Hugging Face's logo

Heisen0928
/
value_function

TensorBoard
Safetensors
Model card Files
xet
 Metrics Community
Heisen0928 commited on
Commit
184f0af
·
verified ·
1 Parent(s): 0cc7bea

Upload folder using huggingface_hub

Browse files
Files changed (46) hide show
  1. .gitattributes +1 -0
  2. robotwin50_pi06_expert_train/checkpoint-2500/added_tokens.json +225 -0
  3. robotwin50_pi06_expert_train/checkpoint-2500/chat_template.jinja +7 -0
  4. robotwin50_pi06_expert_train/checkpoint-2500/config.json +143 -0
  5. robotwin50_pi06_expert_train/checkpoint-2500/generation_config.json +14 -0
  6. robotwin50_pi06_expert_train/checkpoint-2500/global_step2499/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
  7. robotwin50_pi06_expert_train/checkpoint-2500/global_step2499/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
  8. robotwin50_pi06_expert_train/checkpoint-2500/global_step2499/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +3 -0
  9. robotwin50_pi06_expert_train/checkpoint-2500/global_step2499/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +3 -0
  10. robotwin50_pi06_expert_train/checkpoint-2500/global_step2499/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +3 -0
  11. robotwin50_pi06_expert_train/checkpoint-2500/global_step2499/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +3 -0
  12. robotwin50_pi06_expert_train/checkpoint-2500/global_step2499/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +3 -0
  13. robotwin50_pi06_expert_train/checkpoint-2500/global_step2499/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +3 -0
  14. robotwin50_pi06_expert_train/checkpoint-2500/global_step2499/zero_pp_rank_0_mp_rank_00_model_states.pt +3 -0
  15. robotwin50_pi06_expert_train/checkpoint-2500/global_step2499/zero_pp_rank_1_mp_rank_00_model_states.pt +3 -0
  16. robotwin50_pi06_expert_train/checkpoint-2500/global_step2499/zero_pp_rank_2_mp_rank_00_model_states.pt +3 -0
  17. robotwin50_pi06_expert_train/checkpoint-2500/global_step2499/zero_pp_rank_3_mp_rank_00_model_states.pt +3 -0
  18. robotwin50_pi06_expert_train/checkpoint-2500/global_step2499/zero_pp_rank_4_mp_rank_00_model_states.pt +3 -0
  19. robotwin50_pi06_expert_train/checkpoint-2500/global_step2499/zero_pp_rank_5_mp_rank_00_model_states.pt +3 -0
  20. robotwin50_pi06_expert_train/checkpoint-2500/global_step2499/zero_pp_rank_6_mp_rank_00_model_states.pt +3 -0
  21. robotwin50_pi06_expert_train/checkpoint-2500/global_step2499/zero_pp_rank_7_mp_rank_00_model_states.pt +3 -0
  22. robotwin50_pi06_expert_train/checkpoint-2500/latest +1 -0
  23. robotwin50_pi06_expert_train/checkpoint-2500/merges.txt +0 -0
  24. robotwin50_pi06_expert_train/checkpoint-2500/model-00001-of-00002.safetensors +3 -0
  25. robotwin50_pi06_expert_train/checkpoint-2500/model-00002-of-00002.safetensors +3 -0
  26. robotwin50_pi06_expert_train/checkpoint-2500/model.safetensors.index.json +832 -0
  27. robotwin50_pi06_expert_train/checkpoint-2500/rng_state_0.pth +3 -0
  28. robotwin50_pi06_expert_train/checkpoint-2500/rng_state_1.pth +3 -0
  29. robotwin50_pi06_expert_train/checkpoint-2500/rng_state_2.pth +3 -0
  30. robotwin50_pi06_expert_train/checkpoint-2500/rng_state_3.pth +3 -0
  31. robotwin50_pi06_expert_train/checkpoint-2500/rng_state_4.pth +3 -0
  32. robotwin50_pi06_expert_train/checkpoint-2500/rng_state_5.pth +3 -0
  33. robotwin50_pi06_expert_train/checkpoint-2500/rng_state_6.pth +3 -0
  34. robotwin50_pi06_expert_train/checkpoint-2500/rng_state_7.pth +3 -0
  35. robotwin50_pi06_expert_train/checkpoint-2500/scheduler.pt +3 -0
  36. robotwin50_pi06_expert_train/checkpoint-2500/special_tokens_map.json +31 -0
  37. robotwin50_pi06_expert_train/checkpoint-2500/tokenizer.json +3 -0
  38. robotwin50_pi06_expert_train/checkpoint-2500/tokenizer_config.json +1816 -0
  39. robotwin50_pi06_expert_train/checkpoint-2500/trainer_state.json +1792 -0
  40. robotwin50_pi06_expert_train/checkpoint-2500/training_args.bin +3 -0
  41. robotwin50_pi06_expert_train/checkpoint-2500/vocab.json +0 -0
  42. robotwin50_pi06_expert_train/checkpoint-2500/zero_to_fp32.py +760 -0
  43. robotwin50_pi06_expert_train/run_config.json +197 -0
  44. robotwin50_pi06_expert_train/runs/Mar18_15-27-36_g340-cd51-7700-bb90-916f-fa2-f254/events.out.tfevents.1773818927.g340-cd51-7700-bb90-916f-fa2-f254.140016.0 +3 -0
  45. robotwin50_pi06_expert_train/runs/Mar18_15-38-36_g340-cd51-7700-bb90-916f-fa2-f254/events.out.tfevents.1773819616.g340-cd51-7700-bb90-916f-fa2-f254.2920613.0 +3 -0
  46. robotwin50_pi06_expert_train/train_metrics.jsonl +294 -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
+ robotwin50_pi06_expert_train/checkpoint-2500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
robotwin50_pi06_expert_train/checkpoint-2500/added_tokens.json ADDED
@@ -0,0 +1,225 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<extra_id_0>": 151665,
4
+ "<extra_id_100>": 151765,
5
+ "<extra_id_101>": 151766,
6
+ "<extra_id_102>": 151767,
7
+ "<extra_id_103>": 151768,
8
+ "<extra_id_104>": 151769,
9
+ "<extra_id_105>": 151770,
10
+ "<extra_id_106>": 151771,
11
+ "<extra_id_107>": 151772,
12
+ "<extra_id_108>": 151773,
13
+ "<extra_id_109>": 151774,
14
+ "<extra_id_10>": 151675,
15
+ "<extra_id_110>": 151775,
16
+ "<extra_id_111>": 151776,
17
+ "<extra_id_112>": 151777,
18
+ "<extra_id_113>": 151778,
19
+ "<extra_id_114>": 151779,
20
+ "<extra_id_115>": 151780,
21
+ "<extra_id_116>": 151781,
22
+ "<extra_id_117>": 151782,
23
+ "<extra_id_118>": 151783,
24
+ "<extra_id_119>": 151784,
25
+ "<extra_id_11>": 151676,
26
+ "<extra_id_120>": 151785,
27
+ "<extra_id_121>": 151786,
28
+ "<extra_id_122>": 151787,
29
+ "<extra_id_123>": 151788,
30
+ "<extra_id_124>": 151789,
31
+ "<extra_id_125>": 151790,
32
+ "<extra_id_126>": 151791,
33
+ "<extra_id_127>": 151792,
34
+ "<extra_id_128>": 151793,
35
+ "<extra_id_129>": 151794,
36
+ "<extra_id_12>": 151677,
37
+ "<extra_id_130>": 151795,
38
+ "<extra_id_131>": 151796,
39
+ "<extra_id_132>": 151797,
40
+ "<extra_id_133>": 151798,
41
+ "<extra_id_134>": 151799,
42
+ "<extra_id_135>": 151800,
43
+ "<extra_id_136>": 151801,
44
+ "<extra_id_137>": 151802,
45
+ "<extra_id_138>": 151803,
46
+ "<extra_id_139>": 151804,
47
+ "<extra_id_13>": 151678,
48
+ "<extra_id_140>": 151805,
49
+ "<extra_id_141>": 151806,
50
+ "<extra_id_142>": 151807,
51
+ "<extra_id_143>": 151808,
52
+ "<extra_id_144>": 151809,
53
+ "<extra_id_145>": 151810,
54
+ "<extra_id_146>": 151811,
55
+ "<extra_id_147>": 151812,
56
+ "<extra_id_148>": 151813,
57
+ "<extra_id_149>": 151814,
58
+ "<extra_id_14>": 151679,
59
+ "<extra_id_150>": 151815,
60
+ "<extra_id_151>": 151816,
61
+ "<extra_id_152>": 151817,
62
+ "<extra_id_153>": 151818,
63
+ "<extra_id_154>": 151819,
64
+ "<extra_id_155>": 151820,
65
+ "<extra_id_156>": 151821,
66
+ "<extra_id_157>": 151822,
67
+ "<extra_id_158>": 151823,
68
+ "<extra_id_159>": 151824,
69
+ "<extra_id_15>": 151680,
70
+ "<extra_id_160>": 151825,
71
+ "<extra_id_161>": 151826,
72
+ "<extra_id_162>": 151827,
73
+ "<extra_id_163>": 151828,
74
+ "<extra_id_164>": 151829,
75
+ "<extra_id_165>": 151830,
76
+ "<extra_id_166>": 151831,
77
+ "<extra_id_167>": 151832,
78
+ "<extra_id_168>": 151833,
79
+ "<extra_id_169>": 151834,
80
+ "<extra_id_16>": 151681,
81
+ "<extra_id_170>": 151835,
82
+ "<extra_id_171>": 151836,
83
+ "<extra_id_172>": 151837,
84
+ "<extra_id_173>": 151838,
85
+ "<extra_id_174>": 151839,
86
+ "<extra_id_175>": 151840,
87
+ "<extra_id_176>": 151841,
88
+ "<extra_id_177>": 151842,
89
+ "<extra_id_178>": 151843,
90
+ "<extra_id_179>": 151844,
91
+ "<extra_id_17>": 151682,
92
+ "<extra_id_180>": 151845,
93
+ "<extra_id_181>": 151846,
94
+ "<extra_id_182>": 151847,
95
+ "<extra_id_183>": 151848,
96
+ "<extra_id_184>": 151849,
97
+ "<extra_id_185>": 151850,
98
+ "<extra_id_186>": 151851,
99
+ "<extra_id_187>": 151852,
100
+ "<extra_id_188>": 151853,
101
+ "<extra_id_189>": 151854,
102
+ "<extra_id_18>": 151683,
103
+ "<extra_id_190>": 151855,
104
+ "<extra_id_191>": 151856,
105
+ "<extra_id_192>": 151857,
106
+ "<extra_id_193>": 151858,
107
+ "<extra_id_194>": 151859,
108
+ "<extra_id_195>": 151860,
109
+ "<extra_id_196>": 151861,
110
+ "<extra_id_197>": 151862,
111
+ "<extra_id_198>": 151863,
112
+ "<extra_id_199>": 151864,
113
+ "<extra_id_19>": 151684,
114
+ "<extra_id_1>": 151666,
115
+ "<extra_id_200>": 151865,
116
+ "<extra_id_20>": 151685,
117
+ "<extra_id_21>": 151686,
118
+ "<extra_id_22>": 151687,
119
+ "<extra_id_23>": 151688,
120
+ "<extra_id_24>": 151689,
121
+ "<extra_id_25>": 151690,
122
+ "<extra_id_26>": 151691,
123
+ "<extra_id_27>": 151692,
124
+ "<extra_id_28>": 151693,
125
+ "<extra_id_29>": 151694,
126
+ "<extra_id_2>": 151667,
127
+ "<extra_id_30>": 151695,
128
+ "<extra_id_31>": 151696,
129
+ "<extra_id_32>": 151697,
130
+ "<extra_id_33>": 151698,
131
+ "<extra_id_34>": 151699,
132
+ "<extra_id_35>": 151700,
133
+ "<extra_id_36>": 151701,
134
+ "<extra_id_37>": 151702,
135
+ "<extra_id_38>": 151703,
136
+ "<extra_id_39>": 151704,
137
+ "<extra_id_3>": 151668,
138
+ "<extra_id_40>": 151705,
139
+ "<extra_id_41>": 151706,
140
+ "<extra_id_42>": 151707,
141
+ "<extra_id_43>": 151708,
142
+ "<extra_id_44>": 151709,
143
+ "<extra_id_45>": 151710,
144
+ "<extra_id_46>": 151711,
145
+ "<extra_id_47>": 151712,
146
+ "<extra_id_48>": 151713,
147
+ "<extra_id_49>": 151714,
148
+ "<extra_id_4>": 151669,
149
+ "<extra_id_50>": 151715,
150
+ "<extra_id_51>": 151716,
151
+ "<extra_id_52>": 151717,
152
+ "<extra_id_53>": 151718,
153
+ "<extra_id_54>": 151719,
154
+ "<extra_id_55>": 151720,
155
+ "<extra_id_56>": 151721,
156
+ "<extra_id_57>": 151722,
157
+ "<extra_id_58>": 151723,
158
+ "<extra_id_59>": 151724,
159
+ "<extra_id_5>": 151670,
160
+ "<extra_id_60>": 151725,
161
+ "<extra_id_61>": 151726,
162
+ "<extra_id_62>": 151727,
163
+ "<extra_id_63>": 151728,
164
+ "<extra_id_64>": 151729,
165
+ "<extra_id_65>": 151730,
166
+ "<extra_id_66>": 151731,
167
+ "<extra_id_67>": 151732,
168
+ "<extra_id_68>": 151733,
169
+ "<extra_id_69>": 151734,
170
+ "<extra_id_6>": 151671,
171
+ "<extra_id_70>": 151735,
172
+ "<extra_id_71>": 151736,
173
+ "<extra_id_72>": 151737,
174
+ "<extra_id_73>": 151738,
175
+ "<extra_id_74>": 151739,
176
+ "<extra_id_75>": 151740,
177
+ "<extra_id_76>": 151741,
178
+ "<extra_id_77>": 151742,
179
+ "<extra_id_78>": 151743,
180
+ "<extra_id_79>": 151744,
181
+ "<extra_id_7>": 151672,
182
+ "<extra_id_80>": 151745,
183
+ "<extra_id_81>": 151746,
184
+ "<extra_id_82>": 151747,
185
+ "<extra_id_83>": 151748,
186
+ "<extra_id_84>": 151749,
187
+ "<extra_id_85>": 151750,
188
+ "<extra_id_86>": 151751,
189
+ "<extra_id_87>": 151752,
190
+ "<extra_id_88>": 151753,
191
+ "<extra_id_89>": 151754,
192
+ "<extra_id_8>": 151673,
193
+ "<extra_id_90>": 151755,
194
+ "<extra_id_91>": 151756,
195
+ "<extra_id_92>": 151757,
196
+ "<extra_id_93>": 151758,
197
+ "<extra_id_94>": 151759,
198
+ "<extra_id_95>": 151760,
199
+ "<extra_id_96>": 151761,
200
+ "<extra_id_97>": 151762,
201
+ "<extra_id_98>": 151763,
202
+ "<extra_id_99>": 151764,
203
+ "<extra_id_9>": 151674,
204
+ "<tool_call>": 151657,
205
+ "<|box_end|>": 151649,
206
+ "<|box_start|>": 151648,
207
+ "<|endoftext|>": 151643,
208
+ "<|file_sep|>": 151664,
209
+ "<|fim_middle|>": 151660,
210
+ "<|fim_pad|>": 151662,
211
+ "<|fim_prefix|>": 151659,
212
+ "<|fim_suffix|>": 151661,
213
+ "<|im_end|>": 151645,
214
+ "<|im_start|>": 151644,
215
+ "<|image_pad|>": 151655,
216
+ "<|object_ref_end|>": 151647,
217
+ "<|object_ref_start|>": 151646,
218
+ "<|quad_end|>": 151651,
219
+ "<|quad_start|>": 151650,
220
+ "<|repo_name|>": 151663,
221
+ "<|video_pad|>": 151656,
222
+ "<|vision_end|>": 151653,
223
+ "<|vision_pad|>": 151654,
224
+ "<|vision_start|>": 151652
225
+ }
robotwin50_pi06_expert_train/checkpoint-2500/chat_template.jinja ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
2
+ You are a helpful assistant.<|im_end|>
3
+ {% endif %}<|im_start|>{{ message['role'] }}
4
+ {% if message['content'] is string %}{{ message['content'] }}<|im_end|>
5
+ {% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
6
+ {% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
7
+ {% endif %}
robotwin50_pi06_expert_train/checkpoint-2500/config.json ADDED
@@ -0,0 +1,143 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2_5_VLForConditionalGeneration"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "eos_token_id": 151645,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 2048,
10
+ "image_token_id": 151655,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 11008,
13
+ "max_position_embeddings": 128000,
14
+ "max_window_layers": 70,
15
+ "model_type": "qwen2_5_vl",
16
+ "num_attention_heads": 16,
17
+ "num_hidden_layers": 36,
18
+ "num_key_value_heads": 2,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_scaling": {
21
+ "mrope_section": [
22
+ 16,
23
+ 24,
24
+ 24
25
+ ],
26
+ "rope_type": "default",
27
+ "type": "default"
28
+ },
29
+ "rope_theta": 1000000.0,
30
+ "sliding_window": 32768,
31
+ "text_config": {
32
+ "architectures": [
33
+ "Qwen2_5_VLForConditionalGeneration"
34
+ ],
35
+ "attention_dropout": 0.0,
36
+ "bos_token_id": 151643,
37
+ "eos_token_id": 151645,
38
+ "hidden_act": "silu",
39
+ "hidden_size": 2048,
40
+ "image_token_id": null,
41
+ "initializer_range": 0.02,
42
+ "intermediate_size": 11008,
43
+ "layer_types": [
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention",
51
+ "full_attention",
52
+ "full_attention",
53
+ "full_attention",
54
+ "full_attention",
55
+ "full_attention",
56
+ "full_attention",
57
+ "full_attention",
58
+ "full_attention",
59
+ "full_attention",
60
+ "full_attention",
61
+ "full_attention",
62
+ "full_attention",
63
+ "full_attention",
64
+ "full_attention",
65
+ "full_attention",
66
+ "full_attention",
67
+ "full_attention",
68
+ "full_attention",
69
+ "full_attention",
70
+ "full_attention",
71
+ "full_attention",
72
+ "full_attention",
73
+ "full_attention",
74
+ "full_attention",
75
+ "full_attention",
76
+ "full_attention",
77
+ "full_attention",
78
+ "full_attention",
79
+ "full_attention"
80
+ ],
81
+ "max_position_embeddings": 128000,
82
+ "max_window_layers": 70,
83
+ "model_type": "qwen2_5_vl_text",
84
+ "num_attention_heads": 16,
85
+ "num_hidden_layers": 36,
86
+ "num_key_value_heads": 2,
87
+ "rms_norm_eps": 1e-06,
88
+ "rope_scaling": {
89
+ "mrope_section": [
90
+ 16,
91
+ 24,
92
+ 24
93
+ ],
94
+ "rope_type": "default",
95
+ "type": "default"
96
+ },
97
+ "rope_theta": 1000000.0,
98
+ "sliding_window": null,
99
+ "tie_word_embeddings": true,
100
+ "torch_dtype": "bfloat16",
101
+ "use_cache": true,
102
+ "use_sliding_window": false,
103
+ "video_token_id": null,
104
+ "vision_end_token_id": 151653,
105
+ "vision_start_token_id": 151652,
106
+ "vision_token_id": 151654,
107
+ "vocab_size": 151866
108
+ },
109
+ "torch_dtype": "bfloat16",
110
+ "transformers_version": "4.53.2",
111
+ "use_cache": false,
112
+ "use_sliding_window": false,
113
+ "video_token_id": 151656,
114
+ "vision_config": {
115
+ "depth": 32,
116
+ "fullatt_block_indexes": [
117
+ 7,
118
+ 15,
119
+ 23,
120
+ 31
121
+ ],
122
+ "hidden_act": "silu",
123
+ "hidden_size": 1280,
124
+ "in_channels": 3,
125
+ "in_chans": 3,
126
+ "initializer_range": 0.02,
127
+ "intermediate_size": 3420,
128
+ "model_type": "qwen2_5_vl",
129
+ "num_heads": 16,
130
+ "out_hidden_size": 2048,
131
+ "patch_size": 14,
132
+ "spatial_merge_size": 2,
133
+ "spatial_patch_size": 14,
134
+ "temporal_patch_size": 2,
135
+ "tokens_per_second": 2,
136
+ "torch_dtype": "bfloat16",
137
+ "window_size": 112
138
+ },
139
+ "vision_end_token_id": 151653,
140
+ "vision_start_token_id": 151652,
141
+ "vision_token_id": 151654,
142
+ "vocab_size": 151866
143
+ }
robotwin50_pi06_expert_train/checkpoint-2500/generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "attn_implementation": "flash_attention_2",
3
+ "bos_token_id": 151643,
4
+ "do_sample": true,
5
+ "eos_token_id": [
6
+ 151645,
7
+ 151643
8
+ ],
9
+ "pad_token_id": 151643,
10
+ "repetition_penalty": 1.05,
11
+ "temperature": 1e-06,
12
+ "transformers_version": "4.53.2",
13
+ "vocab_size": 151866
14
+ }
robotwin50_pi06_expert_train/checkpoint-2500/global_step2499/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfbe640492901d5aeade360de622bca2fd49e2740d758c864f9a5b4bd0ef1aa7
3
+ size 2341883525
robotwin50_pi06_expert_train/checkpoint-2500/global_step2499/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3929b55abd81564651b28099384dc13274b1c5ef0a472bc61815b2536685e2c4
3
+ size 2341883525
robotwin50_pi06_expert_train/checkpoint-2500/global_step2499/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58610472af078ea9a3ee3ede1121864e292ffebbcd128ef98f4b3d4e652752c5
3
+ size 2341883525
robotwin50_pi06_expert_train/checkpoint-2500/global_step2499/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c059bc90ea6f8e793244bb9a403bc2e605c898bac03f6320a65e8484cbf57748
3
+ size 2341883525
robotwin50_pi06_expert_train/checkpoint-2500/global_step2499/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cdd067abd9ed40785e243bb2715e5a0f4d62354742736214959acae35b1a017
3
+ size 2341883525
robotwin50_pi06_expert_train/checkpoint-2500/global_step2499/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f51ae24462e0fa4b7e656a17b0f100f6eeacb053941aa994288a53cb59a1d4f1
3
+ size 2341883525
robotwin50_pi06_expert_train/checkpoint-2500/global_step2499/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fde02e6836c10ca3fb9318fc96b4fb5780b74bc755dd13e71f0995f460ee630
3
+ size 2341883525
robotwin50_pi06_expert_train/checkpoint-2500/global_step2499/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeba4d8fd853ea59cbb9af2973c2b40c1a369f3ceeea093f6a6959861de630af
3
+ size 2341883525
robotwin50_pi06_expert_train/checkpoint-2500/global_step2499/zero_pp_rank_0_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c855989bc59d42e6c597a8645d09b19d5457098bddd12ac9260f67c5a80a8925
3
+ size 79544831
robotwin50_pi06_expert_train/checkpoint-2500/global_step2499/zero_pp_rank_1_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40728d1cc28df13df0a1637de1942536573eec552ae2fadcf9474c8b38745dbb
3
+ size 79544767
robotwin50_pi06_expert_train/checkpoint-2500/global_step2499/zero_pp_rank_2_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4eb1da81a728a95616a90d76aa153792b524b0bcfbb1810104aaadc891c4668d
3
+ size 79544767
robotwin50_pi06_expert_train/checkpoint-2500/global_step2499/zero_pp_rank_3_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae25e38f726ac96cc541183c4dc2e2e3c2adc2ff488b5ca65fae613852608909
3
+ size 79544767
robotwin50_pi06_expert_train/checkpoint-2500/global_step2499/zero_pp_rank_4_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce6b34901f68fc1695d87a1aeb738dc1815c3179519319c2bc5ce7fd6dc840b9
3
+ size 79544767
robotwin50_pi06_expert_train/checkpoint-2500/global_step2499/zero_pp_rank_5_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc693157bf2ebd5e150e50cf53eb6ec90cef00c7974afd0259acd6c2cf45ac0c
3
+ size 79544767
robotwin50_pi06_expert_train/checkpoint-2500/global_step2499/zero_pp_rank_6_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0f7782e0b2b36ef87399e6946c02bce4b9537dc18ea2c50a26dea010f692a8e
3
+ size 79544767
robotwin50_pi06_expert_train/checkpoint-2500/global_step2499/zero_pp_rank_7_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a2905082e4d0cbdc1ccff9597939cc94d2ec0a18b5819d80fd30eda0513d22a
3
+ size 79544767
robotwin50_pi06_expert_train/checkpoint-2500/latest ADDED
@@ -0,0 +1 @@
 
 
1
+ global_step2499
robotwin50_pi06_expert_train/checkpoint-2500/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
robotwin50_pi06_expert_train/checkpoint-2500/model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2aaaeaed33a11beb2489256c7fd1d51d540b3823d4a783cc874861bc7ab63bfc
3
+ size 4997464040
robotwin50_pi06_expert_train/checkpoint-2500/model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b76b206818f64ef1b749527b05c70b0a33268c993e49364b3809c266c1d0fa6
3
+ size 2511587184
robotwin50_pi06_expert_train/checkpoint-2500/model.safetensors.index.json ADDED
@@ -0,0 +1,832 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 755712,
4
+ "total_size": 7508959232
5
+ },
6
+ "weight_map": {
7
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
17
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
19
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
26
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
29
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
31
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
38
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
41
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
42
+ "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
43
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
50
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
53
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
55
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
62
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
65
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
67
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
74
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
77
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
78
+ "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
79
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
86
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
89
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
90
+ "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
91
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
94
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
98
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
100
+ "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
101
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
102
+ "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
103
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
104
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
108
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
110
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
112
+ "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
113
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
114
+ "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
115
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
116
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
122
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
124
+ "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
125
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
126
+ "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
127
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
128
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
129
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
130
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
133
+ "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
134
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
135
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
136
+ "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
137
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
138
+ "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
139
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
140
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
141
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
142
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
143
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
144
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
145
+ "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
146
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
147
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
148
+ "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
149
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
150
+ "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
151
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
152
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
153
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
154
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
155
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
156
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
157
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
158
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
159
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
160
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
161
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
162
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
163
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
164
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
165
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
166
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
167
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
168
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
169
+ "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
170
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
171
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
172
+ "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
173
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
174
+ "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
175
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
176
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
177
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
178
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
179
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
180
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
181
+ "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
182
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
183
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
184
+ "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
185
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
186
+ "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
187
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
