Hugging Face's logo

chomeed
/
robometer-4b-full-threading-d0

Transformers
Safetensors
qwen2_5_vl
reward_model
rbm
robometer
mimicgen
text-generation-inference
Model card Files
xet
 Community
chomeed commited on
Commit
8e0d74a
·
verified ·
1 Parent(s): 7308249

Full fine-tune of Robometer-4B on mimicgen threading_d0 (best ckpt, step 500)

Browse files
Files changed (10) hide show
  1. README.md +20 -0
  2. config.json +119 -0
  3. config.yaml +179 -0
  4. dataset_random_state.json +634 -0
  5. metrics.json +35 -0
  6. model-00001-of-00002.safetensors +3 -0
  7. model-00002-of-00002.safetensors +3 -0
  8. model.safetensors.index.json +740 -0
  9. trainer_state.json +3534 -0
  10. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: Qwen/Qwen3-VL-4B-Instruct
4
+ tags:
5
+ - reward_model
6
+ - rbm
7
+ - preference_comparisons
8
+ library_name: transformers
9
+ ---
10
+
11
+ # chomeed/robometer-4b-full-threading-d0
12
+
13
+ ## Model Details
14
+
15
+ - **Base Model**: Qwen/Qwen3-VL-4B-Instruct
16
+ - **Model Type**: qwen2_5_vl
17
+
18
+ ## Citation
19
+
20
+ If you use this model, please cite:
config.json ADDED
@@ -0,0 +1,119 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RFM"
4
+ ],
5
+ "dtype": "bfloat16",
6
+ "image_token_id": 151655,
7
+ "model_type": "qwen2_5_vl",
8
+ "pad_token_id": 151654,
9
+ "text_config": {
10
+ "architectures": [
11
+ "RBM"
12
+ ],
13
+ "attention_bias": false,
14
+ "attention_dropout": 0.0,
15
+ "bos_token_id": 151643,
16
+ "dtype": "float32",
17
+ "eos_token_id": 151645,
18
+ "head_dim": 128,
19
+ "hidden_act": "silu",
20
+ "hidden_size": 2560,
21
+ "initializer_range": 0.02,
22
+ "intermediate_size": 9728,
23
+ "layer_types": [
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
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
+ ],
61
+ "max_position_embeddings": 262144,
62
+ "max_window_layers": 80,
63
+ "model_type": "qwen2_5_vl_text",
64
+ "num_attention_heads": 32,
65
+ "num_hidden_layers": 36,
66
+ "num_key_value_heads": 8,
67
+ "rms_norm_eps": 1e-06,
68
+ "rope_scaling": {
69
+ "mrope_interleaved": true,
70
+ "mrope_section": [
71
+ 24,
72
+ 20,
73
+ 20
74
+ ],
75
+ "rope_type": "default"
76
+ },
77
+ "rope_theta": 5000000,
78
+ "sliding_window": null,
79
+ "tie_word_embeddings": true,
80
+ "use_cache": true,
81
+ "use_sliding_window": false,
82
+ "vocab_size": 151674
83
+ },
84
+ "transformers_version": "4.57.6",
85
+ "unsloth_fixed": true,
86
+ "unsloth_version": "2025.10.11",
87
+ "video_token_id": 151656,
88
+ "vision_config": {
89
+ "deepstack_visual_indexes": [
90
+ 5,
91
+ 11,
92
+ 17
93
+ ],
94
+ "depth": 24,
95
+ "dtype": "float32",
96
+ "fullatt_block_indexes": [
97
+ 7,
98
+ 15,
99
+ 23,
100
+ 31
101
+ ],
102
+ "hidden_act": "gelu_pytorch_tanh",
103
+ "hidden_size": 1024,
104
+ "in_channels": 3,
105
+ "initializer_range": 0.02,
106
+ "intermediate_size": 4096,
107
+ "model_type": "qwen2_5_vl",
108
+ "num_heads": 16,
109
+ "num_position_embeddings": 2304,
110
+ "out_hidden_size": 2560,
111
+ "patch_size": 16,
112
+ "spatial_merge_size": 2,
113
+ "temporal_patch_size": 2,
114
+ "tokens_per_second": 4,
115
+ "window_size": 112
116
+ },
117
+ "vision_end_token_id": 151653,
118
+ "vision_start_token_id": 151652
119
+ }
config.yaml ADDED
@@ -0,0 +1,179 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ custom_eval:
2
+ comparisons_per_task: 5
3
+ confusion_matrix:
4
+ - mw
5
+ confusion_matrix_n_trajectories_per_source: 5
6
+ custom_eval_random_seed: 42
7
+ eval_types:
8
+ - reward_alignment
9
+ - policy_ranking
10
+ max_comparisons: null
11
+ num_examples_per_quality_pr: 5
12
+ num_partial_successes: 5
13
+ pad_frames: true
14
+ policy_ranking:
15
+ - chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm
16
+ policy_ranking_max_tasks: 1
17
+ quality_preference:
18
+ - mw
19
+ reward_alignment:
20
+ - chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm
21
+ reward_alignment_max_plots_failure: 5
22
+ reward_alignment_max_plots_successful: 5
23
+ reward_alignment_max_trajectories: null
24
+ subsample_n_frames: null
25
+ use_frame_steps: true
26
+ data:
27
+ data_source_weights: null
28
+ dataloader_num_workers: 8
29
+ dataloader_persistent_workers: true
30
+ dataloader_pin_memory: true
31
+ dataset_preference_ratio: 0.7
32
+ dataset_success_cutoff_file: robometer/data/dataset_success_cutoff.txt
33
+ dataset_type: rbm
34
+ eval_datasets:
35
+ - chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm
36
+ eval_subset_size: null
37
+ load_embeddings: false
38
+ max_frames: 16
39
+ max_frames_after_preprocessing: 64
40
+ max_success: 1.0
41
+ max_trajectories: -1
42
+ min_frames_per_trajectory: 5
43
+ min_success: 0.5
44
+ partial_success_threshold: 0.2
45
+ predict_last_frame_partial_progress: false
46
+ preference_strategy_ratio:
47
+ - 1.0
48
+ - 1.0
49
+ - 1.0
50
+ - 1.0
51
+ progress_discrete_bins: 10
52
+ progress_loss_type: discrete
53
+ progress_pred_type: absolute_first_frame
54
+ progress_strategy_ratio:
55
+ - 1.0
56
+ - 1.0
57
+ - 1.0
58
+ - 1.0
59
+ resized_height: null
60
+ resized_width: null
61
+ sample_type_ratio:
62
+ - 1.0
63
+ - 0.0
64
+ - 0.0
65
+ seed: 42
66
+ shuffle: true
67
+ shuffle_progress_frames: false
68
+ train_datasets:
69
+ - chomeed_mimicgen_threading_d0_train_rfm_mimicgen_threading_d0_train_rfm
70
+ traj_same_source_prob: 0.5
71
+ use_multi_image: true
72
+ use_per_frame_progress_token: true
73
+ debug: false
74
+ logging:
75
+ log_level: INFO
76
+ log_to: []
77
+ save_best:
78
+ greater_is_better:
79
+ - true
80
+ - true
81
+ hub_private: false
82
+ hub_save_every: 1000
83
+ hub_token: null
84
+ keep_top_k: 5
85
+ metric_names:
86
+ - eval_rew_align/pearson_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm
87
+ - eval_p_rank/kendall_last_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm
88
+ save_every: 1000
89
+ upload_to_hub: false
90
+ save_model: true
91
+ save_processor: true
92
+ wandb_entity: jesbu1
93
+ wandb_mode: null
94
+ wandb_notes: training Robometer
95
+ wandb_project: robometer
96
+ loss:
97
+ predict_last_frame_progress: false
98
+ progress_discrete_bins: 10
99
+ progress_loss_type: discrete
100
+ success_positive_weight: 1.0
101
+ mode: train
102
+ model:
103
+ average_temporal_patches: true
104
+ base_model_id: Qwen/Qwen3-VL-4B-Instruct
105
+ frame_pooling: mean
106
+ frame_pooling_attn_temperature: 1.0
107
+ model_type: default
108
+ peft_vision_encoder: false
109
+ progress_discrete_bins: 10
110
+ progress_loss_type: discrete
111
+ quantization: false
112
+ rewind: null
113
+ torch_dtype: bfloat16
114
+ train_language_model: true
115
+ train_preference_head: true
116
+ train_progress_head: true
117
+ train_success_head: true
118
+ train_vision_encoder: false
119
+ trust_remote_code: true
120
+ use_multi_image: true
121
+ use_peft: false
122
+ use_per_frame_progress_token: true
123
+ use_unsloth: true
124
+ peft:
125
+ bias: none
126
+ lora_alpha: 64
127
+ lora_dropout: 0.05
128
+ peft_vision_encoder: false
129
+ r: 32
130
+ target_modules:
131
+ - q_proj
132
+ - k_proj
133
+ - v_proj
134
+ - o_proj
135
+ - gate_proj
136
+ - up_proj
137
+ - down_proj
138
+ trainer_cls: rbm_heads
139
+ training:
140
+ beta: 0.1
141
+ bf16: true
142
+ custom_eval_steps: 100
143
+ dataloader_num_workers: 8
144
+ dataloader_persistent_workers: true
145
+ dataloader_pin_memory: true
146
+ ddp_bucket_cap_mb: 25
147
+ ddp_find_unused_parameters: false
148
+ do_eval: true
149
+ eval_steps: 100
150
+ evaluation_strategy: steps
151
+ exp_name: mimicgen_threading_d0_full
152
+ fp16: false
153
+ gradient_accumulation_steps: 1
154
+ gradient_checkpointing: true
155
+ learning_rate: 2.0e-05
156
+ load_from_checkpoint: robometer/Robometer-4B
157
+ logging_steps: 1
158
+ lr_scheduler_type: cosine
159
+ max_grad_norm: 10.0
160
+ max_seq_length: 1024
161
+ max_steps: 1000
162
+ num_gpus: 2
163
+ num_train_epochs: -1
164
+ output_dir: ./logs
165
+ overwrite_output_dir: true
166
+ per_device_eval_batch_size: 8
167
+ per_device_train_batch_size: 8
168
+ predict_pref_progress: true
169
+ prediction_loss_only: true
170
+ remove_unused_columns: false
171
+ resume_from_checkpoint: null
172
+ run_default_eval: false
173
+ save_steps: 200
174
+ save_strategy: 'no'
175
+ vision_encoder_lr: 1.0e-05
176
+ vision_encoder_num_layers: 3
177
+ warmup_ratio: 0.1
178
+ warmup_steps: 0
179
+ weight_decay: 0.01
dataset_random_state.json ADDED
@@ -0,0 +1,634 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "pref_sampler": [
3
+ 3,
4
+ [
5
+ 2147483648,
6
+ 3564348608,
7
+ 1266698288,
8
+ 4212342371,
9
+ 3595291661,
10
+ 3180588708,
11
+ 3037210256,
12
+ 946923017,
13
+ 2565409715,
14
+ 2900535780,
15
+ 924383152,
16
+ 4180157270,
17
+ 4230508198,
18
+ 2039675917,
19
+ 3755350407,
20
+ 2362848650,
21
+ 2818100609,
22
+ 2097423432,
23
+ 524478045,
24
+ 540883378,
25
+ 281170210,
26
+ 1485176884,
27
+ 1493190386,
28
+ 1773214509,
29
+ 380915208,
30
+ 3667698522,
31
+ 2648371337,
32
+ 2961234806,
33
+ 3857480267,
34
+ 1582950522,
35
+ 246289694,
36
+ 3322185604,
37
+ 1944574775,
38
+ 302623699,
39
+ 169865066,
40
+ 1143540808,
41
+ 3733177770,
42
+ 513116636,
43
+ 1411153081,
44
+ 3205493053,
45
+ 768926902,
46
+ 549624109,
47
+ 1470655403,
48
+ 59539609,
49
+ 3678480009,
50
+ 3087139671,
51
+ 1176835859,
52
+ 2078491503,
53
+ 2299934332,
54
+ 1592059249,
55
+ 1062716176,
56
+ 2654193596,
57
+ 3531838733,
58
+ 2661260596,
59
+ 3881209635,
60
+ 2106865768,
61
+ 4154287292,
62
+ 2082185616,
63
+ 2301197011,
64
+ 2177349827,
65
+ 3082181756,
66
+ 1787663536,
67
+ 3714670796,
68
+ 3018262113,
69
+ 1670056238,
70
+ 1856738750,
71
+ 99824592,
72
+ 2279837081,
73
+ 1414647942,
74
+ 3416675731,
75
+ 3458782472,
76
+ 3997022236,
77
+ 468762002,
78
+ 2666158583,
79
+ 953353270,
80
+ 1788980658,
81
+ 3802061067,
82
+ 407586584,
83
+ 1844776834,
84
+ 1906917274,
85
+ 3154715663,
86
+ 3028370222,
87
+ 4156024188,
88
+ 3996363428,
89
+ 80495456,
90
+ 2659800972,
91
+ 2005649973,
92
+ 3818358673,
93
+ 3952623596,
94
+ 2506862371,
95
+ 3282302532,
96
+ 263923435,
97
+ 3384662671,
98
+ 3292439172,
99
+ 3119957588,
100
+ 1224426111,
101
+ 899864150,
102
+ 215262826,
103
+ 1619647231,
104
+ 3347694949,
105
+ 3497868538,
106
+ 2029552053,
107
+ 2992804824,
108
+ 4080010250,
109
+ 2023513186,
110
+ 1885979437,
111
+ 3564622190,
112
+ 3775424270,
113
+ 2297810139,
114
+ 3549449169,
115
+ 2664856277,
116
+ 3274801974,
117
+ 2794883969,
118
+ 980412666,
119
+ 2980215653,
120
+ 2794389321,
121
+ 2816521934,
122
+ 1266970739,
123
+ 542306338,
124
+ 3646225311,
125
+ 3598997630,
126
+ 2111980720,
127
+ 2949252482,
128
+ 2489027658,
129
+ 352815024,
130
+ 11610683,
131
+ 1386663624,
132
+ 2004196796,
133
+ 1161461546,
134
+ 1921293780,
135
+ 2463949525,
136
+ 1647009713,
137
+ 3550093655,
138
+ 2563894064,
139
+ 3486310554,
140
+ 1506105865,
141
+ 243092931,
142
+ 2659437476,
143
+ 4200687059,
144
+ 2284345122,
145
+ 1974438610,
146
+ 3591096528,
147
+ 967119212,
148
+ 3362401375,
149
+ 140678365,
150
+ 311602112,
151
+ 2361740275,
152
+ 2139598582,
153
+ 3632873481,
154
+ 2762232439,
155
+ 4156482318,
156
+ 381637792,
157
+ 3253346525,
158
+ 2492118775,
159
+ 1502434558,
160
+ 3164497290,
161
+ 3550998357,
162
+ 2412448305,
163
+ 2223955385,
164
+ 4122879535,
165
+ 350121793,
166
+ 1835149778,
167
+ 2175117867,
168
+ 989674750,
169
+ 3178241202,
170
+ 3553093569,
171
+ 3470650311,
172
+ 2829698151,
173
+ 3209427769,
174
+ 1779174943,
175
+ 275388428,
176
+ 4044574515,
177
+ 715447260,
178
+ 3180940440,
179
+ 4020772289,
180
+ 1322708567,
181
+ 3189868792,
182
+ 4250485633,
183
+ 716970023,
184
+ 2307550151,
185
+ 1074996711,
186
+ 1217573599,
187
+ 197006094,
188
+ 2178394212,
189
+ 1255233746,
190
+ 4164251484,
191
+ 1405608772,
192
+ 2808160475,
193
+ 1304736088,
194
+ 1796071066,
195
+ 2761748078,
196
+ 3570739698,
197
+ 1616118556,
198
+ 2232868135,
199
+ 3567541936,
200
+ 3470600401,
201
+ 3031621994,
202
+ 3351764214,
203
+ 1359785149,
204
+ 2617497797,
205
+ 3340028190,
206
+ 356162828,
207
+ 2083806068,
208
+ 2503635608,
209
+ 4024838996,
210
+ 2577080371,
211
+ 2897993505,
212
+ 3120733934,
213
+ 905794891,
214
+ 2506078507,
215
+ 4211618666,
216
+ 3777871979,
217
+ 809751414,
218
+ 4080874167,
219
+ 1562977008,
220
+ 3917373055,
221
+ 2132779194,
222
+ 4014249473,
223
+ 4067327082,
224
+ 2582869847,
225
+ 1780081876,
226
+ 1842619106,
227
+ 3381761227,
228
+ 921004274,
229
+ 1393256920,
230
+ 1883566732,
231
+ 2702071861,
232
+ 865327389,
233
+ 1622085203,
234
+ 3021825820,
235
+ 2687061406,
236
+ 1748902923,
237
+ 689023977,
238
+ 308399650,
239
+ 2377287978,
240
+ 1646969411,
241
+ 1051806316,
242
+ 4277884230,
243
+ 2041056290,
244
+ 101134519,
245
+ 2032472116,
246
+ 4112521069,
247
+ 151202901,
248
+ 2773743461,
249
+ 551348559,
250
+ 3476836808,
251
+ 510935951,
252
+ 625057077,
253
+ 3757450756,
254
+ 2977698135,
255
+ 3027776859,
256
+ 2616998041,
257
+ 2773430005,
258
+ 544190486,
259
+ 2241368212,
260
+ 1141105829,
261
+ 1452816309,
262
+ 4199229235,
263
+ 3218013033,
264
+ 4229475816,
265
+ 1659576351,
266
+ 3020348754,
267
+ 1193400518,
268
+ 3208584597,
269
+ 1151197733,
270
+ 2597187966,
271
+ 503065140,
272
+ 2421841572,
273
+ 1437291709,
274
+ 1909275895,
275
+ 2872630545,
276
+ 793588217,
277
+ 3792934707,
278
+ 1784451785,
279
+ 2921385648,
280
+ 1669902526,
281
+ 4189978976,
282
+ 1196986251,
283
+ 434805516,
284
+ 1907541826,
285
+ 2624415034,
286
+ 1687778718,
287
+ 650746582,
288
+ 1949153382,
289
+ 4148493093,
290
+ 841300520,
291
+ 1164202054,
292
+ 4203468658,
293
+ 4106300911,
294
+ 850346789,
295
+ 1715730760,
296
+ 3114661489,
297
+ 2866524548,
298
+ 1360448945,
299
+ 3601318775,
300
+ 1743078223,
301
+ 2413855408,
302
+ 1211895622,
303
+ 325117146,
304
+ 2721152875,
305
+ 1284334485,
306
+ 2446538832,
307
+ 739014618,
308
+ 2237045115,
309
+ 842553465,
310
+ 2538598293,
311
+ 746460793,
312
+ 4010387366,
313
+ 2002655192,
314
+ 4193733112,
315
+ 1194380773,
316
+ 3918217378,
317
+ 1447487475,
318
+ 5659228,
319
+ 3408847694,
320
+ 4190318700,
321
+ 1862549564,
322
+ 781683719,
323
+ 1194618118,
324
+ 755053413,
325
+ 3436011942,
326
+ 2885435303,
327
+ 3081151348,
328
+ 2017642831,
329
+ 1053816502,
330
+ 1086627485,
331
+ 2157296554,
332
+ 110650022,
333
+ 965352898,
334
+ 1003174194,
335
+ 1288956241,
336
+ 4057404871,
337
+ 2965068465,
338
+ 2897064481,
339
+ 2457377317,
340
+ 1879872545,
341
+ 358455290,
342
+ 375086701,
343
+ 3015902095,
344
+ 1676249984,
345
+ 924455526,
346
+ 2084169389,
347
+ 1989014644,
348
+ 1993749926,
349
+ 2009424973,
350
+ 2113340508,
351
+ 3980883273,
352
+ 2915977458,
353
+ 203328382,
354
+ 3020815229,
355
+ 2415050113,
356
+ 4103009585,
357
+ 3700885489,
358
+ 2916647550,
359
+ 1523006503,
360
+ 174302338,
361
+ 2476909338,
362
+ 1969322490,
363
+ 4285741984,
364
+ 1528449097,
365
+ 3355315515,
366
+ 4217241278,
367
+ 599579127,
368
+ 2572243673,
369
+ 3035856735,
370
+ 1539140489,
371
+ 1782314913,
372
+ 4238644287,
373
+ 1746424142,
374
+ 1978148312,
375
+ 2380746849,
376
+ 184941882,
377
+ 1106717981,
378
+ 1720750349,
379
+ 981701307,
380
+ 3953154731,
381
+ 3257809181,
382
+ 2892339376,
383
+ 3339778166,
384
+ 3676936849,
385
+ 87425948,
386
+ 3029257381,
387
+ 2037942523,
388
+ 3807628706,
389
+ 2861474706,
390
+ 1058852346,
391
+ 1322765211,
392
+ 2686046342,
393
+ 2689342655,
394
+ 2303436168,
395
+ 2571627181,
396
+ 1986057734,
397
+ 1183564308,
398
+ 2829677523,
399
+ 1295563975,
400
+ 503126586,
401
+ 2025890348,
402
+ 4179277821,
403
+ 1735262467,
404
+ 981331774,
405
+ 1613447066,
406
+ 1011606109,
407
+ 2000062246,
408
+ 3581448390,
409
+ 3477731384,
410
+ 3641307373,
411
+ 3508544379,
412
+ 2327233491,
413
+ 3931944343,
414
+ 4189052882,
415
+ 2990416380,
416
+ 422406169,
417
+ 202291313,
418
+ 2531006461,
419
+ 4277024116,
420
+ 3815144003,
421
+ 821314585,
422
+ 1344175168,
423
+ 3562834071,
424
+ 1339615445,
425
+ 1831545190,
426
+ 3115548822,
427
+ 743512780,
428
+ 4006999448,
429
+ 3720181735,
430
+ 1012033521,
431
+ 919931041,
432
+ 2628967879,
433
+ 1151876565,
434
+ 1268107129,
435
+ 3674829936,
436
+ 834977846,
437
+ 743987006,
438
+ 3947536548,
439
+ 3706529695,
440
+ 4121073678,
441
+ 2507605742,
442
+ 1595636918,
443
+ 2708047833,
444
+ 2427507331,
445
+ 3868216331,
446
+ 3254240010,
447
+ 2097683411,
448
+ 3279710596,
449
+ 3686819053,
450
+ 1843541720,
451
+ 1683793619,
452
+ 3245287285,
453
+ 3571828776,
454
+ 3733296431,
455
+ 3806747478,
456
+ 1390930605,
457
+ 3860422228,
458
+ 114397037,
459
+ 1931519825,
460
+ 2770684378,
461
+ 1556101783,
462
+ 1436111731,
463
+ 4031950081,
464
+ 562876656,
465
+ 1775895782,
466
+ 612364620,
467
+ 1313509772,
468
+ 4283410242,
469
+ 3252958463,
470
+ 2176555836,
471
+ 3933073367,
472
+ 3013277102,
473
+ 1444071961,
474
+ 3120949516,
475
+ 2824578890,
476
+ 325676929,
477
+ 943677134,
478
+ 1800649256,
479
+ 1721927060,
480
+ 347498719,
481
+ 1435221321,
482
+ 2623572981,
483
+ 1408548470,
484
+ 4145586315,
485
+ 2901889237,
486
+ 1849377952,
487
+ 1239144551,
488
+ 3382598266,
489
+ 2992893897,
490
+ 3738297588,
491
+ 611280106,
492
+ 3897415338,
493
+ 2370299241,
494
+ 1772308583,
495
+ 3697465753,
496
+ 354508058,
497
+ 2702360134,
498
+ 591308331,
499
+ 3524072501,
500
+ 976616000,
501
+ 2563717192,
502
+ 3078266097,
503
+ 1376594703,
504
+ 4209795919,
505
+ 2454412767,
506
+ 2712206031,
507
+ 2963860163,
508
+ 3734324882,
509
+ 2248653800,
510
+ 324872786,
511
+ 3789837448,
512
+ 3779000146,
513
+ 527733939,
514
+ 2844165793,
515
+ 576499681,
516
+ 1618787435,
517
+ 2638888650,
518
+ 57511068,
519
+ 2804627518,
520
+ 2993670030,
521
+ 481402236,
522
+ 2810124845,
523
+ 1416045214,
524
+ 1723694191,
525
+ 1214944572,
526
+ 3188123783,
527
+ 1139185907,
528
+ 3851015362,
529
+ 1719652470,
530
+ 1661343029,
531
+ 3644307578,
532
+ 3564178709,
533
+ 1256656955,
534
+ 46631590,
535
+ 4231317929,
536
+ 3098958589,
537
+ 1834956625,
538
+ 2206185428,
539
+ 3695688374,
540
+ 3647957317,
541
+ 1064098871,
542
+ 1739100906,
543
+ 2579568980,
544
+ 27974051,
545
+ 2617466775,
546
+ 964075233,
547
+ 907049942,
548
+ 4164146575,
549
+ 3377168066,
550
+ 2524828266,
551
+ 1083546008,
552
+ 2992960953,
553
+ 2260789066,
554
+ 1543742095,
555
+ 2843842831,
556
+ 1375722284,
557
+ 3574521313,
558
+ 110842534,
559
+ 2310998251,
560
+ 3076511734,
561
+ 783145600,
562
+ 1287776608,
563
+ 3087144146,
564
+ 305559823,
565
+ 2356293719,
566
+ 3228441476,
567
+ 1678938122,
568
+ 3775814061,
569
+ 1620283952,
