551289e-05,
1928
+ "loss": 0.2841,
1929
+ "step": 272
1930
+ },
1931
+ {
1932
+ "epoch": 0.9191919191919192,
1933
+ "grad_norm": 0.313174843788147,
1934
+ "learning_rate": 9.788947265156827e-05,
1935
+ "loss": 0.2605,
1936
+ "step": 273
1937
+ },
1938
+ {
1939
+ "epoch": 0.9225589225589226,
1940
+ "grad_norm": 0.3173663914203644,
1941
+ "learning_rate": 9.785554104270118e-05,
1942
+ "loss": 0.2564,
1943
+ "step": 274
1944
+ },
1945
+ {
1946
+ "epoch": 0.9259259259259259,
1947
+ "grad_norm": 0.36193931102752686,
1948
+ "learning_rate": 9.782134481615281e-05,
1949
+ "loss": 0.2659,
1950
+ "step": 275
1951
+ },
1952
+ {
1953
+ "epoch": 0.9292929292929293,
1954
+ "grad_norm": 0.3565308451652527,
1955
+ "learning_rate": 9.778688416101154e-05,
1956
+ "loss": 0.2734,
1957
+ "step": 276
1958
+ },
1959
+ {
1960
+ "epoch": 0.9326599326599326,
1961
+ "grad_norm": 0.32475653290748596,
1962
+ "learning_rate": 9.775215926782788e-05,
1963
+ "loss": 0.2754,
1964
+ "step": 277
1965
+ },
1966
+ {
1967
+ "epoch": 0.936026936026936,
1968
+ "grad_norm": 0.4006199836730957,
1969
+ "learning_rate": 9.771717032861346e-05,
1970
+ "loss": 0.2662,
1971
+ "step": 278
1972
+ },
1973
+ {
1974
+ "epoch": 0.9393939393939394,
1975
+ "grad_norm": 0.31218966841697693,
1976
+ "learning_rate": 9.768191753683998e-05,
1977
+ "loss": 0.2442,
1978
+ "step": 279
1979
+ },
1980
+ {
1981
+ "epoch": 0.9427609427609428,
1982
+ "grad_norm": 0.3531815707683563,
1983
+ "learning_rate": 9.764640108743808e-05,
1984
+ "loss": 0.2485,
1985
+ "step": 280
1986
+ },
1987
+ {
1988
+ "epoch": 0.9461279461279462,
1989
+ "grad_norm": 0.38060134649276733,
1990
+ "learning_rate": 9.761062117679632e-05,
1991
+ "loss": 0.2797,
1992
+ "step": 281
1993
+ },
1994
+ {
1995
+ "epoch": 0.9494949494949495,
1996
+ "grad_norm": 0.416530966758728,
1997
+ "learning_rate": 9.757457800276006e-05,
1998
+ "loss": 0.2615,
1999
+ "step": 282
2000
+ },
2001
+ {
2002
+ "epoch": 0.9528619528619529,
2003
+ "grad_norm": 0.3815469741821289,
2004
+ "learning_rate": 9.75382717646304e-05,
2005
+ "loss": 0.255,
2006
+ "step": 283
2007
+ },
2008
+ {
2009
+ "epoch": 0.9562289562289562,
2010
+ "grad_norm": 0.41139233112335205,
2011
+ "learning_rate": 9.750170266316303e-05,
2012
+ "loss": 0.2615,
2013
+ "step": 284
2014
+ },
2015
+ {
2016
+ "epoch": 0.9595959595959596,
2017
+ "grad_norm": 0.374959260225296,
2018
+ "learning_rate": 9.746487090056713e-05,
2019
+ "loss": 0.2638,
2020
+ "step": 285
2021
+ },
2022
+ {
2023
+ "epoch": 0.9629629629629629,
2024
+ "grad_norm": 0.35468292236328125,
2025
+ "learning_rate": 9.742777668050434e-05,
2026
+ "loss": 0.2572,
2027
+ "step": 286
2028
+ },
2029
+ {
2030
+ "epoch": 0.9663299663299664,
2031
+ "grad_norm": 0.35659849643707275,
2032
+ "learning_rate": 9.739042020808746e-05,
2033
+ "loss": 0.266,
2034
+ "step": 287
2035
+ },
2036
+ {
2037
+ "epoch": 0.9696969696969697,
2038
+ "grad_norm": 0.37296387553215027,
2039
+ "learning_rate": 9.735280168987949e-05,
2040
+ "loss": 0.2677,
2041
+ "step": 288
2042
+ },
2043
+ {
2044
+ "epoch": 0.9730639730639731,
2045
+ "grad_norm": 0.34908655285835266,
2046
+ "learning_rate": 9.73149213338924e-05,
2047