188
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
189
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
190
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
191
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
192
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
193
+ "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
194
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
195
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
196
+ "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
197
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
198
+ "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
199
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
200
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
201
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
202
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
203
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
204
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
205
+ "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
206
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
207
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
208
+ "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
209
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
210
+ "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
211
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
212
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
213
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
214
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
215
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
216
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
217
+ "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
218
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
219
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
220
+ "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
221
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
222
+ "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
223
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
224
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
225
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
226
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
227
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
228
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
229
+ "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
230
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
231
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
232
+ "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
233
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
234
+ "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
235
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
236
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
237
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
238
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
239
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
240
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
241
+ "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
242
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
243
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
244
+ "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
245
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
246
+ "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
247
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
248
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
249
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
250
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
251
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
252
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
253
+ "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
254
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
255
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
256
+ "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
257
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
258
+ "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
259
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
260
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
261
+ "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
262
+ "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
263
+ "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
264
+ "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
265
+ "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
266
+ "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
267
+ "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
268
+ "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
269
+ "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
270
+ "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
271
+ "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
272
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
273
+ "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
274
+ "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
275
+ "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
276
+ "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
277
+ "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
278
+ "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
279
+ "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
280
+ "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
281
+ "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
282
+ "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
283
+ "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
284
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
285
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
286
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
287
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
288
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
289
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
290
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
291
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
292
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
293
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
294
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
295
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
296
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
297
+ "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
298
+ "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
299
+ "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
300
+ "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
301
+ "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
302
+ "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
303
+ "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
304
+ "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
305
+ "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
306
+ "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
307
+ "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
308
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
309
+ "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
310
+ "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
311
+ "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
312
+ "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
313
+ "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
314
+ "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
315
+ "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
316
+ "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
317
+ "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
318
+ "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
319
+ "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
320
+ "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
321
+ "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
322
+ "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
323
+ "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
324
+ "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
325
+ "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
326
+ "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
327
+ "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
328
+ "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
329
+ "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
330
+ "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
331
+ "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
332
+ "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
333
+ "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
334
+ "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
335
+ "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
336
+ "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
337
+ "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
338
+ "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
339
+ "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
340
+ "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
341
+ "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
342
+ "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
343
+ "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
344
+ "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
345
+ "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
346
+ "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
347
+ "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
348
+ "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
349
+ "model.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
350
+ "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
351
+ "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
352
+ "model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
353
+ "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
354
+ "model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
355
+ "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
356
+ "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
357
+ "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
358
+ "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
359
+ "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
360
+ "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
361
+ "model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
362
+ "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
363
+ "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
364
+ "model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
365
+ "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
366
+ "model.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
367
+ "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
368
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
369
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
370
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
371
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
372
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
373
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
374
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
375
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
376
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
377
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
378
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
379
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
380
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
381
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
382
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
383
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
384
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
385
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
386
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
387
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
388
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
389
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
390
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
391
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
392
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
393
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
394
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
395
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
396
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
397
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
398
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
399
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
400
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
401
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
402
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
403
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
404
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
405
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
406
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
407
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
408
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
409
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
410
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
411
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
412
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
413
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
414
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
415
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
416
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
417
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
418
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
419
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
420
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
421
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
422
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
423
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
424
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
425
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
426
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
427
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
428
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
429
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
430
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
431
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
432
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
433
+ "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
434
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
435
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
436
+ "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
437
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
438
+ "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
439
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
440
+ "model.norm.weight": "model-00002-of-00002.safetensors",
441
+ "visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
442
+ "visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
443
+ "visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
444
+ "visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
445
+ "visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
446
+ "visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
447
+ "visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
448
+ "visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
449
+ "visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
450
+ "visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
451
+ "visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
452
+ "visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
453
+ "visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
454
+ "visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
455
+ "visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
456
+ "visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
457
+ "visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
458
+ "visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
459
+ "visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
460
+ "visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
461
+ "visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
462
+ "visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
463
+ "visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
464
+ "visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
465
+ "visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
466
+ "visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
467
+ "visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
468
+ "visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
469
+ "visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
470
+ "visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
471
+ "visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
472
+ "visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
473
+ "visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
474
+ "visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
475
+ "visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
476
+ "visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
477
+ "visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
478
+ "visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
479
+ "visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
480
+ "visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
481
+ "visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
482
+ "visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
483
+ "visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
484
+ "visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
485
+ "visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
486
+ "visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
487
+ "visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
488
+ "visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
489
+ "visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
490
+ "visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
491
+ "visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
492
+ "visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
493
+ "visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
494
+ "visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
495
+ "visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
496
+ "visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
497
+ "visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
498
+ "visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
499
+ "visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
500
+ "visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
501
+ "visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
502
+ "visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
503
+ "visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
504
+ "visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
505
+ "visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
506
+ "visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
507
+ "visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
508
+ "visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
509
+ "visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
510
+ "visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
511
+ "visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
512
+ "visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
513
+ "visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
514
+ "visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
515
+ "visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
516
+ "visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
517
+ "visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
518
+ "visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
519
+ "visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
520
+ "visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
521
+ "visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
522
+ "visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
523
+ "visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
524
+ "visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
525
+ "visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
526
+ "visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
527
+ "visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
528
+ "visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
529
+ "visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
530
+ "visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
531
+ "visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
532
+ "visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
533
+ "visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
534
+ "visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
535
+ "visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
536
+ "visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
537
+ "visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
538
+ "visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
539
+ "visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
540
+ "visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
541
+ "visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
542
+ "visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
543
+ "visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
544
+ "visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
545
+ "visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
546
+ "visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
547
+ "visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
548
+ "visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
549
+ "visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
550
+ "visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
551
+ "visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
552
+ "visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
553
+ "visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
554
+ "visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
555
+ "visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
556
+ "visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
557
+ "visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
558
+ "visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
559
+ "visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
560
+ "visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
561
+ "visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
562
+ "visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
563
+ "visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
564
+ "visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
565
+ "visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
566
+ "visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
567
+ "visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
568
+ "visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
569
+ "visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
570
+ "visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
571
+ "visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
572
+ "visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
573
+ "visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
574
+ "visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
575
+ "visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
576
+ "visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
577
+ "visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
578
+ "visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
579
+ "visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
580
+ "visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
581
+ "visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
582
+ "visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
583
+ "visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
584
+ "visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
585
+ "visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
586
+ "visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
587
+ "visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
588
+ "visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
589
+ "visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
590
+ "visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
591
+ "visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
592
+ "visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
593
+ "visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
594
+ "visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
595
+ "visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
596
+ "visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
597
+ "visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
598
+ "visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
599
+ "visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
600
+ "visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
601
+ "visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
602
+ "visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
603
+ "visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
604
+ "visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
605
+ "visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
606
+ "visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
607
+ "visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
608
+ "visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
609
+ "visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
610
+ "visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
611
+ "visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
612
+ "visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