570
+ 2512027726,
571
+ 1031432407,
572
+ 962295099,
573
+ 3877418501,
574
+ 968669928,
575
+ 304126693,
576
+ 3711291137,
577
+ 3847527101,
578
+ 494066767,
579
+ 4050229756,
580
+ 4169448589,
581
+ 671763915,
582
+ 1095747781,
583
+ 4006132710,
584
+ 394725957,
585
+ 200521654,
586
+ 2715998750,
587
+ 1477567673,
588
+ 895171901,
589
+ 3370105999,
590
+ 2684157455,
591
+ 4153990023,
592
+ 3966076501,
593
+ 2043374409,
594
+ 144443759,
595
+ 6764556,
596
+ 1611650045,
597
+ 1480956755,
598
+ 1388276468,
599
+ 4136518438,
600
+ 1538041336,
601
+ 266773992,
602
+ 1623357516,
603
+ 2267298390,
604
+ 3183919402,
605
+ 1084292424,
606
+ 2796136160,
607
+ 2413448816,
608
+ 2850375199,
609
+ 3510894040,
610
+ 2644778623,
611
+ 3317288284,
612
+ 3697317540,
613
+ 1465776787,
614
+ 1843489446,
615
+ 1416711171,
616
+ 744701117,
617
+ 1286781349,
618
+ 3748640476,
619
+ 861982119,
620
+ 2377742909,
621
+ 1171768136,
622
+ 2701877439,
623
+ 3839724288,
624
+ 2869791015,
625
+ 2386067954,
626
+ 2629214347,
627
+ 955801623,
628
+ 3831079317,
629
+ 624
630
+ ],
631
+ null
632
+ ],
633
+ "progress_sampler": null
634
+ }
metrics.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "step": 500,
3
+ "metrics": {
4
+ "eval_rew_align/success_auprc_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm": 0.16177469536688965,
5
+ "eval_rew_align/positive_success_acc_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm": 0.05,
6
+ "eval_rew_align/negative_success_acc_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm": 1.0,
7
+ "eval_rew_align/loss_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm": 3.2358126759529116,
8
+ "eval_rew_align/pearson_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm": 0.980422842373061,
9
+ "eval_p_rank/kendall_last_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm": 1.0,
10
+ "eval_p_rank/kendall_rewind_last_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm": 1.0,
11
+ "eval_p_rank/avg_succ_fail_diff_last_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm": 0.20341934760411584,
12
+ "eval_p_rank/min_succ_fail_diff_last_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm": 0.20341934760411584,
13
+ "eval_p_rank/max_succ_fail_diff_last_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm": 0.20341934760411584,
14
+ "eval_p_rank/ranking_acc_last_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm": 1.0,
15
+ "eval_p_rank/ranking_acc_all_pairs_last_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm": 1.0,
16
+ "eval_p_rank/ranking_acc_failure_vs_successful_last_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm": 1.0,
17
+ "eval_p_rank/kendall_avg_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm": 1.0,
18
+ "eval_p_rank/kendall_rewind_avg_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm": 1.0,
19
+ "eval_p_rank/avg_succ_fail_diff_avg_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm": 0.20341934760411584,
20
+ "eval_p_rank/min_succ_fail_diff_avg_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm": 0.20341934760411584,
21
+ "eval_p_rank/max_succ_fail_diff_avg_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm": 0.20341934760411584,
22
+ "eval_p_rank/ranking_acc_avg_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm": 1.0,
23
+ "eval_p_rank/ranking_acc_all_pairs_avg_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm": 1.0,
24
+ "eval_p_rank/ranking_acc_failure_vs_successful_avg_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm": 1.0,
25
+ "eval_p_rank/kendall_sum_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm": 1.0,
26
+ "eval_p_rank/kendall_rewind_sum_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm": 1.0,
27
+ "eval_p_rank/avg_succ_fail_diff_sum_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm": 0.20341934760411584,
28
+ "eval_p_rank/min_succ_fail_diff_sum_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm": 0.20341934760411584,
29
+ "eval_p_rank/max_succ_fail_diff_sum_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm": 0.20341934760411584,
30
+ "eval_p_rank/ranking_acc_sum_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm": 1.0,
31
+ "eval_p_rank/ranking_acc_all_pairs_sum_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm": 1.0,
32
+ "eval_p_rank/ranking_acc_failure_vs_successful_sum_chomeed_mimicgen_threading_d0_test_rfm_mimicgen_threading_d0_test_rfm": 1.0,
33
+ "time/custom_evaluations": 96.72939321910962
34
+ }
35
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a5bd5bbf895e808bd20298d5925e8d8a67a6a9533c37bb368b10a02cdd88dca
3
+ size 4959486112
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a33ba235c11f151e44af79bd907a3239d603c384e1dd4e309dffa31ec6c0026
3
+ size 3935253104
model.safetensors.index.json ADDED
@@ -0,0 +1,740 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 4447004940,
4
+ "total_size": 8894651928
5
+ },
6
+ "weight_map": {
7
+ "frame_pool_attn.weight": "model-00002-of-00002.safetensors",
8
+ "model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors",
9
+ "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
10
+ "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
12
+ "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
13
+ "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
14
+ "model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
15
+ "model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
17
+ "model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
18
+ "model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
20
+ "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
21
+ "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
22
+ "model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
24
+ "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
25
+ "model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
26
+ "model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
27
+ "model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
28
+ "model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
29
+ "model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
30
+ "model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
31
+ "model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
32
+ "model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
35
+ "model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
36
+ "model.language_model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
37
+ "model.language_model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
38
+ "model.language_model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
39
+ "model.language_model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
40
+ "model.language_model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
41
+ "model.language_model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
42
+ "model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
43
+ "model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
44
+ "model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
45
+ "model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
46
+ "model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
47
+ "model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
48
+ "model.language_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
49
+ "model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
50
+ "model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
51
+ "model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
53
+ "model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
54
+ "model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
55
+ "model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
56
+ "model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
57
+ "model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
58
+ "model.language_model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
59
+ "model.language_model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.language_model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
61
+ "model.language_model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
62
+ "model.language_model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
63
+ "model.language_model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
64
+ "model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
65
+ "model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
66
+ "model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
67
+ "model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
68
+ "model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
69
+ "model.language_model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
70
+ "model.language_model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
71
+ "model.language_model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
72
+ "model.language_model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
73
+ "model.language_model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
74
+ "model.language_model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
75
+ "model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
76
+ "model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
77
+ "model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
78
+ "model.language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
79
+ "model.language_model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
80
+ "model.language_model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
81
+ "model.language_model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.language_model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
83
+ "model.language_model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
84
+ "model.language_model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
85
+ "model.language_model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
86
+ "model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
87
+ "model.language_model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.language_model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
89
+ "model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
90
+ "model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
91
+ "model.language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
92
+ "model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
93
+ "model.language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
94
+ "model.language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
95
+ "model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
96
+ "model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
97
+ "model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
98
+ "model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
99
+ "model.language_model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
100
+ "model.language_model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
101
+ "model.language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
102
+ "model.language_model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
103
+ "model.language_model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
104
+ "model.language_model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
105
+ "model.language_model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
106
+ "model.language_model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
107
+ "model.language_model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
108
+ "model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
109
+ "model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
110
+ "model.language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
111
+ "model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
112
+ "model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
113
+ "model.language_model.layers.17.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
114
+ "model.language_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
115
+ "model.language_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
116
+ "model.language_model.layers.17.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
117
+ "model.language_model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
118
+ "model.language_model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
119
+ "model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
120
+ "model.language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
121
+ "model.language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
122
+ "model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
123
+ "model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
124
+ "model.language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
125
+ "model.language_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
126
+ "model.language_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
127
+ "model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
128
+ "model.language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
129
+ "model.language_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
130
+ "model.language_model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
131
+ "model.language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
132
+ "model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
133
+ "model.language_model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
134
+ "model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
135
+ "model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
136
+ "model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
137
+ "model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
138
+ "model.language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
139
+ "model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
140
+ "model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
141
+ "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
142
+ "model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
143
+ "model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
144
+ "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
145
+ "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
146
+ "model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
147
+ "model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
148
+ "model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
149
+ "model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
150
+ "model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
151
+ "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
152
+ "model.language_model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
153
+ "model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
154
+ "model.language_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
155
+ "model.language_model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
156
+ "model.language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
157
+ "model.language_model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
158
+ "model.language_model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
159
+ "model.language_model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
160
+ "model.language_model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
161
+ "model.language_model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
162
+ "model.language_model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
163
+ "model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
164
+ "model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
165
+ "model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
166
+ "model.language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
167
+ "model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
168
+ "model.language_model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
169
+ "model.language_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
170
+ "model.language_model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
171
+ "model.language_model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
172
+ "model.language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
173
+ "model.language_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
174
+ "model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
175
+ "model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
176
+ "model.language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
177
+ "model.language_model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
178
+ "model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
179
+ "model.language_model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
180
+ "model.language_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
181
+ "model.language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
182
+ "model.language_model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
183
+ "model.language_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
184
+ "model.language_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
185
+ "model.language_model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
186
+ "model.language_model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
187
+ "model.language_model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
188
+ "model.language_model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
189
+ "model.language_model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
190
+ "model.language_model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
191
+ "model.language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
192
+ "model.language_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
193
+ "model.language_model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
194
+ "model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
195
+ "model.language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
196
+ "model.language_model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
197
+ "model.language_model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
198
+ "model.language_model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
199
+ "model.language_model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
200
+ "model.language_model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
201
+ "model.language_model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