+ "loss": 0.2732,
2048
+ "step": 289
2049
+ },
2050
+ {
2051
+ "epoch": 0.9764309764309764,
2052
+ "grad_norm": 0.3758234679698944,
2053
+ "learning_rate": 9.727677934958599e-05,
2054
+ "loss": 0.2738,
2055
+ "step": 290
2056
+ },
2057
+ {
2058
+ "epoch": 0.9797979797979798,
2059
+ "grad_norm": 0.35159602761268616,
2060
+ "learning_rate": 9.723837594786672e-05,
2061
+ "loss": 0.2684,
2062
+ "step": 291
2063
+ },
2064
+ {
2065
+ "epoch": 0.9831649831649831,
2066
+ "grad_norm": 0.33813127875328064,
2067
+ "learning_rate": 9.719971134108658e-05,
2068
+ "loss": 0.2682,
2069
+ "step": 292
2070
+ },
2071
+ {
2072
+ "epoch": 0.9865319865319865,
2073
+ "grad_norm": 0.32259315252304077,
2074
+ "learning_rate": 9.716078574304189e-05,
2075
+ "loss": 0.2721,
2076
+ "step": 293
2077
+ },
2078
+ {
2079
+ "epoch": 0.98989898989899,
2080
+ "grad_norm": 0.3467171788215637,
2081
+ "learning_rate": 9.712159936897213e-05,
2082
+ "loss": 0.264,
2083
+ "step": 294
2084
+ },
2085
+ {
2086
+ "epoch": 0.9932659932659933,
2087
+ "grad_norm": 0.33499976992607117,
2088
+ "learning_rate": 9.708215243555875e-05,
2089
+ "loss": 0.2636,
2090
+ "step": 295
2091
+ },
2092
+ {
2093
+ "epoch": 0.9966329966329966,
2094
+ "grad_norm": 0.2971048355102539,
2095
+ "learning_rate": 9.704244516092392e-05,
2096
+ "loss": 0.2644,
2097
+ "step": 296
2098
+ },
2099
+ {
2100
+ "epoch": 1.0,
2101
+ "grad_norm": 0.3515819013118744,
2102
+ "learning_rate": 9.700247776462943e-05,
2103
+ "loss": 0.2587,
2104
+ "step": 297
2105
+ },
2106
+ {
2107
+ "epoch": 1.0033670033670035,
2108
+ "grad_norm": 0.31730222702026367,
2109
+ "learning_rate": 9.696225046767538e-05,
2110
+ "loss": 0.2544,
2111
+ "step": 298
2112
+ },
2113
+ {
2114
+ "epoch": 1.0067340067340067,
2115
+ "grad_norm": 0.3283955752849579,
2116
+ "learning_rate": 9.6921763492499e-05,
2117
+ "loss": 0.2547,
2118
+ "step": 299
2119
+ },
2120
+ {
2121
+ "epoch": 1.0101010101010102,
2122
+ "grad_norm": 0.3477189242839813,
2123
+ "learning_rate": 9.688101706297341e-05,
2124
+ "loss": 0.2639,
2125
+ "step": 300
2126
+ },
2127
+ {
2128
+ "epoch": 1.0101010101010102,
2129
+ "eval_loss": 0.12977388501167297,
2130
+ "eval_runtime": 33.026,
2131
+ "eval_samples_per_second": 30.279,
2132
+ "eval_steps_per_second": 1.908,
2133
+ "step": 300
2134
+ }
2135
+ ],
2136
+ "logging_steps": 1,
2137
+ "max_steps": 1485,
2138
+ "num_input_tokens_seen": 0,
2139
+ "num_train_epochs": 5,
2140
+ "save_steps": 100,
2141
+ "stateful_callbacks": {
2142
+ "TrainerControl": {
2143
+ "args": {
2144
+ "should_epoch_stop": false,
2145
+ "should_evaluate": false,
2146
+ "should_log": false,
2147
+ "should_save": true,
2148
+ "should_training_stop": false
2149
+ },
2150
+ "attributes": {}
2151
+ }
2152
+ },
2153
+ "total_flos": 4.0144381690668646e+17,
2154
+ "train_batch_size": 4,
2155
+ "trial_name": null,
2156
+ "trial_params": null
2157
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6508d83f63ab1198e30dbd0ff3243ef9c7492121e98c91692ed234e29d5c5577
3
+ size 7288
zero_to_fp32.py ADDED
@@ -0,0 +1,760 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #!/usr/bin/env python
2
+
3
+ # Copyright (c) Microsoft Corporation.