613
+ "visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
614
+ "visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
615
+ "visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
616
+ "visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
617
+ "visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
618
+ "visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
619
+ "visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
620
+ "visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
621
+ "visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
622
+ "visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
623
+ "visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
624
+ "visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
625
+ "visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
626
+ "visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
627
+ "visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
628
+ "visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
629
+ "visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
630
+ "visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
631
+ "visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
632
+ "visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
633
+ "visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
634
+ "visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
635
+ "visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
636
+ "visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
637
+ "visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
638
+ "visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
639
+ "visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
640
+ "visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
641
+ "visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
642
+ "visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
643
+ "visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
644
+ "visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
645
+ "visual.blocks.24.attn.proj.bias": "model-00001-of-00002.safetensors",
646
+ "visual.blocks.24.attn.proj.weight": "model-00001-of-00002.safetensors",
647
+ "visual.blocks.24.attn.qkv.bias": "model-00001-of-00002.safetensors",
648
+ "visual.blocks.24.attn.qkv.weight": "model-00001-of-00002.safetensors",
649
+ "visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
650
+ "visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
651
+ "visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
652
+ "visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
653
+ "visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
654
+ "visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
655
+ "visual.blocks.24.norm1.weight": "model-00001-of-00002.safetensors",
656
+ "visual.blocks.24.norm2.weight": "model-00001-of-00002.safetensors",
657
+ "visual.blocks.25.attn.proj.bias": "model-00001-of-00002.safetensors",
658
+ "visual.blocks.25.attn.proj.weight": "model-00001-of-00002.safetensors",
659
+ "visual.blocks.25.attn.qkv.bias": "model-00001-of-00002.safetensors",
660
+ "visual.blocks.25.attn.qkv.weight": "model-00001-of-00002.safetensors",
661
+ "visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
662
+ "visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
663
+ "visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
664
+ "visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
665
+ "visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
666
+ "visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
667
+ "visual.blocks.25.norm1.weight": "model-00001-of-00002.safetensors",
668
+ "visual.blocks.25.norm2.weight": "model-00001-of-00002.safetensors",
669
+ "visual.blocks.26.attn.proj.bias": "model-00001-of-00002.safetensors",
670
+ "visual.blocks.26.attn.proj.weight": "model-00001-of-00002.safetensors",
671
+ "visual.blocks.26.attn.qkv.bias": "model-00001-of-00002.safetensors",
672
+ "visual.blocks.26.attn.qkv.weight": "model-00001-of-00002.safetensors",
673
+ "visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
674
+ "visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
675
+ "visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
676
+ "visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
677
+ "visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
678
+ "visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
679
+ "visual.blocks.26.norm1.weight": "model-00001-of-00002.safetensors",
680
+ "visual.blocks.26.norm2.weight": "model-00001-of-00002.safetensors",
681
+ "visual.blocks.27.attn.proj.bias": "model-00001-of-00002.safetensors",
682
+ "visual.blocks.27.attn.proj.weight": "model-00001-of-00002.safetensors",
683
+ "visual.blocks.27.attn.qkv.bias": "model-00001-of-00002.safetensors",
684
+ "visual.blocks.27.attn.qkv.weight": "model-00001-of-00002.safetensors",
685
+ "visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
686
+ "visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
687
+ "visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
688
+ "visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
689
+ "visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
690
+ "visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
691
+ "visual.blocks.27.norm1.weight": "model-00001-of-00002.safetensors",
692
+ "visual.blocks.27.norm2.weight": "model-00001-of-00002.safetensors",
693
+ "visual.blocks.28.attn.proj.bias": "model-00001-of-00002.safetensors",
694
+ "visual.blocks.28.attn.proj.weight": "model-00001-of-00002.safetensors",
695
+ "visual.blocks.28.attn.qkv.bias": "model-00001-of-00002.safetensors",
696
+ "visual.blocks.28.attn.qkv.weight": "model-00001-of-00002.safetensors",
697
+ "visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
698
+ "visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
699
+ "visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
700
+ "visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
701
+ "visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
702
+ "visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
703
+ "visual.blocks.28.norm1.weight": "model-00001-of-00002.safetensors",
704
+ "visual.blocks.28.norm2.weight": "model-00001-of-00002.safetensors",
705
+ "visual.blocks.29.attn.proj.bias": "model-00001-of-00002.safetensors",
706
+ "visual.blocks.29.attn.proj.weight": "model-00001-of-00002.safetensors",
707
+ "visual.blocks.29.attn.qkv.bias": "model-00001-of-00002.safetensors",
708
+ "visual.blocks.29.attn.qkv.weight": "model-00001-of-00002.safetensors",
709
+ "visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
710
+ "visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
711
+ "visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
712
+ "visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
713
+ "visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
714
+ "visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
715
+ "visual.blocks.29.norm1.weight": "model-00001-of-00002.safetensors",
716
+ "visual.blocks.29.norm2.weight": "model-00001-of-00002.safetensors",
717
+ "visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
718
+ "visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
719
+ "visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
720
+ "visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
721
+ "visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
722
+ "visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
723
+ "visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
724
+ "visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
725
+ "visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
726
+ "visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
727
+ "visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
728
+ "visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
729
+ "visual.blocks.30.attn.proj.bias": "model-00001-of-00002.safetensors",
730
+ "visual.blocks.30.attn.proj.weight": "model-00001-of-00002.safetensors",
731
+ "visual.blocks.30.attn.qkv.bias": "model-00001-of-00002.safetensors",
732
+ "visual.blocks.30.attn.qkv.weight": "model-00001-of-00002.safetensors",
733
+ "visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
734
+ "visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
735
+ "visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
736
+ "visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
737
+ "visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
738
+ "visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
739
+ "visual.blocks.30.norm1.weight": "model-00001-of-00002.safetensors",
740
+ "visual.blocks.30.norm2.weight": "model-00001-of-00002.safetensors",
741
+ "visual.blocks.31.attn.proj.bias": "model-00001-of-00002.safetensors",
742
+ "visual.blocks.31.attn.proj.weight": "model-00001-of-00002.safetensors",
743
+ "visual.blocks.31.attn.qkv.bias": "model-00001-of-00002.safetensors",
744
+ "visual.blocks.31.attn.qkv.weight": "model-00001-of-00002.safetensors",
745
+ "visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
746
+ "visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
747
+ "visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
748
+ "visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
749
+ "visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
750
+ "visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
751
+ "visual.blocks.31.norm1.weight": "model-00001-of-00002.safetensors",
752
+ "visual.blocks.31.norm2.weight": "model-00001-of-00002.safetensors",
753
+ "visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
754
+ "visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
755
+ "visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
756
+ "visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
757
+ "visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
758
+ "visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
759
+ "visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
760
+ "visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
761
+ "visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
762
+ "visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
763
+ "visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
764
+ "visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
765
+ "visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
766
+ "visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
767
+ "visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
768
+ "visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
769
+ "visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
770
+ "visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
771
+ "visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
772
+ "visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
773
+ "visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
774
+ "visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
775
+ "visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
776
+ "visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
777
+ "visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
778
+ "visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
779
+ "visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
780
+ "visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
781
+ "visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
782
+ "visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
783
+ "visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
784
+ "visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
785
+ "visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
786
+ "visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
787
+ "visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
788
+ "visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
789
+ "visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
790
+ "visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
791
+ "visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
792
+ "visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
793
+ "visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
794
+ "visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
795
+ "visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
796
+ "visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
797
+ "visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
798
+ "visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
799
+ "visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
800
+ "visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
801
+ "visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
802
+ "visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
803
+ "visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
804
+ "visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
805
+ "visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
806
+ "visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
807
+ "visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
808
+ "visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
809
+ "visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
810
+ "visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
811
+ "visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
812
+ "visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
813
+ "visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
814
+ "visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
815
+ "visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
816
+ "visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
817
+ "visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
818
+ "visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
819
+ "visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
820
+ "visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
821
+ "visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
822
+ "visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
823
+ "visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
824
+ "visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
825
+ "visual.merger.ln_q.weight": "model-00001-of-00002.safetensors",
826
+ "visual.merger.mlp.0.bias": "model-00001-of-00002.safetensors",
827
+ "visual.merger.mlp.0.weight": "model-00001-of-00002.safetensors",
828
+ "visual.merger.mlp.2.bias": "model-00001-of-00002.safetensors",
829
+ "visual.merger.mlp.2.weight": "model-00001-of-00002.safetensors",
830
+ "visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors"
831
+ }
832
+ }
robotwin50_pi06_expert_train/checkpoint-2500/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb608c894af42758f8f8f47f96a171b11d6164b464b56075993233760c918fef
3
+ size 16325
robotwin50_pi06_expert_train/checkpoint-2500/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35deaabe10396919e53b2274736981b26bc690165c8839845f178b355a6a7588
3
+ size 16389
robotwin50_pi06_expert_train/checkpoint-2500/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c5deee061a76a9e05b4634f5abad786b4042e744cc4c156a2ab76dc3c94fcac
3
+ size 16389
robotwin50_pi06_expert_train/checkpoint-2500/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13579f7ca365ea6f9cef83929c34833cd97f9b5764a434989b4e3e2db87dce56
3
+ size 16389
robotwin50_pi06_expert_train/checkpoint-2500/rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:073d0b1d7e2e3930e5c29fc418e6246462ab2a00396c3a86e1448d373503f1b2
3
+ size 16389
robotwin50_pi06_expert_train/checkpoint-2500/rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c60731015889939e665a308a0933ac6c327734a4699cf5615217db0cfaf03ca
3
+ size 16389
robotwin50_pi06_expert_train/checkpoint-2500/rng_state_6.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:416648e7a35618f28d73625751a8fc2ad066533414d19f6fc0c39932429023fc
3
+ size 16389
robotwin50_pi06_expert_train/checkpoint-2500/rng_state_7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:619b5c49446c94dca2b233ad17098e42f7d58a945c2eced1aa23e50469a75431
3
+ size 16389
robotwin50_pi06_expert_train/checkpoint-2500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7eca608778627ed3e09c9e7555c3e381ead97f99794881e7694b3b210abc9473
3
+ size 1465
robotwin50_pi06_expert_train/checkpoint-2500/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
robotwin50_pi06_expert_train/checkpoint-2500/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b5a4f3a53631b5d6b52bab7ddf0623dc957ef6a48ef9ad7e458a493026fbf0c
3
+ size 11460177
robotwin50_pi06_expert_train/checkpoint-2500/tokenizer_config.json ADDED
@@ -0,0 +1,1816 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<extra_id_0>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": true
188
+ },
189
+ "151666": {
190
+ "content": "<extra_id_1>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": true
196
+ },
197
+ "151667": {
198
+ "content": "<extra_id_2>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": true
204
+ },
205
+ "151668": {
206
+ "content": "<extra_id_3>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": true
212
+ },
213
+ "151669": {
214
+ "content": "<extra_id_4>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": true
220
+ },
221
+ "151670": {
222
+ "content": "<extra_id_5>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": true
228
+ },
229
+ "151671": {
230
+ "content": "<extra_id_6>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": true
236
+ },
237
+ "151672": {
238
+ "content": "<extra_id_7>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": true
244
+ },
245
+ "151673": {
246
+ "content": "<extra_id_8>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": true
252
+ },
253
+ "151674": {
254
+ "content": "<extra_id_9>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": true
260
+ },
261
+ "151675": {
262
+ "content": "<extra_id_10>",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": true
268
+ },
269
+ "151676": {
270
+ "content": "<extra_id_11>",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": false,
274
+ "single_word": false,
275
+ "special": true
276
+ },
277
+ "151677": {
278
+ "content": "<extra_id_12>",
279
+ "lstrip": false,
280
+ "normalized": false,
281
+ "rstrip": false,
282
+ "single_word": false,
283
+ "special": true
284
+ },
285
+ "151678": {
286
+ "content": "<extra_id_13>",
287
+ "lstrip": false,
288
+ "normalized": false,
289
+ "rstrip": false,
290
+ "single_word": false,
291
+ "special": true
292
+ },
293
+ "151679": {
294
+ "content": "<extra_id_14>",
295
+ "lstrip": false,
296
+ "normalized": false,
297
+ "rstrip": false,
298
+ "single_word": false,
299
+ "special": true
300
+ },
301
+ "151680": {
302
+ "content": "<extra_id_15>",
303
+ "lstrip": false,
304
+ "normalized": false,
305
+ "rstrip": false,
306
+ "single_word": false,
307
+ "special": true
308
+ },
309
+ "151681": {
310
+ "content": "<extra_id_16>",
311
+ "lstrip": false,
312
+ "normalized": false,
313
+ "rstrip": false,
314
+ "single_word": false,
315
+ "special": true
316
+ },
317
+ "151682": {
318
+ "content": "<extra_id_17>",
319
+ "lstrip": false,
320
+ "normalized": false,
321
+ "rstrip": false,
322
+ "single_word": false,
323
+ "special": true
324
+ },
325
+ "151683": {
326
+ "content": "<extra_id_18>",
327
+ "lstrip": false,
328
+ "normalized": false,
329
+ "rstrip": false,
330
+ "single_word": false,
331
+ "special": true
332
+ },
333
+ "151684": {
334
+ "content": "<extra_id_19>",
335
+ "lstrip": false,
336
+ "normalized": false,
337
+ "rstrip": false,
338
+ "single_word": false,
339
+ "special": true
340
+ },
341
+ "151685": {
342
+ "content": "<extra_id_20>",
343
+ "lstrip": false,
344
+ "normalized": false,
345
+ "rstrip": false,
346
+ "single_word": false,
347
+ "special": true
348
+ },
349
+ "151686": {
350
+ "content": "<extra_id_21>",
351
+ "lstrip": false,
352
+ "normalized": false,
353
+ "rstrip": false,
354
+ "single_word": false,
355
+ "special": true
356
+ },
357
+ "151687": {
358
+ "content": "<extra_id_22>",
359
+ "lstrip": false,
360
+ "normalized": false,
361
+ "rstrip": false,
362
+ "single_word": false,
363
+ "special": true
364
+ },
365
+ "151688": {
366
+ "content": "<extra_id_23>",
367
+ "lstrip": false,
368
+ "normalized": false,
369
+ "rstrip": false,
370
+ "single_word": false,
371
+ "special": true
372
+ },
373
+ "151689": {
374
+ "content": "<extra_id_24>",
375
+ "lstrip": false,
376
+ "normalized": false,
377
+ "rstrip": false,
378
+ "single_word": false,
379
+ "special": true
380
+ },
381
+ "151690": {
382
+ "content": "<extra_id_25>",
383
+ "lstrip": false,
384
+ "normalized": false,
385
+ "rstrip": false,
386
+ "single_word": false,
387
+ "special": true
388
+ },
389
+ "151691": {
390
+ "content": "<extra_id_26>",
391
+ "lstrip": false,
392
+ "normalized": false,
393
+ "rstrip": false,
394
+ "single_word": false,
395
+ "special": true
396
+ },
397
+ "151692": {
398
+ "content": "<extra_id_27>",
399
+ "lstrip": false,
400
+ "normalized": false,
401
+ "rstrip": false,
402
+ "single_word": false,
403
+ "special": true
404
+ },
405
+ "151693": {
406
+ "content": "<extra_id_28>",
407
+ "lstrip": false,
408
+ "normalized": false,
409
+ "rstrip": false,
410
+ "single_word": false,
411
+ "special": true
412
+ },
413
+ "151694": {
414
+ "content": "<extra_id_29>",
415
+ "lstrip": false,
416
+ "normalized": false,
417
+ "rstrip": false,
418
+ "single_word": false,
419
+ "special": true
420
+ },
421
+ "151695": {
422
+ "content": "<extra_id_30>",
423
+ "lstrip": false,
424
+ "normalized": false,
425
+ "rstrip": false,
426
+ "single_word": false,
427
+ "special": true
428
+ },
429
+ "151696": {
430
+ "content": "<extra_id_31>",
431
+ "lstrip": false,
432
+ "normalized": false,
433
+ "rstrip": false,
434
+ "single_word": false,
435
+ "special": true
436
+ },
437
+ "151697": {
438
+ "content": "<extra_id_32>",
439
+ "lstrip": false,
440
+ "normalized": false,
441
+ "rstrip": false,
442
+ "single_word": false,
443
+ "special": true
444
+ },
445
+ "151698": {
446
+ "content": "<extra_id_33>",
447
+ "lstrip": false,
448
+ "normalized": false,
449
+ "rstrip": false,
450
+ "single_word": false,
451
+ "special": true
452
+ },
453
+ "151699": {
454
+ "content": "<extra_id_34>",
455
+ "lstrip": false,
456
+ "normalized": false,
457
+ "rstrip": false,
458
+ "single_word": false,
459
+ "special": true
460
+ },
461
+ "151700": {
462
+ "content": "<extra_id_35>",
463
+ "lstrip": false,
464
+ "normalized": false,
465
+ "rstrip": false,
466
+ "single_word": false,
467
+ "special": true
468
+ },
469
+ "151701": {
470
+ "content": "<extra_id_36>",
471
+ "lstrip": false,
472
+ "normalized": false,
473
+ "rstrip": false,
474
+ "single_word": false,
475
+ "special": true
476
+ },
477
+ "151702": {
478
+ "content": "<extra_id_37>",
479
+ "lstrip": false,
480
+ "normalized": false,
481
+ "rstrip": false,
482
+ "single_word": false,
483
+ "special": true
484
+ },
485
+ "151703": {
486
+ "content": "<extra_id_38>",
487
+ "lstrip": false,
488
+ "normalized": false,
489
+ "rstrip": false,
490
+ "single_word": false,
491
+ "special": true
492
+ },
493
+ "151704": {
494
+ "content": "<extra_id_39>",
495
+ "lstrip": false,
496
+ "normalized": false,
497
+ "rstrip": false,
498
+ "single_word": false,
499
+ "special": true
500
+ },
501
+ "151705": {
502
+ "content": "<extra_id_40>",
503
+ "lstrip": false,
504
+ "normalized": false,
505
+ "rstrip": false,
506
+ "single_word": false,
507
+ "special": true
508
+ },
509
+ "151706": {
510
+ "content": "<extra_id_41>",
511
+ "lstrip": false,
512
+ "normalized": false,
513
+ "rstrip": false,
514
+ "single_word": false,
515
+ "special": true
516
+ },
517
+ "151707": {
518
+ "content": "<extra_id_42>",
519
+ "lstrip": false,
520
+ "normalized": false,
521
+ "rstrip": false,
522
+ "single_word": false,
523
+ "special": true
524
+ },
525
+ "151708": {
526
+ "content": "<extra_id_43>",
527
+ "lstrip": false,
528
+ "normalized": false,
529
+ "rstrip": false,
530
+ "single_word": false,
531
+ "special": true
532
+ },
533
+ "151709": {
534
+ "content": "<extra_id_44>",
535
+ "lstrip": false,
536
+ "normalized": false,
537
+ "rstrip": false,
538
+ "single_word": false,
539
+ "special": true
540
+ },
541
+ "151710": {
542
+ "content": "<extra_id_45>",
543
+ "lstrip": false,
544
+ "normalized": false,
545
+ "rstrip": false,
546
+ "single_word": false,
547
+ "special": true
548
+ },
549
+ "151711": {
550
+ "content": "<extra_id_46>",
551
+ "lstrip": false,
552
+ "normalized": false,
553
+ "rstrip": false,
554
+ "single_word": false,
555
+ "special": true
556
+ },
557
+ "151712": {
558
+ "content": "<extra_id_47>",
559
+ "lstrip": false,
560
+ "normalized": false,
561
+ "rstrip": false,
562
+ "single_word": false,
563
+ "special": true
564
+ },
565
+ "151713": {
566
+ "content": "<extra_id_48>",
567
+ "lstrip": false,
568
+ "normalized": false,
569
+ "rstrip": false,
570
+ "single_word": false,
571
+ "special": true
572
+ },
573
+ "151714": {
574
+ "content": "<extra_id_49>",
575
+ "lstrip": false,
576
+ "normalized": false,
577
+ "rstrip": false,
578
+ "single_word": false,
579
+ "special": true
580
+ },
581
+ "151715": {
582
+ "content": "<extra_id_50>",
583
+ "lstrip": false,
584
+ "normalized": false,
585
+ "rstrip": false,
586
+ "single_word": false,
587
+ "special": true
588
+ },
589
+ "151716": {
590
+ "content": "<extra_id_51>",
591
+ "lstrip": false,
592
+ "normalized": false,
593
+ "rstrip": false,
594
+ "single_word": false,
595
+ "special": true
596
+ },
597
+ "151717": {
598
+ "content": "<extra_id_52>",
599
+ "lstrip": false,
600
+ "normalized": false,
601
+ "rstrip": false,
602
+ "single_word": false,
603
+ "special": true
604
+ },
605
+ "151718": {
606
+ "content": "<extra_id_53>",
607
+ "lstrip": false,
608
+ "normalized": false,
609
+ "rstrip": false,
610
+ "single_word": false,
611
+ "special": true
612
+ },
613
+ "151719": {
614
+ "content": "<extra_id_54>",
615
+ "lstrip": false,
616
+ "normalized": false,
617
+ "rstrip": false,
618
+ "single_word": false,
619
+ "special": true
620
+ },
621
+ "151720": {
622