202
+ "model.language_model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
203
+ "model.language_model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
204
+ "model.language_model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
205
+ "model.language_model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
206
+ "model.language_model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
207
+ "model.language_model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
208
+ "model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
209
+ "model.language_model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
210
+ "model.language_model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
211
+ "model.language_model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
212
+ "model.language_model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
213
+ "model.language_model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
214
+ "model.language_model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
215
+ "model.language_model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
216
+ "model.language_model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
217
+ "model.language_model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
218
+ "model.language_model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
219
+ "model.language_model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
220
+ "model.language_model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
221
+ "model.language_model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
222
+ "model.language_model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
223
+ "model.language_model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
224
+ "model.language_model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
225
+ "model.language_model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
226
+ "model.language_model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
227
+ "model.language_model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
228
+ "model.language_model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
229
+ "model.language_model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
230
+ "model.language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
231
+ "model.language_model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
232
+ "model.language_model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
233
+ "model.language_model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
234
+ "model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
235
+ "model.language_model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
236
+ "model.language_model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
237
+ "model.language_model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
238
+ "model.language_model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
239
+ "model.language_model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
240
+ "model.language_model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
241
+ "model.language_model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
242
+ "model.language_model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
243
+ "model.language_model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
244
+ "model.language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
245
+ "model.language_model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
246
+ "model.language_model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
247
+ "model.language_model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
248
+ "model.language_model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
249
+ "model.language_model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
250
+ "model.language_model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
251
+ "model.language_model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
252
+ "model.language_model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
253
+ "model.language_model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
254
+ "model.language_model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
255
+ "model.language_model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
256
+ "model.language_model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
257
+ "model.language_model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
258
+ "model.language_model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
259
+ "model.language_model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
260
+ "model.language_model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
261
+ "model.language_model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
262
+ "model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
263
+ "model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
264
+ "model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
265
+ "model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
266
+ "model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
267
+ "model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
268
+ "model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
269
+ "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
270
+ "model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
271
+ "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
272
+ "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
273
+ "model.language_model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
274
+ "model.language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
275
+ "model.language_model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
276
+ "model.language_model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
277
+ "model.language_model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
278
+ "model.language_model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
279
+ "model.language_model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
280
+ "model.language_model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
281
+ "model.language_model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
282
+ "model.language_model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
283
+ "model.language_model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
284
+ "model.language_model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
285
+ "model.language_model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
286
+ "model.language_model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
287
+ "model.language_model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
288
+ "model.language_model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
289
+ "model.language_model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
290
+ "model.language_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
291
+ "model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
292
+ "model.language_model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
293
+ "model.language_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
294
+ "model.language_model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
295
+ "model.language_model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
296
+ "model.language_model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
297
+ "model.language_model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
298
+ "model.language_model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
299
+ "model.language_model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
300
+ "model.language_model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
301
+ "model.language_model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
302
+ "model.language_model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
303
+ "model.language_model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
304
+ "model.language_model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
305
+ "model.language_model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
306
+ "model.language_model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
307
+ "model.language_model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
308
+ "model.language_model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
309
+ "model.language_model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
310
+ "model.language_model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
311
+ "model.language_model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
312
+ "model.language_model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
313
+ "model.language_model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
314
+ "model.language_model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
315
+ "model.language_model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
316
+ "model.language_model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
317
+ "model.language_model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
318
+ "model.language_model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
319
+ "model.language_model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
320
+ "model.language_model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
321
+ "model.language_model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
322
+ "model.language_model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
323
+ "model.language_model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
324
+ "model.language_model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
325
+ "model.language_model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
326
+ "model.language_model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
327
+ "model.language_model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
328
+ "model.language_model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
329
+ "model.language_model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
330
+ "model.language_model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
331
+ "model.language_model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
332
+ "model.language_model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
333
+ "model.language_model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
334
+ "model.language_model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
335
+ "model.language_model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
336
+ "model.language_model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
337
+ "model.language_model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
338
+ "model.language_model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
339
+ "model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
340
+ "model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
341
+ "model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
342
+ "model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
343
+ "model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
344
+ "model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
345
+ "model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
346
+ "model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
347
+ "model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
348
+ "model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
349
+ "model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
350
+ "model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
351
+ "model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
352
+ "model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
353
+ "model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
354
+ "model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
355
+ "model.language_model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
356
+ "model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
357
+ "model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
358
+ "model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
359
+ "model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
360
+ "model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
361
+ "model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
362
+ "model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
363
+ "model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
364
+ "model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
365
+ "model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
366
+ "model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
367
+ "model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
368
+ "model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
369
+ "model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
370
+ "model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
371
+ "model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
372
+ "model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
373
+ "model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
374
+ "model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
375
+ "model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
376
+ "model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
377
+ "model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
378
+ "model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
379
+ "model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
380
+ "model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
381
+ "model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
382
+ "model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
383
+ "model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
384
+ "model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
385
+ "model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
386
+ "model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
387
+ "model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
388
+ "model.language_model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
389
+ "model.language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
390
+ "model.language_model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
391
+ "model.language_model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
392
+ "model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
393
+ "model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
394
+ "model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
395
+ "model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
396
+ "model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
397
+ "model.language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
398
+ "model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
399
+ "model.language_model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
400
+ "model.language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
401
+ "model.language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
402
+ "model.language_model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
403
+ "model.language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
404
+ "model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
405
+ "model.language_model.norm.weight": "model-00002-of-00002.safetensors",
406
+ "model.visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
407
+ "model.visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
408
+ "model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
409
+ "model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
410
+ "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
411
+ "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
412
+ "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
413
+ "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
414
+ "model.visual.blocks.0.norm1.bias": "model-00001-of-00002.safetensors",
415
+ "model.visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
416
+ "model.visual.blocks.0.norm2.bias": "model-00001-of-00002.safetensors",
417
+ "model.visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
418
+ "model.visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
419
+ "model.visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
420
+ "model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
421
+ "model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
422
+ "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
423
+ "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
424
+ "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
425
+ "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
426
+ "model.visual.blocks.1.norm1.bias": "model-00001-of-00002.safetensors",
427
+ "model.visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
428
+ "model.visual.blocks.1.norm2.bias": "model-00001-of-00002.safetensors",
429
+ "model.visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
430
+ "model.visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
431
+ "model.visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
432
+ "model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
433
+ "model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
434
+ "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
435
+ "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
436
+ "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
437
+ "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
438
+ "model.visual.blocks.10.norm1.bias": "model-00001-of-00002.safetensors",
439
+ "model.visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
440
+ "model.visual.blocks.10.norm2.bias": "model-00001-of-00002.safetensors",
441
+ "model.visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
442
+ "model.visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
443
+ "model.visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
444
+ "model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
445
+ "model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
446
+ "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
447
+ "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
448
+ "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
449
+ "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
450