4
+ # SPDX-License-Identifier: Apache-2.0
5
+
6
+ # DeepSpeed Team
7
+
8
+ # This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
9
+ # copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
10
+ # the future. Once extracted, the weights don't require DeepSpeed and can be used in any
11
+ # application.
12
+ #
13
+ # example:
14
+ # python zero_to_fp32.py . output_dir/
15
+ # or
16
+ # python zero_to_fp32.py . output_dir/ --safe_serialization
17
+
18
+ import argparse
19
+ import torch
20
+ import glob
21
+ import math
22
+ import os
23
+ import re
24
+ import gc
25
+ import json
26
+ import numpy as np
27
+ from tqdm import tqdm
28
+ from collections import OrderedDict
29
+ from dataclasses import dataclass
30
+
31
+ # while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
32
+ # DeepSpeed data structures it has to be available in the current python environment.
33
+ from deepspeed.utils import logger
34
+ from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
35
+ FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
36
+ FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
37
+
38
+
39
+ @dataclass
40
+ class zero_model_state:
41
+ buffers: dict()
42
+ param_shapes: dict()
43
+ shared_params: list
44
+ ds_version: int
45
+ frozen_param_shapes: dict()
46
+ frozen_param_fragments: dict()
47
+
48
+
49
+ debug = 0
50
+
51
+ # load to cpu
52
+ device = torch.device('cpu')
53
+
54
+
55
+ def atoi(text):
56
+ return int(text) if text.isdigit() else text
57
+
58
+
59
+ def natural_keys(text):
60
+ '''
61
+ alist.sort(key=natural_keys) sorts in human order
62
+ http://nedbatchelder.com/blog/200712/human_sorting.html
63
+ (See Toothy's implementation in the comments)
64
+ '''
65
+ return [atoi(c) for c in re.split(r'(\d+)', text)]
66
+
67
+
68
+ def get_model_state_file(checkpoint_dir, zero_stage):
69
+ if not os.path.isdir(checkpoint_dir):
70
+ raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
71
+
72
+ # there should be only one file
73
+ if zero_stage <= 2:
74
+ file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
75
+ elif zero_stage == 3:
76
+ file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
77
+
78
+ if not os.path.exists(file):
79
+ raise FileNotFoundError(f"can't find model states file at '{file}'")
80
+
81
+ return file
82
+
83
+
84
+ def get_checkpoint_files(checkpoint_dir, glob_pattern):
85
+ # XXX: need to test that this simple glob rule works for multi-node setup too
86
+ ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
87
+
88
+ if len(ckpt_files) == 0:
89
+ raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
90
+
91
+ return ckpt_files
92
+
93
+
94
+ def get_optim_files(checkpoint_dir):
95
+ return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
96
+
97
+
98
+ def get_model_state_files(checkpoint_dir):
99
+ return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
100
+
101
+
102
+ def parse_model_states(files):
103
+ zero_model_states = []
104
+ for file in files:
105
+ state_dict = torch.load(file, map_location=device, weights_only=False)
106
+
107
+ if BUFFER_NAMES not in state_dict:
108
+ raise ValueError(f"{file} is not a model state checkpoint")
109
+ buffer_names = state_dict[BUFFER_NAMES]
110
+ if debug:
111
+ print("Found buffers:", buffer_names)
112
+
113
+ # recover just the buffers while restoring them to fp32 if they were saved in fp16
114
+ buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
115
+ param_shapes = state_dict[PARAM_SHAPES]
116
+
117
+ # collect parameters that are included in param_shapes
118
+ param_names = []
119
+ for s in param_shapes:
120
+ for name in s.keys():
121
+ param_names.append(name)
122
+
123
+ # update with frozen parameters
124
+ frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
125
+ if frozen_param_shapes is not None:
126
+ if debug:
127
+ print(f"Found frozen_param_shapes: {frozen_param_shapes}")
128
+ param_names += list(frozen_param_shapes.keys())