+ "content": "<extra_id_55>",
623
+ "lstrip": false,
624
+ "normalized": false,
625
+ "rstrip": false,
626
+ "single_word": false,
627
+ "special": true
628
+ },
629
+ "151721": {
630
+ "content": "<extra_id_56>",
631
+ "lstrip": false,
632
+ "normalized": false,
633
+ "rstrip": false,
634
+ "single_word": false,
635
+ "special": true
636
+ },
637
+ "151722": {
638
+ "content": "<extra_id_57>",
639
+ "lstrip": false,
640
+ "normalized": false,
641
+ "rstrip": false,
642
+ "single_word": false,
643
+ "special": true
644
+ },
645
+ "151723": {
646
+ "content": "<extra_id_58>",
647
+ "lstrip": false,
648
+ "normalized": false,
649
+ "rstrip": false,
650
+ "single_word": false,
651
+ "special": true
652
+ },
653
+ "151724": {
654
+ "content": "<extra_id_59>",
655
+ "lstrip": false,
656
+ "normalized": false,
657
+ "rstrip": false,
658
+ "single_word": false,
659
+ "special": true
660
+ },
661
+ "151725": {
662
+ "content": "<extra_id_60>",
663
+ "lstrip": false,
664
+ "normalized": false,
665
+ "rstrip": false,
666
+ "single_word": false,
667
+ "special": true
668
+ },
669
+ "151726": {
670
+ "content": "<extra_id_61>",
671
+ "lstrip": false,
672
+ "normalized": false,
673
+ "rstrip": false,
674
+ "single_word": false,
675
+ "special": true
676
+ },
677
+ "151727": {
678
+ "content": "<extra_id_62>",
679
+ "lstrip": false,
680
+ "normalized": false,
681
+ "rstrip": false,
682
+ "single_word": false,
683
+ "special": true
684
+ },
685
+ "151728": {
686
+ "content": "<extra_id_63>",
687
+ "lstrip": false,
688
+ "normalized": false,
689
+ "rstrip": false,
690
+ "single_word": false,
691
+ "special": true
692
+ },
693
+ "151729": {
694
+ "content": "<extra_id_64>",
695
+ "lstrip": false,
696
+ "normalized": false,
697
+ "rstrip": false,
698
+ "single_word": false,
699
+ "special": true
700
+ },
701
+ "151730": {
702
+ "content": "<extra_id_65>",
703
+ "lstrip": false,
704
+ "normalized": false,
705
+ "rstrip": false,
706
+ "single_word": false,
707
+ "special": true
708
+ },
709
+ "151731": {
710
+ "content": "<extra_id_66>",
711
+ "lstrip": false,
712
+ "normalized": false,
713
+ "rstrip": false,
714
+ "single_word": false,
715
+ "special": true
716
+ },
717
+ "151732": {
718
+ "content": "<extra_id_67>",
719
+ "lstrip": false,
720
+ "normalized": false,
721
+ "rstrip": false,
722
+ "single_word": false,
723
+ "special": true
724
+ },
725
+ "151733": {
726
+ "content": "<extra_id_68>",
727
+ "lstrip": false,
728
+ "normalized": false,
729
+ "rstrip": false,
730
+ "single_word": false,
731
+ "special": true
732
+ },
733
+ "151734": {
734
+ "content": "<extra_id_69>",
735
+ "lstrip": false,
736
+ "normalized": false,
737
+ "rstrip": false,
738
+ "single_word": false,
739
+ "special": true
740
+ },
741
+ "151735": {
742
+ "content": "<extra_id_70>",
743
+ "lstrip": false,
744
+ "normalized": false,
745
+ "rstrip": false,
746
+ "single_word": false,
747
+ "special": true
748
+ },
749
+ "151736": {
750
+ "content": "<extra_id_71>",
751
+ "lstrip": false,
752
+ "normalized": false,
753
+ "rstrip": false,
754
+ "single_word": false,
755
+ "special": true
756
+ },
757
+ "151737": {
758
+ "content": "<extra_id_72>",
759
+ "lstrip": false,
760
+ "normalized": false,
761
+ "rstrip": false,
762
+ "single_word": false,
763
+ "special": true
764
+ },
765
+ "151738": {
766
+ "content": "<extra_id_73>",
767
+ "lstrip": false,
768
+ "normalized": false,
769
+ "rstrip": false,
770
+ "single_word": false,
771
+ "special": true
772
+ },
773
+ "151739": {
774
+ "content": "<extra_id_74>",
775
+ "lstrip": false,
776
+ "normalized": false,
777
+ "rstrip": false,
778
+ "single_word": false,
779
+ "special": true
780
+ },
781
+ "151740": {
782
+ "content": "<extra_id_75>",
783
+ "lstrip": false,
784
+ "normalized": false,
785
+ "rstrip": false,
786
+ "single_word": false,
787
+ "special": true
788
+ },
789
+ "151741": {
790
+ "content": "<extra_id_76>",
791
+ "lstrip": false,
792
+ "normalized": false,
793
+ "rstrip": false,
794
+ "single_word": false,
795
+ "special": true
796
+ },
797
+ "151742": {
798
+ "content": "<extra_id_77>",
799
+ "lstrip": false,
800
+ "normalized": false,
801
+ "rstrip": false,
802
+ "single_word": false,
803
+ "special": true
804
+ },
805
+ "151743": {
806
+ "content": "<extra_id_78>",
807
+ "lstrip": false,
808
+ "normalized": false,
809
+ "rstrip": false,
810
+ "single_word": false,
811
+ "special": true
812
+ },
813
+ "151744": {
814
+ "content": "<extra_id_79>",
815
+ "lstrip": false,
816
+ "normalized": false,
817
+ "rstrip": false,
818
+ "single_word": false,
819
+ "special": true
820
+ },
821
+ "151745": {
822
+ "content": "<extra_id_80>",
823
+ "lstrip": false,
824
+ "normalized": false,
825
+ "rstrip": false,
826
+ "single_word": false,
827
+ "special": true
828
+ },
829
+ "151746": {
830
+ "content": "<extra_id_81>",
831
+ "lstrip": false,
832
+ "normalized": false,
833
+ "rstrip": false,
834
+ "single_word": false,
835
+ "special": true
836
+ },
837
+ "151747": {
838
+ "content": "<extra_id_82>",
839
+ "lstrip": false,
840
+ "normalized": false,
841
+ "rstrip": false,
842
+ "single_word": false,
843
+ "special": true
844
+ },
845
+ "151748": {
846
+ "content": "<extra_id_83>",
847
+ "lstrip": false,
848
+ "normalized": false,
849
+ "rstrip": false,
850
+ "single_word": false,
851
+ "special": true
852
+ },
853
+ "151749": {
854
+ "content": "<extra_id_84>",
855
+ "lstrip": false,
856
+ "normalized": false,
857
+ "rstrip": false,
858
+ "single_word": false,
859
+ "special": true
860
+ },
861
+ "151750": {
862
+ "content": "<extra_id_85>",
863
+ "lstrip": false,
864
+ "normalized": false,
865
+ "rstrip": false,
866
+ "single_word": false,
867
+ "special": true
868
+ },
869
+ "151751": {
870
+ "content": "<extra_id_86>",
871
+ "lstrip": false,
872
+ "normalized": false,
873
+ "rstrip": false,
874
+ "single_word": false,
875
+ "special": true
876
+ },
877
+ "151752": {
878
+ "content": "<extra_id_87>",
879
+ "lstrip": false,
880
+ "normalized": false,
881
+ "rstrip": false,
882
+ "single_word": false,
883
+ "special": true
884
+ },
885
+ "151753": {
886
+ "content": "<extra_id_88>",
887
+ "lstrip": false,
888
+ "normalized": false,
889
+ "rstrip": false,
890
+ "single_word": false,
891
+ "special": true
892
+ },
893
+ "151754": {
894
+ "content": "<extra_id_89>",
895
+ "lstrip": false,
896
+ "normalized": false,
897
+ "rstrip": false,
898
+ "single_word": false,
899
+ "special": true
900
+ },
901
+ "151755": {
902
+ "content": "<extra_id_90>",
903
+ "lstrip": false,
904
+ "normalized": false,
905
+ "rstrip": false,
906
+ "single_word": false,
907
+ "special": true
908
+ },
909
+ "151756": {
910
+ "content": "<extra_id_91>",
911
+ "lstrip": false,
912
+ "normalized": false,
913
+ "rstrip": false,
914
+ "single_word": false,
915
+ "special": true
916
+ },
917
+ "151757": {
918
+ "content": "<extra_id_92>",
919
+ "lstrip": false,
920
+ "normalized": false,
921
+ "rstrip": false,
922
+ "single_word": false,
923
+ "special": true
924
+ },
925
+ "151758": {
926
+ "content": "<extra_id_93>",
927
+ "lstrip": false,
928
+ "normalized": false,
929
+ "rstrip": false,
930
+ "single_word": false,
931
+ "special": true
932
+ },
933
+ "151759": {
934
+ "content": "<extra_id_94>",
935
+ "lstrip": false,
936
+ "normalized": false,
937
+ "rstrip": false,
938
+ "single_word": false,
939
+ "special": true
940
+ },
941
+ "151760": {
942
+ "content": "<extra_id_95>",
943
+ "lstrip": false,
944
+ "normalized": false,
945
+ "rstrip": false,
946
+ "single_word": false,
947
+ "special": true
948
+ },
949
+ "151761": {
950
+ "content": "<extra_id_96>",
951
+ "lstrip": false,
952
+ "normalized": false,
953
+ "rstrip": false,
954
+ "single_word": false,
955
+ "special": true
956
+ },
957
+ "151762": {
958
+ "content": "<extra_id_97>",
959
+ "lstrip": false,
960
+ "normalized": false,
961
+ "rstrip": false,
962
+ "single_word": false,
963
+ "special": true
964
+ },
965
+ "151763": {
966
+ "content": "<extra_id_98>",
967
+ "lstrip": false,
968
+ "normalized": false,
969
+ "rstrip": false,
970
+ "single_word": false,
971
+ "special": true
972
+ },
973
+ "151764": {
974
+ "content": "<extra_id_99>",
975
+ "lstrip": false,
976
+ "normalized": false,
977
+ "rstrip": false,
978
+ "single_word": false,
979
+ "special": true
980
+ },
981
+ "151765": {
982
+ "content": "<extra_id_100>",
983
+ "lstrip": false,
984
+ "normalized": false,
985
+ "rstrip": false,
986
+ "single_word": false,
987
+ "special": true
988
+ },
989
+ "151766": {
990
+ "content": "<extra_id_101>",
991
+ "lstrip": false,
992
+ "normalized": false,
993
+ "rstrip": false,
994
+ "single_word": false,
995
+ "special": true
996
+ },
997
+ "151767": {
998
+ "content": "<extra_id_102>",
999
+ "lstrip": false,
1000
+ "normalized": false,
1001
+ "rstrip": false,
1002
+ "single_word": false,
1003
+ "special": true
1004
+ },
1005
+ "151768": {
1006
+ "content": "<extra_id_103>",
1007
+ "lstrip": false,
1008
+ "normalized": false,
1009
+ "rstrip": false,
1010
+ "single_word": false,
1011
+ "special": true
1012
+ },
1013
+ "151769": {
1014
+ "content": "<extra_id_104>",
1015
+ "lstrip": false,
1016
+ "normalized": false,
1017
+ "rstrip": false,
1018
+ "single_word": false,
1019
+ "special": true
1020
+ },
1021
+ "151770": {
1022
+ "content": "<extra_id_105>",
1023
+ "lstrip": false,
1024
+ "normalized": false,
1025
+ "rstrip": false,
1026
+ "single_word": false,
1027
+ "special": true
1028
+ },
1029
+ "151771": {
1030
+ "content": "<extra_id_106>",
1031
+ "lstrip": false,
1032
+ "normalized": false,
1033
+ "rstrip": false,
1034
+ "single_word": false,
1035
+ "special": true
1036
+ },
1037
+ "151772": {
1038
+ "content": "<extra_id_107>",
1039
+ "lstrip": false,
1040
+ "normalized": false,
1041
+ "rstrip": false,
1042
+ "single_word": false,
1043
+ "special": true
1044
+ },
1045
+ "151773": {
1046
+ "content": "<extra_id_108>",
1047
+ "lstrip": false,
1048
+ "normalized": false,
1049
+ "rstrip": false,
1050
+ "single_word": false,
1051
+ "special": true
1052
+ },
1053
+ "151774": {
1054
+ "content": "<extra_id_109>",
1055
+ "lstrip": false,
1056
+ "normalized": false,
1057
+ "rstrip": false,
1058
+ "single_word": false,
1059
+ "special": true
1060
+ },
1061
+ "151775": {
1062
+ "content": "<extra_id_110>",
1063
+ "lstrip": false,
1064
+ "normalized": false,
1065
+ "rstrip": false,
1066
+ "single_word": false,
1067
+ "special": true
1068
+ },
1069
+ "151776": {
1070
+ "content": "<extra_id_111>",
1071
+ "lstrip": false,
1072
+ "normalized": false,
1073
+ "rstrip": false,
1074
+ "single_word": false,
1075
+ "special": true
1076
+ },
1077
+ "151777": {
1078
+ "content": "<extra_id_112>",
1079
+ "lstrip": false,
1080
+ "normalized": false,
1081
+ "rstrip": false,
1082
+ "single_word": false,
1083
+ "special": true
1084
+ },
1085
+ "151778": {
1086
+ "content": "<extra_id_113>",
1087
+ "lstrip": false,
1088
+ "normalized": false,
1089
+ "rstrip": false,
1090
+ "single_word": false,
1091
+ "special": true
1092
+ },
1093
+ "151779": {
1094
+ "content": "<extra_id_114>",
1095
+ "lstrip": false,
1096
+ "normalized": false,
1097
+ "rstrip": false,
1098
+ "single_word": false,
1099
+ "special": true
1100
+ },
1101
+ "151780": {
1102
+ "content": "<extra_id_115>",
1103
+ "lstrip": false,
1104
+ "normalized": false,
1105
+ "rstrip": false,
1106
+ "single_word": false,
1107
+ "special": true
1108
+ },
1109
+ "151781": {
1110
+ "content": "<extra_id_116>",
1111
+ "lstrip": false,
1112
+ "normalized": false,
1113
+ "rstrip": false,
1114
+ "single_word": false,
1115
+ "special": true
1116
+ },
1117
+ "151782": {
1118
+ "content": "<extra_id_117>",
1119
+ "lstrip": false,
1120
+ "normalized": false,
1121
+ "rstrip": false,
1122
+ "single_word": false,
1123
+ "special": true
1124
+ },
1125
+ "151783": {
1126
+ "content": "<extra_id_118>",
1127
+ "lstrip": false,
1128
+ "normalized": false,
1129
+ "rstrip": false,
1130
+ "single_word": false,
1131
+ "special": true
1132
+ },
1133
+ "151784": {
1134
+ "content": "<extra_id_119>",
1135
+ "lstrip": false,
1136
+ "normalized": false,
1137
+ "rstrip": false,
1138
+ "single_word": false,
1139
+ "special": true
1140
+ },
1141
+ "151785": {
1142
+ "content": "<extra_id_120>",
1143
+ "lstrip": false,
1144
+ "normalized": false,
1145
+ "rstrip": false,
1146
+ "single_word": false,
1147
+ "special": true
1148
+ },
1149
+ "151786": {
1150
+ "content": "<extra_id_121>",
1151
+ "lstrip": false,
1152
+ "normalized": false,
1153
+ "rstrip": false,
1154
+ "single_word": false,
1155
+ "special": true
1156
+ },
1157
+ "151787": {
1158
+ "content": "<extra_id_122>",
1159
+ "lstrip": false,
1160
+ "normalized": false,
1161
+ "rstrip": false,
1162
+ "single_word": false,
1163
+ "special": true
1164
+ },
1165
+ "151788": {
1166
+ "content": "<extra_id_123>",
1167
+ "lstrip": false,
1168
+ "normalized": false,
1169
+ "rstrip": false,
1170
+ "single_word": false,
1171
+ "special": true
1172
+ },
1173
+ "151789": {
1174
+ "content": "<extra_id_124>",
1175
+ "lstrip": false,
1176
+ "normalized": false,
1177
+ "rstrip": false,
1178
+ "single_word": false,
1179
+ "special": true
1180
+ },
1181
+ "151790": {
1182
+ "content": "<extra_id_125>",
1183
+ "lstrip": false,
1184
+ "normalized": false,
1185
+ "rstrip": false,
1186
+ "single_word": false,
1187
+ "special": true
1188
+ },
1189
+ "151791": {
1190
+ "content": "<extra_id_126>",
1191
+ "lstrip": false,
1192
+ "normalized": false,
1193
+ "rstrip": false,
1194
+ "single_word": false,
1195
+ "special": true
1196
+ },
1197
+ "151792": {
1198
+ "content": "<extra_id_127>",
1199
+ "lstrip": false,
1200
+ "normalized": false,
1201
+ "rstrip": false,
1202
+ "single_word": false,
1203
+ "special": true
1204
+ },
1205
+ "151793": {
1206
+ "content": "<extra_id_128>",
1207
+ "lstrip": false,
1208
+ "normalized": false,
1209
+ "rstrip": false,
1210
+ "single_word": false,
1211
+ "special": true
1212
+ },
1213
+ "151794": {
1214
+ "content": "<extra_id_129>",
1215
+ "lstrip": false,
1216
+ "normalized": false,
1217
+ "rstrip": false,
1218
+ "single_word": false,
1219
+ "special": true
1220
+ },
1221
+ "151795": {
1222
+ "content": "<extra_id_130>",
1223
+ "lstrip": false,
1224
+ "normalized": false,
1225
+ "rstrip": false,
1226
+ "single_word": false,
1227
+ "special": true
1228
+ },
1229
+ "151796": {
1230
+ "content": "<extra_id_131>",
1231
+ "lstrip": false,
1232
+ "normalized": false,
1233
+ "rstrip": false,
1234
+ "single_word": false,
1235
+ "special": true
1236
+ },
1237
+ "151797": {
1238
+ "content": "<extra_id_132>",
1239
+ "lstrip": false,
1240
+ "normalized": false,
1241
+ "rstrip": false,
1242
+ "single_word": false,
1243
+ "special": true
1244
+ },
1245
+ "151798": {
1246
+ "content": "<extra_id_133>",
1247
+ "lstrip": false,
1248
+ "normalized": false,
1249
+ "rstrip": false,
1250
+ "single_word": false,
1251
+ "special": true
1252
+ },
1253
+ "151799": {
1254
+ "content": "<extra_id_134>",
1255
+ "lstrip": false,
1256
+ "normalized": false,
1257
+ "rstrip": false,
1258
+ "single_word": false,
1259
+ "special": true
1260
+ },
1261
+ "151800": {
1262
+ "content": "<extra_id_135>",
1263
+ "lstrip": false,
1264
+ "normalized": false,
1265
+ "rstrip": false,
1266
+ "single_word": false,
1267
+ "special": true
1268
+ },
1269
+ "151801": {
1270
+ "content": "<extra_id_136>",
1271
+ "lstrip": false,
1272
+ "normalized": false,
1273
+ "rstrip": false,
1274
+ "single_word": false,
1275
+ "special": true
1276
+ },
1277
+ "151802": {
1278
+ "content": "<extra_id_137>",
1279
+ "lstrip": false,
1280
+ "normalized": false,
1281
+ "rstrip": false,
1282
+ "single_word": false,
1283
+ "special": true
1284
+ },
1285
+ "151803": {
1286
+ "content": "<extra_id_138>",
1287
+ "lstrip": false,
1288
+ "normalized": false,
1289
+ "rstrip": false,
1290
+ "single_word": false,
1291
+ "special": true
1292
+ },
1293
+ "151804": {
1294
+ "content": "<extra_id_139>",
1295
+ "lstrip": false,
1296
+ "normalized": false,
1297
+ "rstrip": false,
1298
+ "single_word": false,
1299
+ "special": true
1300
+ },
1301
+ "151805": {
1302
+ "content": "<extra_id_140>",
1303
+ "lstrip": false,
1304
+ "normalized": false,
1305
+ "rstrip": false,
1306
+ "single_word": false,
1307
+ "special": true
1308
+ },
1309
+ "151806": {
1310
+ "content": "<extra_id_141>",
1311
+ "lstrip": false,
1312
+ "normalized": false,
1313
+ "rstrip": false,
1314
+ "single_word": false,
1315
+ "special": true
1316
+ },
1317
+ "151807": {
1318
+ "content": "<extra_id_142>",
1319
+ "lstrip": false,
1320
+ "normalized": false,
1321
+ "rstrip": false,
1322
+ "single_word": false,
1323
+ "special": true
1324
+ },
1325
+ "151808": {
1326
+ "content": "<extra_id_143>",
1327
+ "lstrip": false,
1328
+ "normalized": false,
1329
+ "rstrip": false,
1330
+ "single_word": false,
1331
+ "special": true
1332
+ },
1333
+ "151809": {
1334
+ "content": "<extra_id_144>",
1335
+ "lstrip": false,
1336
+ "normalized": false,
1337
+ "rstrip": false,
1338
+ "single_word": false,
1339
+ "special": true
1340
+ },
1341
+ "151810": {
1342
+ "content": "<extra_id_145>",
1343
+ "lstrip": false,
1344
+ "normalized": false,
1345
+ "rstrip": false,
1346
+ "single_word": false,
1347
+ "special": true
1348
+ },
1349
+ "151811": {
1350
+ "content": "<extra_id_146>",
1351
+ "lstrip": false,
1352
+ "normalized": false,
1353
+ "rstrip": false,
1354
+ "single_word": false,
1355
+ "special": true
1356
+ },
1357
+ "151812": {
1358
+ "content": "<extra_id_147>",
1359
+ "lstrip": false,
1360
+ "normalized": false,
1361
+ "rstrip": false,
1362
+ "single_word": false,
1363
+ "special": true
1364
+ },
1365
+ "151813": {
1366
+ "content": "<extra_id_148>",
1367
+ "lstrip": false,
1368
+ "normalized": false,
1369
+ "rstrip": false,
1370
+ "single_word": false,
1371
+ "special": true
1372
+ },
1373
+ "151814": {
1374
+ "content": "<extra_id_149>",
1375
+ "lstrip": false,
1376
+ "normalized": false,
1377
+ "rstrip": false,
1378
+ "single_word": false,
1379
+ "special": true
1380
+ },
1381
+ "151815": {
1382
+ "content": "<extra_id_150>",
1383
+ "lstrip": false,
1384
+ "normalized": false,
1385
+ "rstrip": false,
1386
+ "single_word": false,
1387
+ "special": true
1388
+ },
1389
+ "151816": {
1390
+ "content": "<extra_id_151>",
1391
+ "lstrip": false,
1392
+ "normalized": false,
1393
+ "rstrip": false,
1394
+ "single_word": false,
1395
+ "special": true
1396
+ },
1397
+ "151817": {
1398
+ "content": "<extra_id_152>",
1399
+ "lstrip": false,
1400
+ "normalized": false,
1401
+ "rstrip": false,
1402
+ "single_word": false,
1403
+ "special": true
1404
+ },
1405
+ "151818": {
1406
+ "content": "<extra_id_153>",
1407
+ "lstrip": false,
1408
+ "normalized": false,
1409
+ "rstrip": false,
1410
+ "single_word": false,
1411
+ "special": true
1412
+ },
1413
+ "151819": {
1414
+ "content": "<extra_id_154>",
1415
+ "lstrip": false,
1416
+ "normalized": false,
1417
+ "rstrip": false,
1418
+ "single_word": false,
1419
+ "special": true
1420
+ },
1421
+ "151820": {
1422
+ "content": "<extra_id_155>",
1423
+ "lstrip": false,
1424
+ "normalized": false,
1425
+ "rstrip": false,
1426
+ "single_word": false,
1427
+ "special": true
1428
+ },
1429
+ "151821": {
1430
+ "content": "<extra_id_156>",
1431
+ "lstrip": false,
1432
+ "normalized": false,
1433
+ "rstrip": false,
1434
+ "single_word": false,
1435
+ "special": true
1436
+ },
1437
+ "151822": {
1438
+ "content": "<extra_id_157>",
1439
+ "lstrip": false,
1440
+ "normalized": false,
1441
+ "rstrip": false,
1442
+ "single_word": false,
1443
+ "special": true
1444
+ },
1445
+ "151823": {
1446
+ "content": "<extra_id_158>",
1447
+ "lstrip": false,
1448
+ "normalized": false,
1449
+ "rstrip": false,
1450
+ "single_word": false,
1451
+ "special": true
1452
+ },
1453
+ "151824": {
1454
+ "content": "<extra_id_159>",
1455
+ "lstrip": false,
1456
+ "normalized": false,
1457
+ "rstrip": false,
1458
+ "single_word": false,
1459
+ "special": true
1460
+ },
1461
+ "151825": {
1462
+ "content": "<extra_id_160>",
1463
+ "lstrip": false,
1464
+ "normalized": false,
1465
+ "rstrip": false,
1466
+ "single_word": false,
1467
+ "special": true
1468
+ },
1469
+ "151826": {
1470
+ "content": "<extra_id_161>",
1471
+ "lstrip": false,
1472
+ "normalized": false,
1473
+ "rstrip": false,
1474
+ "single_word": false,
1475
+ "special": true
1476
+ },
1477
+ "151827": {
1478
+ "content": "<extra_id_162>",
1479
+ "lstrip": false,
1480
+ "normalized": false,
1481
+ "rstrip": false,
1482
+ "single_word": false,
1483
+ "special": true
1484
+ },
1485
+ "151828": {
1486
+ "content": "<extra_id_163>",
1487
+ "lstrip": false,
1488
+ "normalized": false,
1489
+ "rstrip": false,
1490
+ "single_word": false,
1491
+ "special": true
1492
+ },
1493
+ "151829": {
1494
+ "content": "<extra_id_164>",
1495
+ "lstrip": false,
1496
+ "normalized": false,
1497
+ "rstrip": false,
1498
+ "single_word": false,
1499
+ "special": true
1500
+ },
1501
+ "151830": {
1502
+ "content": "<extra_id_165>",
1503
+ "lstrip": false,
1504
+ "normalized": false,
1505
+ "rstrip": false,
1506
+ "single_word": false,
1507
+ "special": true
1508
+ },
1509
+ "151831": {
1510
+ "content": "<extra_id_166>",
1511
+ "lstrip": false,
1512
+ "normalized": false,
1513
+ "rstrip": false,
1514
+ "single_word": false,
1515
+ "special": true
1516
+ },
1517
+ "151832": {
1518
+ "content": "<extra_id_167>",
1519
+ "lstrip": false,
1520
+ "normalized": false,
1521
+ "rstrip": false,
1522
+ "single_word": false,
1523
+ "special": true
1524
+ },
1525
+ "151833": {
1526
+ "content": "<extra_id_168>",
1527
+ "lstrip": false,
1528
+ "normalized": false,
1529
+ "rstrip": false,
1530
+ "single_word": false,
1531
+ "special": true
1532
+ },
1533
+ "151834": {
1534
+ "content": "<extra_id_169>",
1535
+ "lstrip": false,
1536
+ "normalized": false,
1537
+ "rstrip": false,
1538
+ "single_word": false,
1539
+ "special": true
1540
+ },
1541
+ "151835": {
1542
+ "content": "<extra_id_170>",
1543
+ "lstrip": false,
1544
+ "normalized": false,
1545
+ "rstrip": false,
1546
+ "single_word": false,
1547
+ "special": true
1548
+ },
1549
+ "151836": {
1550
+ "content": "<extra_id_171>",
1551
+ "lstrip": false,
1552
+ "normalized": false,
1553
+ "rstrip": false,
1554
+ "single_word": false,
1555
+ "special": true
1556
+ },
1557
+ "151837": {
1558
+ "content": "<extra_id_172>",
1559
+ "lstrip": false,
1560
+ "normalized": false,
1561
+ "rstrip": false,
1562
+ "single_word": false,
1563
+ "special": true
1564
+ },
1565
+ "151838": {
1566
+ "content": "<extra_id_173>",
1567
+ "lstrip": false,
1568
+ "normalized": false,
1569
+ "rstrip": false,
1570
+ "single_word": false,
1571
+ "special": true
1572
+ },
1573
+ "151839": {
1574
+ "content": "<extra_id_174>",
1575
+ "lstrip": false,
1576
+ "normalized": false,
1577
+ "rstrip": false,
1578
+ "single_word": false,
1579
+ "special": true
1580
+ },
1581
+ "151840": {
1582
+ "content": "<extra_id_175>",
1583
+ "lstrip": false,
1584
+ "normalized": false,
1585
+ "rstrip": false,
1586
+ "single_word": false,
1587
+ "special": true
1588
+ },
1589
+ "151841": {
1590
+ "content": "<extra_id_176>",
1591
+ "lstrip": false,
1592
+ "normalized": false,
1593
+ "rstrip": false,
1594
+ "single_word": false,
1595
+ "special": true
1596
+ },
1597
+ "151842": {
1598
+ "content": "<extra_id_177>",
1599
+ "lstrip": false,
1600
+ "normalized": false,
1601
+ "rstrip": false,
1602
+ "single_word": false,
1603
+ "special": true
1604
+ },
1605
+ "151843": {
1606
+ "content": "<extra_id_178>",
1607
+ "lstrip": false,
1608
+ "normalized": false,
1609
+ "rstrip": false,
1610
+ "single_word": false,
1611
+ "special": true
1612
+ },
1613
+ "151844": {
1614
+ "content": "<extra_id_179>",
1615
+ "lstrip": false,
1616
+ "normalized": false,
1617
+ "rstrip": false,
1618
+ "single_word": false,
1619
+ "special": true
1620
+ },
1621
+ "151845": {
1622
+ "content": "<extra_id_180>",
1623
+ "lstrip": false,
1624
+ "normalized": false,
1625
+ "rstrip": false,
1626
+ "single_word": false,
1627
+ "special": true
1628
+ },
1629
+ "151846": {
1630
+ "content": "<extra_id_181>",
1631
+ "lstrip": false,
1632
+ "normalized": false,
1633
+ "rstrip": false,
1634
+ "single_word": false,
1635
+ "special": true
1636
+ },
1637
+ "151847": {
1638
+ "content": "<extra_id_182>",
1639
+ "lstrip": false,
1640
+ "normalized": false,
1641
+ "rstrip": false,
1642
+ "single_word": false,
1643
+ "special": true
1644
+ },
1645
+ "151848": {
1646
+ "content": "<extra_id_183>",
1647
+ "lstrip": false,
1648
+ "normalized": false,
1649
+ "rstrip": false,
1650
+ "single_word": false,
1651
+ "special": true
1652
+ },
1653
+ "151849": {
1654
+ "content": "<extra_id_184>",
1655
+ "lstrip": false,
1656
+ "normalized": false,
1657
+ "rstrip": false,
1658
+ "single_word": false,
1659
+ "special": true
1660
+ },
1661
+ "151850": {
1662
+ "content": "<extra_id_185>",
1663
+ "lstrip": false,
1664
+ "normalized": false,
1665
+ "rstrip": false,
1666
+ "single_word": false,
1667
+ "special": true
1668
+ },
1669
+ "151851": {
1670
+ "content": "<extra_id_186>",
1671
+ "lstrip": false,
1672
+ "normalized": false,
1673
+ "rstrip": false,
1674
+ "single_word": false,
1675
+ "special": true
1676
+ },
1677
+ "151852": {
1678
+ "content": "<extra_id_187>",
1679
+ "lstrip": false,
1680
+ "normalized": false,
1681
+ "rstrip": false,
1682
+ "single_word": false,
1683
+ "special": true
1684
+ },
1685
+ "151853": {
1686
+ "content": "<extra_id_188>",
1687
+ "lstrip": false,
1688
+ "normalized": false,
1689
+ "rstrip": false,
1690
+ "single_word": false,
1691
+ "special": true
1692
+ },
1693
+ "151854": {
1694
+ "content": "<extra_id_189>",
1695
+ "lstrip": false,
1696
+ "normalized": false,
1697
+ "rstrip": false,
1698
+ "single_word": false,
1699
+ "special": true
1700
+ },
1701
+ "151855": {
1702
+ "content": "<extra_id_190>",
1703
+ "lstrip": false,
1704
+ "normalized": false,
1705
+ "rstrip": false,
1706
+ "single_word": false,
1707
+ "special": true
1708
+ },
1709
+ "151856": {
1710
+ "content": "<extra_id_191>",
1711
+ "lstrip": false,
1712
+ "normalized": false,
1713
+ "rstrip": false,
1714
+ "single_word": false,
1715
+ "special": true
1716
+ },
1717
+ "151857": {
1718
+ "content": "<extra_id_192>",
1719