+ "model.visual.blocks.11.norm1.bias": "model-00001-of-00002.safetensors",
451
+ "model.visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
452
+ "model.visual.blocks.11.norm2.bias": "model-00001-of-00002.safetensors",
453
+ "model.visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
454
+ "model.visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
455
+ "model.visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
456
+ "model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
457
+ "model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
458
+ "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
459
+ "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
460
+ "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
461
+ "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
462
+ "model.visual.blocks.12.norm1.bias": "model-00001-of-00002.safetensors",
463
+ "model.visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
464
+ "model.visual.blocks.12.norm2.bias": "model-00001-of-00002.safetensors",
465
+ "model.visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
466
+ "model.visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
467
+ "model.visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
468
+ "model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
469
+ "model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
470
+ "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
471
+ "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
472
+ "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
473
+ "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
474
+ "model.visual.blocks.13.norm1.bias": "model-00001-of-00002.safetensors",
475
+ "model.visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
476
+ "model.visual.blocks.13.norm2.bias": "model-00001-of-00002.safetensors",
477
+ "model.visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
478
+ "model.visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
479
+ "model.visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
480
+ "model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
481
+ "model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
482
+ "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
483
+ "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
484
+ "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
485
+ "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
486
+ "model.visual.blocks.14.norm1.bias": "model-00001-of-00002.safetensors",
487
+ "model.visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
488
+ "model.visual.blocks.14.norm2.bias": "model-00001-of-00002.safetensors",
489
+ "model.visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
490
+ "model.visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
491
+ "model.visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
492
+ "model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
493
+ "model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
494
+ "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
495
+ "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
496
+ "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
497
+ "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
498
+ "model.visual.blocks.15.norm1.bias": "model-00001-of-00002.safetensors",
499
+ "model.visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
500
+ "model.visual.blocks.15.norm2.bias": "model-00001-of-00002.safetensors",
501
+ "model.visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
502
+ "model.visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
503
+ "model.visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
504
+ "model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
505
+ "model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
506
+ "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
507
+ "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
508
+ "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
509
+ "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
510
+ "model.visual.blocks.16.norm1.bias": "model-00001-of-00002.safetensors",
511
+ "model.visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
512
+ "model.visual.blocks.16.norm2.bias": "model-00001-of-00002.safetensors",
513
+ "model.visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
514
+ "model.visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
515
+ "model.visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
516
+ "model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
517
+ "model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
518
+ "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
519
+ "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
520
+ "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
521
+ "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
522
+ "model.visual.blocks.17.norm1.bias": "model-00001-of-00002.safetensors",
523
+ "model.visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
524
+ "model.visual.blocks.17.norm2.bias": "model-00001-of-00002.safetensors",
525
+ "model.visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
526
+ "model.visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
527
+ "model.visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
528
+ "model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
529
+ "model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
530
+ "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
531
+ "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
532
+ "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
533
+ "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
534
+ "model.visual.blocks.18.norm1.bias": "model-00001-of-00002.safetensors",
535
+ "model.visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
536
+ "model.visual.blocks.18.norm2.bias": "model-00001-of-00002.safetensors",
537
+ "model.visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
538
+ "model.visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
539
+ "model.visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
540
+ "model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
541
+ "model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
542
+ "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
543
+ "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
544
+ "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
545
+ "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
546
+ "model.visual.blocks.19.norm1.bias": "model-00001-of-00002.safetensors",
547
+ "model.visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
548
+ "model.visual.blocks.19.norm2.bias": "model-00001-of-00002.safetensors",
549
+ "model.visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
550
+ "model.visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
551
+ "model.visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
552
+ "model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
553
+ "model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
554
+ "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
555
+ "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
556
+ "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
557
+ "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
558
+ "model.visual.blocks.2.norm1.bias": "model-00001-of-00002.safetensors",
559
+ "model.visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
560
+ "model.visual.blocks.2.norm2.bias": "model-00001-of-00002.safetensors",
561
+ "model.visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
562
+ "model.visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
563
+ "model.visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
564
+ "model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
565
+ "model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
566
+ "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
567
+ "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
568
+ "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
569
+ "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
570
+ "model.visual.blocks.20.norm1.bias": "model-00001-of-00002.safetensors",
571
+ "model.visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
572
+ "model.visual.blocks.20.norm2.bias": "model-00001-of-00002.safetensors",
573
+ "model.visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
574
+ "model.visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
575
+ "model.visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
576
+ "model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
577
+ "model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
578
+ "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
579
+ "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
580
+ "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
581
+ "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
582
+ "model.visual.blocks.21.norm1.bias": "model-00001-of-00002.safetensors",
583
+ "model.visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
584
+ "model.visual.blocks.21.norm2.bias": "model-00001-of-00002.safetensors",
585
+ "model.visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
586
+ "model.visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
587
+ "model.visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
588
+ "model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
589
+ "model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
590
+ "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
591
+ "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
592
+ "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
593
+ "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
594
+ "model.visual.blocks.22.norm1.bias": "model-00001-of-00002.safetensors",
595
+ "model.visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
596
+ "model.visual.blocks.22.norm2.bias": "model-00001-of-00002.safetensors",
597
+ "model.visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
598
+ "model.visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
599
+ "model.visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
600
+ "model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
601
+ "model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
602
+ "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
603
+ "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
604
+ "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
605
+ "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
606
+ "model.visual.blocks.23.norm1.bias": "model-00001-of-00002.safetensors",
607
+ "model.visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
608
+ "model.visual.blocks.23.norm2.bias": "model-00001-of-00002.safetensors",
609
+ "model.visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
610
+ "model.visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
611
+ "model.visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
612
+ "model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
613
+ "model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
614
+ "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
615
+ "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
616
+ "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
617
+ "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
618
+ "model.visual.blocks.3.norm1.bias": "model-00001-of-00002.safetensors",
619
+ "model.visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
620
+ "model.visual.blocks.3.norm2.bias": "model-00001-of-00002.safetensors",
621
+ "model.visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
622
+ "model.visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
623
+ "model.visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
624
+ "model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
625
+ "model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
626
+ "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
627
+ "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
628
+ "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
629
+ "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
630
+ "model.visual.blocks.4.norm1.bias": "model-00001-of-00002.safetensors",
631
+ "model.visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
632
+ "model.visual.blocks.4.norm2.bias": "model-00001-of-00002.safetensors",
633
+ "model.visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
634
+ "model.visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
635
+ "model.visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
636
+ "model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
637
+ "model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
638
+ "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
639
+ "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
640
+ "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
641
+ "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
642
+ "model.visual.blocks.5.norm1.bias": "model-00001-of-00002.safetensors",
643
+ "model.visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
644
+ "model.visual.blocks.5.norm2.bias": "model-00001-of-00002.safetensors",
645
+ "model.visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
646
+ "model.visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
647
+ "model.visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
648
+ "model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
649
+ "model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
650
+ "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
651
+ "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
652
+ "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
653
+ "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
654
+ "model.visual.blocks.6.norm1.bias": "model-00001-of-00002.safetensors",
655
+ "model.visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
656
+ "model.visual.blocks.6.norm2.bias": "model-00001-of-00002.safetensors",
657
+ "model.visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
658
+ "model.visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
659
+ "model.visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
660
+ "model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
661
+ "model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
662
+ "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
663
+ "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
664
+ "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
665
+ "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
666
+ "model.visual.blocks.7.norm1.bias": "model-00001-of-00002.safetensors",
667
+ "model.visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
668
+ "model.visual.blocks.7.norm2.bias": "model-00001-of-00002.safetensors",
669
+ "model.visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
670
+ "model.visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
671
+ "model.visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
672
+ "model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
673
+ "model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
674
+ "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
675
+ "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
676
+ "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
677
+ "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
678
+ "model.visual.blocks.8.norm1.bias": "model-00001-of-00002.safetensors",
679
+ "model.visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
680
+ "model.visual.blocks.8.norm2.bias": "model-00001-of-00002.safetensors",
681
+ "model.visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
682
+ "model.visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
683
+ "model.visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
684
+ "model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
685
+ "model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
686
+ "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
687
+ "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
688
+ "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
689
+ "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
690
+ "model.visual.blocks.9.norm1.bias": "model-00001-of-00002.safetensors",
691
+ "model.visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
692
+ "model.visual.blocks.9.norm2.bias": "model-00001-of-00002.safetensors",
693
+ "model.visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
694
+ "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00002.safetensors",
695
+ "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00001-of-00002.safetensors",
696
+ "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00001-of-00002.safetensors",
697
+ "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00002.safetensors",
698
+ "model.visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00002.safetensors",
699
+ "model.visual.deepstack_merger_list.0.norm.weight": "model-00001-of-00002.safetensors",
700
+ "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00001-of-00002.safetensors",
701
+ "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00001-of-00002.safetensors",
702
+ "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00002.safetensors",
703
+ "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00002.safetensors",
704
+ "model.visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00002.safetensors",
705
+ "model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00002.safetensors",
706
+ "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00001-of-00002.safetensors",
707
+ "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00001-of-00002.safetensors",
708
+ "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00001-of-00002.safetensors",
709
+ "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00002.safetensors",
710
+ "model.visual.deepstack_merger_list.2.norm.bias": "model-00001-of-00002.safetensors",
711
+ "model.visual.deepstack_merger_list.2.norm.weight": "model-00001-of-00002.safetensors",
712
+ "model.visual.merger.linear_fc1.bias": "model-00001-of-00002.safetensors",
713
+ "model.visual.merger.linear_fc1.weight": "model-00001-of-00002.safetensors",
714
+ "model.visual.merger.linear_fc2.bias": "model-00001-of-00002.safetensors",
715
+ "model.visual.merger.linear_fc2.weight": "model-00001-of-00002.safetensors",