129
+
130
+ # handle shared params
131
+ shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
132
+
133
+ ds_version = state_dict.get(DS_VERSION, None)
134
+
135
+ frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
136
+
137
+ z_model_state = zero_model_state(buffers=buffers,
138
+ param_shapes=param_shapes,
139
+ shared_params=shared_params,
140
+ ds_version=ds_version,
141
+ frozen_param_shapes=frozen_param_shapes,
142
+ frozen_param_fragments=frozen_param_fragments)
143
+ zero_model_states.append(z_model_state)
144
+
145
+ return zero_model_states
146
+
147
+
148
+ def parse_optim_states(files, ds_checkpoint_dir):
149
+ total_files = len(files)
150
+ state_dicts = []
151
+ for f in tqdm(files, desc='Loading checkpoint shards'):
152
+ state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
153
+ # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
154
+ # and also handle the case where it was already removed by another helper script
155
+ state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
156
+ state_dicts.append(state_dict)
157
+
158
+ if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
159
+ raise ValueError(f"{files[0]} is not a zero checkpoint")
160
+ zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
161
+ world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
162
+
163
+ # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
164
+ # parameters can be different from data parallelism for non-expert parameters. So we can just
165
+ # use the max of the partition_count to get the dp world_size.
166
+
167
+ if type(world_size) is list:
168
+ world_size = max(world_size)
169
+
170
+ if world_size != total_files:
171
+ raise ValueError(
172
+ f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
173
+ "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
174
+ )
175
+
176
+ # the groups are named differently in each stage
177
+ if zero_stage <= 2:
178
+ fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
179
+ elif zero_stage == 3:
180
+ fp32_groups_key = FP32_FLAT_GROUPS
181
+ else:
182
+ raise ValueError(f"unknown zero stage {zero_stage}")
183
+
184
+ fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
185
+ return zero_stage, world_size, fp32_flat_groups
186
+
187
+
188
+ def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
189
+ """
190
+ Returns fp32 state_dict reconstructed from ds checkpoint
191
+
192
+ Args:
193
+ - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
194
+
195
+ """
196
+ print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
197
+
198
+ optim_files = get_optim_files(ds_checkpoint_dir)
199
+ zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
200
+ print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
201
+
202
+ model_files = get_model_state_files(ds_checkpoint_dir)
203
+
204
+ zero_model_states = parse_model_states(model_files)
205
+ print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
206
+
207
+ if zero_stage <= 2:
208
+ return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
209
+ exclude_frozen_parameters)
210
+ elif zero_stage == 3:
211
+ return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
212
+ exclude_frozen_parameters)
213
+
214
+
215
+ def _zero2_merge_frozen_params(state_dict, zero_model_states):
216
+ if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
217
+ return
218
+
219
+ frozen_param_shapes = zero_model_states[0].frozen_param_shapes
220
+ frozen_param_fragments = zero_model_states[0].frozen_param_fragments
221
+
222
+ if debug:
223
+ num_elem = sum(s.numel() for s in frozen_param_shapes.values())
224
+ print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
225
+
226
+ wanted_params = len(frozen_param_shapes)
227
+ wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
228
+ avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
229
+ print(f'Frozen params: Have {avail_numel} numels to process.')