+ "lstrip": false,
1720
+ "normalized": false,
1721
+ "rstrip": false,
1722
+ "single_word": false,
1723
+ "special": true
1724
+ },
1725
+ "151858": {
1726
+ "content": "<extra_id_193>",
1727
+ "lstrip": false,
1728
+ "normalized": false,
1729
+ "rstrip": false,
1730
+ "single_word": false,
1731
+ "special": true
1732
+ },
1733
+ "151859": {
1734
+ "content": "<extra_id_194>",
1735
+ "lstrip": false,
1736
+ "normalized": false,
1737
+ "rstrip": false,
1738
+ "single_word": false,
1739
+ "special": true
1740
+ },
1741
+ "151860": {
1742
+ "content": "<extra_id_195>",
1743
+ "lstrip": false,
1744
+ "normalized": false,
1745
+ "rstrip": false,
1746
+ "single_word": false,
1747
+ "special": true
1748
+ },
1749
+ "151861": {
1750
+ "content": "<extra_id_196>",
1751
+ "lstrip": false,
1752
+ "normalized": false,
1753
+ "rstrip": false,
1754
+ "single_word": false,
1755
+ "special": true
1756
+ },
1757
+ "151862": {
1758
+ "content": "<extra_id_197>",
1759
+ "lstrip": false,
1760
+ "normalized": false,
1761
+ "rstrip": false,
1762
+ "single_word": false,
1763
+ "special": true
1764
+ },
1765
+ "151863": {
1766
+ "content": "<extra_id_198>",
1767
+ "lstrip": false,
1768
+ "normalized": false,
1769
+ "rstrip": false,
1770
+ "single_word": false,
1771
+ "special": true
1772
+ },
1773
+ "151864": {
1774
+ "content": "<extra_id_199>",
1775
+ "lstrip": false,
1776
+ "normalized": false,
1777
+ "rstrip": false,
1778
+ "single_word": false,
1779
+ "special": true
1780
+ },
1781
+ "151865": {
1782
+ "content": "<extra_id_200>",
1783
+ "lstrip": false,
1784
+ "normalized": false,
1785
+ "rstrip": false,
1786
+ "single_word": false,
1787
+ "special": true
1788
+ }
1789
+ },
1790
+ "additional_special_tokens": [
1791
+ "<|im_start|>",
1792
+ "<|im_end|>",
1793
+ "<|object_ref_start|>",
1794
+ "<|object_ref_end|>",
1795
+ "<|box_start|>",
1796
+ "<|box_end|>",
1797
+ "<|quad_start|>",
1798
+ "<|quad_end|>",
1799
+ "<|vision_start|>",
1800
+ "<|vision_end|>",
1801
+ "<|vision_pad|>",
1802
+ "<|image_pad|>",
1803
+ "<|video_pad|>"
1804
+ ],
1805
+ "bos_token": null,
1806
+ "clean_up_tokenization_spaces": false,
1807
+ "eos_token": "<|im_end|>",
1808
+ "errors": "replace",
1809
+ "extra_special_tokens": {},
1810
+ "model_max_length": 512,
1811
+ "pad_token": "<|endoftext|>",
1812
+ "processor_class": "Qwen2_5_VLProcessor",
1813
+ "split_special_tokens": false,
1814
+ "tokenizer_class": "Qwen2Tokenizer",
1815
+ "unk_token": null
1816
+ }
robotwin50_pi06_expert_train/checkpoint-2500/trainer_state.json ADDED
@@ -0,0 +1,1792 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.028815478028198,
6
+ "eval_steps": 2500,
7
+ "global_step": 2500,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.004116496861171143,
14
+ "grad_norm": 722.9849266591084,
15
+ "learning_rate": 1.0000000000000001e-07,
16
+ "loss": 79.4593,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.008232993722342286,
21
+ "grad_norm": 713.4423322869009,
22
+ "learning_rate": 2.1111111111111113e-07,
23
+ "loss": 79.3183,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.01234949058351343,
28
+ "grad_norm": 619.0335944754007,
29
+ "learning_rate": 3.2222222222222227e-07,
30
+ "loss": 78.0929,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.016465987444684572,
35
+ "grad_norm": 439.772626183607,
36
+ "learning_rate": 4.333333333333334e-07,
37
+ "loss": 75.0743,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.020582484305855717,
42
+ "grad_norm": 281.08070517386403,
43
+ "learning_rate": 5.444444444444444e-07,
44
+ "loss": 69.3428,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.02469898116702686,
49
+ "grad_norm": 238.72306538307805,
50
+ "learning_rate": 6.555555555555556e-07,
51
+ "loss": 64.8186,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.028815478028198005,
56
+ "grad_norm": 265.61586056265025,
57
+ "learning_rate": 7.666666666666667e-07,
58
+ "loss": 59.6238,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.032931974889369144,
63
+ "grad_norm": 92.19312055336448,
64
+ "learning_rate": 8.777777777777778e-07,
65
+ "loss": 52.8731,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.03704847175054029,
70
+ "grad_norm": 45.48770884961453,
71
+ "learning_rate": 9.88888888888889e-07,
72
+ "loss": 49.676,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.041164968611711435,
77
+ "grad_norm": 27.08086194848908,
78
+ "learning_rate": 1.1e-06,
79
+ "loss": 48.4892,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.04528146547288258,
84
+ "grad_norm": 19.32379182470467,
85
+ "learning_rate": 1.2111111111111111e-06,
86
+ "loss": 48.0497,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.04939796233405372,
91
+ "grad_norm": 16.380874066084196,
92
+ "learning_rate": 1.3222222222222222e-06,
93
+ "loss": 47.7781,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.053514459195224864,
98
+ "grad_norm": 15.371140813384557,
99
+ "learning_rate": 1.4333333333333335e-06,
100
+ "loss": 47.5811,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.05763095605639601,
105
+ "grad_norm": 15.84809592222176,
106
+ "learning_rate": 1.5444444444444446e-06,
107
+ "loss": 47.4215,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.06174745291756715,
112
+ "grad_norm": 16.994317821440845,
113
+ "learning_rate": 1.6555555555555559e-06,
114
+ "loss": 47.2557,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.06586394977873829,
119
+ "grad_norm": 18.743638967461997,
120
+ "learning_rate": 1.7666666666666668e-06,
121
+ "loss": 47.0796,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.06998044663990943,
126
+ "grad_norm": 20.92550528148297,
127
+ "learning_rate": 1.8777777777777778e-06,
128
+ "loss": 46.8693,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.07409694350108058,
133
+ "grad_norm": 23.935804629158547,
134
+ "learning_rate": 1.988888888888889e-06,
135
+ "loss": 46.6118,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.07821344036225172,
140
+ "grad_norm": 28.229572692610986,
141
+ "learning_rate": 2.1000000000000002e-06,
142
+ "loss": 46.267,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.08232993722342287,
147
+ "grad_norm": 34.37693332521861,
148
+ "learning_rate": 2.2111111111111113e-06,
149
+ "loss": 45.7269,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.08644643408459401,
154
+ "grad_norm": 43.4433932596704,
155
+ "learning_rate": 2.3222222222222224e-06,
156
+ "loss": 44.9702,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.09056293094576516,
161
+ "grad_norm": 58.28038941283432,
162
+ "learning_rate": 2.4333333333333335e-06,
163
+ "loss": 43.7522,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.09467942780693629,
168
+ "grad_norm": 71.69823530504809,
169
+ "learning_rate": 2.5444444444444446e-06,
170
+ "loss": 41.9094,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.09879592466810744,
175
+ "grad_norm": 69.78057028859453,
176
+ "learning_rate": 2.6555555555555556e-06,
177
+ "loss": 39.6286,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.10291242152927858,
182
+ "grad_norm": 65.2702064062225,
183
+ "learning_rate": 2.766666666666667e-06,
184
+ "loss": 37.279,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.10702891839044973,
189
+ "grad_norm": 62.147050273188626,
190
+ "learning_rate": 2.8777777777777782e-06,
191
+ "loss": 34.8486,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.11114541525162087,
196
+ "grad_norm": 58.3163917534024,
197
+ "learning_rate": 2.988888888888889e-06,
198
+ "loss": 32.3669,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.11526191211279202,
203
+ "grad_norm": 73.8699537282808,
204
+ "learning_rate": 3.1000000000000004e-06,
205
+ "loss": 29.9582,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.11937840897396315,
210
+ "grad_norm": 59.22493609025033,
211
+ "learning_rate": 3.2111111111111115e-06,
212
+ "loss": 27.8124,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.1234949058351343,
217
+ "grad_norm": 42.636994581457614,
218
+ "learning_rate": 3.322222222222222e-06,
219
+ "loss": 25.908,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.12761140269630544,
224
+ "grad_norm": 36.81511952341932,
225
+ "learning_rate": 3.4333333333333336e-06,
226
+ "loss": 24.4843,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.13172789955747657,
231
+ "grad_norm": 27.381915904890327,
232
+ "learning_rate": 3.5444444444444447e-06,
233
+ "loss": 23.4653,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.13584439641864773,
238
+ "grad_norm": 23.598517571067614,
239
+ "learning_rate": 3.6555555555555562e-06,
240
+ "loss": 22.7909,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.13996089327981887,
245
+ "grad_norm": 23.294478325249578,
246
+ "learning_rate": 3.766666666666667e-06,
247
+ "loss": 22.3688,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.14407739014099002,
252
+ "grad_norm": 20.093643447034683,
253
+ "learning_rate": 3.877777777777778e-06,
254
+ "loss": 22.0982,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.14819388700216116,
259
+ "grad_norm": 19.394487535911193,
260
+ "learning_rate": 3.9888888888888895e-06,
261
+ "loss": 21.9086,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.15231038386333232,
266
+ "grad_norm": 18.119665979499104,
267
+ "learning_rate": 4.1e-06,
268
+ "loss": 21.7863,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.15642688072450345,
273
+ "grad_norm": 17.07344526731236,
274
+ "learning_rate": 4.211111111111112e-06,
275
+ "loss": 21.6972,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.16054337758567458,
280
+ "grad_norm": 17.2895867054574,
281
+ "learning_rate": 4.322222222222223e-06,
282
+ "loss": 21.6276,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.16465987444684574,
287
+ "grad_norm": 18.055980258041934,
288
+ "learning_rate": 4.433333333333334e-06,
289
+ "loss": 21.5774,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.16877637130801687,
294
+ "grad_norm": 17.602944740266267,
295
+ "learning_rate": 4.544444444444445e-06,
296
+ "loss": 21.5305,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.17289286816918803,
301
+ "grad_norm": 17.047319458414727,
302
+ "learning_rate": 4.655555555555556e-06,
303
+ "loss": 21.4996,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.17700936503035916,
308
+ "grad_norm": 17.326432935336033,
309
+ "learning_rate": 4.766666666666667e-06,
310
+ "loss": 21.4706,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.18112586189153032,
315
+ "grad_norm": 17.554696739458905,
316
+ "learning_rate": 4.877777777777778e-06,
317
+ "loss": 21.4449,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.18524235875270145,
322
+ "grad_norm": 16.57900811727561,
323
+ "learning_rate": 4.988888888888889e-06,
324
+ "loss": 21.4242,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.18935885561387258,
329
+ "grad_norm": 16.41658497950142,
330
+ "learning_rate": 5.1e-06,
331
+ "loss": 21.4136,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.19347535247504374,
336
+ "grad_norm": 14.851397065124416,
337
+ "learning_rate": 5.211111111111111e-06,
338
+ "loss": 21.3904,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.19759184933621488,
343
+ "grad_norm": 16.86165644628761,
344
+ "learning_rate": 5.322222222222223e-06,
345
+ "loss": 21.3748,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.20170834619738603,
350
+ "grad_norm": 16.021934417394476,
351
+ "learning_rate": 5.4333333333333335e-06,
352
+ "loss": 21.3649,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.20582484305855717,
357
+ "grad_norm": 16.71987330752045,
358
+ "learning_rate": 5.544444444444445e-06,
359
+ "loss": 21.357,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 0.2099413399197283,
364
+ "grad_norm": 16.033384348770003,
365
+ "learning_rate": 5.6555555555555566e-06,
366
+ "loss": 21.345,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 0.21405783678089946,
371
+ "grad_norm": 16.503614387128653,
372
+ "learning_rate": 5.766666666666667e-06,
373
+ "loss": 21.3308,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 0.2181743336420706,
378
+ "grad_norm": 16.5197017811903,
379
+ "learning_rate": 5.877777777777778e-06,
380
+ "loss": 21.3167,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 0.22229083050324175,
385
+ "grad_norm": 18.609397075134556,
386
+ "learning_rate": 5.98888888888889e-06,
387
+ "loss": 21.2952,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 0.22640732736441288,
392
+ "grad_norm": 18.044456751597316,
393
+ "learning_rate": 6.1e-06,
394
+ "loss": 21.2694,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 0.23052382422558404,
399
+ "grad_norm": 18.440050806349944,
400
+ "learning_rate": 6.211111111111111e-06,
401
+ "loss": 21.2149,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 0.23464032108675517,
406
+ "grad_norm": 36.12491809597436,
407
+ "learning_rate": 6.322222222222223e-06,
408
+ "loss": 21.1566,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 0.2387568179479263,
413
+ "grad_norm": 17.843619309609803,
414
+ "learning_rate": 6.433333333333333e-06,
415
+ "loss": 21.0841,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 0.24287331480909746,
420
+ "grad_norm": 18.299191738513812,
421
+ "learning_rate": 6.544444444444445e-06,
422
+ "loss": 20.9708,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 0.2469898116702686,
427
+ "grad_norm": 18.056905789458586,
428
+ "learning_rate": 6.655555555555556e-06,
429
+ "loss": 20.8825,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 0.2511063085314397,
434
+ "grad_norm": 44.82326463049171,
435
+ "learning_rate": 6.7666666666666665e-06,
436
+ "loss": 20.8147,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 0.2552228053926109,
441
+ "grad_norm": 27.094157559455603,
442
+ "learning_rate": 6.8777777777777785e-06,
443
+ "loss": 20.7548,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 0.25933930225378204,
448
+ "grad_norm": 27.88387397100189,
449
+ "learning_rate": 6.9888888888888895e-06,
450
+ "loss": 20.6822,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 0.26345579911495315,
455
+ "grad_norm": 31.290911839762394,
456
+ "learning_rate": 7.100000000000001e-06,
457
+ "loss": 20.5884,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 0.2675722959761243,
462
+ "grad_norm": 24.27245501884365,
463
+ "learning_rate": 7.211111111111112e-06,
464
+ "loss": 20.5162,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 0.27168879283729547,
469
+ "grad_norm": 23.89703899570296,
470
+ "learning_rate": 7.322222222222223e-06,
471
+ "loss": 20.4592,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 0.2758052896984666,
476
+ "grad_norm": 57.249160956506614,
477
+ "learning_rate": 7.433333333333334e-06,
478
+ "loss": 20.3787,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 0.27992178655963773,
483
+ "grad_norm": 44.42291899504958,
484
+ "learning_rate": 7.544444444444445e-06,
485
+ "loss": 20.207,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 0.2840382834208089,
490
+ "grad_norm": 91.55863776649939,
491
+ "learning_rate": 7.655555555555556e-06,
492
+ "loss": 20.143,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 0.28815478028198005,
497
+ "grad_norm": 57.092128520356646,
498
+ "learning_rate": 7.766666666666666e-06,
499
+ "loss": 19.9418,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 0.29227127714315115,
504
+ "grad_norm": 37.42956925364744,
505
+ "learning_rate": 7.877777777777778e-06,
506
+ "loss": 19.6662,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 0.2963877740043223,
511
+ "grad_norm": 24.54779334825758,
512
+ "learning_rate": 7.98888888888889e-06,
513
+ "loss": 19.4289,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 0.3005042708654935,
518
+ "grad_norm": 20.193177185866038,
519
+ "learning_rate": 8.1e-06,
520
+ "loss": 19.2373,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 0.30462076772666463,
525
+ "grad_norm": 60.48422812921962,
526
+ "learning_rate": 8.211111111111112e-06,
527
+ "loss": 19.173,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 0.30873726458783574,
532
+ "grad_norm": 27.558098824852753,
533
+ "learning_rate": 8.322222222222223e-06,
534
+ "loss": 18.9043,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 0.3128537614490069,
539
+ "grad_norm": 29.51167246824426,
540
+ "learning_rate": 8.433333333333334e-06,
541
+ "loss": 18.6651,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 0.31697025831017805,
546
+ "grad_norm": 21.93310893699215,
547
+ "learning_rate": 8.544444444444445e-06,
548
+ "loss": 18.4818,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 0.32108675517134916,
553
+ "grad_norm": 51.99252088836799,
554
+ "learning_rate": 8.655555555555557e-06,
555
+ "loss": 18.4864,
556
+ "step": 780
557
+ },
558
+ {
559
+ "epoch": 0.3252032520325203,
560
+ "grad_norm": 35.01362198000449,
561
+ "learning_rate": 8.766666666666669e-06,
562
+ "loss": 18.205,
563
+ "step": 790
564
+ },
565
+ {
566
+ "epoch": 0.3293197488936915,
567
+ "grad_norm": 30.09623662803406,
568
+ "learning_rate": 8.877777777777779e-06,
569
+ "loss": 18.0342,
570
+ "step": 800
571
+ },
572
+ {
573
+ "epoch": 0.33343624575486264,
574
+ "grad_norm": 55.16314161967726,
575
+ "learning_rate": 8.988888888888889e-06,
576
+ "loss": 17.8646,
577
+ "step": 810
578
+ },
579
+ {
580
+ "epoch": 0.33755274261603374,
581
+ "grad_norm": 33.375878351461154,
582
+ "learning_rate": 9.100000000000001e-06,
583
+ "loss": 17.6275,
584
+ "step": 820
585
+ },
586
+ {
587
+ "epoch": 0.3416692394772049,
588
+ "grad_norm": 27.20030408565347,
589
+ "learning_rate": 9.211111111111111e-06,
590
+ "loss": 17.53,
591
+ "step": 830
592
+ },
593
+ {
594
+ "epoch": 0.34578573633837606,
595
+ "grad_norm": 44.94165316928541,
596
+ "learning_rate": 9.322222222222223e-06,
597
+ "loss": 17.4118,
598
+ "step": 840
599
+ },
600
+ {
601
+ "epoch": 0.34990223319954716,
602
+ "grad_norm": 51.21107811701123,
603
+ "learning_rate": 9.433333333333335e-06,
604
+ "loss": 17.2221,
605
+ "step": 850
606
+ },
607
+ {
608
+ "epoch": 0.3540187300607183,
609
+ "grad_norm": 48.69081492082153,
610
+ "learning_rate": 9.544444444444445e-06,
611
+ "loss": 17.0648,
612
+ "step": 860
613
+ },
614
+ {
615
+ "epoch": 0.3581352269218895,
616
+ "grad_norm": 59.568062971869644,
617
+ "learning_rate": 9.655555555555556e-06,
618
+ "loss": 16.9709,
619
+ "step": 870
620
+ },
621
+ {
622
+ "epoch": 0.36225172378306064,
623
+ "grad_norm": 48.20595634997982,
624
+ "learning_rate": 9.766666666666667e-06,
625
+ "loss": 16.7922,
626
+ "step": 880
627
+ },
628
+ {
629
+ "epoch": 0.36636822064423175,
630
+ "grad_norm": 38.89100659846126,
631
+ "learning_rate": 9.877777777777778e-06,
632
+ "loss": 16.5606,
633
+ "step": 890
634
+ },
635
+ {
636
+ "epoch": 0.3704847175054029,
637
+ "grad_norm": 55.476242446929724,
638
+ "learning_rate": 9.98888888888889e-06,
639
+ "loss": 16.5196,
640
+ "step": 900
641
+ },
642
+ {
643
+ "epoch": 0.37460121436657406,
644
+ "grad_norm": 33.8871713799869,
645
+ "learning_rate": 9.996907216494847e-06,
646
+ "loss": 16.2859,
647
+ "step": 910
648
+ },
649
+ {
650
+ "epoch": 0.37871771122774517,
651
+ "grad_norm": 48.67199287721736,
652
+ "learning_rate": 9.993470790378008e-06,
653
+ "loss": 16.1253,
654
+ "step": 920
655
+ },
656
+ {
657
+ "epoch": 0.38283420808891633,
658
+ "grad_norm": 53.10677273121955,
659
+ "learning_rate": 9.99003436426117e-06,
660
+ "loss": 16.1184,
661
+ "step": 930
662
+ },
663
+ {
664
+ "epoch": 0.3869507049500875,
665
+ "grad_norm": 36.47115886963749,
666
+ "learning_rate": 9.986597938144331e-06,
667
+ "loss": 15.8454,
668
+ "step": 940
669
+ },
670
+ {
671
+ "epoch": 0.3910672018112586,
672
+ "grad_norm": 46.9950180770148,
673
+ "learning_rate": 9.983161512027493e-06,
674
+ "loss": 15.7934,
675
+ "step": 950
676
+ },
677
+ {
678
+ "epoch": 0.39518369867242975,
679
+ "grad_norm": 41.780425293570616,
680
+ "learning_rate": 9.979725085910654e-06,
681
+ "loss": 15.7013,
682
+ "step": 960
683
+ },
684
+ {
685
+ "epoch": 0.3993001955336009,
686
+ "grad_norm": 61.01443519953337,
687
+ "learning_rate": 9.976288659793816e-06,
688
+ "loss": 15.5447,
689
+ "step": 970
690
+ },
691
+ {
692
+ "epoch": 0.40341669239477207,
693
+ "grad_norm": 37.005722827889784,
694
+ "learning_rate": 9.972852233676977e-06,
695
+ "loss": 15.4402,
696
+ "step": 980
697
+ },
698
+ {
699
+ "epoch": 0.4075331892559432,
700
+ "grad_norm": 34.50549181078069,
701
+ "learning_rate": 9.969415807560139e-06,
702
+ "loss": 15.3771,
703
+ "step": 990
704
+ },
705
+ {
706
+ "epoch": 0.41164968611711433,
707
+ "grad_norm": 43.56802220640922,
708
+ "learning_rate": 9.965979381443299e-06,
709
+ "loss": 15.1859,
710
+ "step": 1000
711
+ },
712
+ {
713
+ "epoch": 0.4157661829782855,
714
+ "grad_norm": 44.27192419759802,
715
+ "learning_rate": 9.96254295532646e-06,
716
+ "loss": 15.1377,
717
+ "step": 1010
718
+ },
719
+ {
720
+ "epoch": 0.4198826798394566,
721
+ "grad_norm": 54.39835842981886,
722
+ "learning_rate": 9.959106529209622e-06,
723
+ "loss": 15.0264,
724
+ "step": 1020
725
+ },
726
+ {
727
+ "epoch": 0.42399917670062776,
728
+ "grad_norm": 39.41791238776903,
729
+ "learning_rate": 9.955670103092783e-06,
730
+ "loss": 14.9343,
731
+ "step": 1030
732
+ },
733
+ {
734
+ "epoch": 0.4281156735617989,
735
+ "grad_norm": 33.82937492863744,
736
+ "learning_rate": 9.952233676975945e-06,
737
+ "loss": 14.7589,
738
+ "step": 1040
739
+ },
740
+ {
741
+ "epoch": 0.4322321704229701,
742
+ "grad_norm": 40.479975837330905,
743
+ "learning_rate": 9.948797250859106e-06,
744
+ "loss": 14.6838,
745
+ "step": 1050
746
+ },
747
+ {
748
+ "epoch": 0.4363486672841412,
749
+ "grad_norm": 49.56506719825334,
750
+ "learning_rate": 9.945360824742268e-06,
751
+ "loss": 14.5806,
752
+ "step": 1060
753
+ },
754
+ {
755
+ "epoch": 0.44046516414531234,
756
+ "grad_norm": 43.92728436690805,
757
+ "learning_rate": 9.94192439862543e-06,
758
+ "loss": 14.5519,
759
+ "step": 1070
760
+ },
761
+ {
762
+ "epoch": 0.4445816610064835,
763
+ "grad_norm": 38.083124431784405,
764
+ "learning_rate": 9.938487972508592e-06,
765
+ "loss": 14.4566,
766
+ "step": 1080
767
+ },
768
+ {
769
+ "epoch": 0.4486981578676546,
770
+ "grad_norm": 40.83368623786197,
771
+ "learning_rate": 9.935051546391754e-06,
772
+ "loss": 14.4637,
773
+ "step": 1090
774
+ },
775
+ {
776
+ "epoch": 0.45281465472882576,
777
+ "grad_norm": 39.888961137074325,
778
+ "learning_rate": 9.931615120274915e-06,
779
+ "loss": 14.2926,
780
+ "step": 1100
781
+ },
782
+ {
783
+ "epoch": 0.4569311515899969,
784
+ "grad_norm": 52.98917099950452,
785
+ "learning_rate": 9.928178694158077e-06,
786
+ "loss": 14.2284,
787
+ "step": 1110
788
+ },
789
+ {
790
+ "epoch": 0.4610476484511681,
791
+ "grad_norm": 39.86769855717651,
792
+ "learning_rate": 9.924742268041238e-06,
793
+ "loss": 14.1538,
794
+ "step": 1120
795
+ },
796
+ {
797
+ "epoch": 0.4651641453123392,
798
+ "grad_norm": 41.47546966771517,
799
+ "learning_rate": 9.9213058419244e-06,
800
+ "loss": 14.1268,
801
+ "step": 1130
802
+ },
803
+ {
804
+ "epoch": 0.46928064217351034,
805
+ "grad_norm": 43.66832808351295,
806
+ "learning_rate": 9.917869415807561e-06,
807
+ "loss": 14.0239,
808
+ "step": 1140
809
+ },
810
+ {
811
+ "epoch": 0.4733971390346815,
812
+ "grad_norm": 38.15090916854303,
813
+ "learning_rate": 9.914432989690723e-06,
814
+ "loss": 13.9388,
815
+ "step": 1150
816
+ },
817
+ {
818
+ "epoch": 0.4775136358958526,
819
+ "grad_norm": 34.56956210917117,
820
+ "learning_rate": 9.910996563573884e-06,
821
+ "loss": 13.911,
822
+ "step": 1160
823
+ },
824
+ {
825
+ "epoch": 0.48163013275702377,
826
+ "grad_norm": 33.31934413400173,
827
+ "learning_rate": 9.907560137457046e-06,
828
+ "loss": 13.8416,
829
+ "step": 1170
830
+ },
831
+ {
832
+ "epoch": 0.4857466296181949,
833
+ "grad_norm": 37.93411062451452,
834
+ "learning_rate": 9.904123711340207e-06,
835
+ "loss": 13.8095,
836
+ "step": 1180
837
+ },
838
+ {
839
+ "epoch": 0.4898631264793661,
840
+ "grad_norm": 38.20924261082129,
841
+ "learning_rate": 9.900687285223369e-06,
842
+ "loss": 13.7295,
843
+ "step": 1190
844
+ },
845
+ {
846
+ "epoch": 0.4939796233405372,
847
+ "grad_norm": 53.63569573152946,
848
+ "learning_rate": 9.89725085910653e-06,
849
+ "loss": 13.6506,
850
+ "step": 1200
851
+ },
852
+ {
853
+ "epoch": 0.49809612020170835,
854
+ "grad_norm": 43.14530877212232,
855
+ "learning_rate": 9.893814432989692e-06,
856
+ "loss": 13.6186,
857
+ "step": 1210
858
+ },
859
+ {
860
+ "epoch": 0.5022126170628795,
861
+ "grad_norm": 49.03916689519157,
862
+ "learning_rate": 9.890378006872853e-06,
863
+ "loss": 13.6416,
864
+ "step": 1220
865
+ },
866
+ {
867
+ "epoch": 0.5063291139240507,
868
+ "grad_norm": 36.49026973775023,
869
+ "learning_rate": 9.886941580756015e-06,
870
+ "loss": 13.574,
871
+ "step": 1230
872
+ },
873
+ {
874
+ "epoch": 0.5104456107852218,
875
+ "grad_norm": 32.76071554080421,
876
+ "learning_rate": 9.883505154639176e-06,
877
+ "loss": 13.4854,
878
+ "step": 1240
879
+ },
880
+ {
881
+ "epoch": 0.5145621076463929,
882
+ "grad_norm": 36.789924557345806,
883
+ "learning_rate": 9.880068728522338e-06,
884
+ "loss": 13.3827,
885
+ "step": 1250
886
+ },
887
+ {
888
+ "epoch": 0.5186786045075641,
889
+ "grad_norm": 28.079567041126435,
890
+ "learning_rate": 9.8766323024055e-06,
891
+ "loss": 13.3305,
892
+ "step": 1260
893
+ },
894
+ {
895
+ "epoch": 0.5227951013687352,
896
+ "grad_norm": 43.55514700081209,
897
+ "learning_rate": 9.87319587628866e-06,
898
+ "loss": 13.33,
899
+ "step": 1270
900
+ },
901
+ {
902
+ "epoch": 0.5269115982299063,
903
+ "grad_norm": 28.76115488681788,
904
+ "learning_rate": 9.869759450171822e-06,
905
+ "loss": 13.2651,
906
+ "step": 1280
907
+ },
908
+ {
909
+ "epoch": 0.5310280950910775,
910
+ "grad_norm": 37.358128749691296,
911
+ "learning_rate": 9.866323024054984e-06,
912
+ "loss": 13.2312,
913
+ "step": 1290
914
+ },
915
+ {
916
+ "epoch": 0.5351445919522486,
917
+ "grad_norm": 44.992288758478345,
918
+ "learning_rate": 9.862886597938145e-06,
919
+ "loss": 13.1897,
920
+ "step": 1300
921
+ },
922
+ {
923
+ "epoch": 0.5392610888134198,
924
+ "grad_norm": 28.47379704494871,
925
+ "learning_rate": 9.859450171821307e-06,
926
+ "loss": 13.1063,
927
+ "step": 1310
928