716
+ "model.visual.merger.norm.bias": "model-00001-of-00002.safetensors",
717
+ "model.visual.merger.norm.weight": "model-00001-of-00002.safetensors",
718
+ "model.visual.patch_embed.proj.bias": "model-00001-of-00002.safetensors",
719
+ "model.visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors",
720
+ "model.visual.pos_embed.weight": "model-00001-of-00002.safetensors",
721
+ "preference_head.0.bias": "model-00001-of-00002.safetensors",
722
+ "preference_head.0.weight": "model-00001-of-00002.safetensors",
723
+ "preference_head.1.bias": "model-00001-of-00002.safetensors",
724
+ "preference_head.1.weight": "model-00001-of-00002.safetensors",
725
+ "preference_head.4.bias": "model-00001-of-00002.safetensors",
726
+ "preference_head.4.weight": "model-00001-of-00002.safetensors",
727
+ "progress_head.0.bias": "model-00001-of-00002.safetensors",
728
+ "progress_head.0.weight": "model-00001-of-00002.safetensors",
729
+ "progress_head.1.bias": "model-00001-of-00002.safetensors",
730
+ "progress_head.1.weight": "model-00001-of-00002.safetensors",
731
+ "progress_head.4.bias": "model-00001-of-00002.safetensors",
732
+ "progress_head.4.weight": "model-00001-of-00002.safetensors",
733
+ "success_head.0.bias": "model-00001-of-00002.safetensors",
734
+ "success_head.0.weight": "model-00001-of-00002.safetensors",
735
+ "success_head.1.bias": "model-00001-of-00002.safetensors",
736
+ "success_head.1.weight": "model-00001-of-00002.safetensors",
737
+ "success_head.4.bias": "model-00001-of-00002.safetensors",
738
+ "success_head.4.weight": "model-00001-of-00002.safetensors"
739
+ }
740
+ }
trainer_state.json ADDED
@@ -0,0 +1,3534 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.025,
6
+ "eval_steps": 100,
7
+ "global_step": 500,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 5e-05,
14
+ "grad_norm": 122.16051483154297,
15
+ "learning_rate": 0.0,
16
+ "loss": 1.8961,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.0001,
21
+ "grad_norm": 68.64327239990234,
22
+ "learning_rate": 2.0000000000000002e-07,
23
+ "loss": 0.7336,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.00015,
28
+ "grad_norm": 34.362892150878906,
29
+ "learning_rate": 4.0000000000000003e-07,
30
+ "loss": 0.5657,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.0002,
35
+ "grad_norm": 151.97335815429688,
36
+ "learning_rate": 6.000000000000001e-07,
37
+ "loss": 1.3111,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.00025,
42
+ "grad_norm": 94.8849105834961,
43
+ "learning_rate": 8.000000000000001e-07,
44
+ "loss": 1.1928,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.0003,
49
+ "grad_norm": 68.24564361572266,
50
+ "learning_rate": 1.0000000000000002e-06,
51
+ "loss": 0.7754,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.00035,
56
+ "grad_norm": 106.96430969238281,
57
+ "learning_rate": 1.2000000000000002e-06,
58
+ "loss": 1.3711,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.0004,
63
+ "grad_norm": 51.82062911987305,
64
+ "learning_rate": 1.4000000000000001e-06,
65
+ "loss": 0.6345,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.00045,
70
+ "grad_norm": 106.7470703125,
71
+ "learning_rate": 1.6000000000000001e-06,
72
+ "loss": 1.4213,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.0005,
77
+ "grad_norm": 63.274295806884766,
78
+ "learning_rate": 1.8000000000000001e-06,
79
+ "loss": 0.612,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.00055,
84
+ "grad_norm": 88.51773071289062,
85
+ "learning_rate": 2.0000000000000003e-06,
86
+ "loss": 0.951,
87
+ "step": 11
88
+ },
89
+ {
90
+ "epoch": 0.0006,
91
+ "grad_norm": 120.4432373046875,
92
+ "learning_rate": 2.2e-06,
93
+ "loss": 1.3452,
94
+ "step": 12
95
+ },
96
+ {
97
+ "epoch": 0.00065,
98
+ "grad_norm": 68.23249053955078,
99
+ "learning_rate": 2.4000000000000003e-06,
100
+ "loss": 0.594,
101
+ "step": 13
102
+ },
103
+ {
104
+ "epoch": 0.0007,
105
+ "grad_norm": 113.59532165527344,
106
+ "learning_rate": 2.6e-06,
107
+ "loss": 1.4108,
108
+ "step": 14
109
+ },
110
+ {
111
+ "epoch": 0.00075,
112
+ "grad_norm": 78.14495086669922,
113
+ "learning_rate": 2.8000000000000003e-06,
114
+ "loss": 1.217,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 0.0008,
119
+ "grad_norm": 71.44093322753906,
120
+ "learning_rate": 3e-06,
121
+ "loss": 0.9976,
122
+ "step": 16
123
+ },
124
+ {
125
+ "epoch": 0.00085,
126
+ "grad_norm": 109.85679626464844,
127
+ "learning_rate": 3.2000000000000003e-06,
128
+ "loss": 0.9354,
129
+ "step": 17
130
+ },
131
+ {
132
+ "epoch": 0.0009,
133
+ "grad_norm": 166.82241821289062,
134
+ "learning_rate": 3.4000000000000005e-06,
135
+ "loss": 0.7291,
136
+ "step": 18
137
+ },
138
+ {
139
+ "epoch": 0.00095,
140
+ "grad_norm": 132.03396606445312,
141
+ "learning_rate": 3.6000000000000003e-06,
142
+ "loss": 0.8239,
143
+ "step": 19
144
+ },
145
+ {
146
+ "epoch": 0.001,
147
+ "grad_norm": 117.53083801269531,
148
+ "learning_rate": 3.8000000000000005e-06,
149
+ "loss": 1.138,
150
+ "step": 20
151
+ },
152
+ {
153
+ "epoch": 0.00105,
154
+ "grad_norm": 131.66677856445312,
155
+ "learning_rate": 4.000000000000001e-06,
156
+ "loss": 1.407,
157
+ "step": 21
158
+ },
159
+ {
160
+ "epoch": 0.0011,
161
+ "grad_norm": 65.3564453125,
162
+ "learning_rate": 4.2000000000000004e-06,
163
+ "loss": 0.3293,
164
+ "step": 22
165
+ },
166
+ {
167
+ "epoch": 0.00115,
168
+ "grad_norm": 61.042724609375,
169
+ "learning_rate": 4.4e-06,
170
+ "loss": 0.4492,
171
+ "step": 23
172
+ },
173
+ {
174
+ "epoch": 0.0012,
175
+ "grad_norm": 21.75531578063965,
176
+ "learning_rate": 4.600000000000001e-06,
177
+ "loss": 0.254,
178
+ "step": 24
179
+ },
180
+ {
181
+ "epoch": 0.00125,
182
+ "grad_norm": 100.22628021240234,
183
+ "learning_rate": 4.800000000000001e-06,
184
+ "loss": 1.13,
185
+ "step": 25
186
+ },
187
+ {
188
+ "epoch": 0.0013,
189
+ "grad_norm": 39.203861236572266,
190
+ "learning_rate": 5e-06,
191
+ "loss": 0.3655,
192
+ "step": 26
193
+ },
194
+ {
195
+ "epoch": 0.00135,
196
+ "grad_norm": 73.43659210205078,
197
+ "learning_rate": 5.2e-06,
198
+ "loss": 0.3976,
199
+ "step": 27
200
+ },
201
+ {
202
+ "epoch": 0.0014,
203
+ "grad_norm": 16.97100067138672,
204
+ "learning_rate": 5.400000000000001e-06,
205
+ "loss": 0.1936,
206
+ "step": 28
207
+ },
208
+ {
209
+ "epoch": 0.00145,
210
+ "grad_norm": 19.03237533569336,
211
+ "learning_rate": 5.600000000000001e-06,
212
+ "loss": 0.2026,
213
+ "step": 29
214
+ },
215
+ {
216
+ "epoch": 0.0015,
217
+ "grad_norm": 37.67095184326172,
218
+ "learning_rate": 5.8e-06,
219
+ "loss": 0.3037,
220
+ "step": 30
221
+ },
222
+ {
223
+ "epoch": 0.00155,
224
+ "grad_norm": 50.00007629394531,
225
+ "learning_rate": 6e-06,
226
+ "loss": 0.5524,
227
+ "step": 31
228
+ },
229
+ {
230
+ "epoch": 0.0016,
231
+ "grad_norm": 103.01881408691406,
232
+ "learning_rate": 6.200000000000001e-06,
233
+ "loss": 0.4411,
234
+ "step": 32
235
+ },
236
+ {
237
+ "epoch": 0.00165,
238
+ "grad_norm": 72.95085906982422,
239
+ "learning_rate": 6.4000000000000006e-06,
240
+ "loss": 0.5604,
241
+ "step": 33
242
+ },
243
+ {
244
+ "epoch": 0.0017,
245
+ "grad_norm": 82.70050811767578,
246
+ "learning_rate": 6.600000000000001e-06,
247
+ "loss": 0.5243,
248
+ "step": 34
249
+ },
250
+ {
251
+ "epoch": 0.00175,
252
+ "grad_norm": 44.8000602722168,
253
+ "learning_rate": 6.800000000000001e-06,
254
+ "loss": 0.4454,
255
+ "step": 35
256
+ },
257
+ {
258
+ "epoch": 0.0018,
259
+ "grad_norm": 74.06373596191406,
260
+ "learning_rate": 7e-06,
261
+ "loss": 0.8086,
262
+ "step": 36
263
+ },
264
+ {
265
+ "epoch": 0.00185,
266
+ "grad_norm": 26.03671646118164,
267
+ "learning_rate": 7.2000000000000005e-06,
268
+ "loss": 0.2051,
269
+ "step": 37
270
+ },
271
+ {
272
+ "epoch": 0.0019,
273
+ "grad_norm": 51.14949035644531,
274
+ "learning_rate": 7.4e-06,
275
+ "loss": 0.8955,
276
+ "step": 38
277
+ },
278
+ {
279
+ "epoch": 0.00195,
280
+ "grad_norm": 43.66708755493164,
281
+ "learning_rate": 7.600000000000001e-06,
282
+ "loss": 0.9189,
283
+ "step": 39
284
+ },
285
+ {
286
+ "epoch": 0.002,
287
+ "grad_norm": 9.864336967468262,
288
+ "learning_rate": 7.800000000000002e-06,
289
+ "loss": 0.1676,
290
+ "step": 40
291
+ },
292
+ {
293
+ "epoch": 0.00205,
294
+ "grad_norm": 73.50960540771484,
295
+ "learning_rate": 8.000000000000001e-06,
296
+ "loss": 0.4905,
297
+ "step": 41
298
+ },
299
+ {
300
+ "epoch": 0.0021,
301
+ "grad_norm": 21.008272171020508,
302
+ "learning_rate": 8.2e-06,
303
+ "loss": 0.1899,
304
+ "step": 42
305
+ },
306
+ {
307
+ "epoch": 0.00215,
308
+ "grad_norm": 33.150264739990234,
309
+ "learning_rate": 8.400000000000001e-06,
310
+ "loss": 0.7959,
311
+ "step": 43
312
+ },
313
+ {
314
+ "epoch": 0.0022,
315
+ "grad_norm": 5.327113151550293,
316
+ "learning_rate": 8.6e-06,
317
+ "loss": 0.2044,
318
+ "step": 44
319
+ },
320
+ {
321
+ "epoch": 0.00225,
322
+ "grad_norm": 6.212099075317383,
323
+ "learning_rate": 8.8e-06,
324
+ "loss": 0.1377,
325
+ "step": 45
326
+ },
327
+ {
328
+ "epoch": 0.0023,
329
+ "grad_norm": 41.24404525756836,
330
+ "learning_rate": 9e-06,
331
+ "loss": 0.1969,
332
+ "step": 46
333
+ },
334
+ {
335
+ "epoch": 0.00235,
336
+ "grad_norm": 55.61800765991211,
337
+ "learning_rate": 9.200000000000002e-06,
338
+ "loss": 0.8883,
339
+ "step": 47
340
+ },
341
+ {
342
+ "epoch": 0.0024,
343
+ "grad_norm": 43.88951110839844,
344
+ "learning_rate": 9.4e-06,
345
+ "loss": 0.3443,
346
+ "step": 48
347
+ },
348
+ {
349
+ "epoch": 0.00245,
350
+ "grad_norm": 16.66773796081543,
351
+ "learning_rate": 9.600000000000001e-06,
352
+ "loss": 0.1734,
353
+ "step": 49
354
+ },
355
+ {
356
+ "epoch": 0.0025,
357
+ "grad_norm": 80.06915283203125,
358
+ "learning_rate": 9.800000000000001e-06,
359
+ "loss": 0.4474,
360
+ "step": 50
361
+ },
362
+ {
363
+ "epoch": 0.00255,
364
+ "grad_norm": 66.25089263916016,
365
+ "learning_rate": 1e-05,
366
+ "loss": 0.6609,
367
+ "step": 51
368
+ },
369
+ {
370
+ "epoch": 0.0026,
371
+ "grad_norm": 21.153078079223633,
372
+ "learning_rate": 1.02e-05,
373
+ "loss": 0.1893,
374
+ "step": 52
375
+ },
376
+ {
377
+ "epoch": 0.00265,
378
+ "grad_norm": 68.32752227783203,
379
+ "learning_rate": 1.04e-05,
380
+ "loss": 0.4948,
381
+ "step": 53
382
+ },
383
+ {
384
+ "epoch": 0.0027,
385
+ "grad_norm": 54.980567932128906,
386
+ "learning_rate": 1.0600000000000002e-05,
387
+ "loss": 0.613,
388
+ "step": 54
389
+ },
390
+ {
391
+ "epoch": 0.00275,
392
+ "grad_norm": 15.39164924621582,
393
+ "learning_rate": 1.0800000000000002e-05,
394
+ "loss": 0.1968,
395
+ "step": 55
396
+ },
397
+ {
398
+ "epoch": 0.0028,
399
+ "grad_norm": 44.391944885253906,
400
+ "learning_rate": 1.1000000000000001e-05,
401
+ "loss": 0.4588,
402
+ "step": 56
403
+ },
404
+ {
405
+ "epoch": 0.00285,
406
+ "grad_norm": 10.547879219055176,
407
+ "learning_rate": 1.1200000000000001e-05,
408
+ "loss": 0.1715,
409
+ "step": 57
410
+ },
411
+ {
412
+ "epoch": 0.0029,
413
+ "grad_norm": 38.64859390258789,
414
+ "learning_rate": 1.14e-05,
415
+ "loss": 0.7959,
416
+ "step": 58
417
+ },
418
+ {
419
+ "epoch": 0.00295,
420
+ "grad_norm": 4.460653781890869,
421
+ "learning_rate": 1.16e-05,
422
+ "loss": 0.1458,
423
+ "step": 59
424
+ },
425
+ {
426
+ "epoch": 0.003,
427
+ "grad_norm": 25.946611404418945,
428
+ "learning_rate": 1.18e-05,
429
+ "loss": 0.566,
430
+ "step": 60
431
+ },
432
+ {
433
+ "epoch": 0.00305,
434
+ "grad_norm": 18.941125869750977,
435
+ "learning_rate": 1.2e-05,
436
+ "loss": 0.1629,
437
+ "step": 61
438
+ },
439
+ {
440
+ "epoch": 0.0031,
441
+ "grad_norm": 35.03038787841797,
442
+ "learning_rate": 1.22e-05,
443
+ "loss": 0.2886,
444
+ "step": 62
445
+ },
446
+ {
447
+ "epoch": 0.00315,
448
+ "grad_norm": 47.16691970825195,
449
+ "learning_rate": 1.2400000000000002e-05,
450
+ "loss": 0.5181,
451
+ "step": 63
452
+ },
453
+ {
454
+ "epoch": 0.0032,
455
+ "grad_norm": 33.76936340332031,
456
+ "learning_rate": 1.2600000000000001e-05,
457
+ "loss": 0.3963,
458
+ "step": 64
459
+ },
460
+ {
461
+ "epoch": 0.00325,
462
+ "grad_norm": 6.850577354431152,
463
+ "learning_rate": 1.2800000000000001e-05,
464
+ "loss": 0.1536,
465
+ "step": 65
466
+ },
467
+ {
468
+ "epoch": 0.0033,
469
+ "grad_norm": 20.172531127929688,
470
+ "learning_rate": 1.3000000000000001e-05,
471
+ "loss": 0.2775,
472
+ "step": 66
473
+ },
474
+ {
475
+ "epoch": 0.00335,
476
+ "grad_norm": 65.00743103027344,
477
+ "learning_rate": 1.3200000000000002e-05,
478
+ "loss": 0.7195,
479
+ "step": 67
480
+ },
481
+ {
482
+ "epoch": 0.0034,
483
+ "grad_norm": 52.568260192871094,
484
+ "learning_rate": 1.3400000000000002e-05,
485
+ "loss": 0.766,
486
+ "step": 68
487
+ },
488
+ {
489
+ "epoch": 0.00345,
490
+ "grad_norm": 9.241539001464844,
491
+ "learning_rate": 1.3600000000000002e-05,
492
+ "loss": 0.1225,
493
+ "step": 69
494
+ },
495
+ {
496
+ "epoch": 0.0035,
497
+ "grad_norm": 4.773672103881836,
498
+ "learning_rate": 1.38e-05,
499
+ "loss": 0.1336,
500
+ "step": 70
501
+ },
502
+ {
503
+ "epoch": 0.00355,
504
+ "grad_norm": 48.60388946533203,
505
+ "learning_rate": 1.4e-05,
506
+ "loss": 0.5573,
507
+ "step": 71
508
+ },
509
+ {
510
+ "epoch": 0.0036,
511
+ "grad_norm": 27.8742618560791,
512
+ "learning_rate": 1.4200000000000001e-05,
513
+ "loss": 0.2066,
514
+ "step": 72
515
+ },
516
+ {
517
+ "epoch": 0.00365,
518
+ "grad_norm": 26.072481155395508,
519
+ "learning_rate": 1.4400000000000001e-05,
520
+ "loss": 0.5932,
521
+ "step": 73
522
+ },
523
+ {
524
+ "epoch": 0.0037,
525
+ "grad_norm": 7.826942443847656,
526
+ "learning_rate": 1.46e-05,
527
+ "loss": 0.1474,
528
+ "step": 74
529
+ },
530
+ {
531
+ "epoch": 0.00375,
532
+ "grad_norm": 18.62906837463379,
533
+ "learning_rate": 1.48e-05,
534
+ "loss": 0.1875,
535
+ "step": 75
536
+ },
537
+ {
538
+ "epoch": 0.0038,
539
+ "grad_norm": 8.554287910461426,
540
+ "learning_rate": 1.5000000000000002e-05,
541
+ "loss": 0.1298,
542
+ "step": 76
543
+ },
544
+ {
545
+ "epoch": 0.00385,
546
+ "grad_norm": 5.140439987182617,
547
+ "learning_rate": 1.5200000000000002e-05,
548
+ "loss": 0.1242,
549
+ "step": 77
550
+ },
551
+ {
552
+ "epoch": 0.0039,
553
+ "grad_norm": 3.9687063694000244,
554
+ "learning_rate": 1.54e-05,
555
+ "loss": 0.122,
556
+ "step": 78
557
+ },
558
+ {
559
+ "epoch": 0.00395,
560
+ "grad_norm": 33.81657028198242,
561
+ "learning_rate": 1.5600000000000003e-05,
562
+ "loss": 0.239,
563
+ "step": 79
564
+ },
565
+ {
566
+ "epoch": 0.004,
567
+ "grad_norm": 18.419599533081055,
568
+ "learning_rate": 1.58e-05,
569
+ "loss": 0.5223,
570
+ "step": 80
571
+ },
572
+ {
573
+ "epoch": 0.00405,
574
+ "grad_norm": 15.859134674072266,
575
+ "learning_rate": 1.6000000000000003e-05,
576
+ "loss": 0.197,
577
+ "step": 81
578
+ },
579
+ {
580
+ "epoch": 0.0041,
581
+ "grad_norm": 52.44767761230469,
582
+ "learning_rate": 1.62e-05,
583
+ "loss": 0.5309,
584
+ "step": 82
585
+ },
586
+ {
587
+ "epoch": 0.00415,
588
+ "grad_norm": 8.842545509338379,
589
+ "learning_rate": 1.64e-05,
590
+ "loss": 0.1521,
591
+ "step": 83
592
+ },
593
+ {
594
+ "epoch": 0.0042,
595
+ "grad_norm": 2.0674080848693848,
596
+ "learning_rate": 1.66e-05,
597
+ "loss": 0.113,
598
+ "step": 84
599
+ },
600
+ {
601
+ "epoch": 0.00425,
602
+ "grad_norm": 1.7234963178634644,
603
+ "learning_rate": 1.6800000000000002e-05,
604
+ "loss": 0.1075,
605
+ "step": 85
606
+ },
607
+ {
608
+ "epoch": 0.0043,
609
+ "grad_norm": 7.167241096496582,
610
+ "learning_rate": 1.7e-05,
611
+ "loss": 0.1667,
612
+ "step": 86
613
+ },
614
+ {
615
+ "epoch": 0.00435,
616
+ "grad_norm": 39.83475112915039,
617
+ "learning_rate": 1.72e-05,
618
+ "loss": 0.2723,
619
+ "step": 87
620
+ },
621
+ {
622
+ "epoch": 0.0044,
623
+ "grad_norm": 21.659135818481445,
624
+ "learning_rate": 1.7400000000000003e-05,
625
+ "loss": 0.2837,
626
+ "step": 88
627
+ },
628
+ {
629
+ "epoch": 0.00445,
630
+ "grad_norm": 11.999871253967285,
631
+ "learning_rate": 1.76e-05,
632
+ "loss": 0.1919,
633
+ "step": 89
634
+ },
635
+ {
636
+ "epoch": 0.0045,
637
+ "grad_norm": 26.082788467407227,
638
+ "learning_rate": 1.7800000000000002e-05,
639
+ "loss": 0.1552,
640
+ "step": 90
641
+ },
642
+ {
643
+ "epoch": 0.00455,
644
+ "grad_norm": 2.2943668365478516,
645
+ "learning_rate": 1.8e-05,
646
+ "loss": 0.0816,
647
+ "step": 91
648
+ },
649
+ {
650
+ "epoch": 0.0046,
651
+ "grad_norm": 2.454077959060669,
652
+ "learning_rate": 1.8200000000000002e-05,
653
+ "loss": 0.105,
654
+ "step": 92
655
+ },
656
+ {
657
+ "epoch": 0.00465,
658
+ "grad_norm": 4.69025993347168,
659
+ "learning_rate": 1.8400000000000003e-05,
660
+ "loss": 0.1104,
661
+ "step": 93
662
+ },
663
+ {
664
+ "epoch": 0.0047,
665
+ "grad_norm": 14.2959566116333,
666
+ "learning_rate": 1.86e-05,
667
+ "loss": 0.8841,
668
+ "step": 94
669
+ },
670
+ {
671
+ "epoch": 0.00475,
672
+ "grad_norm": 39.46820068359375,
673
+ "learning_rate": 1.88e-05,
674
+ "loss": 0.764,
675
+ "step": 95
676
+ },
677
+ {
678
+ "epoch": 0.0048,
679
+ "grad_norm": 2.3603274822235107,
680
+ "learning_rate": 1.9e-05,
681
+ "loss": 0.119,
682
+ "step": 96
683
+ },
684
+ {
685
+ "epoch": 0.00485,
686
+ "grad_norm": 14.50840950012207,
687
+ "learning_rate": 1.9200000000000003e-05,
688
+ "loss": 0.7894,
689
+ "step": 97
690
+ },
691
+ {
692
+ "epoch": 0.0049,
693
+ "grad_norm": 55.66713333129883,
694
+ "learning_rate": 1.94e-05,
695
+ "loss": 0.3007,
696
+ "step": 98
697
+ },
698
+ {
699
+ "epoch": 0.00495,
700
+ "grad_norm": 73.19747924804688,
701
+ "learning_rate": 1.9600000000000002e-05,
702
+ "loss": 0.3876,
703
+ "step": 99
704
+ },
705
+ {
706
+ "epoch": 0.005,
707
+ "grad_norm": 12.380102157592773,
708
+ "learning_rate": 1.98e-05,
709
+ "loss": 0.4437,
710
+ "step": 100
711
+ },
712
+ {
713
+ "epoch": 0.00505,
714
+ "grad_norm": 60.36326217651367,
715
+ "learning_rate": 2e-05,
716
+ "loss": 0.3569,
717
+ "step": 101
718
+ },
719
+ {
720
+ "epoch": 0.0051,
721
+ "grad_norm": 37.3046989440918,
722
+ "learning_rate": 1.9999939076577906e-05,
723
+ "loss": 0.4898,
724
+ "step": 102
725
+ },
726
+ {
727
+ "epoch": 0.00515,
728
+ "grad_norm": 15.11868953704834,
729
+ "learning_rate": 1.9999756307053947e-05,
730
+ "loss": 0.5021,
731
+ "step": 103
732
+ },
733
+ {
734
+ "epoch": 0.0052,
735
+ "grad_norm": 15.323163986206055,
736
+ "learning_rate": 1.9999451693655125e-05,
737
+ "loss": 0.3722,
738
+ "step": 104
739
+ },
740
+ {
741
+ "epoch": 0.00525,
742
+ "grad_norm": 4.708047389984131,
743
+ "learning_rate": 1.9999025240093045e-05,
744
+ "loss": 0.1488,
745
+ "step": 105
746
+ },
747
+ {
748
+ "epoch": 0.0053,
749