230
+ print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
231
+
232
+ total_params = 0
233
+ total_numel = 0
234
+ for name, shape in frozen_param_shapes.items():
235
+ total_params += 1
236
+ unpartitioned_numel = shape.numel()
237
+ total_numel += unpartitioned_numel
238
+
239
+ state_dict[name] = frozen_param_fragments[name]
240
+
241
+ if debug:
242
+ print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
243
+
244
+ print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
245
+
246
+
247
+ def _has_callable(obj, fn):
248
+ attr = getattr(obj, fn, None)
249
+ return callable(attr)
250
+
251
+
252
+ def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
253
+ param_shapes = zero_model_states[0].param_shapes
254
+
255
+ # Reconstruction protocol:
256
+ #
257
+ # XXX: document this
258
+
259
+ if debug:
260
+ for i in range(world_size):
261
+ for j in range(len(fp32_flat_groups[0])):
262
+ print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
263
+
264
+ # XXX: memory usage doubles here (zero2)
265
+ num_param_groups = len(fp32_flat_groups[0])
266
+ merged_single_partition_of_fp32_groups = []
267
+ for i in range(num_param_groups):
268
+ merged_partitions = [sd[i] for sd in fp32_flat_groups]
269
+ full_single_fp32_vector = torch.cat(merged_partitions, 0)
270
+ merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
271
+ avail_numel = sum(
272
+ [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
273
+
274
+ if debug:
275
+ wanted_params = sum([len(shapes) for shapes in param_shapes])
276
+ wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
277
+ # not asserting if there is a mismatch due to possible padding
278
+ print(f"Have {avail_numel} numels to process.")
279
+ print(f"Need {wanted_numel} numels in {wanted_params} params.")
280
+
281
+ # params
282
+ # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
283
+ # out-of-core computing solution
284
+ total_numel = 0
285
+ total_params = 0
286
+ for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
287
+ offset = 0
288
+ avail_numel = full_single_fp32_vector.numel()
289
+ for name, shape in shapes.items():
290
+
291
+ unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
292
+ total_numel += unpartitioned_numel
293
+ total_params += 1
294
+
295
+ if debug:
296
+ print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
297
+ state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
298
+ offset += unpartitioned_numel
299
+
300
+ # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
301
+ # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
302
+ # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
303
+ # live optimizer object, so we are checking that the numbers are within the right range
304
+ align_to = 2 * world_size
305
+
306
+ def zero2_align(x):
307
+ return align_to * math.ceil(x / align_to)
308
+
309
+ if debug:
310
+ print(f"original offset={offset}, avail_numel={avail_numel}")
311
+
312
+ offset = zero2_align(offset)
313
+ avail_numel = zero2_align(avail_numel)
314
+
315
+ if debug:
316
+ print(f"aligned offset={offset}, avail_numel={avail_numel}")
317
+
318
+ # Sanity check
319
+ if offset != avail_numel:
320
+ raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
321
+
322
+ print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
323
+
324
+
325
+ def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
326
+ exclude_frozen_parameters):
327
+ state_dict = OrderedDict()
328
+
329
+ # buffers
330
+ buffers = zero_model_states[0].buffers
331
+ state_dict.update(buffers)
332
+ if debug:
333
+ print(f"added {len(buffers)} buffers")
334
+
335
+ if not exclude_frozen_parameters:
336
+ _zero2_merge_frozen_params(state_dict, zero_model_states)
337
+
338
+ _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
339
+
340
+ # recover shared parameters
341
+ for pair in zero_model_states[0].shared_params:
342
+ if pair[1] in state_dict:
343
+ state_dict[pair[0]] = state_dict[pair[1]]
344
+
345
+ return state_dict
346
+
347
+
348
+ def zero3_partitioned_param_info(unpartitioned_numel, world_size):
349
+ remainder = unpartitioned_numel % world_size
350
+ padding_numel = (world_size - remainder) if remainder else 0
351
+ partitioned_numel = math.ceil(unpartitioned_numel / world_size)
352
+ return partitioned_numel, padding_numel
353
+
354
+
355
+ def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
356
+ if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
357
+ return
358
+
359
+ if debug:
360
+ for i in range(world_size):
361
+ num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
362
+ print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
363
+
364
+ frozen_param_shapes = zero_model_states[0].frozen_param_shapes
365
+ wanted_params = len(frozen_param_shapes)
366
+ wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
367
+ avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
368
+ print(f'Frozen params: Have {avail_numel} numels to process.')