+ },
929
+ {
930
+ "epoch": 0.5433775856745909,
931
+ "grad_norm": 31.796429799283633,
932
+ "learning_rate": 9.856013745704468e-06,
933
+ "loss": 13.0747,
934
+ "step": 1320
935
+ },
936
+ {
937
+ "epoch": 0.547494082535762,
938
+ "grad_norm": 39.38678551108492,
939
+ "learning_rate": 9.85257731958763e-06,
940
+ "loss": 13.0861,
941
+ "step": 1330
942
+ },
943
+ {
944
+ "epoch": 0.5516105793969333,
945
+ "grad_norm": 38.812099741482996,
946
+ "learning_rate": 9.849140893470791e-06,
947
+ "loss": 13.046,
948
+ "step": 1340
949
+ },
950
+ {
951
+ "epoch": 0.5557270762581044,
952
+ "grad_norm": 34.79929463071014,
953
+ "learning_rate": 9.845704467353953e-06,
954
+ "loss": 13.0339,
955
+ "step": 1350
956
+ },
957
+ {
958
+ "epoch": 0.5598435731192755,
959
+ "grad_norm": 36.095752723061416,
960
+ "learning_rate": 9.842268041237114e-06,
961
+ "loss": 12.9433,
962
+ "step": 1360
963
+ },
964
+ {
965
+ "epoch": 0.5639600699804467,
966
+ "grad_norm": 36.27956418944883,
967
+ "learning_rate": 9.838831615120276e-06,
968
+ "loss": 12.907,
969
+ "step": 1370
970
+ },
971
+ {
972
+ "epoch": 0.5680765668416178,
973
+ "grad_norm": 35.72628600227518,
974
+ "learning_rate": 9.835395189003437e-06,
975
+ "loss": 12.91,
976
+ "step": 1380
977
+ },
978
+ {
979
+ "epoch": 0.5721930637027889,
980
+ "grad_norm": 36.2974491311879,
981
+ "learning_rate": 9.831958762886599e-06,
982
+ "loss": 12.8805,
983
+ "step": 1390
984
+ },
985
+ {
986
+ "epoch": 0.5763095605639601,
987
+ "grad_norm": 38.753865801889205,
988
+ "learning_rate": 9.82852233676976e-06,
989
+ "loss": 12.8487,
990
+ "step": 1400
991
+ },
992
+ {
993
+ "epoch": 0.5804260574251312,
994
+ "grad_norm": 37.15806127726735,
995
+ "learning_rate": 9.825085910652922e-06,
996
+ "loss": 12.8255,
997
+ "step": 1410
998
+ },
999
+ {
1000
+ "epoch": 0.5845425542863023,
1001
+ "grad_norm": 31.930169790036125,
1002
+ "learning_rate": 9.821649484536083e-06,
1003
+ "loss": 12.7318,
1004
+ "step": 1420
1005
+ },
1006
+ {
1007
+ "epoch": 0.5886590511474735,
1008
+ "grad_norm": 46.704762225618985,
1009
+ "learning_rate": 9.818213058419245e-06,
1010
+ "loss": 12.8322,
1011
+ "step": 1430
1012
+ },
1013
+ {
1014
+ "epoch": 0.5927755480086446,
1015
+ "grad_norm": 33.776587810887825,
1016
+ "learning_rate": 9.814776632302406e-06,
1017
+ "loss": 12.7815,
1018
+ "step": 1440
1019
+ },
1020
+ {
1021
+ "epoch": 0.5968920448698158,
1022
+ "grad_norm": 29.58229351266127,
1023
+ "learning_rate": 9.811340206185568e-06,
1024
+ "loss": 12.7486,
1025
+ "step": 1450
1026
+ },
1027
+ {
1028
+ "epoch": 0.601008541730987,
1029
+ "grad_norm": 33.63398991455025,
1030
+ "learning_rate": 9.80790378006873e-06,
1031
+ "loss": 12.6896,
1032
+ "step": 1460
1033
+ },
1034
+ {
1035
+ "epoch": 0.605125038592158,
1036
+ "grad_norm": 36.832689858066715,
1037
+ "learning_rate": 9.804467353951891e-06,
1038
+ "loss": 12.6699,
1039
+ "step": 1470
1040
+ },
1041
+ {
1042
+ "epoch": 0.6092415354533293,
1043
+ "grad_norm": 37.43208595185383,
1044
+ "learning_rate": 9.801030927835052e-06,
1045
+ "loss": 12.5471,
1046
+ "step": 1480
1047
+ },
1048
+ {
1049
+ "epoch": 0.6133580323145004,
1050
+ "grad_norm": 33.7941307098917,
1051
+ "learning_rate": 9.797594501718214e-06,
1052
+ "loss": 12.6142,
1053
+ "step": 1490
1054
+ },
1055
+ {
1056
+ "epoch": 0.6174745291756715,
1057
+ "grad_norm": 31.9466158932975,
1058
+ "learning_rate": 9.794158075601375e-06,
1059
+ "loss": 12.5338,
1060
+ "step": 1500
1061
+ },
1062
+ {
1063
+ "epoch": 0.6215910260368427,
1064
+ "grad_norm": 38.30578087105521,
1065
+ "learning_rate": 9.790721649484537e-06,
1066
+ "loss": 12.4764,
1067
+ "step": 1510
1068
+ },
1069
+ {
1070
+ "epoch": 0.6257075228980138,
1071
+ "grad_norm": 32.61697454595358,
1072
+ "learning_rate": 9.787285223367698e-06,
1073
+ "loss": 12.4952,
1074
+ "step": 1520
1075
+ },
1076
+ {
1077
+ "epoch": 0.6298240197591849,
1078
+ "grad_norm": 40.16758133155219,
1079
+ "learning_rate": 9.78384879725086e-06,
1080
+ "loss": 12.4546,
1081
+ "step": 1530
1082
+ },
1083
+ {
1084
+ "epoch": 0.6339405166203561,
1085
+ "grad_norm": 48.80638115137875,
1086
+ "learning_rate": 9.780412371134021e-06,
1087
+ "loss": 12.4843,
1088
+ "step": 1540
1089
+ },
1090
+ {
1091
+ "epoch": 0.6380570134815272,
1092
+ "grad_norm": 37.475171347455756,
1093
+ "learning_rate": 9.776975945017183e-06,
1094
+ "loss": 12.4931,
1095
+ "step": 1550
1096
+ },
1097
+ {
1098
+ "epoch": 0.6421735103426983,
1099
+ "grad_norm": 33.28595513208406,
1100
+ "learning_rate": 9.773539518900344e-06,
1101
+ "loss": 12.4005,
1102
+ "step": 1560
1103
+ },
1104
+ {
1105
+ "epoch": 0.6462900072038695,
1106
+ "grad_norm": 31.086866920620285,
1107
+ "learning_rate": 9.770103092783506e-06,
1108
+ "loss": 12.3441,
1109
+ "step": 1570
1110
+ },
1111
+ {
1112
+ "epoch": 0.6504065040650406,
1113
+ "grad_norm": 39.3394583771368,
1114
+ "learning_rate": 9.766666666666667e-06,
1115
+ "loss": 12.2734,
1116
+ "step": 1580
1117
+ },
1118
+ {
1119
+ "epoch": 0.6545230009262117,
1120
+ "grad_norm": 32.802912711135214,
1121
+ "learning_rate": 9.763230240549829e-06,
1122
+ "loss": 12.3482,
1123
+ "step": 1590
1124
+ },
1125
+ {
1126
+ "epoch": 0.658639497787383,
1127
+ "grad_norm": 37.29399518826948,
1128
+ "learning_rate": 9.75979381443299e-06,
1129
+ "loss": 12.3565,
1130
+ "step": 1600
1131
+ },
1132
+ {
1133
+ "epoch": 0.6627559946485541,
1134
+ "grad_norm": 31.346208761120682,
1135
+ "learning_rate": 9.756357388316152e-06,
1136
+ "loss": 12.2918,
1137
+ "step": 1610
1138
+ },
1139
+ {
1140
+ "epoch": 0.6668724915097253,
1141
+ "grad_norm": 32.38506378128921,
1142
+ "learning_rate": 9.752920962199313e-06,
1143
+ "loss": 12.2984,
1144
+ "step": 1620
1145
+ },
1146
+ {
1147
+ "epoch": 0.6709889883708964,
1148
+ "grad_norm": 37.55618381493301,
1149
+ "learning_rate": 9.749484536082475e-06,
1150
+ "loss": 12.2223,
1151
+ "step": 1630
1152
+ },
1153
+ {
1154
+ "epoch": 0.6751054852320675,
1155
+ "grad_norm": 30.159408332251935,
1156
+ "learning_rate": 9.746048109965636e-06,
1157
+ "loss": 12.2059,
1158
+ "step": 1640
1159
+ },
1160
+ {
1161
+ "epoch": 0.6792219820932387,
1162
+ "grad_norm": 33.64269413817189,
1163
+ "learning_rate": 9.742611683848798e-06,
1164
+ "loss": 12.1934,
1165
+ "step": 1650
1166
+ },
1167
+ {
1168
+ "epoch": 0.6833384789544098,
1169
+ "grad_norm": 33.350706787266056,
1170
+ "learning_rate": 9.73917525773196e-06,
1171
+ "loss": 12.2187,
1172
+ "step": 1660
1173
+ },
1174
+ {
1175
+ "epoch": 0.6874549758155809,
1176
+ "grad_norm": 33.39405862288003,
1177
+ "learning_rate": 9.735738831615121e-06,
1178
+ "loss": 12.163,
1179
+ "step": 1670
1180
+ },
1181
+ {
1182
+ "epoch": 0.6915714726767521,
1183
+ "grad_norm": 33.41635090076034,
1184
+ "learning_rate": 9.732302405498283e-06,
1185
+ "loss": 12.1662,
1186
+ "step": 1680
1187
+ },
1188
+ {
1189
+ "epoch": 0.6956879695379232,
1190
+ "grad_norm": 30.14281470411853,
1191
+ "learning_rate": 9.728865979381444e-06,
1192
+ "loss": 12.2065,
1193
+ "step": 1690
1194
+ },
1195
+ {
1196
+ "epoch": 0.6998044663990943,
1197
+ "grad_norm": 30.467396684661566,
1198
+ "learning_rate": 9.725429553264606e-06,
1199
+ "loss": 12.1291,
1200
+ "step": 1700
1201
+ },
1202
+ {
1203
+ "epoch": 0.7039209632602655,
1204
+ "grad_norm": 30.441530111439768,
1205
+ "learning_rate": 9.721993127147767e-06,
1206
+ "loss": 12.0492,
1207
+ "step": 1710
1208
+ },
1209
+ {
1210
+ "epoch": 0.7080374601214366,
1211
+ "grad_norm": 28.49347966966388,
1212
+ "learning_rate": 9.718556701030929e-06,
1213
+ "loss": 12.0813,
1214
+ "step": 1720
1215
+ },
1216
+ {
1217
+ "epoch": 0.7121539569826077,
1218
+ "grad_norm": 30.721181306779684,
1219
+ "learning_rate": 9.71512027491409e-06,
1220
+ "loss": 12.0821,
1221
+ "step": 1730
1222
+ },
1223
+ {
1224
+ "epoch": 0.716270453843779,
1225
+ "grad_norm": 29.129251982891667,
1226
+ "learning_rate": 9.711683848797252e-06,
1227
+ "loss": 12.0637,
1228
+ "step": 1740
1229
+ },
1230
+ {
1231
+ "epoch": 0.7203869507049501,
1232
+ "grad_norm": 29.95019721435932,
1233
+ "learning_rate": 9.708247422680413e-06,
1234
+ "loss": 11.9994,
1235
+ "step": 1750
1236
+ },
1237
+ {
1238
+ "epoch": 0.7245034475661213,
1239
+ "grad_norm": 32.81918337349151,
1240
+ "learning_rate": 9.704810996563575e-06,
1241
+ "loss": 12.024,
1242
+ "step": 1760
1243
+ },
1244
+ {
1245
+ "epoch": 0.7286199444272924,
1246
+ "grad_norm": 39.5144099446638,
1247
+ "learning_rate": 9.701374570446736e-06,
1248
+ "loss": 12.0285,
1249
+ "step": 1770
1250
+ },
1251
+ {
1252
+ "epoch": 0.7327364412884635,
1253
+ "grad_norm": 31.653909615694747,
1254
+ "learning_rate": 9.697938144329898e-06,
1255
+ "loss": 11.9479,
1256
+ "step": 1780
1257
+ },
1258
+ {
1259
+ "epoch": 0.7368529381496347,
1260
+ "grad_norm": 33.40571679023385,
1261
+ "learning_rate": 9.694501718213059e-06,
1262
+ "loss": 11.9523,
1263
+ "step": 1790
1264
+ },
1265
+ {
1266
+ "epoch": 0.7409694350108058,
1267
+ "grad_norm": 37.473942426771224,
1268
+ "learning_rate": 9.69106529209622e-06,
1269
+ "loss": 11.9416,
1270
+ "step": 1800
1271
+ },
1272
+ {
1273
+ "epoch": 0.7450859318719769,
1274
+ "grad_norm": 36.94155127706317,
1275
+ "learning_rate": 9.687628865979382e-06,
1276
+ "loss": 12.0463,
1277
+ "step": 1810
1278
+ },
1279
+ {
1280
+ "epoch": 0.7492024287331481,
1281
+ "grad_norm": 37.68814388273857,
1282
+ "learning_rate": 9.684192439862544e-06,
1283
+ "loss": 11.8785,
1284
+ "step": 1820
1285
+ },
1286
+ {
1287
+ "epoch": 0.7533189255943192,
1288
+ "grad_norm": 28.366410820050916,
1289
+ "learning_rate": 9.680756013745705e-06,
1290
+ "loss": 11.8984,
1291
+ "step": 1830
1292
+ },
1293
+ {
1294
+ "epoch": 0.7574354224554903,
1295
+ "grad_norm": 32.286183742630165,
1296
+ "learning_rate": 9.677319587628867e-06,
1297
+ "loss": 11.7795,
1298
+ "step": 1840
1299
+ },
1300
+ {
1301
+ "epoch": 0.7615519193166616,
1302
+ "grad_norm": 34.20137530626946,
1303
+ "learning_rate": 9.673883161512028e-06,
1304
+ "loss": 11.7833,
1305
+ "step": 1850
1306
+ },
1307
+ {
1308
+ "epoch": 0.7656684161778327,
1309
+ "grad_norm": 26.974205102100083,
1310
+ "learning_rate": 9.67044673539519e-06,
1311
+ "loss": 11.8231,
1312
+ "step": 1860
1313
+ },
1314
+ {
1315
+ "epoch": 0.7697849130390038,
1316
+ "grad_norm": 30.78227640084708,
1317
+ "learning_rate": 9.667010309278351e-06,
1318
+ "loss": 11.839,
1319
+ "step": 1870
1320
+ },
1321
+ {
1322
+ "epoch": 0.773901409900175,
1323
+ "grad_norm": 32.775223259236476,
1324
+ "learning_rate": 9.663573883161513e-06,
1325
+ "loss": 11.7576,
1326
+ "step": 1880
1327
+ },
1328
+ {
1329
+ "epoch": 0.7780179067613461,
1330
+ "grad_norm": 32.09910452344205,
1331
+ "learning_rate": 9.660137457044674e-06,
1332
+ "loss": 11.8203,
1333
+ "step": 1890
1334
+ },
1335
+ {
1336
+ "epoch": 0.7821344036225172,
1337
+ "grad_norm": 34.679912416674696,
1338
+ "learning_rate": 9.656701030927836e-06,
1339
+ "loss": 11.7395,
1340
+ "step": 1900
1341
+ },
1342
+ {
1343
+ "epoch": 0.7862509004836884,
1344
+ "grad_norm": 41.08474046950697,
1345
+ "learning_rate": 9.653264604810997e-06,
1346
+ "loss": 11.7656,
1347
+ "step": 1910
1348
+ },
1349
+ {
1350
+ "epoch": 0.7903673973448595,
1351
+ "grad_norm": 43.79171589552821,
1352
+ "learning_rate": 9.649828178694159e-06,
1353
+ "loss": 11.7157,
1354
+ "step": 1920
1355
+ },
1356
+ {
1357
+ "epoch": 0.7944838942060307,
1358
+ "grad_norm": 32.06890784949689,
1359
+ "learning_rate": 9.64639175257732e-06,
1360
+ "loss": 11.7633,
1361
+ "step": 1930
1362
+ },
1363
+ {
1364
+ "epoch": 0.7986003910672018,
1365
+ "grad_norm": 33.88840596948513,
1366
+ "learning_rate": 9.642955326460482e-06,
1367
+ "loss": 11.7696,
1368
+ "step": 1940
1369
+ },
1370
+ {
1371
+ "epoch": 0.8027168879283729,
1372
+ "grad_norm": 43.3525380610554,
1373
+ "learning_rate": 9.639518900343643e-06,
1374
+ "loss": 11.6768,
1375
+ "step": 1950
1376
+ },
1377
+ {
1378
+ "epoch": 0.8068333847895441,
1379
+ "grad_norm": 29.03141895521922,
1380
+ "learning_rate": 9.636082474226805e-06,
1381
+ "loss": 11.6438,
1382
+ "step": 1960
1383
+ },
1384
+ {
1385
+ "epoch": 0.8109498816507152,
1386
+ "grad_norm": 31.577350376305315,
1387
+ "learning_rate": 9.632646048109966e-06,
1388
+ "loss": 11.648,
1389
+ "step": 1970
1390
+ },
1391
+ {
1392
+ "epoch": 0.8150663785118863,
1393
+ "grad_norm": 29.395462355828993,
1394
+ "learning_rate": 9.629209621993128e-06,
1395
+ "loss": 11.5621,
1396
+ "step": 1980
1397
+ },
1398
+ {
1399
+ "epoch": 0.8191828753730576,
1400
+ "grad_norm": 36.070659840431695,
1401
+ "learning_rate": 9.625773195876289e-06,
1402
+ "loss": 11.6605,
1403
+ "step": 1990
1404
+ },
1405
+ {
1406
+ "epoch": 0.8232993722342287,
1407
+ "grad_norm": 40.63936989861702,
1408
+ "learning_rate": 9.62233676975945e-06,
1409
+ "loss": 11.6847,
1410
+ "step": 2000
1411
+ },
1412
+ {
1413
+ "epoch": 0.8274158690953998,
1414
+ "grad_norm": 28.74096555707873,
1415
+ "learning_rate": 9.618900343642612e-06,
1416
+ "loss": 11.5951,
1417
+ "step": 2010
1418
+ },
1419
+ {
1420
+ "epoch": 0.831532365956571,
1421
+ "grad_norm": 26.857379564051325,
1422
+ "learning_rate": 9.615463917525774e-06,
1423
+ "loss": 11.5425,
1424
+ "step": 2020
1425
+ },
1426
+ {
1427
+ "epoch": 0.8356488628177421,
1428
+ "grad_norm": 34.26526481929795,
1429
+ "learning_rate": 9.612027491408935e-06,
1430
+ "loss": 11.5395,
1431
+ "step": 2030
1432
+ },
1433
+ {
1434
+ "epoch": 0.8397653596789132,
1435
+ "grad_norm": 39.61591003341877,
1436
+ "learning_rate": 9.608591065292097e-06,
1437
+ "loss": 11.5239,
1438
+ "step": 2040
1439
+ },
1440
+ {
1441
+ "epoch": 0.8438818565400844,
1442
+ "grad_norm": 32.799457497612636,
1443
+ "learning_rate": 9.605154639175258e-06,
1444
+ "loss": 11.5221,
1445
+ "step": 2050
1446
+ },
1447
+ {
1448
+ "epoch": 0.8479983534012555,
1449
+ "grad_norm": 30.46702989419665,
1450
+ "learning_rate": 9.60171821305842e-06,
1451
+ "loss": 11.5188,
1452
+ "step": 2060
1453
+ },
1454
+ {
1455
+ "epoch": 0.8521148502624267,
1456
+ "grad_norm": 36.16227939472805,
1457
+ "learning_rate": 9.598281786941581e-06,
1458
+ "loss": 11.5045,
1459
+ "step": 2070
1460
+ },
1461
+ {
1462
+ "epoch": 0.8562313471235978,
1463
+ "grad_norm": 35.47038057679002,
1464
+ "learning_rate": 9.594845360824743e-06,
1465
+ "loss": 11.5307,
1466
+ "step": 2080
1467
+ },
1468
+ {
1469
+ "epoch": 0.8603478439847689,
1470
+ "grad_norm": 32.257372818520146,
1471
+ "learning_rate": 9.591408934707904e-06,
1472
+ "loss": 11.523,
1473
+ "step": 2090
1474
+ },
1475
+ {
1476
+ "epoch": 0.8644643408459401,
1477
+ "grad_norm": 29.92970511160102,
1478
+ "learning_rate": 9.587972508591066e-06,
1479
+ "loss": 11.5006,
1480
+ "step": 2100
1481
+ },
1482
+ {
1483
+ "epoch": 0.8685808377071113,
1484
+ "grad_norm": 31.548453221760763,
1485
+ "learning_rate": 9.584536082474227e-06,
1486
+ "loss": 11.4492,
1487
+ "step": 2110
1488
+ },
1489
+ {
1490
+ "epoch": 0.8726973345682824,
1491
+ "grad_norm": 34.57267127412313,
1492
+ "learning_rate": 9.581099656357389e-06,
1493
+ "loss": 11.4804,
1494
+ "step": 2120
1495
+ },
1496
+ {
1497
+ "epoch": 0.8768138314294536,
1498
+ "grad_norm": 34.17219698271619,
1499
+ "learning_rate": 9.57766323024055e-06,
1500
+ "loss": 11.4529,
1501
+ "step": 2130
1502
+ },
1503
+ {
1504
+ "epoch": 0.8809303282906247,
1505
+ "grad_norm": 29.479641794210973,
1506
+ "learning_rate": 9.574226804123712e-06,
1507
+ "loss": 11.3922,
1508
+ "step": 2140
1509
+ },
1510
+ {
1511
+ "epoch": 0.8850468251517958,
1512
+ "grad_norm": 32.38400767680429,
1513
+ "learning_rate": 9.570790378006873e-06,
1514
+ "loss": 11.394,
1515
+ "step": 2150
1516
+ },
1517
+ {
1518
+ "epoch": 0.889163322012967,
1519
+ "grad_norm": 32.32981900594448,
1520
+ "learning_rate": 9.567353951890035e-06,
1521
+ "loss": 11.3841,
1522
+ "step": 2160
1523
+ },
1524
+ {
1525
+ "epoch": 0.8932798188741381,
1526
+ "grad_norm": 33.61678562259265,
1527
+ "learning_rate": 9.563917525773196e-06,
1528
+ "loss": 11.3688,
1529
+ "step": 2170
1530
+ },
1531
+ {
1532
+ "epoch": 0.8973963157353092,
1533
+ "grad_norm": 32.71587409986399,
1534
+ "learning_rate": 9.560481099656358e-06,
1535
+ "loss": 11.3808,
1536
+ "step": 2180
1537
+ },
1538
+ {
1539
+ "epoch": 0.9015128125964804,
1540
+ "grad_norm": 29.54893232627574,
1541
+ "learning_rate": 9.55704467353952e-06,
1542
+ "loss": 11.3336,
1543
+ "step": 2190
1544
+ },
1545
+ {
1546
+ "epoch": 0.9056293094576515,
1547
+ "grad_norm": 32.06137522253644,
1548
+ "learning_rate": 9.55360824742268e-06,
1549
+ "loss": 11.3034,
1550
+ "step": 2200
1551
+ },
1552
+ {
1553
+ "epoch": 0.9097458063188227,
1554
+ "grad_norm": 36.467602001920255,
1555
+ "learning_rate": 9.550171821305842e-06,
1556
+ "loss": 11.3092,
1557
+ "step": 2210
1558
+ },
1559
+ {
1560
+ "epoch": 0.9138623031799938,
1561
+ "grad_norm": 36.697441519061755,
1562
+ "learning_rate": 9.546735395189004e-06,
1563
+ "loss": 11.3535,
1564
+ "step": 2220
1565
+ },
1566
+ {
1567
+ "epoch": 0.9179788000411649,
1568
+ "grad_norm": 29.195704697132054,
1569
+ "learning_rate": 9.543298969072165e-06,
1570
+ "loss": 11.2906,
1571
+ "step": 2230
1572
+ },
1573
+ {
1574
+ "epoch": 0.9220952969023362,
1575
+ "grad_norm": 28.12150721519504,
1576
+ "learning_rate": 9.539862542955327e-06,
1577
+ "loss": 11.2277,
1578
+ "step": 2240
1579
+ },
1580
+ {
1581
+ "epoch": 0.9262117937635073,
1582
+ "grad_norm": 28.28187759539184,
1583
+ "learning_rate": 9.536426116838488e-06,
1584
+ "loss": 11.2413,
1585
+ "step": 2250
1586
+ },
1587
+ {
1588
+ "epoch": 0.9303282906246784,
1589
+ "grad_norm": 38.194498763414195,
1590
+ "learning_rate": 9.53298969072165e-06,
1591
+ "loss": 11.2062,
1592
+ "step": 2260
1593
+ },
1594
+ {
1595
+ "epoch": 0.9344447874858496,
1596
+ "grad_norm": 30.60316989712369,
1597
+ "learning_rate": 9.529553264604811e-06,
1598
+ "loss": 11.2868,
1599
+ "step": 2270
1600
+ },
1601
+ {
1602
+ "epoch": 0.9385612843470207,
1603
+ "grad_norm": 32.2566760579608,
1604
+ "learning_rate": 9.526116838487973e-06,
1605
+ "loss": 11.3455,
1606
+ "step": 2280
1607
+ },
1608
+ {
1609
+ "epoch": 0.9426777812081918,
1610
+ "grad_norm": 29.363121550952414,
1611
+ "learning_rate": 9.522680412371134e-06,
1612
+ "loss": 11.2271,
1613
+ "step": 2290
1614
+ },
1615
+ {
1616
+ "epoch": 0.946794278069363,
1617
+ "grad_norm": 34.44659489587604,
1618
+ "learning_rate": 9.519243986254296e-06,
1619
+ "loss": 11.2572,
1620
+ "step": 2300
1621
+ },
1622
+ {
1623
+ "epoch": 0.9509107749305341,
1624
+ "grad_norm": 38.421619327615275,
1625
+ "learning_rate": 9.515807560137457e-06,
1626
+ "loss": 11.2059,
1627
+ "step": 2310
1628
+ },
1629
+ {
1630
+ "epoch": 0.9550272717917052,
1631
+ "grad_norm": 28.45314623909409,
1632
+ "learning_rate": 9.512371134020619e-06,
1633
+ "loss": 11.2005,
1634
+ "step": 2320
1635
+ },
1636
+ {
1637
+ "epoch": 0.9591437686528764,
1638
+ "grad_norm": 33.71882176291607,
1639
+ "learning_rate": 9.50893470790378e-06,
1640
+ "loss": 11.1696,
1641
+ "step": 2330
1642
+ },
1643
+ {
1644
+ "epoch": 0.9632602655140475,
1645
+ "grad_norm": 40.284639005118564,
1646
+ "learning_rate": 9.505498281786942e-06,
1647
+ "loss": 11.1289,
1648
+ "step": 2340
1649
+ },
1650
+ {
1651
+ "epoch": 0.9673767623752186,
1652
+ "grad_norm": 29.578038874639823,
1653
+ "learning_rate": 9.502061855670103e-06,
1654
+ "loss": 11.1945,
1655
+ "step": 2350
1656
+ },
1657
+ {
1658
+ "epoch": 0.9714932592363899,
1659
+ "grad_norm": 30.78279090155006,
1660
+ "learning_rate": 9.498625429553265e-06,
1661
+ "loss": 11.1547,
1662
+ "step": 2360
1663
+ },
1664
+ {
1665
+ "epoch": 0.975609756097561,
1666
+ "grad_norm": 32.32491917371623,
1667
+ "learning_rate": 9.495189003436426e-06,
1668
+ "loss": 11.1499,
1669
+ "step": 2370
1670
+ },
1671
+ {
1672
+ "epoch": 0.9797262529587322,
1673
+ "grad_norm": 33.912601882090534,
1674
+ "learning_rate": 9.491752577319588e-06,
1675
+ "loss": 11.0843,
1676
+ "step": 2380
1677
+ },
1678
+ {
1679
+ "epoch": 0.9838427498199033,
1680
+ "grad_norm": 33.636974029662824,
1681
+ "learning_rate": 9.48831615120275e-06,
1682
+ "loss": 11.0857,
1683
+ "step": 2390
1684
+ },
1685
+ {
1686
+ "epoch": 0.9879592466810744,
1687
+ "grad_norm": 28.479925241415103,
1688
+ "learning_rate": 9.48487972508591e-06,
1689
+ "loss": 11.117,
1690
+ "step": 2400
1691
+ },
1692
+ {
1693
+ "epoch": 0.9920757435422456,
1694
+ "grad_norm": 32.19633310187057,
1695
+ "learning_rate": 9.481443298969072e-06,
1696
+ "loss": 11.1586,
1697
+ "step": 2410
1698
+ },
1699
+ {
1700
+ "epoch": 0.9961922404034167,
1701
+ "grad_norm": 30.24939985897427,
1702
+ "learning_rate": 9.478006872852234e-06,
1703
+ "loss": 11.0449,
1704
+ "step": 2420
1705
+ },
1706
+ {
1707
+ "epoch": 1.0,
1708
+ "grad_norm": 27.59918285796063,
1709
+ "learning_rate": 9.474570446735395e-06,
1710
+ "loss": 10.2576,
1711
+ "step": 2430
1712
+ },
1713
+ {
1714
+ "epoch": 1.004116496861171,
1715
+ "grad_norm": 29.145692709878713,
1716
+ "learning_rate": 9.471134020618557e-06,
1717
+ "loss": 10.9205,
1718
+ "step": 2440
1719
+ },
1720
+ {
1721
+ "epoch": 1.0082329937223422,
1722
+ "grad_norm": 34.22402623391047,
1723
+ "learning_rate": 9.467697594501718e-06,
1724
+ "loss": 10.8674,
1725
+ "step": 2450
1726
+ },
1727
+ {
1728
+ "epoch": 1.0123494905835135,
1729
+ "grad_norm": 31.116476736190727,
1730
+ "learning_rate": 9.46426116838488e-06,
1731
+ "loss": 10.9685,
1732
+ "step": 2460
1733
+ },
1734
+ {
1735
+ "epoch": 1.0164659874446846,
1736
+ "grad_norm": 31.010011036576245,
1737
+ "learning_rate": 9.460824742268041e-06,
1738
+ "loss": 10.8758,
1739
+ "step": 2470
1740
+ },
1741
+ {
1742
+ "epoch": 1.0205824843058557,
1743
+ "grad_norm": 33.554395898942225,
1744
+ "learning_rate": 9.457388316151203e-06,
1745
+ "loss": 10.8832,
1746
+ "step": 2480
1747
+ },
1748
+ {
1749
+ "epoch": 1.0246989811670268,
1750
+ "grad_norm": 33.7710211448291,
1751
+ "learning_rate": 9.453951890034366e-06,
1752
+ "loss": 10.8374,
1753
+ "step": 2490
1754
+ },
1755
+ {
1756
+ "epoch": 1.028815478028198,
1757
+ "grad_norm": 36.176567342791,
1758
+ "learning_rate": 9.450515463917528e-06,
1759
+ "loss": 10.8073,
1760
+ "step": 2500
1761
+ },
1762
+ {
1763
+ "epoch": 1.028815478028198,
1764
+ "eval_loss": 3.158303737640381,
1765
+ "eval_runtime": 3671.6298,
1766
+ "eval_samples_per_second": 149.924,
1767
+ "eval_steps_per_second": 0.293,
1768
+ "step": 2500
1769
+ }
1770
+ ],
1771
+ "logging_steps": 10,
1772
+ "max_steps": 30000,
1773
+ "num_input_tokens_seen": 0,
1774
+ "num_train_epochs": 13,
1775
+ "save_steps": 2500,
1776
+ "stateful_callbacks": {
1777
+ "TrainerControl": {
1778
+ "args": {
1779
+ "should_epoch_stop": false,
1780
+ "should_evaluate": false,
1781
+ "should_log": false,
1782
+ "should_save": true,
1783
+ "should_training_stop": false
1784
+ },
1785
+ "attributes": {}
1786
+ }
1787
+ },
1788
+ "total_flos": 3776084605665280.0,
1789
+ "train_batch_size": 32,
1790
+ "trial_name": null,
1791
+ "trial_params": null
1792
+ }
robotwin50_pi06_expert_train/checkpoint-2500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b40b7dd8164e7afb8abb6454c6811fe9fc57d912437b37070af11a8073b6640d
3
+ size 8081
robotwin50_pi06_expert_train/checkpoint-2500/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
robotwin50_pi06_expert_train/checkpoint-2500/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)
robotwin50_pi06_expert_train/run_config.json ADDED
@@ -0,0 +1,197 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "data_args": {
3
+ "base_interval": 2,
4
+ "camera_names": "cam_high",
5
+ "data_flatten": false,
6
+ "data_packing": false,
7
+ "dataset_use": "/mnt/bn/ic-vlm/zhufangqi/code/datasets/robotwin_50_lerobot/adjust_bottle/aloha-agilex_randomized_500,/mnt/bn/ic-vlm/zhufangqi/code/datasets/robotwin_50_lerobot/beat_block_hammer/aloha-agilex_randomized_500,/mnt/bn/ic-vlm/zhufangqi/code/datasets/robotwin_50_lerobot/blocks_ranking_rgb/aloha-agilex_randomized_500,/mnt/bn/ic-vlm/zhufangqi/code/datasets/robotwin_50_lerobot/blocks_ranking_size/aloha-agilex_randomized_500,/mnt/bn/ic-vlm/zhufangqi/code/datasets/robotwin_50_lerobot/click_alarmclock/aloha-agilex_randomized_500,/mnt/bn/ic-vlm/zhufangqi/code/datasets/robotwin_50_lerobot/click_bell/aloha-agilex_randomized_500,/mnt/bn/ic-vlm/zhufangqi/code/datasets/robotwin_50_lerobot/dump_bin_bigbin/aloha-agilex_randomized_500,/mnt/bn/ic-vlm/zhufangqi/code/datasets/robotwin_50_lerobot/grab_roller/aloha-agilex_randomized_500,/mnt/bn/ic-vlm/zhufangqi/code/datasets/robotwin_50_lerobot/handover_block/aloha-agilex_randomized_500,/mnt/bn/ic-vlm/zhufangqi/code/datasets/robotwin_50_lerobot/handover_mic/aloha-agilex_randomized_500,/mnt/bn/ic-vlm/zhufangqi/code/datasets/robotwin_50_lerobot/hanging_mug/aloha-agilex_randomized_500,/mnt/bn/ic-vlm/zhufangqi/code/datasets/robotwin_50_lerobot/lift_pot/aloha-agilex_randomized_500,/mnt/bn/ic-vlm/zhufangqi/code/datasets/robotwin_50_lerobot/move_can_pot/aloha-agilex_randomized_500,/mnt/bn/ic-vlm/zhufangqi/code/datasets/robotwin_50_lerobot/move_pillbottle_pad/aloha-agilex_randomized_500,/mnt/bn/ic-vlm/zhufangqi/code/datasets/robotwin_50_lerobot/move_playingcard_away/aloha-agilex_randomized_500,/mnt/bn/ic-vlm/zhufangqi/code/datasets/robotwin_50_lerobot/move_stapler_pad/aloha-agilex_randomized_500,/mnt/bn/ic-vlm/zhufangqi/code/datasets/robotwin_50_lerobot/open_laptop/aloha-agilex_randomized_500,/mnt/bn/ic-vlm/zhufangqi/code/datasets/robotwin_50_lerobot/open_microwave/aloha-agilex_randomized_500,/mnt/bn/ic-vlm/zhufangqi/code/datasets/robotwin_50_lerobot/pick_diverse_bottles/aloha-agilex_randomized_500,/mnt/bn/ic-vlm/zhufangqi/code/datasets/robotwin_50_lerobot/pick_dual_bottles/aloha-agilex_randomized_500,/mnt/bn/ic-vlm/zhufangqi/code/datasets/robotwin_50_lerobot/place_a2b_left/aloha-agilex_randomized_500,/mnt/bn/ic-vlm/zhufangqi/code/datasets/robotwin_50_lerobot/place_a2b_right/aloha-agilex_randomized_500,/mnt/bn/ic-vlm/zhufangqi/code/datasets/robotwin_50_lerobot/place_bread_basket/aloha-agilex_randomized_500,/mnt/bn/ic-vlm/zhufangqi/code/datasets/robotwin_50_lerobot/place_bread_skillet/aloha-agilex_randomized_500,/mnt/bn/ic-vlm/zhufangqi/code/datasets/robotwin_50_lerobot/place_burger_fries/aloha-agilex_randomized_500,/mnt/bn/ic-vlm/zhufangqi/code/datasets/robotwin_50_lerobot/place_can_basket/aloha-agilex_randomized_500,/mnt/bn/ic-vlm/zhufangqi/code/datasets/robotwin_50_lerobot/place_cans_plasticbox/aloha-agilex_randomized_500,/mnt/bn/ic-vlm/zhufangqi/code/datasets/robotwin_50_lerobot/place_container_plate/aloha-agilex_randomized_500,/mnt/bn/ic-vlm/zhufangqi/code/datasets/robotwin_50_lerobot/place_dual_shoes/aloha-agilex_randomized_500,/mnt/bn/ic-vlm/zhufangqi/code/datasets/robotwin_50_lerobot/place_empty_cup/aloha-agilex_randomized_500,/mnt/bn/ic-vlm/zhufangqi/code/datasets/robotwin_50_lerobot/place_fan/aloha-agilex_randomized_500,/mnt/bn/ic-vlm/zhufangqi/code/datasets/robotwin_50_lerobot/place_mouse_pad/aloha-agilex_randomized_500,/mnt/bn/ic-vlm/zhufangqi/code/datasets/robotwin_50_lerobot/place_object_basket/aloha-agilex_randomized_500,/mnt/bn/ic-vlm/zhufangqi/code/datasets/robotwin_50_lerobot/place_object_scale/aloha-agilex_randomized_500,/mnt/bn/ic-vlm/zhufangqi/code/datasets/robotwin_50_lerobot/place_object_stand/aloha-agilex_randomized_500,/mnt/bn/ic-vlm/zhufangqi/code/datasets/robotwin_50_lerobot/place_phone_stand/aloha-agilex_randomized_500,/mnt/bn/ic-vlm/zhufangqi/code/datasets/robotwin_50_lerobot/place_shoe/aloha-agilex_randomized_500,/mnt/bn/ic-vlm/zhufangqi/code/datasets/robotwin_50_lerobot/press_stapler/aloha-agilex_randomized_500,/mnt/bn/ic-vlm/zhufangqi/code/datasets/robotwin_50_lerobot/put_bottles_dustbin/aloha-agilex_randomized_500,/mnt/bn/ic-vlm/zhufangqi/code/datasets/robotwin_50_lerobot/put_object_cabinet/aloha-agilex_randomized_500,/mnt/bn/ic-vlm/zhufangqi/code/datasets/robotwin_50_lerobot/rotate_qrcode/aloha-agilex_randomized_500,/mnt/bn/ic-vlm/zhufangqi/code/datasets/robotwin_50_lerobot/scan_object/aloha-agilex_randomized_500,/mnt/bn/ic-vlm/zhufangqi/code/datasets/robotwin_50_lerobot/shake_bottle/aloha-agilex_randomized_500,/mnt/bn/ic-vlm/zhufangqi/code/datasets/robotwin_50_lerobot/shake_bottle_horizontally/aloha-agilex_randomized_500,/mnt/bn/ic-vlm/zhufangqi/code/datasets/robotwin_50_lerobot/stack_blocks_three/aloha-agilex_randomized_500,/mnt/bn/ic-vlm/zhufangqi/code/datasets/robotwin_50_lerobot/stack_blocks_two/aloha-agilex_randomized_500,/mnt/bn/ic-vlm/zhufangqi/code/datasets/robotwin_50_lerobot/stack_bowls_three/aloha-agilex_randomized_500,/mnt/bn/ic-vlm/zhufangqi/code/datasets/robotwin_50_lerobot/stack_bowls_two/aloha-agilex_randomized_500,/mnt/bn/ic-vlm/zhufangqi/code/datasets/robotwin_50_lerobot/stamp_seal/aloha-agilex_randomized_500,/mnt/bn/ic-vlm/zhufangqi/code/datasets/robotwin_50_lerobot/turn_switch/aloha-agilex_randomized_500",