+ "grad_norm": 4.781192779541016,
750
+ "learning_rate": 1.9998476951563914e-05,
751
+ "loss": 0.1934,
752
+ "step": 106
753
+ },
754
+ {
755
+ "epoch": 0.00535,
756
+ "grad_norm": 56.712425231933594,
757
+ "learning_rate": 1.9997806834748455e-05,
758
+ "loss": 0.8702,
759
+ "step": 107
760
+ },
761
+ {
762
+ "epoch": 0.0054,
763
+ "grad_norm": 24.84933853149414,
764
+ "learning_rate": 1.9997014897811834e-05,
765
+ "loss": 0.7662,
766
+ "step": 108
767
+ },
768
+ {
769
+ "epoch": 0.00545,
770
+ "grad_norm": 88.01167297363281,
771
+ "learning_rate": 1.9996101150403543e-05,
772
+ "loss": 0.323,
773
+ "step": 109
774
+ },
775
+ {
776
+ "epoch": 0.0055,
777
+ "grad_norm": 7.916687965393066,
778
+ "learning_rate": 1.9995065603657317e-05,
779
+ "loss": 0.1437,
780
+ "step": 110
781
+ },
782
+ {
783
+ "epoch": 0.00555,
784
+ "grad_norm": 27.291078567504883,
785
+ "learning_rate": 1.999390827019096e-05,
786
+ "loss": 0.2062,
787
+ "step": 111
788
+ },
789
+ {
790
+ "epoch": 0.0056,
791
+ "grad_norm": 39.047706604003906,
792
+ "learning_rate": 1.999262916410621e-05,
793
+ "loss": 0.3426,
794
+ "step": 112
795
+ },
796
+ {
797
+ "epoch": 0.00565,
798
+ "grad_norm": 85.04743957519531,
799
+ "learning_rate": 1.9991228300988586e-05,
800
+ "loss": 0.4455,
801
+ "step": 113
802
+ },
803
+ {
804
+ "epoch": 0.0057,
805
+ "grad_norm": 45.45951843261719,
806
+ "learning_rate": 1.998970569790715e-05,
807
+ "loss": 1.1456,
808
+ "step": 114
809
+ },
810
+ {
811
+ "epoch": 0.00575,
812
+ "grad_norm": 26.305465698242188,
813
+ "learning_rate": 1.9988061373414342e-05,
814
+ "loss": 0.4286,
815
+ "step": 115
816
+ },
817
+ {
818
+ "epoch": 0.0058,
819
+ "grad_norm": 4.146256446838379,
820
+ "learning_rate": 1.9986295347545738e-05,
821
+ "loss": 0.1529,
822
+ "step": 116
823
+ },
824
+ {
825
+ "epoch": 0.00585,
826
+ "grad_norm": 41.741695404052734,
827
+ "learning_rate": 1.9984407641819812e-05,
828
+ "loss": 0.3335,
829
+ "step": 117
830
+ },
831
+ {
832
+ "epoch": 0.0059,
833
+ "grad_norm": 4.166099548339844,
834
+ "learning_rate": 1.9982398279237657e-05,
835
+ "loss": 0.1271,
836
+ "step": 118
837
+ },
838
+ {
839
+ "epoch": 0.00595,
840
+ "grad_norm": 16.836219787597656,
841
+ "learning_rate": 1.9980267284282718e-05,
842
+ "loss": 0.3735,
843
+ "step": 119
844
+ },
845
+ {
846
+ "epoch": 0.006,
847
+ "grad_norm": 12.967101097106934,
848
+ "learning_rate": 1.9978014682920503e-05,
849
+ "loss": 0.2148,
850
+ "step": 120
851
+ },
852
+ {
853
+ "epoch": 0.00605,
854
+ "grad_norm": 5.404827117919922,
855
+ "learning_rate": 1.9975640502598243e-05,
856
+ "loss": 0.1681,
857
+ "step": 121
858
+ },
859
+ {
860
+ "epoch": 0.0061,
861
+ "grad_norm": 1.8873947858810425,
862
+ "learning_rate": 1.997314477224458e-05,
863
+ "loss": 0.109,
864
+ "step": 122
865
+ },
866
+ {
867
+ "epoch": 0.00615,
868
+ "grad_norm": 2.6838910579681396,
869
+ "learning_rate": 1.9970527522269204e-05,
870
+ "loss": 0.1122,
871
+ "step": 123
872
+ },
873
+ {
874
+ "epoch": 0.0062,
875
+ "grad_norm": 3.9862358570098877,
876
+ "learning_rate": 1.9967788784562474e-05,
877
+ "loss": 0.1129,
878
+ "step": 124
879
+ },
880
+ {
881
+ "epoch": 0.00625,
882
+ "grad_norm": 17.899574279785156,
883
+ "learning_rate": 1.9964928592495046e-05,
884
+ "loss": 0.1527,
885
+ "step": 125
886
+ },
887
+ {
888
+ "epoch": 0.0063,
889
+ "grad_norm": 27.26593589782715,
890
+ "learning_rate": 1.9961946980917457e-05,
891
+ "loss": 0.2046,
892
+ "step": 126
893
+ },
894
+ {
895
+ "epoch": 0.00635,
896
+ "grad_norm": 69.12671661376953,
897
+ "learning_rate": 1.9958843986159705e-05,
898
+ "loss": 0.3191,
899
+ "step": 127
900
+ },
901
+ {
902
+ "epoch": 0.0064,
903
+ "grad_norm": 29.109697341918945,
904
+ "learning_rate": 1.99556196460308e-05,
905
+ "loss": 0.7056,
906
+ "step": 128
907
+ },
908
+ {
909
+ "epoch": 0.00645,
910
+ "grad_norm": 3.6510722637176514,
911
+ "learning_rate": 1.9952273999818312e-05,
912
+ "loss": 0.1104,
913
+ "step": 129
914
+ },
915
+ {
916
+ "epoch": 0.0065,
917
+ "grad_norm": 56.172035217285156,
918
+ "learning_rate": 1.9948807088287884e-05,
919
+ "loss": 0.5127,
920
+ "step": 130
921
+ },
922
+ {
923
+ "epoch": 0.00655,
924
+ "grad_norm": 36.64286804199219,
925
+ "learning_rate": 1.9945218953682736e-05,
926
+ "loss": 0.3449,
927
+ "step": 131
928
+ },
929
+ {
930
+ "epoch": 0.0066,
931
+ "grad_norm": 6.342191219329834,
932
+ "learning_rate": 1.9941509639723155e-05,
933
+ "loss": 0.1143,
934
+ "step": 132
935
+ },
936
+ {
937
+ "epoch": 0.00665,
938
+ "grad_norm": 14.290639877319336,
939
+ "learning_rate": 1.9937679191605964e-05,
940
+ "loss": 0.1838,
941
+ "step": 133
942
+ },
943
+ {
944
+ "epoch": 0.0067,
945
+ "grad_norm": 2.2349565029144287,
946
+ "learning_rate": 1.9933727656003964e-05,
947
+ "loss": 0.0817,
948
+ "step": 134
949
+ },
950
+ {
951
+ "epoch": 0.00675,
952
+ "grad_norm": 3.0459256172180176,
953
+ "learning_rate": 1.992965508106537e-05,
954
+ "loss": 0.1034,
955
+ "step": 135
956
+ },
957
+ {
958
+ "epoch": 0.0068,
959
+ "grad_norm": 54.64921951293945,
960
+ "learning_rate": 1.9925461516413224e-05,
961
+ "loss": 0.8331,
962
+ "step": 136
963
+ },
964
+ {
965
+ "epoch": 0.00685,
966
+ "grad_norm": 48.370426177978516,
967
+ "learning_rate": 1.9921147013144782e-05,
968
+ "loss": 0.2902,
969
+ "step": 137
970
+ },
971
+ {
972
+ "epoch": 0.0069,
973
+ "grad_norm": 4.709333896636963,
974
+ "learning_rate": 1.9916711623830904e-05,
975
+ "loss": 0.1155,
976
+ "step": 138
977
+ },
978
+ {
979
+ "epoch": 0.00695,
980
+ "grad_norm": 16.851655960083008,
981
+ "learning_rate": 1.991215540251542e-05,
982
+ "loss": 0.6068,
983
+ "step": 139
984
+ },
985
+ {
986
+ "epoch": 0.007,
987
+ "grad_norm": 4.256289482116699,
988
+ "learning_rate": 1.9907478404714438e-05,
989
+ "loss": 0.0947,
990
+ "step": 140
991
+ },
992
+ {
993
+ "epoch": 0.00705,
994
+ "grad_norm": 10.517683029174805,
995
+ "learning_rate": 1.9902680687415704e-05,
996
+ "loss": 0.0943,
997
+ "step": 141
998
+ },
999
+ {
1000
+ "epoch": 0.0071,
1001
+ "grad_norm": 23.348649978637695,
1002
+ "learning_rate": 1.989776230907789e-05,
1003
+ "loss": 0.1692,
1004
+ "step": 142
1005
+ },
1006
+ {
1007
+ "epoch": 0.00715,
1008
+ "grad_norm": 12.16116714477539,
1009
+ "learning_rate": 1.9892723329629885e-05,
1010
+ "loss": 0.1112,
1011
+ "step": 143
1012
+ },
1013
+ {
1014
+ "epoch": 0.0072,
1015
+ "grad_norm": 1.416853427886963,
1016
+ "learning_rate": 1.988756381047006e-05,
1017
+ "loss": 0.0841,
1018
+ "step": 144
1019
+ },
1020
+ {
1021
+ "epoch": 0.00725,
1022
+ "grad_norm": 1.5739504098892212,
1023
+ "learning_rate": 1.988228381446553e-05,
1024
+ "loss": 0.0962,
1025
+ "step": 145
1026
+ },
1027
+ {
1028
+ "epoch": 0.0073,
1029
+ "grad_norm": 69.6449966430664,
1030
+ "learning_rate": 1.9876883405951378e-05,
1031
+ "loss": 0.2386,
1032
+ "step": 146
1033
+ },
1034
+ {
1035
+ "epoch": 0.00735,
1036
+ "grad_norm": 4.477534294128418,
1037
+ "learning_rate": 1.987136265072988e-05,
1038
+ "loss": 0.0814,
1039
+ "step": 147
1040
+ },
1041
+ {
1042
+ "epoch": 0.0074,
1043
+ "grad_norm": 2.3994815349578857,
1044
+ "learning_rate": 1.9865721616069695e-05,
1045
+ "loss": 0.0919,
1046
+ "step": 148
1047
+ },
1048
+ {
1049
+ "epoch": 0.00745,
1050
+ "grad_norm": 2.9941301345825195,
1051
+ "learning_rate": 1.985996037070505e-05,
1052
+ "loss": 0.0951,
1053
+ "step": 149
1054
+ },
1055
+ {
1056
+ "epoch": 0.0075,
1057
+ "grad_norm": 2.181401252746582,
1058
+ "learning_rate": 1.9854078984834904e-05,
1059
+ "loss": 0.1014,
1060
+ "step": 150
1061
+ },
1062
+ {
1063
+ "epoch": 0.00755,
1064
+ "grad_norm": 42.53776550292969,
1065
+ "learning_rate": 1.9848077530122083e-05,
1066
+ "loss": 0.4801,
1067
+ "step": 151
1068
+ },
1069
+ {
1070
+ "epoch": 0.0076,
1071
+ "grad_norm": 37.03893280029297,
1072
+ "learning_rate": 1.984195607969242e-05,
1073
+ "loss": 0.4286,
1074
+ "step": 152
1075
+ },
1076
+ {
1077
+ "epoch": 0.00765,
1078
+ "grad_norm": 3.7320573329925537,
1079
+ "learning_rate": 1.983571470813386e-05,
1080
+ "loss": 0.0751,
1081
+ "step": 153
1082
+ },
1083
+ {
1084
+ "epoch": 0.0077,
1085
+ "grad_norm": 36.467708587646484,
1086
+ "learning_rate": 1.9829353491495545e-05,
1087
+ "loss": 0.2603,
1088
+ "step": 154
1089
+ },
1090
+ {
1091
+ "epoch": 0.00775,
1092
+ "grad_norm": 1.3517638444900513,
1093
+ "learning_rate": 1.982287250728689e-05,
1094
+ "loss": 0.0881,
1095
+ "step": 155
1096
+ },
1097
+ {
1098
+ "epoch": 0.0078,
1099
+ "grad_norm": 3.801837921142578,
1100
+ "learning_rate": 1.9816271834476642e-05,
1101
+ "loss": 0.0931,
1102
+ "step": 156
1103
+ },
1104
+ {
1105
+ "epoch": 0.00785,
1106
+ "grad_norm": 3.4581966400146484,
1107
+ "learning_rate": 1.9809551553491918e-05,
1108
+ "loss": 0.1433,
1109
+ "step": 157
1110
+ },
1111
+ {
1112
+ "epoch": 0.0079,
1113
+ "grad_norm": 10.873891830444336,
1114
+ "learning_rate": 1.9802711746217222e-05,
1115
+ "loss": 0.1472,
1116
+ "step": 158
1117
+ },
1118
+ {
1119
+ "epoch": 0.00795,
1120
+ "grad_norm": 1.951228380203247,
1121
+ "learning_rate": 1.979575249599344e-05,
1122
+ "loss": 0.1118,
1123
+ "step": 159
1124
+ },
1125
+ {
1126
+ "epoch": 0.008,
1127
+ "grad_norm": 1.2118356227874756,
1128
+ "learning_rate": 1.9788673887616852e-05,
1129
+ "loss": 0.0746,
1130
+ "step": 160
1131
+ },
1132
+ {
1133
+ "epoch": 0.00805,
1134
+ "grad_norm": 102.95352935791016,
1135
+ "learning_rate": 1.9781476007338058e-05,
1136
+ "loss": 0.6052,
1137
+ "step": 161
1138
+ },
1139
+ {
1140
+ "epoch": 0.0081,
1141
+ "grad_norm": 1.6797130107879639,
1142
+ "learning_rate": 1.9774158942860962e-05,
1143
+ "loss": 0.0851,
1144
+ "step": 162
1145
+ },
1146
+ {
1147
+ "epoch": 0.00815,
1148
+ "grad_norm": 46.02894592285156,
1149
+ "learning_rate": 1.9766722783341682e-05,
1150
+ "loss": 1.073,
1151
+ "step": 163
1152
+ },
1153
+ {
1154
+ "epoch": 0.0082,
1155
+ "grad_norm": 137.5884246826172,
1156
+ "learning_rate": 1.9759167619387474e-05,
1157
+ "loss": 1.3911,
1158
+ "step": 164
1159
+ },
1160
+ {
1161
+ "epoch": 0.00825,
1162
+ "grad_norm": 13.85587215423584,
1163
+ "learning_rate": 1.9751493543055634e-05,
1164
+ "loss": 1.0056,
1165
+ "step": 165
1166
+ },
1167
+ {
1168
+ "epoch": 0.0083,
1169
+ "grad_norm": 2.5946624279022217,
1170
+ "learning_rate": 1.9743700647852356e-05,
1171
+ "loss": 0.1312,
1172
+ "step": 166
1173
+ },
1174
+ {
1175
+ "epoch": 0.00835,
1176
+ "grad_norm": 38.82013702392578,
1177
+ "learning_rate": 1.9735789028731603e-05,
1178
+ "loss": 0.4317,
1179
+ "step": 167
1180
+ },
1181
+ {
1182
+ "epoch": 0.0084,
1183
+ "grad_norm": 13.546914100646973,
1184
+ "learning_rate": 1.972775878209397e-05,
1185
+ "loss": 0.1253,
1186
+ "step": 168
1187
+ },
1188
+ {
1189
+ "epoch": 0.00845,
1190
+ "grad_norm": 3.1792168617248535,
1191
+ "learning_rate": 1.9719610005785466e-05,
1192
+ "loss": 0.0878,
1193
+ "step": 169
1194
+ },
1195
+ {
1196
+ "epoch": 0.0085,
1197
+ "grad_norm": 1.025294542312622,
1198
+ "learning_rate": 1.971134279909636e-05,
1199
+ "loss": 0.0818,
1200
+ "step": 170
1201
+ },
1202
+ {
1203
+ "epoch": 0.00855,
1204
+ "grad_norm": 3.16849684715271,
1205
+ "learning_rate": 1.9702957262759964e-05,
1206
+ "loss": 0.0923,
1207
+ "step": 171
1208
+ },
1209
+ {
1210
+ "epoch": 0.0086,
1211
+ "grad_norm": 22.248876571655273,
1212
+ "learning_rate": 1.9694453498951392e-05,
1213
+ "loss": 0.4423,
1214
+ "step": 172
1215
+ },
1216
+ {
1217
+ "epoch": 0.00865,
1218
+ "grad_norm": 3.4709620475769043,
1219
+ "learning_rate": 1.9685831611286312e-05,
1220
+ "loss": 0.1042,
1221
+ "step": 173
1222
+ },
1223
+ {
1224
+ "epoch": 0.0087,
1225
+ "grad_norm": 11.294670104980469,
1226
+ "learning_rate": 1.9677091704819714e-05,
1227
+ "loss": 0.1051,
1228
+ "step": 174
1229
+ },
1230
+ {
1231
+ "epoch": 0.00875,
1232
+ "grad_norm": 47.32283401489258,
1233
+ "learning_rate": 1.9668233886044597e-05,
1234
+ "loss": 0.6385,
1235
+ "step": 175
1236
+ },
1237
+ {
1238
+ "epoch": 0.0088,
1239
+ "grad_norm": 2.0372188091278076,
1240
+ "learning_rate": 1.9659258262890683e-05,
1241
+ "loss": 0.0944,
1242
+ "step": 176
1243
+ },
1244
+ {
1245
+ "epoch": 0.00885,
1246
+ "grad_norm": 18.498504638671875,
1247
+ "learning_rate": 1.9650164944723116e-05,
1248
+ "loss": 0.1258,
1249
+ "step": 177
1250
+ },
1251
+ {
1252
+ "epoch": 0.0089,
1253
+ "grad_norm": 6.902488708496094,
1254
+ "learning_rate": 1.96409540423411e-05,
1255
+ "loss": 0.0864,
1256
+ "step": 178
1257
+ },
1258
+ {
1259
+ "epoch": 0.00895,
1260
+ "grad_norm": 3.099083423614502,
1261
+ "learning_rate": 1.9631625667976584e-05,
1262
+ "loss": 0.1176,
1263
+ "step": 179
1264
+ },
1265
+ {
1266
+ "epoch": 0.009,
1267
+ "grad_norm": 47.037715911865234,
1268
+ "learning_rate": 1.9622179935292855e-05,
1269
+ "loss": 0.4287,
1270
+ "step": 180
1271
+ },
1272
+ {
1273
+ "epoch": 0.00905,
1274
+ "grad_norm": 28.77621841430664,
1275
+ "learning_rate": 1.961261695938319e-05,
1276
+ "loss": 0.6359,
1277
+ "step": 181
1278
+ },
1279
+ {
1280
+ "epoch": 0.0091,
1281
+ "grad_norm": 30.206228256225586,
1282
+ "learning_rate": 1.9602936856769432e-05,
1283
+ "loss": 0.2638,
1284
+ "step": 182
1285
+ },
1286
+ {
1287
+ "epoch": 0.00915,
1288
+ "grad_norm": 2.1811752319335938,
1289
+ "learning_rate": 1.9593139745400575e-05,
1290
+ "loss": 0.081,
1291
+ "step": 183
1292
+ },
1293
+ {
1294
+ "epoch": 0.0092,
1295
+ "grad_norm": 4.938018798828125,
1296
+ "learning_rate": 1.9583225744651334e-05,
1297
+ "loss": 0.0994,
1298
+ "step": 184
1299
+ },
1300
+ {
1301
+ "epoch": 0.00925,
1302
+ "grad_norm": 1.8686426877975464,
1303
+ "learning_rate": 1.9573194975320672e-05,
1304
+ "loss": 0.0658,
1305
+ "step": 185
1306
+ },
1307
+ {
1308
+ "epoch": 0.0093,
1309
+ "grad_norm": 1.452397346496582,
1310
+ "learning_rate": 1.9563047559630356e-05,
1311
+ "loss": 0.0799,
1312
+ "step": 186
1313
+ },
1314
+ {
1315
+ "epoch": 0.00935,
1316
+ "grad_norm": 9.045763969421387,
1317
+ "learning_rate": 1.9552783621223437e-05,
1318
+ "loss": 0.1273,
1319
+ "step": 187
1320
+ },
1321
+ {
1322
+ "epoch": 0.0094,
1323
+ "grad_norm": 66.31456756591797,
1324
+ "learning_rate": 1.954240328516277e-05,
1325
+ "loss": 0.7519,
1326
+ "step": 188
1327
+ },
1328
+ {
1329
+ "epoch": 0.00945,
1330
+ "grad_norm": 2.3969008922576904,
1331
+ "learning_rate": 1.9531906677929472e-05,
1332
+ "loss": 0.0895,
1333
+ "step": 189
1334
+ },
1335
+ {
1336
+ "epoch": 0.0095,
1337
+ "grad_norm": 4.230534553527832,
1338
+ "learning_rate": 1.9521293927421388e-05,
1339
+ "loss": 0.1075,
1340
+ "step": 190
1341
+ },
1342
+ {
1343
+ "epoch": 0.00955,
1344
+ "grad_norm": 2.6471550464630127,
1345
+ "learning_rate": 1.9510565162951538e-05,
1346
+ "loss": 0.1113,
1347
+ "step": 191
1348
+ },
1349
+ {
1350
+ "epoch": 0.0096,
1351
+ "grad_norm": 2.1071929931640625,
1352
+ "learning_rate": 1.9499720515246524e-05,
1353
+ "loss": 0.071,
1354
+ "step": 192
1355
+ },
1356
+ {
1357
+ "epoch": 0.00965,
1358
+ "grad_norm": 29.577516555786133,
1359
+ "learning_rate": 1.9488760116444966e-05,
1360
+ "loss": 0.2003,
1361
+ "step": 193
1362
+ },
1363
+ {
1364
+ "epoch": 0.0097,
1365
+ "grad_norm": 2.6140875816345215,
1366
+ "learning_rate": 1.947768410009586e-05,
1367
+ "loss": 0.0934,
1368
+ "step": 194
1369
+ },
1370
+ {
1371
+ "epoch": 0.00975,
1372
+ "grad_norm": 20.867664337158203,
1373
+ "learning_rate": 1.9466492601156964e-05,
1374
+ "loss": 0.6841,
1375
+ "step": 195
1376
+ },
1377
+ {
1378
+ "epoch": 0.0098,
1379
+ "grad_norm": 4.463425159454346,
1380
+ "learning_rate": 1.945518575599317e-05,
1381
+ "loss": 0.1023,
1382
+ "step": 196
1383
+ },
1384
+ {
1385
+ "epoch": 0.00985,
1386
+ "grad_norm": 27.137752532958984,
1387
+ "learning_rate": 1.944376370237481e-05,
1388
+ "loss": 0.28,
1389
+ "step": 197
1390
+ },
1391
+ {
1392
+ "epoch": 0.0099,
1393
+ "grad_norm": 27.44022560119629,
1394
+ "learning_rate": 1.943222657947601e-05,
1395
+ "loss": 0.262,
1396
+ "step": 198
1397
+ },
1398
+ {
1399
+ "epoch": 0.00995,
1400
+ "grad_norm": 86.16558074951172,
1401
+ "learning_rate": 1.942057452787297e-05,
1402
+ "loss": 0.2155,
1403
+ "step": 199
1404
+ },
1405
+ {
1406
+ "epoch": 0.01,
1407
+ "grad_norm": 4.05201530456543,
1408
+ "learning_rate": 1.9408807689542257e-05,
1409
+ "loss": 0.0818,
1410
+ "step": 200
1411
+ },
1412
+ {
1413
+ "epoch": 0.01005,
1414
+ "grad_norm": 2.2698569297790527,
1415
+ "learning_rate": 1.9396926207859085e-05,
1416
+ "loss": 0.0961,
1417
+ "step": 201
1418
+ },
1419
+ {
1420
+ "epoch": 0.0101,
1421
+ "grad_norm": 3.336587429046631,
1422
+ "learning_rate": 1.938493022759556e-05,
1423
+ "loss": 0.0802,
1424
+ "step": 202
1425
+ },
1426
+ {
1427
+ "epoch": 0.01015,
1428
+ "grad_norm": 2.88741397857666,
1429
+ "learning_rate": 1.937281989491892e-05,
1430
+ "loss": 0.0804,
1431
+ "step": 203
1432
+ },
1433
+ {
1434
+ "epoch": 0.0102,
1435
+ "grad_norm": 35.056396484375,
1436
+ "learning_rate": 1.9360595357389735e-05,
1437
+ "loss": 0.5725,
1438
+ "step": 204
1439
+ },
1440
+ {
1441
+ "epoch": 0.01025,
1442
+ "grad_norm": 4.568849086761475,
1443
+ "learning_rate": 1.9348256763960146e-05,
1444
+ "loss": 0.0933,
1445
+ "step": 205
1446
+ },
1447
+ {
1448
+ "epoch": 0.0103,
1449
+ "grad_norm": 54.54572296142578,
1450
+ "learning_rate": 1.9335804264972018e-05,
1451
+ "loss": 0.3056,
1452
+ "step": 206
1453
+ },
1454
+ {
1455
+ "epoch": 0.01035,
1456
+ "grad_norm": 47.241539001464844,
1457
+ "learning_rate": 1.9323238012155125e-05,
1458
+ "loss": 0.2674,
1459
+ "step": 207
1460
+ },
1461
+ {
1462
+ "epoch": 0.0104,
1463
+ "grad_norm": 17.177762985229492,
1464
+ "learning_rate": 1.9310558158625286e-05,
1465
+ "loss": 0.1673,
1466
+ "step": 208
1467
+ },
1468
+ {
1469
+ "epoch": 0.01045,
1470
+ "grad_norm": 1.9468616247177124,
1471
+ "learning_rate": 1.9297764858882516e-05,
1472
+ "loss": 0.1193,
1473
+ "step": 209
1474
+ },
1475
+ {
1476
+ "epoch": 0.0105,
1477
+ "grad_norm": 18.45438575744629,
1478
+ "learning_rate": 1.9284858268809135e-05,
1479
+ "loss": 0.2822,
1480
+ "step": 210
1481
+ },
1482
+ {
1483
+ "epoch": 0.01055,
1484
+ "grad_norm": 43.80156707763672,
1485
+ "learning_rate": 1.9271838545667876e-05,
1486
+ "loss": 0.9663,
1487
+ "step": 211
1488
+ },
1489
+ {
1490
+ "epoch": 0.0106,
1491
+ "grad_norm": 2.534038543701172,
1492
+ "learning_rate": 1.925870584809995e-05,
1493
+ "loss": 0.0924,
1494
+ "step": 212
1495
+ },
1496
+ {
1497
+ "epoch": 0.01065,
1498
+ "grad_norm": 24.710065841674805,
1499
+ "learning_rate": 1.9245460336123136e-05,
1500
+ "loss": 0.1385,
1501
+ "step": 213
1502
+ },
1503
+ {
1504
+ "epoch": 0.0107,
1505
+ "grad_norm": 33.71287536621094,
1506