369
+ print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
370
+
371
+ total_params = 0
372
+ total_numel = 0
373
+ for name, shape in zero_model_states[0].frozen_param_shapes.items():
374
+ total_params += 1
375
+ unpartitioned_numel = shape.numel()
376
+ total_numel += unpartitioned_numel
377
+
378
+ param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
379
+ state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
380
+
381
+ partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
382
+
383
+ if debug:
384
+ print(
385
+ f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
386
+ )
387
+
388
+ print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
389
+
390
+
391
+ class GatheredTensor:
392
+ """
393
+ A pseudo tensor that collects partitioned weights.
394
+ It is more memory efficient when there are multiple groups.
395
+ """
396
+
397
+ def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
398
+ self.flat_groups = flat_groups
399
+ self.flat_groups_offset = flat_groups_offset
400
+ self.offset = offset
401
+ self.partitioned_numel = partitioned_numel
402
+ self.shape = shape
403
+ self.dtype = self.flat_groups[0][0].dtype
404
+
405
+ def contiguous(self):
406
+ """
407
+ Merge partitioned weights from flat_groups into a single tensor.
408
+ """
409
+ end_idx = self.offset + self.partitioned_numel
410
+ world_size = len(self.flat_groups)
411
+ pad_flat_param_chunks = []
412
+
413
+ for rank_i in range(world_size):
414
+ # for each rank, we need to collect weights from related group/groups
415
+ flat_groups_at_rank_i = self.flat_groups[rank_i]
416
+ start_group_id = None
417
+ end_group_id = None
418
+ for group_id in range(len(self.flat_groups_offset)):
419
+ if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
420
+ start_group_id = group_id
421
+ if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
422
+ end_group_id = group_id
423
+ break
424
+ # collect weights from related group/groups
425
+ for group_id in range(start_group_id, end_group_id + 1):
426
+ flat_tensor = flat_groups_at_rank_i[group_id]
427
+ start_offset = self.offset - self.flat_groups_offset[group_id]
428
+ end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
429
+ pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
430
+
431
+ # collect weights from all ranks
432
+ pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
433
+ param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
434
+ return param
435
+
436
+
437
+ def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
438
+ param_shapes = zero_model_states[0].param_shapes
439
+ avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size
440
+
441
+ # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
442
+ # param, re-consolidating each param, while dealing with padding if any
443
+
444
+ # merge list of dicts, preserving order
445
+ param_shapes = {k: v for d in param_shapes for k, v in d.items()}
446
+
447
+ if debug:
448
+ for i in range(world_size):
449
+ print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
450
+
451
+ wanted_params = len(param_shapes)
452
+ wanted_numel = sum(shape.numel() for shape in param_shapes.values())
453
+ # not asserting if there is a mismatch due to possible padding
454
+ avail_numel = fp32_flat_groups[0].numel() * world_size
455
+ print(f"Trainable params: Have {avail_numel} numels to process.")
456
+ print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
457
+
458
+ # params
459
+ # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
460
+ # out-of-core computing solution
461
+ offset = 0
462
+ total_numel = 0
463
+ total_params = 0
464
+ flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
465
+ for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
466
+ unpartitioned_numel = shape.numel()
467
+ total_numel += unpartitioned_numel
468
+ total_params += 1
469
+ partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
470
+
471
+ if debug:
472
+ print(
473
+ f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
474
+ )
475
+
476
+ # memory efficient tensor
477
+ tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
478
+ state_dict[name] = tensor
479
+ offset += partitioned_numel
480
+
481
+ offset *= world_size
482
+
483
+ # Sanity check
484
+ if offset != avail_numel:
485
+ raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
486
+
487
+ print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
488
+
489
+
490
+ def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
491
+ exclude_frozen_parameters):
492
+ state_dict = OrderedDict()
493
+
494
+ # buffers
495
+ buffers = zero_model_states[0].buffers
496
+ state_dict.update(buffers)
497
+ if debug:
498
+ print(f"added {len(buffers)} buffers")
499
+
500
+ if not exclude_frozen_parameters:
501
+ _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
502
+
503
+ _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
504
+
505
+ # recover shared parameters
506
+ for pair in zero_model_states[0].shared_params:
507
+ if pair[1] in state_dict:
508
+ state_dict[pair[0]] = state_dict[pair[1]]
509
+
510
+ return state_dict
511
+
512
+
513
+ def to_torch_tensor(state_dict, return_empty_tensor=False):
514
+ """
515
+ Convert state_dict of GatheredTensor to torch tensor
516
+ """
517
+ torch_state_dict = {}
518
+ converted_tensors = {}
519
+ for name, tensor in state_dict.items():
520
+ tensor_id = id(tensor)
521
+ if tensor_id in converted_tensors: # shared tensors
522
+ shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
523
+ torch_state_dict[name] = shared_tensor
524
+ else:
525
+ converted_tensors[tensor_id] = name
526
+ if return_empty_tensor:
527
+ torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
528
+ else:
529
+ torch_state_dict[name] = tensor.contiguous()
530
+ return torch_state_dict
531
+
532
+
533
+ def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
534
+ tag=None,
535
+ exclude_frozen_parameters=False,
536
+ lazy_mode=False):
537
+ """
538
+ Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
539
+ ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
540
+ via a model hub.