8
+ "image_height": 240,
9
+ "image_width": 320,
10
+ "max_episodes": null,
11
+ "max_pixels": 76800,
12
+ "min_pixels": 76800,
13
+ "pair_add_backward": true,
14
+ "pair_add_zero_anchor": true,
15
+ "pair_data_backend": "map",
16
+ "pair_mode": false,
17
+ "pair_prompt_style": "current_history_delta",
18
+ "pair_target_column": null,
19
+ "use_value_tokenizer": true,
20
+ "val_ratio": 0.1,
21
+ "value_column": "value",
22
+ "value_source": "episode_progress",
23
+ "value_tokenizer_bins": 201,
24
+ "value_tokenizer_max": 1.0,
25
+ "value_tokenizer_min": 0.0,
26
+ "video_fps": 2.0,
27
+ "video_max_frames": 8,
28
+ "video_max_pixels": 802816,
29
+ "video_min_frames": 4,
30
+ "video_min_pixels": 200704
31
+ },
32
+ "model_args": {
33
+ "model_name_or_path": "/mnt/bn/ic-vlm/zhufangqi/code/checkpoints/qwen-vl-resize",
34
+ "tune_mm_llm": true,
35
+ "tune_mm_mlp": true,
36
+ "tune_mm_vision": false
37
+ },
38
+ "training_args": {
39
+ "accelerator_config": {
40
+ "dispatch_batches": null,
41
+ "even_batches": true,
42
+ "gradient_accumulation_kwargs": null,
43
+ "non_blocking": false,
44
+ "split_batches": false,
45
+ "use_seedable_sampler": true
46
+ },
47
+ "adafactor": false,
48
+ "adam_beta1": 0.9,
49
+ "adam_beta2": 0.999,
50
+ "adam_epsilon": 1e-08,
51
+ "auto_find_batch_size": false,
52
+ "average_tokens_across_devices": false,
53
+ "batch_eval_metrics": false,
54
+ "bf16": true,
55
+ "bf16_full_eval": false,
56
+ "cache_dir": null,
57
+ "data_seed": null,
58
+ "dataloader_drop_last": false,
59
+ "dataloader_num_workers": 8,
60
+ "dataloader_persistent_workers": true,
61
+ "dataloader_pin_memory": true,
62
+ "dataloader_prefetch_factor": 2,
63
+ "ddp_backend": null,
64
+ "ddp_broadcast_buffers": null,
65
+ "ddp_bucket_cap_mb": null,
66
+ "ddp_find_unused_parameters": null,
67
+ "ddp_timeout": 1800,
68
+ "debug": [],
69
+ "deepspeed": "/home/tiger/code/cot/src/openpi/qwenvl/scripts/zero3.json",
70
+ "disable_tqdm": false,
71
+ "do_eval": true,
72
+ "do_predict": false,
73
+ "do_train": false,
74
+ "eval_accumulation_steps": null,
75
+ "eval_delay": 0,
76
+ "eval_do_concat_batches": true,
77
+ "eval_on_start": false,
78
+ "eval_steps": 2500,
79
+ "eval_strategy": "steps",
80
+ "eval_use_gather_object": false,
81
+ "fp16": false,
82
+ "fp16_backend": "auto",
83
+ "fp16_full_eval": false,
84
+ "fp16_opt_level": "O1",
85
+ "fsdp": [],
86
+ "fsdp_config": {
87
+ "min_num_params": 0,
88
+ "xla": false,
89
+ "xla_fsdp_grad_ckpt": false,
90
+ "xla_fsdp_v2": false
91
+ },
92
+ "fsdp_min_num_params": 0,
93
+ "fsdp_transformer_layer_cls_to_wrap": null,
94
+ "full_determinism": false,
95
+ "gradient_accumulation_steps": 4,
96
+ "gradient_checkpointing": false,
97
+ "gradient_checkpointing_kwargs": null,
98
+ "greater_is_better": null,
99
+ "group_by_length": false,
100
+ "half_precision_backend": "auto",
101
+ "hub_always_push": false,
102
+ "hub_model_id": null,
103
+ "hub_private_repo": null,
104
+ "hub_revision": null,
105
+ "hub_strategy": "every_save",
106
+ "hub_token": "<HUB_TOKEN>",
107
+ "ignore_data_skip": false,
108
+ "include_for_metrics": [],
109
+ "include_inputs_for_metrics": false,
110
+ "include_num_input_tokens_seen": false,
111
+ "include_tokens_per_second": false,
112
+ "jit_mode_eval": false,
113
+ "label_names": null,
114
+ "label_smoothing_factor": 0.0,
115
+ "learning_rate": 1e-05,
116
+ "length_column_name": "length",
117
+ "liger_kernel_config": null,
118
+ "load_best_model_at_end": false,
119
+ "local_rank": 0,
120
+ "log_level": "passive",
121
+ "log_level_replica": "warning",
122
+ "log_on_each_node": true,
123
+ "logging_dir": "$/mnt/bn/ic-vlm/zhufangqi/code/checkpoints/value_function_pi06/robotwin50_pi06_expert_train/runs/Mar18_23-11-35_g340-cd51-7700-bb90-916f-fa2-f254",
124
+ "logging_first_step": false,
125
+ "logging_nan_inf_filter": true,
126
+ "logging_steps": 10,
127
+ "logging_strategy": "steps",
128
+ "lora_alpha": 128,
129
+ "lora_dropout": 0.0,
130
+ "lora_enable": false,
131
+ "lora_r": 64,
132
+ "lr_scheduler_kwargs": {},
133
+ "lr_scheduler_type": "linear",
134
+ "max_grad_norm": 1.0,
135
+ "max_steps": 30000,
136
+ "metric_for_best_model": null,
137
+ "mm_projector_lr": null,
138
+ "model_max_length": 512,
139
+ "mp_parameters": "",
140
+ "neftune_noise_alpha": null,
141
+ "no_cuda": false,
142
+ "num_train_epochs": 3.0,
143
+ "optim": "adamw_torch",
144
+ "optim_args": null,
145
+ "optim_target_modules": null,
146
+ "output_dir": "$/mnt/bn/ic-vlm/zhufangqi/code/checkpoints/value_function_pi06/robotwin50_pi06_expert_train",
147
+ "overwrite_output_dir": false,
148
+ "pair_use_t_group_weight": true,
149
+ "past_index": -1,
150
+ "per_device_eval_batch_size": 32,
151
+ "per_device_train_batch_size": 32,
152
+ "per_gpu_eval_batch_size": null,
153
+ "per_gpu_train_batch_size": null,
154
+ "prediction_loss_only": false,
155
+ "push_to_hub": false,
156
+ "push_to_hub_model_id": null,
157
+ "push_to_hub_organization": null,
158
+ "push_to_hub_token": "<PUSH_TO_HUB_TOKEN>",
159
+ "ray_scope": "last",
160
+ "remove_unused_columns": true,
161
+ "report_to": [
162
+ "wandb"
163
+ ],
164
+ "restore_callback_states_from_checkpoint": false,
165
+ "resume_from_checkpoint": null,
166
+ "run_name": "robotwin50_pi06_expert_train",
167
+ "save_format": "hf",
168
+ "save_interval": null,
169
+ "save_on_each_node": false,
170
+ "save_only_model": false,
171
+ "save_safetensors": true,
172
+ "save_steps": 2500,
173
+ "save_strategy": "steps",
174
+ "save_total_limit": 5,
175
+ "seed": 42,
176
+ "skip_memory_metrics": true,
177
+ "tf32": null,
178
+ "torch_compile": false,
179
+ "torch_compile_backend": null,
180
+ "torch_compile_mode": null,
181
+ "torch_empty_cache_steps": null,
182
+ "torchdynamo": null,
183
+ "tpu_metrics_debug": false,
184
+ "tpu_num_cores": null,
185
+ "use_cpu": false,
186
+ "use_ipex": false,
187
+ "use_legacy_prediction_loop": false,
188
+ "use_liger_kernel": false,
189
+ "use_mps_device": false,
190
+ "value_head_lr": null,
191
+ "value_head_weight_decay": 0.0,
192
+ "vision_tower_lr": null,
193
+ "warmup_ratio": 0.03,
194
+ "warmup_steps": 0,
195
+ "weight_decay": 0.01
196
+ }
197
+ }
robotwin50_pi06_expert_train/runs/Mar18_15-27-36_g340-cd51-7700-bb90-916f-fa2-f254/events.out.tfevents.1773818927.g340-cd51-7700-bb90-916f-fa2-f254.140016.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47af50902e3ca512ff14d977532d86849d0f0678f2a88b8943176de2c87ccaed
3
+ size 8513
robotwin50_pi06_expert_train/runs/Mar18_15-38-36_g340-cd51-7700-bb90-916f-fa2-f254/events.out.tfevents.1773819616.g340-cd51-7700-bb90-916f-fa2-f254.2920613.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5f0a4e6b297b67e4c0736acd2005aec353c485d13a36a1244e4422cfc071fc9
3
+ size 14377
robotwin50_pi06_expert_train/train_metrics.jsonl ADDED
@@ -0,0 +1,294 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"global_step": 10, "epoch": 0.004116496861171143, "loss": 79.4593, "grad_norm": 722.9849266591084, "learning_rate": 1.0000000000000001e-07}
2
+ {"global_step": 20, "epoch": 0.008232993722342286, "loss": 79.3183, "grad_norm": 713.4423322869009, "learning_rate": 2.1111111111111113e-07}
3
+ {"global_step": 30, "epoch": 0.01234949058351343, "loss": 78.0929, "grad_norm": 619.0335944754007, "learning_rate": 3.2222222222222227e-07}
4
+ {"global_step": 40, "epoch": 0.016465987444684572, "loss": 75.0743, "grad_norm": 439.772626183607, "learning_rate": 4.333333333333334e-07}
5
+ {"global_step": 50, "epoch": 0.020582484305855717, "loss": 69.3428, "grad_norm": 281.08070517386403, "learning_rate": 5.444444444444444e-07}
6
+ {"global_step": 60, "epoch": 0.02469898116702686, "loss": 64.8186, "grad_norm": 238.72306538307805, "learning_rate": 6.555555555555556e-07}
7
+ {"global_step": 70, "epoch": 0.028815478028198005, "loss": 59.6238, "grad_norm": 265.61586056265025, "learning_rate": 7.666666666666667e-07}
8
+ {"global_step": 80, "epoch": 0.032931974889369144, "loss": 52.8731, "grad_norm": 92.19312055336448, "learning_rate": 8.777777777777778e-07}
9
+ {"global_step": 90, "epoch": 0.03704847175054029, "loss": 49.676, "grad_norm": 45.48770884961453, "learning_rate": 9.88888888888889e-07}
10
+ {"global_step": 100, "epoch": 0.041164968611711435, "loss": 48.4892, "grad_norm": 27.08086194848908, "learning_rate": 1.1e-06}
11
+ {"global_step": 110, "epoch": 0.04528146547288258, "loss": 48.0497, "grad_norm": 19.32379182470467, "learning_rate": 1.2111111111111111e-06}
12
+ {"global_step": 120, "epoch": 0.04939796233405372, "loss": 47.7781, "grad_norm": 16.380874066084196, "learning_rate": 1.3222222222222222e-06}
13
+ {"global_step": 130, "epoch": 0.053514459195224864, "loss": 47.5811, "grad_norm": 15.371140813384557, "learning_rate": 1.4333333333333335e-06}
14
+ {"global_step": 140, "epoch": 0.05763095605639601, "loss": 47.4215, "grad_norm": 15.84809592222176, "learning_rate": 1.5444444444444446e-06}
15
+ {"global_step": 150, "epoch": 0.06174745291756715, "loss": 47.2557, "grad_norm": 16.994317821440845, "learning_rate": 1.6555555555555559e-06}
16
+ {"global_step": 160, "epoch": 0.06586394977873829, "loss": 47.0796, "grad_norm": 18.743638967461997, "learning_rate": 1.7666666666666668e-06}
17
+ {"global_step": 170, "epoch": 0.06998044663990943, "loss": 46.8693, "grad_norm": 20.92550528148297, "learning_rate": 1.8777777777777778e-06}
18
+ {"global_step": 180, "epoch": 0.07409694350108058, "loss": 46.6118, "grad_norm": 23.935804629158547, "learning_rate": 1.988888888888889e-06}
19
+ {"global_step": 190, "epoch": 0.07821344036225172, "loss": 46.267, "grad_norm": 28.229572692610986, "learning_rate": 2.1000000000000002e-06}
20
+ {"global_step": 200, "epoch": 0.08232993722342287, "loss": 45.7269, "grad_norm": 34.37693332521861, "learning_rate": 2.2111111111111113e-06}
21
+ {"global_step": 210, "epoch": 0.08644643408459401, "loss": 44.9702, "grad_norm": 43.4433932596704, "learning_rate": 2.3222222222222224e-06}
22
+ {"global_step": 220, "epoch": 0.09056293094576516, "loss": 43.7522, "grad_norm": 58.28038941283432, "learning_rate": 2.4333333333333335e-06}
23
+ {"global_step": 230, "epoch": 0.09467942780693629, "loss": 41.9094, "grad_norm": 71.69823530504809, "learning_rate": 2.5444444444444446e-06}
24
+ {"global_step": 240, "epoch": 0.09879592466810744, "loss": 39.6286, "grad_norm": 69.78057028859453, "learning_rate": 2.6555555555555556e-06}
25
+ {"global_step": 250, "epoch": 0.10291242152927858, "loss": 37.279, "grad_norm": 65.2702064062225, "learning_rate": 2.766666666666667e-06}
26
+ {"global_step": 260, "epoch": 0.10702891839044973, "loss": 34.8486, "grad_norm": 62.147050273188626, "learning_rate": 2.8777777777777782e-06}
27
+ {"global_step": 270, "epoch": 0.11114541525162087, "loss": 32.3669, "grad_norm": 58.3163917534024, "learning_rate": 2.988888888888889e-06}
28
+ {"global_step": 280, "epoch": 0.11526191211279202, "loss": 29.9582, "grad_norm": 73.8699537282808, "learning_rate": 3.1000000000000004e-06}
29
+ {"global_step": 290, "epoch": 0.11937840897396315, "loss": 27.8124, "grad_norm": 59.22493609025033, "learning_rate": 3.2111111111111115e-06}
30
+ {"global_step": 300, "epoch": 0.1234949058351343, "loss": 25.908, "grad_norm": 42.636994581457614, "learning_rate": 3.322222222222222e-06}
31
+ {"global_step": 310, "epoch": 0.12761140269630544, "loss": 24.4843, "grad_norm": 36.81511952341932, "learning_rate": 3.4333333333333336e-06}
32
+ {"global_step": 320, "epoch": 0.13172789955747657, "loss": 23.4653, "grad_norm": 27.381915904890327, "learning_rate": 3.5444444444444447e-06}
33
+ {"global_step": 330, "epoch": 0.13584439641864773, "loss": 22.7909, "grad_norm": 23.598517571067614, "learning_rate": 3.6555555555555562e-06}
34
+ {"global_step": 340, "epoch": 0.13996089327981887, "loss": 22.3688, "grad_norm": 23.294478325249578, "learning_rate": 3.766666666666667e-06}
35
+ {"global_step": 350, "epoch": 0.14407739014099002, "loss": 22.0982, "grad_norm": 20.093643447034683, "learning_rate": 3.877777777777778e-06}
36
+ {"global_step": 360, "epoch": 0.14819388700216116, "loss": 21.9086, "grad_norm": 19.394487535911193, "learning_rate": 3.9888888888888895e-06}
37
+ {"global_step": 370, "epoch": 0.15231038386333232, "loss": 21.7863, "grad_norm": 18.119665979499104, "learning_rate": 4.1e-06}
38
+ {"global_step": 380, "epoch": 0.15642688072450345, "loss": 21.6972, "grad_norm": 17.07344526731236, "learning_rate": 4.211111111111112e-06}
39
+ {"global_step": 390, "epoch": 0.16054337758567458, "loss": 21.6276, "grad_norm": 17.2895867054574, "learning_rate": 4.322222222222223e-06}
40
+ {"global_step": 400, "epoch": 0.16465987444684574, "loss": 21.5774, "grad_norm": 18.055980258041934, "learning_rate": 4.433333333333334e-06}
41
+ {"global_step": 410, "epoch": 0.16877637130801687, "loss": 21.5305, "grad_norm": 17.602944740266267, "learning_rate": 4.544444444444445e-06}
42
+ {"global_step": 420, "epoch": 0.17289286816918803, "loss": 21.4996, "grad_norm": 17.047319458414727, "learning_rate": 4.655555555555556e-06}
43
+ {"global_step": 430, "epoch": 0.17700936503035916, "loss": 21.4706, "grad_norm": 17.326432935336033, "learning_rate": 4.766666666666667e-06}
44
+ {"global_step": 440, "epoch": 0.18112586189153032, "loss": 21.4449, "grad_norm": 17.554696739458905, "learning_rate": 4.877777777777778e-06}
45
+ {"global_step": 450, "epoch": 0.18524235875270145, "loss": 21.4242, "grad_norm": 16.57900811727561, "learning_rate": 4.988888888888889e-06}
46
+ {"global_step": 460, "epoch": 0.18935885561387258, "loss": 21.4136, "grad_norm": 16.41658497950142, "learning_rate": 5.1e-06}
47
+ {"global_step": 470, "epoch": 0.19347535247504374, "loss": 21.3904, "grad_norm": 14.851397065124416, "learning_rate": 5.211111111111111e-06}
48
+ {"global_step": 480, "epoch": 0.19759184933621488, "loss": 21.3748, "grad_norm": 16.86165644628761, "learning_rate": 5.322222222222223e-06}
49
+ {"global_step": 490, "epoch": 0.20170834619738603, "loss": 21.3649, "grad_norm": 16.021934417394476, "learning_rate": 5.4333333333333335e-06}
50
+ {"global_step": 500, "epoch": 0.20582484305855717, "loss": 21.357, "grad_norm": 16.71987330752045, "learning_rate": 5.544444444444445e-06}
51
+ {"global_step": 510, "epoch": 0.2099413399197283, "loss": 21.345, "grad_norm": 16.033384348770003, "learning_rate": 5.6555555555555566e-06}
52
+ {"global_step": 520, "epoch": 0.21405783678089946, "loss": 21.3308, "grad_norm": 16.503614387128653, "learning_rate": 5.766666666666667e-06}
53
+ {"global_step": 530, "epoch": 0.2181743336420706, "loss": 21.3167, "grad_norm": 16.5197017811903, "learning_rate": 5.877777777777778e-06}
54
+ {"global_step": 540, "epoch": 0.22229083050324175, "loss": 21.2952, "grad_norm": 18.609397075134556, "learning_rate": 5.98888888888889e-06}
55
+ {"global_step": 550, "epoch": 0.22640732736441288, "loss": 21.2694, "grad_norm": 18.044456751597316, "learning_rate": 6.1e-06}
56
+ {"global_step": 560, "epoch": 0.23052382422558404, "loss": 21.2149, "grad_norm": 18.440050806349944, "learning_rate": 6.211111111111111e-06}
57
+ {"global_step": 570, "epoch": 0.23464032108675517, "loss": 21.1566, "grad_norm": 36.12491809597436, "learning_rate": 6.322222222222223e-06}
58
+ {"global_step": 580, "epoch": 0.2387568179479263, "loss": 21.0841, "grad_norm": 17.843619309609803, "learning_rate": 6.433333333333333e-06}
59
+ {"global_step": 590, "epoch": 0.24287331480909746, "loss": 20.9708, "grad_norm": 18.299191738513812, "learning_rate": 6.544444444444445e-06}
60
+ {"global_step": 600, "epoch": 0.2469898116702686, "loss": 20.8825, "grad_norm": 18.056905789458586, "learning_rate": 6.655555555555556e-06}
61
+ {"global_step": 610, "epoch": 0.2511063085314397, "loss": 20.8147, "grad_norm": 44.82326463049171, "learning_rate": 6.7666666666666665e-06}
62
+ {"global_step": 620, "epoch": 0.2552228053926109, "loss": 20.7548, "grad_norm": 27.094157559455603, "learning_rate": 6.8777777777777785e-06}
63
+ {"global_step": 630, "epoch": 0.25933930225378204, "loss": 20.6822, "grad_norm": 27.88387397100189, "learning_rate": 6.9888888888888895e-06}
64
+ {"global_step": 640, "epoch": 0.26345579911495315, "loss": 20.5884, "grad_norm": 31.290911839762394, "learning_rate": 7.100000000000001e-06}
65
+ {"global_step": 650, "epoch": 0.2675722959761243, "loss": 20.5162, "grad_norm": 24.27245501884365, "learning_rate": 7.211111111111112e-06}
66
+ {"global_step": 660, "epoch": 0.27168879283729547, "loss": 20.4592, "grad_norm": 23.89703899570296, "learning_rate": 7.322222222222223e-06}
67
+ {"global_step": 670, "epoch": 0.2758052896984666, "loss": 20.3787, "grad_norm": 57.249160956506614, "learning_rate": 7.433333333333334e-06}
68
+ {"global_step": 680, "epoch": 0.27992178655963773, "loss": 20.207, "grad_norm": 44.42291899504958, "learning_rate": 7.544444444444445e-06}
69
+ {"global_step": 690, "epoch": 0.2840382834208089, "loss": 20.143, "grad_norm": 91.55863776649939, "learning_rate": 7.655555555555556e-06}
70
+ {"global_step": 700, "epoch": 0.28815478028198005, "loss": 19.9418, "grad_norm": 57.092128520356646, "learning_rate": 7.766666666666666e-06}
71
+ {"global_step": 710, "epoch": 0.29227127714315115, "loss": 19.6662, "grad_norm": 37.42956925364744, "learning_rate": 7.877777777777778e-06}
72
+ {"global_step": 720, "epoch": 0.2963877740043223, "loss": 19.4289, "grad_norm": 24.54779334825758, "learning_rate": 7.98888888888889e-06}
73
+ {"global_step": 730, "epoch": 0.3005042708654935, "loss": 19.2373, "grad_norm": 20.193177185866038, "learning_rate": 8.1e-06}
74
+ {"global_step": 740, "epoch": 0.30462076772666463, "loss": 19.173, "grad_norm": 60.48422812921962, "learning_rate": 8.211111111111112e-06}
75
+ {"global_step": 750, "epoch": 0.30873726458783574, "loss": 18.9043, "grad_norm": 27.558098824852753, "learning_rate": 8.322222222222223e-06}
76
+ {"global_step": 760, "epoch": 0.3128537614490069, "loss": 18.6651, "grad_norm": 29.51167246824426, "learning_rate": 8.433333333333334e-06}
77
+ {"global_step": 770, "epoch": 0.31697025831017805, "loss": 18.4818, "grad_norm": 21.93310893699215, "learning_rate": 8.544444444444445e-06}
78
+ {"global_step": 780, "epoch": 0.32108675517134916, "loss": 18.4864, "grad_norm": 51.99252088836799, "learning_rate": 8.655555555555557e-06}
79
+ {"global_step": 790, "epoch": 0.3252032520325203, "loss": 18.205, "grad_norm": 35.01362198000449, "learning_rate": 8.766666666666669e-06}
80
+ {"global_step": 800, "epoch": 0.3293197488936915, "loss": 18.0342, "grad_norm": 30.09623662803406, "learning_rate": 8.877777777777779e-06}
81
+ {"global_step": 810, "epoch": 0.33343624575486264, "loss": 17.8646, "grad_norm": 55.16314161967726, "learning_rate": 8.988888888888889e-06}
82
+ {"global_step": 820, "epoch": 0.33755274261603374, "loss": 17.6275, "grad_norm": 33.375878351461154, "learning_rate": 9.100000000000001e-06}
83
+ {"global_step": 830, "epoch": 0.3416692394772049, "loss": 17.53, "grad_norm": 27.20030408565347, "learning_rate": 9.211111111111111e-06}
84
+ {"global_step": 840, "epoch": 0.34578573633837606, "loss": 17.4118, "grad_norm": 44.94165316928541, "learning_rate": 9.322222222222223e-06}
85
+ {"global_step": 850, "epoch": 0.34990223319954716, "loss": 17.2221, "grad_norm": 51.21107811701123, "learning_rate": 9.433333333333335e-06}
86
+ {"global_step": 860, "epoch": 0.3540187300607183, "loss": 17.0648, "grad_norm": 48.69081492082153, "learning_rate": 9.544444444444445e-06}
87
+ {"global_step": 870, "epoch": 0.3581352269218895, "loss": 16.9709, "grad_norm": 59.568062971869644, "learning_rate": 9.655555555555556e-06}
88
+ {"global_step": 880, "epoch": 0.36225172378306064, "loss": 16.7922, "grad_norm": 48.20595634997982, "learning_rate": 9.766666666666667e-06}
89
+ {"global_step": 890, "epoch": 0.36636822064423175, "loss": 16.5606, "grad_norm": 38.89100659846126, "learning_rate": 9.877777777777778e-06}
90
+ {"global_step": 900, "epoch": 0.3704847175054029, "loss": 16.5196, "grad_norm": 55.476242446929724, "learning_rate": 9.98888888888889e-06}
91
+ {"global_step": 910, "epoch": 0.37460121436657406, "loss": 16.2859, "grad_norm": 33.8871713799869, "learning_rate": 9.996907216494847e-06}
92
+ {"global_step": 920, "epoch": 0.37871771122774517, "loss": 16.1253, "grad_norm": 48.67199287721736, "learning_rate": 9.993470790378008e-06}
93
+ {"global_step": 930, "epoch": 0.38283420808891633, "loss": 16.1184, "grad_norm": 53.10677273121955, "learning_rate": 9.99003436426117e-06}
94
+ {"global_step": 940, "epoch": 0.3869507049500875, "loss": 15.8454, "grad_norm": 36.47115886963749, "learning_rate": 9.986597938144331e-06}
95
+ {"global_step": 950, "epoch": 0.3910672018112586, "loss": 15.7934, "grad_norm": 46.9950180770148, "learning_rate": 9.983161512027493e-06}
96
+ {"global_step": 960, "epoch": 0.39518369867242975, "loss": 15.7013, "grad_norm": 41.780425293570616, "learning_rate": 9.979725085910654e-06}
97
+ {"global_step": 970, "epoch": 0.3993001955336009, "loss": 15.5447, "grad_norm": 61.01443519953337, "learning_rate": 9.976288659793816e-06}
98
+ {"global_step": 980, "epoch": 0.40341669239477207, "loss": 15.4402, "grad_norm": 37.005722827889784, "learning_rate": 9.972852233676977e-06}
99
+ {"global_step": 990, "epoch": 0.4075331892559432, "loss": 15.3771, "grad_norm": 34.50549181078069, "learning_rate": 9.969415807560139e-06}
100
+ {"global_step": 1000, "epoch": 0.41164968611711433, "loss": 15.1859, "grad_norm": 43.56802220640922, "learning_rate": 9.965979381443299e-06}
101
+ {"global_step": 1010, "epoch": 0.4157661829782855, "loss": 15.1377, "grad_norm": 44.27192419759802, "learning_rate": 9.96254295532646e-06}
102
+ {"global_step": 1020, "epoch": 0.4198826798394566, "loss": 15.0264, "grad_norm": 54.39835842981886, "learning_rate": 9.959106529209622e-06}
103
+ {"global_step": 1030, "epoch": 0.42399917670062776, "loss": 14.9343, "grad_norm": 39.41791238776903, "learning_rate": 9.955670103092783e-06}
104
+ {"global_step": 1040, "epoch": 0.4281156735617989, "loss": 14.7589, "grad_norm": 33.82937492863744, "learning_rate": 9.952233676975945e-06}
105
+ {"global_step": 1050, "epoch": 0.4322321704229701, "loss": 14.6838, "grad_norm": 40.479975837330905, "learning_rate": 9.948797250859106e-06}
106
+ {"global_step": 1060, "epoch": 0.4363486672841412, "loss": 14.5806, "grad_norm": 49.56506719825334, "learning_rate": 9.945360824742268e-06}
107
+ {"global_step": 1070, "epoch": 0.44046516414531234, "loss": 14.5519, "grad_norm": 43.92728436690805, "learning_rate": 9.94192439862543e-06}
108
+ {"global_step": 1080, "epoch": 0.4445816610064835, "loss": 14.4566, "grad_norm": 38.083124431784405, "learning_rate": 9.938487972508592e-06}
109
+ {"global_step": 1090, "epoch": 0.4486981578676546, "loss": 14.4637, "grad_norm": 40.83368623786197, "learning_rate": 9.935051546391754e-06}
110
+ {"global_step": 1100, "epoch": 0.45281465472882576, "loss": 14.2926, "grad_norm": 39.888961137074325, "learning_rate": 9.931615120274915e-06}
111
+ {"global_step": 1110, "epoch": 0.4569311515899969, "loss": 14.2284, "grad_norm": 52.98917099950452, "learning_rate": 9.928178694158077e-06}
112
+ {"global_step": 1120, "epoch": 0.4610476484511681, "loss": 14.1538, "grad_norm": 39.86769855717651, "learning_rate": 9.924742268041238e-06}
113
+ {"global_step": 1130, "epoch": 0.4651641453123392, "loss": 14.1268, "grad_norm": 41.47546966771517, "learning_rate": 9.9213058419244e-06}
114
+ {"global_step": 1140, "epoch": 0.46928064217351034, "loss": 14.0239, "grad_norm": 43.66832808351295, "learning_rate": 9.917869415807561e-06}
115
+ {"global_step": 1150, "epoch": 0.4733971390346815, "loss": 13.9388, "grad_norm": 38.15090916854303, "learning_rate": 9.914432989690723e-06}
116
+ {"global_step": 1160, "epoch": 0.4775136358958526, "loss": 13.911, "grad_norm": 34.56956210917117, "learning_rate": 9.910996563573884e-06}