+ "learning_rate": 1.923210217112981e-05,
1507
+ "loss": 0.1855,
1508
+ "step": 214
1509
+ },
1510
+ {
1511
+ "epoch": 0.01075,
1512
+ "grad_norm": 16.790836334228516,
1513
+ "learning_rate": 1.9218631515885007e-05,
1514
+ "loss": 0.1124,
1515
+ "step": 215
1516
+ },
1517
+ {
1518
+ "epoch": 0.0108,
1519
+ "grad_norm": 4.847932815551758,
1520
+ "learning_rate": 1.9205048534524405e-05,
1521
+ "loss": 0.102,
1522
+ "step": 216
1523
+ },
1524
+ {
1525
+ "epoch": 0.01085,
1526
+ "grad_norm": 47.94908142089844,
1527
+ "learning_rate": 1.9191353392552346e-05,
1528
+ "loss": 0.6322,
1529
+ "step": 217
1530
+ },
1531
+ {
1532
+ "epoch": 0.0109,
1533
+ "grad_norm": 1.2221285104751587,
1534
+ "learning_rate": 1.9177546256839814e-05,
1535
+ "loss": 0.0878,
1536
+ "step": 218
1537
+ },
1538
+ {
1539
+ "epoch": 0.01095,
1540
+ "grad_norm": 21.5382137298584,
1541
+ "learning_rate": 1.9163627295622397e-05,
1542
+ "loss": 0.5478,
1543
+ "step": 219
1544
+ },
1545
+ {
1546
+ "epoch": 0.011,
1547
+ "grad_norm": 6.854888916015625,
1548
+ "learning_rate": 1.914959667849825e-05,
1549
+ "loss": 0.1052,
1550
+ "step": 220
1551
+ },
1552
+ {
1553
+ "epoch": 0.01105,
1554
+ "grad_norm": 2.5299158096313477,
1555
+ "learning_rate": 1.913545457642601e-05,
1556
+ "loss": 0.0806,
1557
+ "step": 221
1558
+ },
1559
+ {
1560
+ "epoch": 0.0111,
1561
+ "grad_norm": 6.152573585510254,
1562
+ "learning_rate": 1.9121201161722732e-05,
1563
+ "loss": 0.1596,
1564
+ "step": 222
1565
+ },
1566
+ {
1567
+ "epoch": 0.01115,
1568
+ "grad_norm": 4.504411220550537,
1569
+ "learning_rate": 1.910683660806177e-05,
1570
+ "loss": 0.1096,
1571
+ "step": 223
1572
+ },
1573
+ {
1574
+ "epoch": 0.0112,
1575
+ "grad_norm": 34.63329315185547,
1576
+ "learning_rate": 1.9092361090470688e-05,
1577
+ "loss": 0.5244,
1578
+ "step": 224
1579
+ },
1580
+ {
1581
+ "epoch": 0.01125,
1582
+ "grad_norm": 2.805756092071533,
1583
+ "learning_rate": 1.907777478532909e-05,
1584
+ "loss": 0.0859,
1585
+ "step": 225
1586
+ },
1587
+ {
1588
+ "epoch": 0.0113,
1589
+ "grad_norm": 7.697692394256592,
1590
+ "learning_rate": 1.9063077870366504e-05,
1591
+ "loss": 0.1499,
1592
+ "step": 226
1593
+ },
1594
+ {
1595
+ "epoch": 0.01135,
1596
+ "grad_norm": 3.3117737770080566,
1597
+ "learning_rate": 1.9048270524660197e-05,
1598
+ "loss": 0.128,
1599
+ "step": 227
1600
+ },
1601
+ {
1602
+ "epoch": 0.0114,
1603
+ "grad_norm": 84.48941802978516,
1604
+ "learning_rate": 1.903335292863301e-05,
1605
+ "loss": 0.2558,
1606
+ "step": 228
1607
+ },
1608
+ {
1609
+ "epoch": 0.01145,
1610
+ "grad_norm": 5.932098865509033,
1611
+ "learning_rate": 1.901832526405114e-05,
1612
+ "loss": 0.152,
1613
+ "step": 229
1614
+ },
1615
+ {
1616
+ "epoch": 0.0115,
1617
+ "grad_norm": 2.152769088745117,
1618
+ "learning_rate": 1.9003187714021936e-05,
1619
+ "loss": 0.1035,
1620
+ "step": 230
1621
+ },
1622
+ {
1623
+ "epoch": 0.01155,
1624
+ "grad_norm": 2.9696671962738037,
1625
+ "learning_rate": 1.8987940462991673e-05,
1626
+ "loss": 0.133,
1627
+ "step": 231
1628
+ },
1629
+ {
1630
+ "epoch": 0.0116,
1631
+ "grad_norm": 1.1272964477539062,
1632
+ "learning_rate": 1.8972583696743284e-05,
1633
+ "loss": 0.0709,
1634
+ "step": 232
1635
+ },
1636
+ {
1637
+ "epoch": 0.01165,
1638
+ "grad_norm": 54.1812629699707,
1639
+ "learning_rate": 1.895711760239413e-05,
1640
+ "loss": 1.4537,
1641
+ "step": 233
1642
+ },
1643
+ {
1644
+ "epoch": 0.0117,
1645
+ "grad_norm": 6.666309356689453,
1646
+ "learning_rate": 1.8941542368393683e-05,
1647
+ "loss": 0.1203,
1648
+ "step": 234
1649
+ },
1650
+ {
1651
+ "epoch": 0.01175,
1652
+ "grad_norm": 14.333596229553223,
1653
+ "learning_rate": 1.892585818452126e-05,
1654
+ "loss": 0.1418,
1655
+ "step": 235
1656
+ },
1657
+ {
1658
+ "epoch": 0.0118,
1659
+ "grad_norm": 9.919900894165039,
1660
+ "learning_rate": 1.891006524188368e-05,
1661
+ "loss": 0.1157,
1662
+ "step": 236
1663
+ },
1664
+ {
1665
+ "epoch": 0.01185,
1666
+ "grad_norm": 16.620220184326172,
1667
+ "learning_rate": 1.889416373291298e-05,
1668
+ "loss": 0.1148,
1669
+ "step": 237
1670
+ },
1671
+ {
1672
+ "epoch": 0.0119,
1673
+ "grad_norm": 1.308577537536621,
1674
+ "learning_rate": 1.8878153851364013e-05,
1675
+ "loss": 0.0823,
1676
+ "step": 238
1677
+ },
1678
+ {
1679
+ "epoch": 0.01195,
1680
+ "grad_norm": 2.889721155166626,
1681
+ "learning_rate": 1.8862035792312148e-05,
1682
+ "loss": 0.0808,
1683
+ "step": 239
1684
+ },
1685
+ {
1686
+ "epoch": 0.012,
1687
+ "grad_norm": 9.654630661010742,
1688
+ "learning_rate": 1.884580975215084e-05,
1689
+ "loss": 0.1474,
1690
+ "step": 240
1691
+ },
1692
+ {
1693
+ "epoch": 0.01205,
1694
+ "grad_norm": 1.4449971914291382,
1695
+ "learning_rate": 1.8829475928589272e-05,
1696
+ "loss": 0.0831,
1697
+ "step": 241
1698
+ },
1699
+ {
1700
+ "epoch": 0.0121,
1701
+ "grad_norm": 2.7385785579681396,
1702
+ "learning_rate": 1.8813034520649923e-05,
1703
+ "loss": 0.1073,
1704
+ "step": 242
1705
+ },
1706
+ {
1707
+ "epoch": 0.01215,
1708
+ "grad_norm": 2.1100575923919678,
1709
+ "learning_rate": 1.879648572866617e-05,
1710
+ "loss": 0.0856,
1711
+ "step": 243
1712
+ },
1713
+ {
1714
+ "epoch": 0.0122,
1715
+ "grad_norm": 22.79264259338379,
1716
+ "learning_rate": 1.8779829754279806e-05,
1717
+ "loss": 0.1046,
1718
+ "step": 244
1719
+ },
1720
+ {
1721
+ "epoch": 0.01225,
1722
+ "grad_norm": 2.072134017944336,
1723
+ "learning_rate": 1.8763066800438638e-05,
1724
+ "loss": 0.0798,
1725
+ "step": 245
1726
+ },
1727
+ {
1728
+ "epoch": 0.0123,
1729
+ "grad_norm": 28.02008628845215,
1730
+ "learning_rate": 1.874619707139396e-05,
1731
+ "loss": 0.3727,
1732
+ "step": 246
1733
+ },
1734
+ {
1735
+ "epoch": 0.01235,
1736
+ "grad_norm": 1.2192667722702026,
1737
+ "learning_rate": 1.8729220772698096e-05,
1738
+ "loss": 0.0597,
1739
+ "step": 247
1740
+ },
1741
+ {
1742
+ "epoch": 0.0124,
1743
+ "grad_norm": 2.538534641265869,
1744
+ "learning_rate": 1.8712138111201898e-05,
1745
+ "loss": 0.1174,
1746
+ "step": 248
1747
+ },
1748
+ {
1749
+ "epoch": 0.01245,
1750
+ "grad_norm": 3.2410473823547363,
1751
+ "learning_rate": 1.869494929505219e-05,
1752
+ "loss": 0.1064,
1753
+ "step": 249
1754
+ },
1755
+ {
1756
+ "epoch": 0.0125,
1757
+ "grad_norm": 9.867326736450195,
1758
+ "learning_rate": 1.8677654533689287e-05,
1759
+ "loss": 0.7139,
1760
+ "step": 250
1761
+ },
1762
+ {
1763
+ "epoch": 0.01255,
1764
+ "grad_norm": 2.04473876953125,
1765
+ "learning_rate": 1.866025403784439e-05,
1766
+ "loss": 0.0692,
1767
+ "step": 251
1768
+ },
1769
+ {
1770
+ "epoch": 0.0126,
1771
+ "grad_norm": 1.841275930404663,
1772
+ "learning_rate": 1.864274801953705e-05,
1773
+ "loss": 0.0794,
1774
+ "step": 252
1775
+ },
1776
+ {
1777
+ "epoch": 0.01265,
1778
+ "grad_norm": 1.7441390752792358,
1779
+ "learning_rate": 1.8625136692072577e-05,
1780
+ "loss": 0.0713,
1781
+ "step": 253
1782
+ },
1783
+ {
1784
+ "epoch": 0.0127,
1785
+ "grad_norm": 89.4349594116211,
1786
+ "learning_rate": 1.860742027003944e-05,
1787
+ "loss": 0.317,
1788
+ "step": 254
1789
+ },
1790
+ {
1791
+ "epoch": 0.01275,
1792
+ "grad_norm": 59.13755798339844,
1793
+ "learning_rate": 1.8589598969306646e-05,
1794
+ "loss": 0.2077,
1795
+ "step": 255
1796
+ },
1797
+ {
1798
+ "epoch": 0.0128,
1799
+ "grad_norm": 24.257322311401367,
1800
+ "learning_rate": 1.8571673007021124e-05,
1801
+ "loss": 0.3272,
1802
+ "step": 256
1803
+ },
1804
+ {
1805
+ "epoch": 0.01285,
1806
+ "grad_norm": 3.105194091796875,
1807
+ "learning_rate": 1.855364260160507e-05,
1808
+ "loss": 0.0992,
1809
+ "step": 257
1810
+ },
1811
+ {
1812
+ "epoch": 0.0129,
1813
+ "grad_norm": 2.192078113555908,
1814
+ "learning_rate": 1.8535507972753275e-05,
1815
+ "loss": 0.069,
1816
+ "step": 258
1817
+ },
1818
+ {
1819
+ "epoch": 0.01295,
1820
+ "grad_norm": 21.576236724853516,
1821
+ "learning_rate": 1.851726934143048e-05,
1822
+ "loss": 0.54,
1823
+ "step": 259
1824
+ },
1825
+ {
1826
+ "epoch": 0.013,
1827
+ "grad_norm": 4.011931419372559,
1828
+ "learning_rate": 1.849892692986864e-05,
1829
+ "loss": 0.1241,
1830
+ "step": 260
1831
+ },
1832
+ {
1833
+ "epoch": 0.01305,
1834
+ "grad_norm": 1.8716342449188232,
1835
+ "learning_rate": 1.848048096156426e-05,
1836
+ "loss": 0.0919,
1837
+ "step": 261
1838
+ },
1839
+ {
1840
+ "epoch": 0.0131,
1841
+ "grad_norm": 36.63429641723633,
1842
+ "learning_rate": 1.8461931661275642e-05,
1843
+ "loss": 0.8812,
1844
+ "step": 262
1845
+ },
1846
+ {
1847
+ "epoch": 0.01315,
1848
+ "grad_norm": 36.83095169067383,
1849
+ "learning_rate": 1.8443279255020153e-05,
1850
+ "loss": 0.4525,
1851
+ "step": 263
1852
+ },
1853
+ {
1854
+ "epoch": 0.0132,
1855
+ "grad_norm": 2.323366165161133,
1856
+ "learning_rate": 1.842452397007148e-05,
1857
+ "loss": 0.0841,
1858
+ "step": 264
1859
+ },
1860
+ {
1861
+ "epoch": 0.01325,
1862
+ "grad_norm": 14.090721130371094,
1863
+ "learning_rate": 1.8405666034956842e-05,
1864
+ "loss": 0.1602,
1865
+ "step": 265
1866
+ },
1867
+ {
1868
+ "epoch": 0.0133,
1869
+ "grad_norm": 12.795496940612793,
1870
+ "learning_rate": 1.8386705679454243e-05,
1871
+ "loss": 0.182,
1872
+ "step": 266
1873
+ },
1874
+ {
1875
+ "epoch": 0.01335,
1876
+ "grad_norm": 4.722551345825195,
1877
+ "learning_rate": 1.836764313458962e-05,
1878
+ "loss": 0.1357,
1879
+ "step": 267
1880
+ },
1881
+ {
1882
+ "epoch": 0.0134,
1883
+ "grad_norm": 16.780805587768555,
1884
+ "learning_rate": 1.8348478632634067e-05,
1885
+ "loss": 0.3341,
1886
+ "step": 268
1887
+ },
1888
+ {
1889
+ "epoch": 0.01345,
1890
+ "grad_norm": 1.7280741930007935,
1891
+ "learning_rate": 1.8329212407100996e-05,
1892
+ "loss": 0.0941,
1893
+ "step": 269
1894
+ },
1895
+ {
1896
+ "epoch": 0.0135,
1897
+ "grad_norm": 3.2625572681427,
1898
+ "learning_rate": 1.8309844692743283e-05,
1899
+ "loss": 0.1768,
1900
+ "step": 270
1901
+ },
1902
+ {
1903
+ "epoch": 0.01355,
1904
+ "grad_norm": 2.5432939529418945,
1905
+ "learning_rate": 1.8290375725550417e-05,
1906
+ "loss": 0.0925,
1907
+ "step": 271
1908
+ },
1909
+ {
1910
+ "epoch": 0.0136,
1911
+ "grad_norm": 57.257667541503906,
1912
+ "learning_rate": 1.827080574274562e-05,
1913
+ "loss": 0.3118,
1914
+ "step": 272
1915
+ },
1916
+ {
1917
+ "epoch": 0.01365,
1918
+ "grad_norm": 7.988307476043701,
1919
+ "learning_rate": 1.8251134982782952e-05,
1920
+ "loss": 0.1129,
1921
+ "step": 273
1922
+ },
1923
+ {
1924
+ "epoch": 0.0137,
1925
+ "grad_norm": 1.5597671270370483,
1926
+ "learning_rate": 1.8231363685344422e-05,
1927
+ "loss": 0.0753,
1928
+ "step": 274
1929
+ },
1930
+ {
1931
+ "epoch": 0.01375,
1932
+ "grad_norm": 18.671035766601562,
1933
+ "learning_rate": 1.821149209133704e-05,
1934
+ "loss": 0.1241,
1935
+ "step": 275
1936
+ },
1937
+ {
1938
+ "epoch": 0.0138,
1939
+ "grad_norm": 1.7065479755401611,
1940
+ "learning_rate": 1.819152044288992e-05,
1941
+ "loss": 0.0809,
1942
+ "step": 276
1943
+ },
1944
+ {
1945
+ "epoch": 0.01385,
1946
+ "grad_norm": 31.31546401977539,
1947
+ "learning_rate": 1.8171448983351284e-05,
1948
+ "loss": 0.2415,
1949
+ "step": 277
1950
+ },
1951
+ {
1952
+ "epoch": 0.0139,
1953
+ "grad_norm": 2.4892303943634033,
1954
+ "learning_rate": 1.815127795728554e-05,
1955
+ "loss": 0.096,
1956
+ "step": 278
1957
+ },
1958
+ {
1959
+ "epoch": 0.01395,
1960
+ "grad_norm": 2.3767950534820557,
1961
+ "learning_rate": 1.8131007610470278e-05,
1962
+ "loss": 0.1194,
1963
+ "step": 279
1964
+ },
1965
+ {
1966
+ "epoch": 0.014,
1967
+ "grad_norm": 24.376630783081055,
1968
+ "learning_rate": 1.8110638189893267e-05,
1969
+ "loss": 0.2867,
1970
+ "step": 280
1971
+ },
1972
+ {
1973
+ "epoch": 0.01405,
1974
+ "grad_norm": 2.7759625911712646,
1975
+ "learning_rate": 1.8090169943749477e-05,
1976
+ "loss": 0.1072,
1977
+ "step": 281
1978
+ },
1979
+ {
1980
+ "epoch": 0.0141,
1981
+ "grad_norm": 16.7757511138916,
1982
+ "learning_rate": 1.806960312143802e-05,
1983
+ "loss": 0.6312,
1984
+ "step": 282
1985
+ },
1986
+ {
1987
+ "epoch": 0.01415,
1988
+ "grad_norm": 4.640740871429443,
1989
+ "learning_rate": 1.804893797355914e-05,
1990
+ "loss": 0.1236,
1991
+ "step": 283
1992
+ },
1993
+ {
1994
+ "epoch": 0.0142,
1995
+ "grad_norm": 1.8363475799560547,
1996
+ "learning_rate": 1.8028174751911147e-05,
1997
+ "loss": 0.0859,
1998
+ "step": 284
1999
+ },
2000
+ {
2001
+ "epoch": 0.01425,
2002
+ "grad_norm": 1.5419412851333618,
2003
+ "learning_rate": 1.8007313709487334e-05,
2004
+ "loss": 0.0685,
2005
+ "step": 285
2006
+ },
2007
+ {
2008
+ "epoch": 0.0143,
2009
+ "grad_norm": 45.82707214355469,
2010
+ "learning_rate": 1.798635510047293e-05,
2011
+ "loss": 0.552,
2012
+ "step": 286
2013
+ },
2014
+ {
2015
+ "epoch": 0.01435,
2016
+ "grad_norm": 1.4965375661849976,
2017
+ "learning_rate": 1.7965299180241963e-05,
2018
+ "loss": 0.0868,
2019
+ "step": 287
2020
+ },
2021
+ {
2022
+ "epoch": 0.0144,
2023
+ "grad_norm": 34.65620422363281,
2024
+ "learning_rate": 1.7944146205354182e-05,
2025
+ "loss": 0.851,
2026
+ "step": 288
2027
+ },
2028
+ {
2029
+ "epoch": 0.01445,
2030
+ "grad_norm": 2.195761203765869,
2031
+ "learning_rate": 1.792289643355191e-05,
2032
+ "loss": 0.1009,
2033
+ "step": 289
2034
+ },
2035
+ {
2036
+ "epoch": 0.0145,
2037
+ "grad_norm": 1.3684836626052856,
2038
+ "learning_rate": 1.7901550123756906e-05,
2039
+ "loss": 0.0731,
2040
+ "step": 290
2041
+ },
2042
+ {
2043
+ "epoch": 0.01455,
2044
+ "grad_norm": 1.6004326343536377,
2045
+ "learning_rate": 1.788010753606722e-05,
2046
+ "loss": 0.0831,
2047
+ "step": 291
2048
+ },
2049
+ {
2050
+ "epoch": 0.0146,
2051
+ "grad_norm": 26.745464324951172,
2052
+ "learning_rate": 1.785856893175402e-05,
2053
+ "loss": 0.4283,
2054
+ "step": 292
2055
+ },
2056
+ {
2057
+ "epoch": 0.01465,
2058
+ "grad_norm": 78.65120697021484,
2059
+ "learning_rate": 1.78369345732584e-05,
2060
+ "loss": 0.3526,
2061
+ "step": 293
2062
+ },
2063
+ {
2064
+ "epoch": 0.0147,
2065
+ "grad_norm": 1.7803980112075806,
2066
+ "learning_rate": 1.781520472418819e-05,
2067
+ "loss": 0.0837,
2068
+ "step": 294
2069
+ },
2070
+ {
2071
+ "epoch": 0.01475,
2072
+ "grad_norm": 8.317599296569824,
2073
+ "learning_rate": 1.7793379649314743e-05,
2074
+ "loss": 0.1051,
2075
+ "step": 295
2076
+ },
2077
+ {
2078
+ "epoch": 0.0148,
2079
+ "grad_norm": 10.342424392700195,
2080
+ "learning_rate": 1.777145961456971e-05,
2081
+ "loss": 0.11,
2082
+ "step": 296
2083
+ },
2084
+ {
2085
+ "epoch": 0.01485,
2086
+ "grad_norm": 35.15061950683594,
2087
+ "learning_rate": 1.7749444887041797e-05,
2088
+ "loss": 0.3765,
2089
+ "step": 297
2090
+ },
2091
+ {
2092
+ "epoch": 0.0149,
2093
+ "grad_norm": 11.10451889038086,
2094
+ "learning_rate": 1.7727335734973512e-05,
2095
+ "loss": 0.1197,
2096
+ "step": 298
2097
+ },
2098
+ {
2099
+ "epoch": 0.01495,
2100
+ "grad_norm": 1.8988792896270752,
2101
+ "learning_rate": 1.7705132427757895e-05,
2102
+ "loss": 0.1009,
2103
+ "step": 299
2104
+ },
2105
+ {
2106
+ "epoch": 0.015,
2107
+ "grad_norm": 6.130817413330078,
2108
+ "learning_rate": 1.7682835235935236e-05,
2109
+ "loss": 0.1401,
2110
+ "step": 300
2111
+ },
2112
+ {
2113
+ "epoch": 0.01505,
2114
+ "grad_norm": 1.9723719358444214,
2115
+ "learning_rate": 1.766044443118978e-05,
2116
+ "loss": 0.0877,
2117
+ "step": 301
2118
+ },
2119
+ {
2120
+ "epoch": 0.0151,
2121
+ "grad_norm": 2.882294178009033,
2122
+ "learning_rate": 1.7637960286346423e-05,
2123
+ "loss": 0.0815,
2124
+ "step": 302
2125
+ },
2126
+ {
2127
+ "epoch": 0.01515,
2128
+ "grad_norm": 18.67458152770996,
2129
+ "learning_rate": 1.761538307536737e-05,
2130
+ "loss": 0.1527,
2131
+ "step": 303
2132
+ },
2133
+ {
2134
+ "epoch": 0.0152,
2135
+ "grad_norm": 34.37173080444336,
2136
+ "learning_rate": 1.759271307334881e-05,
2137
+ "loss": 0.6591,
2138
+ "step": 304
2139
+ },
2140
+ {
2141
+ "epoch": 0.01525,
2142
+ "grad_norm": 1.8363667726516724,
2143
+ "learning_rate": 1.7569950556517566e-05,
2144
+ "loss": 0.0853,
2145
+ "step": 305
2146
+ },
2147
+ {
2148
+ "epoch": 0.0153,
2149
+ "grad_norm": 1.6190111637115479,
2150
+ "learning_rate": 1.7547095802227723e-05,
2151
+ "loss": 0.0684,
2152
+ "step": 306
2153
+ },
2154
+ {
2155
+ "epoch": 0.01535,
2156
+ "grad_norm": 2.7849435806274414,
2157
+ "learning_rate": 1.7524149088957244e-05,
2158
+ "loss": 0.1081,
2159
+ "step": 307
2160
+ },
2161
+ {
2162
+ "epoch": 0.0154,
2163
+ "grad_norm": 2.385519504547119,
2164
+ "learning_rate": 1.7501110696304598e-05,
2165
+ "loss": 0.0699,
2166
+ "step": 308
2167
+ },
2168
+ {
2169
+ "epoch": 0.01545,
2170
+ "grad_norm": 103.18679809570312,
2171
+ "learning_rate": 1.747798090498532e-05,
2172
+ "loss": 0.2133,
2173
+ "step": 309
2174
+ },
2175
+ {
2176
+ "epoch": 0.0155,
2177
+ "grad_norm": 21.587390899658203,
2178
+ "learning_rate": 1.7454759996828622e-05,
2179
+ "loss": 0.1336,
2180
+ "step": 310
2181
+ },
2182
+ {
2183
+ "epoch": 0.01555,
2184
+ "grad_norm": 64.16925048828125,
2185
+ "learning_rate": 1.7431448254773943e-05,
2186
+ "loss": 0.5498,
2187
+ "step": 311
2188
+ },
2189
+ {
2190
+ "epoch": 0.0156,
2191
+ "grad_norm": 1.3994704484939575,
2192
+ "learning_rate": 1.74080459628675e-05,
2193
+ "loss": 0.0807,
2194
+ "step": 312
2195
+ },
2196
+ {
2197
+ "epoch": 0.01565,
2198
+ "grad_norm": 2.7629127502441406,
2199
+ "learning_rate": 1.7384553406258842e-05,
2200
+ "loss": 0.1061,
2201
+ "step": 313
2202
+ },
2203
+ {
2204
+ "epoch": 0.0157,
2205
+ "grad_norm": 0.7181133031845093,
2206
+ "learning_rate": 1.7360970871197347e-05,
2207
+ "loss": 0.0615,
2208
+ "step": 314
2209
+ },
2210
+ {
2211
+ "epoch": 0.01575,
2212
+ "grad_norm": 1.9693636894226074,
2213
+ "learning_rate": 1.7337298645028764e-05,
2214
+ "loss": 0.0854,
2215
+ "step": 315
2216
+ },
2217
+ {
2218
+ "epoch": 0.0158,
2219
+ "grad_norm": 2.3914601802825928,
2220
+ "learning_rate": 1.7313537016191706e-05,
2221
+ "loss": 0.1046,
2222
+ "step": 316
2223
+ },
2224
+ {
2225
+ "epoch": 0.01585,
2226
+ "grad_norm": 1.8866361379623413,
2227
+ "learning_rate": 1.7289686274214116e-05,
2228
+ "loss": 0.0777,
2229
+ "step": 317
2230
+ },
2231
+ {
2232
+ "epoch": 0.0159,
2233
+ "grad_norm": 8.258055686950684,
2234
+ "learning_rate": 1.7265746709709762e-05,
2235
+ "loss": 0.5726,
2236
+ "step": 318
2237
+ },
2238
+ {
2239
+ "epoch": 0.01595,
2240
+ "grad_norm": 3.7941558361053467,
2241
+ "learning_rate": 1.7241718614374678e-05,
2242
+ "loss": 0.1251,
2243
+ "step": 319
2244
+ },
2245
+ {
2246
+ "epoch": 0.016,
2247
+ "grad_norm": 2.7949891090393066,
2248
+ "learning_rate": 1.7217602280983622e-05,
2249
+ "loss": 0.0826,
2250
+ "step": 320
2251
+ },
2252
+ {
2253
+ "epoch": 0.01605,
2254
+ "grad_norm": 27.749094009399414,