541
+
542
+ Args:
543
+ - ``checkpoint_dir``: path to the desired checkpoint folder
544
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
545
+ - ``exclude_frozen_parameters``: exclude frozen parameters
546
+ - ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
547
+ Convert the pesduo tensor to torch tensor by ``.contiguous()``
548
+
549
+ Returns:
550
+ - pytorch ``state_dict``
551
+
552
+ A typical usage might be ::
553
+
554
+ from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
555
+ # do the training and checkpoint saving
556
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
557
+ model = model.cpu() # move to cpu
558
+ model.load_state_dict(state_dict)
559
+ # submit to model hub or save the model to share with others
560
+
561
+ In this example the ``model`` will no longer be usable in the deepspeed context of the same
562
+ application. i.e. you will need to re-initialize the deepspeed engine, since
563
+ ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
564
+
565
+ If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
566
+
567
+ Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
568
+ You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
569
+ the checkpoint. Or you can load state_dict in lazy mode ::
570
+
571
+ from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
572
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
573
+ for name, lazy_tensor in state_dict.item():
574
+ tensor = lazy_tensor.contiguous() # to cpu
575
+ print(name, tensor)
576
+ # del tensor to release memory if it no longer in use
577
+ """
578
+ if tag is None:
579
+ latest_path = os.path.join(checkpoint_dir, 'latest')
580
+ if os.path.isfile(latest_path):
581
+ with open(latest_path, 'r') as fd:
582
+ tag = fd.read().strip()
583
+ else:
584
+ raise ValueError(f"Unable to find 'latest' file at {latest_path}")
585
+
586
+ ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
587
+
588
+ if not os.path.isdir(ds_checkpoint_dir):
589
+ raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
590
+
591
+ state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
592
+ if lazy_mode:
593
+ return state_dict
594
+ else:
595
+ return to_torch_tensor(state_dict)
596
+
597
+
598
+ def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
599
+ output_dir,
600
+ max_shard_size="5GB",
601
+ safe_serialization=False,
602
+ tag=None,
603
+ exclude_frozen_parameters=False):
604
+ """
605
+ Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
606
+ loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
607
+
608
+ Args:
609
+ - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
610
+ - ``output_dir``: directory to the pytorch fp32 state_dict output files
611
+ - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
612
+ - ``safe_serialization``: whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
613
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
614
+ - ``exclude_frozen_parameters``: exclude frozen parameters
615
+ """
616
+
617
+ # Dependency pre-check
618
+ if safe_serialization:
619
+ try:
620
+ from safetensors.torch import save_file
621
+ except ImportError:
622
+ print('If you want to use `safe_serialization`, please `pip install safetensors`')
623
+ raise
624
+ if max_shard_size is not None:
625
+ try:
626
+ from huggingface_hub import split_torch_state_dict_into_shards
627
+ except ImportError:
628
+ print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
629
+ raise
630
+
631
+ # Convert zero checkpoint to state_dict
632
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
633
+ tag,
634
+ exclude_frozen_parameters,
635
+ lazy_mode=True)
636
+
637
+ # Shard the model if it is too big.