117
+ {"global_step": 1170, "epoch": 0.48163013275702377, "loss": 13.8416, "grad_norm": 33.31934413400173, "learning_rate": 9.907560137457046e-06}
118
+ {"global_step": 1180, "epoch": 0.4857466296181949, "loss": 13.8095, "grad_norm": 37.93411062451452, "learning_rate": 9.904123711340207e-06}
119
+ {"global_step": 1190, "epoch": 0.4898631264793661, "loss": 13.7295, "grad_norm": 38.20924261082129, "learning_rate": 9.900687285223369e-06}
120
+ {"global_step": 1200, "epoch": 0.4939796233405372, "loss": 13.6506, "grad_norm": 53.63569573152946, "learning_rate": 9.89725085910653e-06}
121
+ {"global_step": 1210, "epoch": 0.49809612020170835, "loss": 13.6186, "grad_norm": 43.14530877212232, "learning_rate": 9.893814432989692e-06}
122
+ {"global_step": 1220, "epoch": 0.5022126170628795, "loss": 13.6416, "grad_norm": 49.03916689519157, "learning_rate": 9.890378006872853e-06}
123
+ {"global_step": 1230, "epoch": 0.5063291139240507, "loss": 13.574, "grad_norm": 36.49026973775023, "learning_rate": 9.886941580756015e-06}
124
+ {"global_step": 1240, "epoch": 0.5104456107852218, "loss": 13.4854, "grad_norm": 32.76071554080421, "learning_rate": 9.883505154639176e-06}
125
+ {"global_step": 1250, "epoch": 0.5145621076463929, "loss": 13.3827, "grad_norm": 36.789924557345806, "learning_rate": 9.880068728522338e-06}
126
+ {"global_step": 1260, "epoch": 0.5186786045075641, "loss": 13.3305, "grad_norm": 28.079567041126435, "learning_rate": 9.8766323024055e-06}
127
+ {"global_step": 1270, "epoch": 0.5227951013687352, "loss": 13.33, "grad_norm": 43.55514700081209, "learning_rate": 9.87319587628866e-06}
128
+ {"global_step": 1280, "epoch": 0.5269115982299063, "loss": 13.2651, "grad_norm": 28.76115488681788, "learning_rate": 9.869759450171822e-06}
129
+ {"global_step": 1290, "epoch": 0.5310280950910775, "loss": 13.2312, "grad_norm": 37.358128749691296, "learning_rate": 9.866323024054984e-06}
130
+ {"global_step": 1300, "epoch": 0.5351445919522486, "loss": 13.1897, "grad_norm": 44.992288758478345, "learning_rate": 9.862886597938145e-06}
131
+ {"global_step": 1310, "epoch": 0.5392610888134198, "loss": 13.1063, "grad_norm": 28.47379704494871, "learning_rate": 9.859450171821307e-06}
132
+ {"global_step": 1320, "epoch": 0.5433775856745909, "loss": 13.0747, "grad_norm": 31.796429799283633, "learning_rate": 9.856013745704468e-06}
133
+ {"global_step": 1330, "epoch": 0.547494082535762, "loss": 13.0861, "grad_norm": 39.38678551108492, "learning_rate": 9.85257731958763e-06}
134
+ {"global_step": 1340, "epoch": 0.5516105793969333, "loss": 13.046, "grad_norm": 38.812099741482996, "learning_rate": 9.849140893470791e-06}
135
+ {"global_step": 1350, "epoch": 0.5557270762581044, "loss": 13.0339, "grad_norm": 34.79929463071014, "learning_rate": 9.845704467353953e-06}
136
+ {"global_step": 1360, "epoch": 0.5598435731192755, "loss": 12.9433, "grad_norm": 36.095752723061416, "learning_rate": 9.842268041237114e-06}
137
+ {"global_step": 1370, "epoch": 0.5639600699804467, "loss": 12.907, "grad_norm": 36.27956418944883, "learning_rate": 9.838831615120276e-06}
138
+ {"global_step": 1380, "epoch": 0.5680765668416178, "loss": 12.91, "grad_norm": 35.72628600227518, "learning_rate": 9.835395189003437e-06}
139
+ {"global_step": 1390, "epoch": 0.5721930637027889, "loss": 12.8805, "grad_norm": 36.2974491311879, "learning_rate": 9.831958762886599e-06}
140
+ {"global_step": 1400, "epoch": 0.5763095605639601, "loss": 12.8487, "grad_norm": 38.753865801889205, "learning_rate": 9.82852233676976e-06}
141
+ {"global_step": 1410, "epoch": 0.5804260574251312, "loss": 12.8255, "grad_norm": 37.15806127726735, "learning_rate": 9.825085910652922e-06}
142
+ {"global_step": 1420, "epoch": 0.5845425542863023, "loss": 12.7318, "grad_norm": 31.930169790036125, "learning_rate": 9.821649484536083e-06}
143
+ {"global_step": 1430, "epoch": 0.5886590511474735, "loss": 12.8322, "grad_norm": 46.704762225618985, "learning_rate": 9.818213058419245e-06}
144
+ {"global_step": 1440, "epoch": 0.5927755480086446, "loss": 12.7815, "grad_norm": 33.776587810887825, "learning_rate": 9.814776632302406e-06}
145
+ {"global_step": 1450, "epoch": 0.5968920448698158, "loss": 12.7486, "grad_norm": 29.58229351266127, "learning_rate": 9.811340206185568e-06}
146
+ {"global_step": 1460, "epoch": 0.601008541730987, "loss": 12.6896, "grad_norm": 33.63398991455025, "learning_rate": 9.80790378006873e-06}
147
+ {"global_step": 1470, "epoch": 0.605125038592158, "loss": 12.6699, "grad_norm": 36.832689858066715, "learning_rate": 9.804467353951891e-06}
148
+ {"global_step": 1480, "epoch": 0.6092415354533293, "loss": 12.5471, "grad_norm": 37.43208595185383, "learning_rate": 9.801030927835052e-06}
149
+ {"global_step": 1490, "epoch": 0.6133580323145004, "loss": 12.6142, "grad_norm": 33.7941307098917, "learning_rate": 9.797594501718214e-06}
150
+ {"global_step": 1500, "epoch": 0.6174745291756715, "loss": 12.5338, "grad_norm": 31.9466158932975, "learning_rate": 9.794158075601375e-06}
151
+ {"global_step": 1510, "epoch": 0.6215910260368427, "loss": 12.4764, "grad_norm": 38.30578087105521, "learning_rate": 9.790721649484537e-06}
152
+ {"global_step": 1520, "epoch": 0.6257075228980138, "loss": 12.4952, "grad_norm": 32.61697454595358, "learning_rate": 9.787285223367698e-06}
153
+ {"global_step": 1530, "epoch": 0.6298240197591849, "loss": 12.4546, "grad_norm": 40.16758133155219, "learning_rate": 9.78384879725086e-06}
154
+ {"global_step": 1540, "epoch": 0.6339405166203561, "loss": 12.4843, "grad_norm": 48.80638115137875, "learning_rate": 9.780412371134021e-06}
155
+ {"global_step": 1550, "epoch": 0.6380570134815272, "loss": 12.4931, "grad_norm": 37.475171347455756, "learning_rate": 9.776975945017183e-06}
156
+ {"global_step": 1560, "epoch": 0.6421735103426983, "loss": 12.4005, "grad_norm": 33.28595513208406, "learning_rate": 9.773539518900344e-06}
157
+ {"global_step": 1570, "epoch": 0.6462900072038695, "loss": 12.3441, "grad_norm": 31.086866920620285, "learning_rate": 9.770103092783506e-06}
158
+ {"global_step": 1580, "epoch": 0.6504065040650406, "loss": 12.2734, "grad_norm": 39.3394583771368, "learning_rate": 9.766666666666667e-06}
159
+ {"global_step": 1590, "epoch": 0.6545230009262117, "loss": 12.3482, "grad_norm": 32.802912711135214, "learning_rate": 9.763230240549829e-06}
160
+ {"global_step": 1600, "epoch": 0.658639497787383, "loss": 12.3565, "grad_norm": 37.29399518826948, "learning_rate": 9.75979381443299e-06}
161
+ {"global_step": 1610, "epoch": 0.6627559946485541, "loss": 12.2918, "grad_norm": 31.346208761120682, "learning_rate": 9.756357388316152e-06}
162
+ {"global_step": 1620, "epoch": 0.6668724915097253, "loss": 12.2984, "grad_norm": 32.38506378128921, "learning_rate": 9.752920962199313e-06}
163
+ {"global_step": 1630, "epoch": 0.6709889883708964, "loss": 12.2223, "grad_norm": 37.55618381493301, "learning_rate": 9.749484536082475e-06}
164
+ {"global_step": 1640, "epoch": 0.6751054852320675, "loss": 12.2059, "grad_norm": 30.159408332251935, "learning_rate": 9.746048109965636e-06}
165
+ {"global_step": 1650, "epoch": 0.6792219820932387, "loss": 12.1934, "grad_norm": 33.64269413817189, "learning_rate": 9.742611683848798e-06}
166
+ {"global_step": 1660, "epoch": 0.6833384789544098, "loss": 12.2187, "grad_norm": 33.350706787266056, "learning_rate": 9.73917525773196e-06}
167
+ {"global_step": 1670, "epoch": 0.6874549758155809, "loss": 12.163, "grad_norm": 33.39405862288003, "learning_rate": 9.735738831615121e-06}
168
+ {"global_step": 1680, "epoch": 0.6915714726767521, "loss": 12.1662, "grad_norm": 33.41635090076034, "learning_rate": 9.732302405498283e-06}
169
+ {"global_step": 1690, "epoch": 0.6956879695379232, "loss": 12.2065, "grad_norm": 30.14281470411853, "learning_rate": 9.728865979381444e-06}
170
+ {"global_step": 1700, "epoch": 0.6998044663990943, "loss": 12.1291, "grad_norm": 30.467396684661566, "learning_rate": 9.725429553264606e-06}
171
+ {"global_step": 1710, "epoch": 0.7039209632602655, "loss": 12.0492, "grad_norm": 30.441530111439768, "learning_rate": 9.721993127147767e-06}
172
+ {"global_step": 1720, "epoch": 0.7080374601214366, "loss": 12.0813, "grad_norm": 28.49347966966388, "learning_rate": 9.718556701030929e-06}
173
+ {"global_step": 1730, "epoch": 0.7121539569826077, "loss": 12.0821, "grad_norm": 30.721181306779684, "learning_rate": 9.71512027491409e-06}
174
+ {"global_step": 1740, "epoch": 0.716270453843779, "loss": 12.0637, "grad_norm": 29.129251982891667, "learning_rate": 9.711683848797252e-06}
175
+ {"global_step": 1750, "epoch": 0.7203869507049501, "loss": 11.9994, "grad_norm": 29.95019721435932, "learning_rate": 9.708247422680413e-06}
176
+ {"global_step": 1760, "epoch": 0.7245034475661213, "loss": 12.024, "grad_norm": 32.81918337349151, "learning_rate": 9.704810996563575e-06}
177
+ {"global_step": 1770, "epoch": 0.7286199444272924, "loss": 12.0285, "grad_norm": 39.5144099446638, "learning_rate": 9.701374570446736e-06}
178
+ {"global_step": 1780, "epoch": 0.7327364412884635, "loss": 11.9479, "grad_norm": 31.653909615694747, "learning_rate": 9.697938144329898e-06}
179
+ {"global_step": 1790, "epoch": 0.7368529381496347, "loss": 11.9523, "grad_norm": 33.40571679023385, "learning_rate": 9.694501718213059e-06}
180
+ {"global_step": 1800, "epoch": 0.7409694350108058, "loss": 11.9416, "grad_norm": 37.473942426771224, "learning_rate": 9.69106529209622e-06}
181
+ {"global_step": 1810, "epoch": 0.7450859318719769, "loss": 12.0463, "grad_norm": 36.94155127706317, "learning_rate": 9.687628865979382e-06}
182
+ {"global_step": 1820, "epoch": 0.7492024287331481, "loss": 11.8785, "grad_norm": 37.68814388273857, "learning_rate": 9.684192439862544e-06}
183
+ {"global_step": 1830, "epoch": 0.7533189255943192, "loss": 11.8984, "grad_norm": 28.366410820050916, "learning_rate": 9.680756013745705e-06}
184
+ {"global_step": 1840, "epoch": 0.7574354224554903, "loss": 11.7795, "grad_norm": 32.286183742630165, "learning_rate": 9.677319587628867e-06}
185
+ {"global_step": 1850, "epoch": 0.7615519193166616, "loss": 11.7833, "grad_norm": 34.20137530626946, "learning_rate": 9.673883161512028e-06}
186
+ {"global_step": 1860, "epoch": 0.7656684161778327, "loss": 11.8231, "grad_norm": 26.974205102100083, "learning_rate": 9.67044673539519e-06}
187
+ {"global_step": 1870, "epoch": 0.7697849130390038, "loss": 11.839, "grad_norm": 30.78227640084708, "learning_rate": 9.667010309278351e-06}
188
+ {"global_step": 1880, "epoch": 0.773901409900175, "loss": 11.7576, "grad_norm": 32.775223259236476, "learning_rate": 9.663573883161513e-06}
189
+ {"global_step": 1890, "epoch": 0.7780179067613461, "loss": 11.8203, "grad_norm": 32.09910452344205, "learning_rate": 9.660137457044674e-06}
190
+ {"global_step": 1900, "epoch": 0.7821344036225172, "loss": 11.7395, "grad_norm": 34.679912416674696, "learning_rate": 9.656701030927836e-06}
191
+ {"global_step": 1910, "epoch": 0.7862509004836884, "loss": 11.7656, "grad_norm": 41.08474046950697, "learning_rate": 9.653264604810997e-06}
192
+ {"global_step": 1920, "epoch": 0.7903673973448595, "loss": 11.7157, "grad_norm": 43.79171589552821, "learning_rate": 9.649828178694159e-06}
193
+ {"global_step": 1930, "epoch": 0.7944838942060307, "loss": 11.7633, "grad_norm": 32.06890784949689, "learning_rate": 9.64639175257732e-06}
194
+ {"global_step": 1940, "epoch": 0.7986003910672018, "loss": 11.7696, "grad_norm": 33.88840596948513, "learning_rate": 9.642955326460482e-06}
195
+ {"global_step": 1950, "epoch": 0.8027168879283729, "loss": 11.6768, "grad_norm": 43.3525380610554, "learning_rate": 9.639518900343643e-06}
196
+ {"global_step": 1960, "epoch": 0.8068333847895441, "loss": 11.6438, "grad_norm": 29.03141895521922, "learning_rate": 9.636082474226805e-06}
197
+ {"global_step": 1970, "epoch": 0.8109498816507152, "loss": 11.648, "grad_norm": 31.577350376305315, "learning_rate": 9.632646048109966e-06}
198
+ {"global_step": 1980, "epoch": 0.8150663785118863, "loss": 11.5621, "grad_norm": 29.395462355828993, "learning_rate": 9.629209621993128e-06}
199
+ {"global_step": 1990, "epoch": 0.8191828753730576, "loss": 11.6605, "grad_norm": 36.070659840431695, "learning_rate": 9.625773195876289e-06}
200
+ {"global_step": 2000, "epoch": 0.8232993722342287, "loss": 11.6847, "grad_norm": 40.63936989861702, "learning_rate": 9.62233676975945e-06}
201
+ {"global_step": 2010, "epoch": 0.8274158690953998, "loss": 11.5951, "grad_norm": 28.74096555707873, "learning_rate": 9.618900343642612e-06}
202
+ {"global_step": 2020, "epoch": 0.831532365956571, "loss": 11.5425, "grad_norm": 26.857379564051325, "learning_rate": 9.615463917525774e-06}
203
+ {"global_step": 2030, "epoch": 0.8356488628177421, "loss": 11.5395, "grad_norm": 34.26526481929795, "learning_rate": 9.612027491408935e-06}
204
+ {"global_step": 2040, "epoch": 0.8397653596789132, "loss": 11.5239, "grad_norm": 39.61591003341877, "learning_rate": 9.608591065292097e-06}
205
+ {"global_step": 2050, "epoch": 0.8438818565400844, "loss": 11.5221, "grad_norm": 32.799457497612636, "learning_rate": 9.605154639175258e-06}
206
+ {"global_step": 2060, "epoch": 0.8479983534012555, "loss": 11.5188, "grad_norm": 30.46702989419665, "learning_rate": 9.60171821305842e-06}
207
+ {"global_step": 2070, "epoch": 0.8521148502624267, "loss": 11.5045, "grad_norm": 36.16227939472805, "learning_rate": 9.598281786941581e-06}
208
+ {"global_step": 2080, "epoch": 0.8562313471235978, "loss": 11.5307, "grad_norm": 35.47038057679002, "learning_rate": 9.594845360824743e-06}
209
+ {"global_step": 2090, "epoch": 0.8603478439847689, "loss": 11.523, "grad_norm": 32.257372818520146, "learning_rate": 9.591408934707904e-06}
210
+ {"global_step": 2100, "epoch": 0.8644643408459401, "loss": 11.5006, "grad_norm": 29.92970511160102, "learning_rate": 9.587972508591066e-06}
211
+ {"global_step": 2110, "epoch": 0.8685808377071113, "loss": 11.4492, "grad_norm": 31.548453221760763, "learning_rate": 9.584536082474227e-06}
212
+ {"global_step": 2120, "epoch": 0.8726973345682824, "loss": 11.4804, "grad_norm": 34.57267127412313, "learning_rate": 9.581099656357389e-06}
213
+ {"global_step": 2130, "epoch": 0.8768138314294536, "loss": 11.4529, "grad_norm": 34.17219698271619, "learning_rate": 9.57766323024055e-06}
214
+ {"global_step": 2140, "epoch": 0.8809303282906247, "loss": 11.3922, "grad_norm": 29.479641794210973, "learning_rate": 9.574226804123712e-06}
215
+ {"global_step": 2150, "epoch": 0.8850468251517958, "loss": 11.394, "grad_norm": 32.38400767680429, "learning_rate": 9.570790378006873e-06}
216
+ {"global_step": 2160, "epoch": 0.889163322012967, "loss": 11.3841, "grad_norm": 32.32981900594448, "learning_rate": 9.567353951890035e-06}
217
+ {"global_step": 2170, "epoch": 0.8932798188741381, "loss": 11.3688, "grad_norm": 33.61678562259265, "learning_rate": 9.563917525773196e-06}
218
+ {"global_step": 2180, "epoch": 0.8973963157353092, "loss": 11.3808, "grad_norm": 32.71587409986399, "learning_rate": 9.560481099656358e-06}
219
+ {"global_step": 2190, "epoch": 0.9015128125964804, "loss": 11.3336, "grad_norm": 29.54893232627574, "learning_rate": 9.55704467353952e-06}
220
+ {"global_step": 2200, "epoch": 0.9056293094576515, "loss": 11.3034, "grad_norm": 32.06137522253644, "learning_rate": 9.55360824742268e-06}
221
+ {"global_step": 2210, "epoch": 0.9097458063188227, "loss": 11.3092, "grad_norm": 36.467602001920255, "learning_rate": 9.550171821305842e-06}
222
+ {"global_step": 2220, "epoch": 0.9138623031799938, "loss": 11.3535, "grad_norm": 36.697441519061755, "learning_rate": 9.546735395189004e-06}
223
+ {"global_step": 2230, "epoch": 0.9179788000411649, "loss": 11.2906, "grad_norm": 29.195704697132054, "learning_rate": 9.543298969072165e-06}
224
+ {"global_step": 2240, "epoch": 0.9220952969023362, "loss": 11.2277, "grad_norm": 28.12150721519504, "learning_rate": 9.539862542955327e-06}
225
+ {"global_step": 2250, "epoch": 0.9262117937635073, "loss": 11.2413, "grad_norm": 28.28187759539184, "learning_rate": 9.536426116838488e-06}
226
+ {"global_step": 2260, "epoch": 0.9303282906246784, "loss": 11.2062, "grad_norm": 38.194498763414195, "learning_rate": 9.53298969072165e-06}
227
+ {"global_step": 2270, "epoch": 0.9344447874858496, "loss": 11.2868, "grad_norm": 30.60316989712369, "learning_rate": 9.529553264604811e-06}
228
+ {"global_step": 2280, "epoch": 0.9385612843470207, "loss": 11.3455, "grad_norm": 32.2566760579608, "learning_rate": 9.526116838487973e-06}
229
+ {"global_step": 2290, "epoch": 0.9426777812081918, "loss": 11.2271, "grad_norm": 29.363121550952414, "learning_rate": 9.522680412371134e-06}
230
+ {"global_step": 2300, "epoch": 0.946794278069363, "loss": 11.2572, "grad_norm": 34.44659489587604, "learning_rate": 9.519243986254296e-06}
231
+ {"global_step": 2310, "epoch": 0.9509107749305341, "loss": 11.2059, "grad_norm": 38.421619327615275, "learning_rate": 9.515807560137457e-06}
232
+ {"global_step": 2320, "epoch": 0.9550272717917052, "loss": 11.2005, "grad_norm": 28.45314623909409, "learning_rate": 9.512371134020619e-06}
233
+ {"global_step": 2330, "epoch": 0.9591437686528764, "loss": 11.1696, "grad_norm": 33.71882176291607, "learning_rate": 9.50893470790378e-06}
234
+ {"global_step": 2340, "epoch": 0.9632602655140475, "loss": 11.1289, "grad_norm": 40.284639005118564, "learning_rate": 9.505498281786942e-06}
235
+ {"global_step": 2350, "epoch": 0.9673767623752186, "loss": 11.1945, "grad_norm": 29.578038874639823, "learning_rate": 9.502061855670103e-06}
236
+ {"global_step": 2360, "epoch": 0.9714932592363899, "loss": 11.1547, "grad_norm": 30.78279090155006, "learning_rate": 9.498625429553265e-06}
237
+ {"global_step": 2370, "epoch": 0.975609756097561, "loss": 11.1499, "grad_norm": 32.32491917371623, "learning_rate": 9.495189003436426e-06}
238
+ {"global_step": 2380, "epoch": 0.9797262529587322, "loss": 11.0843, "grad_norm": 33.912601882090534, "learning_rate": 9.491752577319588e-06}
239
+ {"global_step": 2390, "epoch": 0.9838427498199033, "loss": 11.0857, "grad_norm": 33.636974029662824, "learning_rate": 9.48831615120275e-06}
240
+ {"global_step": 2400, "epoch": 0.9879592466810744, "loss": 11.117, "grad_norm": 28.479925241415103, "learning_rate": 9.48487972508591e-06}
241
+ {"global_step": 2410, "epoch": 0.9920757435422456, "loss": 11.1586, "grad_norm": 32.19633310187057, "learning_rate": 9.481443298969072e-06}
242
+ {"global_step": 2420, "epoch": 0.9961922404034167, "loss": 11.0449, "grad_norm": 30.24939985897427, "learning_rate": 9.478006872852234e-06}
243
+ {"global_step": 2430, "epoch": 1.0, "loss": 10.2576, "grad_norm": 27.59918285796063, "learning_rate": 9.474570446735395e-06}
244
+ {"global_step": 2440, "epoch": 1.004116496861171, "loss": 10.9205, "grad_norm": 29.145692709878713, "learning_rate": 9.471134020618557e-06}
245
+ {"global_step": 2450, "epoch": 1.0082329937223422, "loss": 10.8674, "grad_norm": 34.22402623391047, "learning_rate": 9.467697594501718e-06}
246
+ {"global_step": 2460, "epoch": 1.0123494905835135, "loss": 10.9685, "grad_norm": 31.116476736190727, "learning_rate": 9.46426116838488e-06}
247
+ {"global_step": 2470, "epoch": 1.0164659874446846, "loss": 10.8758, "grad_norm": 31.010011036576245, "learning_rate": 9.460824742268041e-06}
248
+ {"global_step": 2480, "epoch": 1.0205824843058557, "loss": 10.8832, "grad_norm": 33.554395898942225, "learning_rate": 9.457388316151203e-06}
249
+ {"global_step": 2490, "epoch": 1.0246989811670268, "loss": 10.8374, "grad_norm": 33.7710211448291, "learning_rate": 9.453951890034366e-06}
250
+ {"global_step": 2500, "epoch": 1.028815478028198, "loss": 10.8073, "grad_norm": 36.176567342791, "learning_rate": 9.450515463917528e-06}
251
+ {"global_step": 2500, "epoch": 1.028815478028198, "eval_loss": 3.158303737640381, "eval_runtime": 3671.6298, "eval_samples_per_second": 149.924, "eval_steps_per_second": 0.293}
252
+ {"global_step": 2510, "epoch": 1.032931974889369, "loss": 10.8554, "grad_norm": 33.415438706038195, "learning_rate": 9.447079037800689e-06}
253
+ {"global_step": 2520, "epoch": 1.0370484717505404, "loss": 10.844, "grad_norm": 33.56857491605213, "learning_rate": 9.44364261168385e-06}
254
+ {"global_step": 2530, "epoch": 1.0411649686117115, "loss": 10.9254, "grad_norm": 28.692610292751354, "learning_rate": 9.440206185567012e-06}
255
+ {"global_step": 2540, "epoch": 1.0452814654728826, "loss": 10.8743, "grad_norm": 37.71077640271992, "learning_rate": 9.436769759450174e-06}
256
+ {"global_step": 2550, "epoch": 1.0493979623340537, "loss": 10.884, "grad_norm": 39.50450285467682, "learning_rate": 9.433333333333335e-06}
257
+ {"global_step": 2560, "epoch": 1.0535144591952248, "loss": 10.8537, "grad_norm": 33.57213304521402, "learning_rate": 9.429896907216497e-06}
258
+ {"global_step": 2570, "epoch": 1.057630956056396, "loss": 10.8328, "grad_norm": 32.59962115413462, "learning_rate": 9.426460481099658e-06}
259
+ {"global_step": 2580, "epoch": 1.0617474529175672, "loss": 10.8917, "grad_norm": 34.910436921816675, "learning_rate": 9.42302405498282e-06}
260
+ {"global_step": 2590, "epoch": 1.0658639497787383, "loss": 10.8385, "grad_norm": 27.303722252736947, "learning_rate": 9.419587628865981e-06}
261
+ {"global_step": 2600, "epoch": 1.0699804466399094, "loss": 10.8006, "grad_norm": 31.339676779439166, "learning_rate": 9.416151202749143e-06}
262
+ {"global_step": 2610, "epoch": 1.0740969435010805, "loss": 10.7646, "grad_norm": 31.406463331327124, "learning_rate": 9.412714776632304e-06}
263
+ {"global_step": 2620, "epoch": 1.0782134403622516, "loss": 10.7957, "grad_norm": 34.52313243956516, "learning_rate": 9.409278350515466e-06}
264
+ {"global_step": 2630, "epoch": 1.082329937223423, "loss": 10.824, "grad_norm": 34.82551474227616, "learning_rate": 9.405841924398627e-06}
265
+ {"global_step": 2640, "epoch": 1.086446434084594, "loss": 10.7844, "grad_norm": 35.0844939375081, "learning_rate": 9.402405498281789e-06}
266
+ {"global_step": 2650, "epoch": 1.0905629309457652, "loss": 10.7582, "grad_norm": 33.8646318867766, "learning_rate": 9.39896907216495e-06}
267
+ {"global_step": 2660, "epoch": 1.0946794278069363, "loss": 10.7714, "grad_norm": 30.267226879030765, "learning_rate": 9.395532646048112e-06}
268
+ {"global_step": 2670, "epoch": 1.0987959246681074, "loss": 10.7044, "grad_norm": 32.65500459467302, "learning_rate": 9.392096219931273e-06}
269
+ {"global_step": 2680, "epoch": 1.1029124215292785, "loss": 10.7325, "grad_norm": 29.90355585105674, "learning_rate": 9.388659793814435e-06}
270
+ {"global_step": 2690, "epoch": 1.1070289183904498, "loss": 10.7143, "grad_norm": 28.569571173298087, "learning_rate": 9.385223367697596e-06}
271
+ {"global_step": 2700, "epoch": 1.111145415251621, "loss": 10.7198, "grad_norm": 34.54223606254732, "learning_rate": 9.381786941580758e-06}
272
+ {"global_step": 2710, "epoch": 1.115261912112792, "loss": 10.7134, "grad_norm": 41.65988359943903, "learning_rate": 9.378350515463919e-06}
273
+ {"global_step": 2720, "epoch": 1.1193784089739631, "loss": 10.7478, "grad_norm": 31.147728489757004, "learning_rate": 9.37491408934708e-06}
274
+ {"global_step": 2730, "epoch": 1.1234949058351342, "loss": 10.7194, "grad_norm": 34.35653519254494, "learning_rate": 9.371477663230242e-06}
275
+ {"global_step": 2740, "epoch": 1.1276114026963056, "loss": 10.709, "grad_norm": 28.753608820035986, "learning_rate": 9.368041237113404e-06}
276
+ {"global_step": 2750, "epoch": 1.1317278995574767, "loss": 10.6483, "grad_norm": 33.40825861778074, "learning_rate": 9.364604810996565e-06}
277
+ {"global_step": 2760, "epoch": 1.1358443964186478, "loss": 10.6871, "grad_norm": 35.80091959274697, "learning_rate": 9.361168384879727e-06}
278
+ {"global_step": 2770, "epoch": 1.1399608932798189, "loss": 10.6778, "grad_norm": 29.44549475248084, "learning_rate": 9.357731958762888e-06}
279
+ {"global_step": 2780, "epoch": 1.14407739014099, "loss": 10.594, "grad_norm": 30.257547070006492, "learning_rate": 9.35429553264605e-06}
280
+ {"global_step": 2790, "epoch": 1.148193887002161, "loss": 10.621, "grad_norm": 32.02247706651434, "learning_rate": 9.350859106529211e-06}
281
+ {"global_step": 2800, "epoch": 1.1523103838633324, "loss": 10.6492, "grad_norm": 29.489438810378612, "learning_rate": 9.347422680412373e-06}
282
+ {"global_step": 2810, "epoch": 1.1564268807245035, "loss": 10.578, "grad_norm": 29.232020772768045, "learning_rate": 9.343986254295534e-06}
283
+ {"global_step": 2820, "epoch": 1.1605433775856746, "loss": 10.6208, "grad_norm": 34.113466181093656, "learning_rate": 9.340549828178694e-06}
284
+ {"global_step": 2830, "epoch": 1.1646598744468457, "loss": 10.6177, "grad_norm": 28.652154767647808, "learning_rate": 9.337113402061855e-06}
285
+ {"global_step": 2840, "epoch": 1.1687763713080168, "loss": 10.6009, "grad_norm": 30.199419083823177, "learning_rate": 9.333676975945017e-06}
286
+ {"global_step": 2850, "epoch": 1.1728928681691881, "loss": 10.6318, "grad_norm": 30.560648700009178, "learning_rate": 9.330240549828178e-06}
287
+ {"global_step": 2860, "epoch": 1.1770093650303592, "loss": 10.6573, "grad_norm": 39.61531783787058, "learning_rate": 9.32680412371134e-06}
288
+ {"global_step": 2870, "epoch": 1.1811258618915303, "loss": 10.5804, "grad_norm": 32.38846280563923, "learning_rate": 9.323367697594501e-06}
289
+ {"global_step": 2880, "epoch": 1.1852423587527015, "loss": 10.618, "grad_norm": 28.914675084096515, "learning_rate": 9.319931271477663e-06}
290
+ {"global_step": 2890, "epoch": 1.1893588556138726, "loss": 10.5063, "grad_norm": 30.757441625032715, "learning_rate": 9.316494845360825e-06}
291
+ {"global_step": 2900, "epoch": 1.1934753524750437, "loss": 10.5521, "grad_norm": 31.287565569939332, "learning_rate": 9.313058419243986e-06}
292
+ {"global_step": 2910, "epoch": 1.1975918493362148, "loss": 10.5292, "grad_norm": 28.929871208415086, "learning_rate": 9.309621993127148e-06}
293
+ {"global_step": 2920, "epoch": 1.201708346197386, "loss": 10.5852, "grad_norm": 31.229185761150184, "learning_rate": 9.306185567010309e-06}
294
+ {"global_step": 2930, "epoch": 1.2058248430585572, "loss": 10.5663, "grad_norm": 33.338469531453924, "learning_rate": 9.30274914089347e-06}