638
+ weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
639
+ if max_shard_size is not None:
640
+ filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
641
+ # an memory-efficient approach for sharding
642
+ empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
643
+ state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
644
+ filename_pattern=filename_pattern,
645
+ max_shard_size=max_shard_size)
646
+ else:
647
+ from collections import namedtuple
648
+ StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
649
+ state_dict_split = StateDictSplit(is_sharded=False,
650
+ filename_to_tensors={weights_name: list(state_dict.keys())})
651
+
652
+ # Save the model by shard
653
+ os.makedirs(output_dir, exist_ok=True)
654
+ filename_to_tensors = state_dict_split.filename_to_tensors.items()
655
+ for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
656
+ shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
657
+ shard_state_dict = to_torch_tensor(shard_state_dict)
658
+ output_path = os.path.join(output_dir, shard_file)
659
+ if safe_serialization:
660
+ save_file(shard_state_dict, output_path, metadata={"format": "pt"})
661
+ else:
662
+ torch.save(shard_state_dict, output_path)
663
+ # release the memory of current shard
664
+ for tensor_name in list(shard_state_dict.keys()):
665
+ del state_dict[tensor_name]
666
+ del shard_state_dict[tensor_name]
667
+ del shard_state_dict
668
+ gc.collect()
669
+
670
+ # Save index if sharded
671
+ if state_dict_split.is_sharded:
672
+ index = {
673
+ "metadata": state_dict_split.metadata,
674
+ "weight_map": state_dict_split.tensor_to_filename,
675
+ }
676
+ save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
677
+ save_index_file = os.path.join(output_dir, save_index_file)
678
+ with open(save_index_file, "w", encoding="utf-8") as f:
679
+ content = json.dumps(index, indent=2, sort_keys=True) + "\n"
680
+ f.write(content)
681
+
682
+
683
+ def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
684
+ """
685
+ 1. Put the provided model to cpu
686
+ 2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
687
+ 3. Load it into the provided model
688
+
689
+ Args:
690
+ - ``model``: the model object to update
691
+ - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
692
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
693
+
694
+ Returns:
695
+ - ``model`: modified model
696
+
697
+ Make sure you have plenty of CPU memory available before you call this function. If you don't
698
+ have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
699
+ conveniently placed for you in the checkpoint folder.
700
+
701
+ A typical usage might be ::
702
+
703
+ from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
704
+ model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
705
+ # submit to model hub or save the model to share with others
706
+
707
+ Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
708
+ of the same application. i.e. you will need to re-initialize the deepspeed engine, since
709
+ ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
710
+
711
+ """
712
+ logger.info(f"Extracting fp32 weights")
713
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
714
+
715
+ logger.info(f"Overwriting model with fp32 weights")
716
+ model = model.cpu()
717
+ model.load_state_dict(state_dict, strict=False)
718
+
719
+ return model
720
+
721
+
722
+ if __name__ == "__main__":
723
+ parser = argparse.ArgumentParser()
724
+ parser.add_argument("checkpoint_dir",
725
+ type=str,
726
+ help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
727
+ parser.add_argument("output_dir",
728
+ type=str,
729
+ help="directory to the pytorch fp32 state_dict output files"
730
+ "(e.g. path/checkpoint-12-output/)")
731
+ parser.add_argument(
732
+ "--max_shard_size",
733
+ type=str,
734
+ default="5GB",
735
+ help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
736
+ "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
737
+ "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
738
+ "without CPU OOM issues.")
739
+ parser.add_argument(
740
+ "--safe_serialization",
741
+ default=False,
742
+ action='store_true',
743
+ help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
744
+ parser.add_argument("-t",
745
+ "--tag",
746
+ type=str,
747
+ default=None,
748
+ help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
749
+ parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
750
+ parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
751
+ args = parser.parse_args()
752
+
753
+ debug = args.debug
754
+
755
+ convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
756
+ args.output_dir,
757
+ max_shard_size=args.max_shard_size,
758
+ safe_serialization=args.safe_serialization,
759
+ tag=args.tag,
760
+ exclude_frozen_parameters=args.exclude_frozen_parameters)