2255
+ "learning_rate": 1.7193398003386514e-05,
2256
+ "loss": 0.4803,
2257
+ "step": 321
2258
+ },
2259
+ {
2260
+ "epoch": 0.0161,
2261
+ "grad_norm": 2.399714708328247,
2262
+ "learning_rate": 1.716910607650483e-05,
2263
+ "loss": 0.1006,
2264
+ "step": 322
2265
+ },
2266
+ {
2267
+ "epoch": 0.01615,
2268
+ "grad_norm": 5.782076835632324,
2269
+ "learning_rate": 1.7144726796328034e-05,
2270
+ "loss": 0.1101,
2271
+ "step": 323
2272
+ },
2273
+ {
2274
+ "epoch": 0.0162,
2275
+ "grad_norm": 2.2748818397521973,
2276
+ "learning_rate": 1.712026045990997e-05,
2277
+ "loss": 0.1027,
2278
+ "step": 324
2279
+ },
2280
+ {
2281
+ "epoch": 0.01625,
2282
+ "grad_norm": 7.266913414001465,
2283
+ "learning_rate": 1.709570736536521e-05,
2284
+ "loss": 0.112,
2285
+ "step": 325
2286
+ },
2287
+ {
2288
+ "epoch": 0.0163,
2289
+ "grad_norm": 1.6896015405654907,
2290
+ "learning_rate": 1.7071067811865477e-05,
2291
+ "loss": 0.0824,
2292
+ "step": 326
2293
+ },
2294
+ {
2295
+ "epoch": 0.01635,
2296
+ "grad_norm": 12.456267356872559,
2297
+ "learning_rate": 1.7046342099635948e-05,
2298
+ "loss": 0.1114,
2299
+ "step": 327
2300
+ },
2301
+ {
2302
+ "epoch": 0.0164,
2303
+ "grad_norm": 7.791019916534424,
2304
+ "learning_rate": 1.7021530529951627e-05,
2305
+ "loss": 0.0909,
2306
+ "step": 328
2307
+ },
2308
+ {
2309
+ "epoch": 0.01645,
2310
+ "grad_norm": 12.910639762878418,
2311
+ "learning_rate": 1.6996633405133656e-05,
2312
+ "loss": 0.1899,
2313
+ "step": 329
2314
+ },
2315
+ {
2316
+ "epoch": 0.0165,
2317
+ "grad_norm": 2.853062152862549,
2318
+ "learning_rate": 1.697165102854565e-05,
2319
+ "loss": 0.0908,
2320
+ "step": 330
2321
+ },
2322
+ {
2323
+ "epoch": 0.01655,
2324
+ "grad_norm": 15.528128623962402,
2325
+ "learning_rate": 1.6946583704589973e-05,
2326
+ "loss": 0.4061,
2327
+ "step": 331
2328
+ },
2329
+ {
2330
+ "epoch": 0.0166,
2331
+ "grad_norm": 48.358848571777344,
2332
+ "learning_rate": 1.692143173870407e-05,
2333
+ "loss": 0.4315,
2334
+ "step": 332
2335
+ },
2336
+ {
2337
+ "epoch": 0.01665,
2338
+ "grad_norm": 3.2647809982299805,
2339
+ "learning_rate": 1.68961954373567e-05,
2340
+ "loss": 0.1223,
2341
+ "step": 333
2342
+ },
2343
+ {
2344
+ "epoch": 0.0167,
2345
+ "grad_norm": 11.482593536376953,
2346
+ "learning_rate": 1.6870875108044233e-05,
2347
+ "loss": 0.1696,
2348
+ "step": 334
2349
+ },
2350
+ {
2351
+ "epoch": 0.01675,
2352
+ "grad_norm": 1.3692466020584106,
2353
+ "learning_rate": 1.684547105928689e-05,
2354
+ "loss": 0.077,
2355
+ "step": 335
2356
+ },
2357
+ {
2358
+ "epoch": 0.0168,
2359
+ "grad_norm": 117.79779052734375,
2360
+ "learning_rate": 1.6819983600624986e-05,
2361
+ "loss": 0.2993,
2362
+ "step": 336
2363
+ },
2364
+ {
2365
+ "epoch": 0.01685,
2366
+ "grad_norm": 2.0206730365753174,
2367
+ "learning_rate": 1.6794413042615168e-05,
2368
+ "loss": 0.092,
2369
+ "step": 337
2370
+ },
2371
+ {
2372
+ "epoch": 0.0169,
2373
+ "grad_norm": 34.888587951660156,
2374
+ "learning_rate": 1.6768759696826608e-05,
2375
+ "loss": 0.1954,
2376
+ "step": 338
2377
+ },
2378
+ {
2379
+ "epoch": 0.01695,
2380
+ "grad_norm": 7.209064483642578,
2381
+ "learning_rate": 1.6743023875837233e-05,
2382
+ "loss": 0.1342,
2383
+ "step": 339
2384
+ },
2385
+ {
2386
+ "epoch": 0.017,
2387
+ "grad_norm": 1.6078732013702393,
2388
+ "learning_rate": 1.6717205893229904e-05,
2389
+ "loss": 0.0846,
2390
+ "step": 340
2391
+ },
2392
+ {
2393
+ "epoch": 0.01705,
2394
+ "grad_norm": 63.080848693847656,
2395
+ "learning_rate": 1.6691306063588583e-05,
2396
+ "loss": 0.411,
2397
+ "step": 341
2398
+ },
2399
+ {
2400
+ "epoch": 0.0171,
2401
+ "grad_norm": 29.949630737304688,
2402
+ "learning_rate": 1.6665324702494524e-05,
2403
+ "loss": 0.6917,
2404
+ "step": 342
2405
+ },
2406
+ {
2407
+ "epoch": 0.01715,
2408
+ "grad_norm": 31.307920455932617,
2409
+ "learning_rate": 1.6639262126522417e-05,
2410
+ "loss": 0.2668,
2411
+ "step": 343
2412
+ },
2413
+ {
2414
+ "epoch": 0.0172,
2415
+ "grad_norm": 13.792570114135742,
2416
+ "learning_rate": 1.661311865323652e-05,
2417
+ "loss": 0.119,
2418
+ "step": 344
2419
+ },
2420
+ {
2421
+ "epoch": 0.01725,
2422
+ "grad_norm": 30.71436882019043,
2423
+ "learning_rate": 1.6586894601186804e-05,
2424
+ "loss": 0.6006,
2425
+ "step": 345
2426
+ },
2427
+ {
2428
+ "epoch": 0.0173,
2429
+ "grad_norm": 2.122511863708496,
2430
+ "learning_rate": 1.6560590289905074e-05,
2431
+ "loss": 0.1022,
2432
+ "step": 346
2433
+ },
2434
+ {
2435
+ "epoch": 0.01735,
2436
+ "grad_norm": 4.920584201812744,
2437
+ "learning_rate": 1.6534206039901057e-05,
2438
+ "loss": 0.1127,
2439
+ "step": 347
2440
+ },
2441
+ {
2442
+ "epoch": 0.0174,
2443
+ "grad_norm": 76.10581970214844,
2444
+ "learning_rate": 1.650774217265851e-05,
2445
+ "loss": 0.2452,
2446
+ "step": 348
2447
+ },
2448
+ {
2449
+ "epoch": 0.01745,
2450
+ "grad_norm": 0.8686180114746094,
2451
+ "learning_rate": 1.6481199010631312e-05,
2452
+ "loss": 0.0773,
2453
+ "step": 349
2454
+ },
2455
+ {
2456
+ "epoch": 0.0175,
2457
+ "grad_norm": 2.1581313610076904,
2458
+ "learning_rate": 1.645457687723951e-05,
2459
+ "loss": 0.1051,
2460
+ "step": 350
2461
+ },
2462
+ {
2463
+ "epoch": 0.01755,
2464
+ "grad_norm": 1.0424079895019531,
2465
+ "learning_rate": 1.6427876096865394e-05,
2466
+ "loss": 0.0849,
2467
+ "step": 351
2468
+ },
2469
+ {
2470
+ "epoch": 0.0176,
2471
+ "grad_norm": 2.0918571949005127,
2472
+ "learning_rate": 1.6401096994849558e-05,
2473
+ "loss": 0.0837,
2474
+ "step": 352
2475
+ },
2476
+ {
2477
+ "epoch": 0.01765,
2478
+ "grad_norm": 2.8070149421691895,
2479
+ "learning_rate": 1.63742398974869e-05,
2480
+ "loss": 0.0866,
2481
+ "step": 353
2482
+ },
2483
+ {
2484
+ "epoch": 0.0177,
2485
+ "grad_norm": 2.4599366188049316,
2486
+ "learning_rate": 1.6347305132022677e-05,
2487
+ "loss": 0.0953,
2488
+ "step": 354
2489
+ },
2490
+ {
2491
+ "epoch": 0.01775,
2492
+ "grad_norm": 1.8522323369979858,
2493
+ "learning_rate": 1.632029302664851e-05,
2494
+ "loss": 0.0858,
2495
+ "step": 355
2496
+ },
2497
+ {
2498
+ "epoch": 0.0178,
2499
+ "grad_norm": 29.34244728088379,
2500
+ "learning_rate": 1.6293203910498375e-05,
2501
+ "loss": 0.3812,
2502
+ "step": 356
2503
+ },
2504
+ {
2505
+ "epoch": 0.01785,
2506
+ "grad_norm": 2.804577112197876,
2507
+ "learning_rate": 1.6266038113644605e-05,
2508
+ "loss": 0.106,
2509
+ "step": 357
2510
+ },
2511
+ {
2512
+ "epoch": 0.0179,
2513
+ "grad_norm": 1.0157254934310913,
2514
+ "learning_rate": 1.6238795967093865e-05,
2515
+ "loss": 0.0745,
2516
+ "step": 358
2517
+ },
2518
+ {
2519
+ "epoch": 0.01795,
2520
+ "grad_norm": 1.1413592100143433,
2521
+ "learning_rate": 1.6211477802783105e-05,
2522
+ "loss": 0.0695,
2523
+ "step": 359
2524
+ },
2525
+ {
2526
+ "epoch": 0.018,
2527
+ "grad_norm": 1.7196788787841797,
2528
+ "learning_rate": 1.6184083953575543e-05,
2529
+ "loss": 0.0858,
2530
+ "step": 360
2531
+ },
2532
+ {
2533
+ "epoch": 0.01805,
2534
+ "grad_norm": 9.58154296875,
2535
+ "learning_rate": 1.6156614753256583e-05,
2536
+ "loss": 0.5321,
2537
+ "step": 361
2538
+ },
2539
+ {
2540
+ "epoch": 0.0181,
2541
+ "grad_norm": 27.282711029052734,
2542
+ "learning_rate": 1.6129070536529767e-05,
2543
+ "loss": 0.2956,
2544
+ "step": 362
2545
+ },
2546
+ {
2547
+ "epoch": 0.01815,
2548
+ "grad_norm": 2.1738831996917725,
2549
+ "learning_rate": 1.610145163901268e-05,
2550
+ "loss": 0.0872,
2551
+ "step": 363
2552
+ },
2553
+ {
2554
+ "epoch": 0.0182,
2555
+ "grad_norm": 54.08341598510742,
2556
+ "learning_rate": 1.607375839723287e-05,
2557
+ "loss": 0.2653,
2558
+ "step": 364
2559
+ },
2560
+ {
2561
+ "epoch": 0.01825,
2562
+ "grad_norm": 32.51065444946289,
2563
+ "learning_rate": 1.6045991148623752e-05,
2564
+ "loss": 0.6676,
2565
+ "step": 365
2566
+ },
2567
+ {
2568
+ "epoch": 0.0183,
2569
+ "grad_norm": 2.3353264331817627,
2570
+ "learning_rate": 1.6018150231520486e-05,
2571
+ "loss": 0.0746,
2572
+ "step": 366
2573
+ },
2574
+ {
2575
+ "epoch": 0.01835,
2576
+ "grad_norm": 2.272801160812378,
2577
+ "learning_rate": 1.599023598515586e-05,
2578
+ "loss": 0.088,
2579
+ "step": 367
2580
+ },
2581
+ {
2582
+ "epoch": 0.0184,
2583
+ "grad_norm": 3.1989638805389404,
2584
+ "learning_rate": 1.5962248749656158e-05,
2585
+ "loss": 0.1,
2586
+ "step": 368
2587
+ },
2588
+ {
2589
+ "epoch": 0.01845,
2590
+ "grad_norm": 2.0776147842407227,
2591
+ "learning_rate": 1.5934188866037017e-05,
2592
+ "loss": 0.0704,
2593
+ "step": 369
2594
+ },
2595
+ {
2596
+ "epoch": 0.0185,
2597
+ "grad_norm": 1.6304274797439575,
2598
+ "learning_rate": 1.5906056676199256e-05,
2599
+ "loss": 0.068,
2600
+ "step": 370
2601
+ },
2602
+ {
2603
+ "epoch": 0.01855,
2604
+ "grad_norm": 1.6919046640396118,
2605
+ "learning_rate": 1.5877852522924733e-05,
2606
+ "loss": 0.0871,
2607
+ "step": 371
2608
+ },
2609
+ {
2610
+ "epoch": 0.0186,
2611
+ "grad_norm": 15.512767791748047,
2612
+ "learning_rate": 1.584957674987216e-05,
2613
+ "loss": 0.2278,
2614
+ "step": 372
2615
+ },
2616
+ {
2617
+ "epoch": 0.01865,
2618
+ "grad_norm": 1.8702269792556763,
2619
+ "learning_rate": 1.5821229701572897e-05,
2620
+ "loss": 0.1016,
2621
+ "step": 373
2622
+ },
2623
+ {
2624
+ "epoch": 0.0187,
2625
+ "grad_norm": 2.2889702320098877,
2626
+ "learning_rate": 1.5792811723426787e-05,
2627
+ "loss": 0.0825,
2628
+ "step": 374
2629
+ },
2630
+ {
2631
+ "epoch": 0.01875,
2632
+ "grad_norm": 0.818047046661377,
2633
+ "learning_rate": 1.5764323161697933e-05,
2634
+ "loss": 0.0647,
2635
+ "step": 375
2636
+ },
2637
+ {
2638
+ "epoch": 0.0188,
2639
+ "grad_norm": 6.705317974090576,
2640
+ "learning_rate": 1.573576436351046e-05,
2641
+ "loss": 0.1588,
2642
+ "step": 376
2643
+ },
2644
+ {
2645
+ "epoch": 0.01885,
2646
+ "grad_norm": 70.91289520263672,
2647
+ "learning_rate": 1.570713567684432e-05,
2648
+ "loss": 0.264,
2649
+ "step": 377
2650
+ },
2651
+ {
2652
+ "epoch": 0.0189,
2653
+ "grad_norm": 4.24697732925415,
2654
+ "learning_rate": 1.5678437450531014e-05,
2655
+ "loss": 0.1044,
2656
+ "step": 378
2657
+ },
2658
+ {
2659
+ "epoch": 0.01895,
2660
+ "grad_norm": 1.2441545724868774,
2661
+ "learning_rate": 1.564967003424938e-05,
2662
+ "loss": 0.0676,
2663
+ "step": 379
2664
+ },
2665
+ {
2666
+ "epoch": 0.019,
2667
+ "grad_norm": 11.383224487304688,
2668
+ "learning_rate": 1.5620833778521306e-05,
2669
+ "loss": 0.1717,
2670
+ "step": 380
2671
+ },
2672
+ {
2673
+ "epoch": 0.01905,
2674
+ "grad_norm": 1.8020143508911133,
2675
+ "learning_rate": 1.5591929034707468e-05,
2676
+ "loss": 0.0915,
2677
+ "step": 381
2678
+ },
2679
+ {
2680
+ "epoch": 0.0191,
2681
+ "grad_norm": 1.5403460264205933,
2682
+ "learning_rate": 1.556295615500305e-05,
2683
+ "loss": 0.0942,
2684
+ "step": 382
2685
+ },
2686
+ {
2687
+ "epoch": 0.01915,
2688
+ "grad_norm": 4.809276103973389,
2689
+ "learning_rate": 1.553391549243344e-05,
2690
+ "loss": 0.1307,
2691
+ "step": 383
2692
+ },
2693
+ {
2694
+ "epoch": 0.0192,
2695
+ "grad_norm": 1.7769126892089844,
2696
+ "learning_rate": 1.5504807400849957e-05,
2697
+ "loss": 0.0981,
2698
+ "step": 384
2699
+ },
2700
+ {
2701
+ "epoch": 0.01925,
2702
+ "grad_norm": 21.044578552246094,
2703
+ "learning_rate": 1.5475632234925505e-05,
2704
+ "loss": 0.1922,
2705
+ "step": 385
2706
+ },
2707
+ {
2708
+ "epoch": 0.0193,
2709
+ "grad_norm": 2.1597342491149902,
2710
+ "learning_rate": 1.5446390350150272e-05,
2711
+ "loss": 0.0778,
2712
+ "step": 386
2713
+ },
2714
+ {
2715
+ "epoch": 0.01935,
2716
+ "grad_norm": 71.87742614746094,
2717
+ "learning_rate": 1.54170821028274e-05,
2718
+ "loss": 0.2516,
2719
+ "step": 387
2720
+ },
2721
+ {
2722
+ "epoch": 0.0194,
2723
+ "grad_norm": 2.8716869354248047,
2724
+ "learning_rate": 1.5387707850068633e-05,
2725
+ "loss": 0.0801,
2726
+ "step": 388
2727
+ },
2728
+ {
2729
+ "epoch": 0.01945,
2730
+ "grad_norm": 3.6430041790008545,
2731
+ "learning_rate": 1.5358267949789968e-05,
2732
+ "loss": 0.0982,
2733
+ "step": 389
2734
+ },
2735
+ {
2736
+ "epoch": 0.0195,
2737
+ "grad_norm": 3.5003151893615723,
2738
+ "learning_rate": 1.53287627607073e-05,
2739
+ "loss": 0.1146,
2740
+ "step": 390
2741
+ },
2742
+ {
2743
+ "epoch": 0.01955,
2744
+ "grad_norm": 33.15953826904297,
2745
+ "learning_rate": 1.529919264233205e-05,
2746
+ "loss": 0.5638,
2747
+ "step": 391
2748
+ },
2749
+ {
2750
+ "epoch": 0.0196,
2751
+ "grad_norm": 68.7998046875,
2752
+ "learning_rate": 1.5269557954966777e-05,
2753
+ "loss": 0.2967,
2754
+ "step": 392
2755
+ },
2756
+ {
2757
+ "epoch": 0.01965,
2758
+ "grad_norm": 4.234882831573486,
2759
+ "learning_rate": 1.5239859059700794e-05,
2760
+ "loss": 0.108,
2761
+ "step": 393
2762
+ },
2763
+ {
2764
+ "epoch": 0.0197,
2765
+ "grad_norm": 1.4191491603851318,
2766
+ "learning_rate": 1.5210096318405768e-05,
2767
+ "loss": 0.0816,
2768
+ "step": 394
2769
+ },
2770
+ {
2771
+ "epoch": 0.01975,
2772
+ "grad_norm": 1.553654670715332,
2773
+ "learning_rate": 1.5180270093731305e-05,
2774
+ "loss": 0.0849,
2775
+ "step": 395
2776
+ },
2777
+ {
2778
+ "epoch": 0.0198,
2779
+ "grad_norm": 28.652915954589844,
2780
+ "learning_rate": 1.5150380749100545e-05,
2781
+ "loss": 0.3633,
2782
+ "step": 396
2783
+ },
2784
+ {
2785
+ "epoch": 0.01985,
2786
+ "grad_norm": 7.698509216308594,
2787
+ "learning_rate": 1.5120428648705716e-05,
2788
+ "loss": 0.1178,
2789
+ "step": 397
2790
+ },
2791
+ {
2792
+ "epoch": 0.0199,
2793
+ "grad_norm": 1.612652063369751,
2794
+ "learning_rate": 1.5090414157503715e-05,
2795
+ "loss": 0.0578,
2796
+ "step": 398
2797
+ },
2798
+ {
2799
+ "epoch": 0.01995,
2800
+ "grad_norm": 19.84796714782715,
2801
+ "learning_rate": 1.5060337641211637e-05,
2802
+ "loss": 0.321,
2803
+ "step": 399
2804
+ },
2805
+ {
2806
+ "epoch": 0.02,
2807
+ "grad_norm": 5.804268836975098,
2808
+ "learning_rate": 1.5030199466302354e-05,
2809
+ "loss": 0.1119,
2810
+ "step": 400
2811
+ },
2812
+ {
2813
+ "epoch": 0.02005,
2814
+ "grad_norm": 30.93545913696289,
2815
+ "learning_rate": 1.5000000000000002e-05,
2816
+ "loss": 0.2467,
2817
+ "step": 401
2818
+ },
2819
+ {
2820
+ "epoch": 0.0201,
2821
+ "grad_norm": 77.25408172607422,
2822
+ "learning_rate": 1.4969739610275556e-05,
2823
+ "loss": 0.3551,
2824
+ "step": 402
2825
+ },
2826
+ {
2827
+ "epoch": 0.02015,
2828
+ "grad_norm": 1.7736424207687378,
2829
+ "learning_rate": 1.493941866584231e-05,
2830
+ "loss": 0.0929,
2831
+ "step": 403
2832
+ },
2833
+ {
2834
+ "epoch": 0.0202,
2835
+ "grad_norm": 5.388272285461426,
2836
+ "learning_rate": 1.490903753615141e-05,
2837
+ "loss": 0.1161,
2838
+ "step": 404
2839
+ },
2840
+ {
2841
+ "epoch": 0.02025,
2842
+ "grad_norm": 2.175442934036255,
2843
+ "learning_rate": 1.4878596591387329e-05,
2844
+ "loss": 0.0694,
2845
+ "step": 405
2846
+ },
2847
+ {
2848
+ "epoch": 0.0203,
2849
+ "grad_norm": 1.5696885585784912,
2850
+ "learning_rate": 1.4848096202463373e-05,
2851
+ "loss": 0.1043,
2852
+ "step": 406
2853
+ },
2854
+ {
2855
+ "epoch": 0.02035,
2856
+ "grad_norm": 1.4840455055236816,
2857
+ "learning_rate": 1.4817536741017153e-05,
2858
+ "loss": 0.0649,
2859
+ "step": 407
2860
+ },
2861
+ {
2862
+ "epoch": 0.0204,
2863
+ "grad_norm": 27.966121673583984,
2864
+ "learning_rate": 1.478691857940607e-05,
2865
+ "loss": 0.1131,
2866
+ "step": 408
2867
+ },
2868
+ {
2869
+ "epoch": 0.02045,
2870
+ "grad_norm": 1.381766438484192,
2871
+ "learning_rate": 1.4756242090702756e-05,
2872
+ "loss": 0.0965,
2873
+ "step": 409
2874
+ },
2875
+ {
2876
+ "epoch": 0.0205,
2877
+ "grad_norm": 1.185716986656189,
2878
+ "learning_rate": 1.4725507648690542e-05,
2879
+ "loss": 0.0692,
2880
+ "step": 410
2881
+ },
2882
+ {
2883
+ "epoch": 0.02055,
2884
+ "grad_norm": 1.860116720199585,
2885
+ "learning_rate": 1.469471562785891e-05,
2886
+ "loss": 0.0943,
2887
+ "step": 411
2888
+ },
2889
+ {
2890
+ "epoch": 0.0206,
2891
+ "grad_norm": 1.27677583694458,
2892
+ "learning_rate": 1.4663866403398915e-05,
2893
+ "loss": 0.061,
2894
+ "step": 412
2895
+ },
2896
+ {
2897
+ "epoch": 0.02065,
2898
+ "grad_norm": 1.2773680686950684,
2899
+ "learning_rate": 1.463296035119862e-05,
2900
+ "loss": 0.079,
2901
+ "step": 413
2902
+ },
2903
+ {
2904
+ "epoch": 0.0207,
2905
+ "grad_norm": 3.0321786403656006,
2906
+ "learning_rate": 1.4601997847838518e-05,
2907
+ "loss": 0.0769,
2908
+ "step": 414
2909
+ },
2910
+ {
2911
+ "epoch": 0.02075,
2912
+ "grad_norm": 1.8801988363265991,
2913
+ "learning_rate": 1.4570979270586944e-05,
2914
+ "loss": 0.0725,
2915
+ "step": 415
2916
+ },
2917
+ {
2918
+ "epoch": 0.0208,
2919
+ "grad_norm": 35.990970611572266,
2920
+ "learning_rate": 1.4539904997395468e-05,
2921
+ "loss": 0.5037,
2922
+ "step": 416
2923
+ },
2924
+ {
2925
+ "epoch": 0.02085,
2926
+ "grad_norm": 21.723236083984375,
2927
+ "learning_rate": 1.4508775406894308e-05,
2928
+ "loss": 0.5753,
2929
+ "step": 417
2930
+ },
2931
+ {
2932
+ "epoch": 0.0209,
2933
+ "grad_norm": 1.4752088785171509,
2934
+ "learning_rate": 1.4477590878387697e-05,
2935
+ "loss": 0.0777,
2936
+ "step": 418
2937
+ },
2938
+ {
2939
+ "epoch": 0.02095,
2940
+ "grad_norm": 81.2683334350586,
2941
+ "learning_rate": 1.4446351791849276e-05,
2942
+ "loss": 0.2849,
2943
+ "step": 419
2944
+ },
2945
+ {
2946
+ "epoch": 0.021,
2947
+ "grad_norm": 1.2820717096328735,
2948
+ "learning_rate": 1.4415058527917454e-05,
2949
+ "loss": 0.0606,
2950
+ "step": 420
2951
+ },
2952
+ {
2953
+ "epoch": 0.02105,
2954
+ "grad_norm": 43.90168380737305,
2955
+ "learning_rate": 1.4383711467890776e-05,
2956
+ "loss": 0.15,
2957
+ "step": 421
2958
+ },
2959
+ {
2960
+ "epoch": 0.0211,
2961
+ "grad_norm": 2.168410301208496,
2962
+ "learning_rate": 1.4352310993723277e-05,
2963
+ "loss": 0.0768,
2964
+ "step": 422
2965
+ },
2966
+ {
2967
+ "epoch": 0.02115,
2968
+ "grad_norm": 2.721632242202759,
2969
+ "learning_rate": 1.4320857488019826e-05,
2970
+ "loss": 0.0778,
2971
+ "step": 423
2972
+ },
2973
+ {
2974
+ "epoch": 0.0212,
2975
+ "grad_norm": 31.003597259521484,
2976
+ "learning_rate": 1.4289351334031461e-05,
2977
+ "loss": 0.3962,
2978
+ "step": 424
2979
+ },
2980
+ {
2981
+ "epoch": 0.02125,
2982
+ "grad_norm": 2.4142940044403076,
2983
+ "learning_rate": 1.4257792915650728e-05,
2984
+ "loss": 0.066,
2985
+ "step": 425
2986
+ },
2987
+ {
2988
+ "epoch": 0.0213,
2989
+ "grad_norm": 0.9857182502746582,
2990
+ "learning_rate": 1.4226182617406996e-05,
2991
+ "loss": 0.0628,
2992
+ "step": 426
2993
+ },
2994
+ {
2995
+ "epoch": 0.02135,
2996
+ "grad_norm": 27.239112854003906,
2997
+ "learning_rate": 1.4194520824461773e-05,
2998
+ "loss": 0.1553,
2999
+ "step": 427
3000
+ },
3001
+ {
3002
+ "epoch": 0.0214,
3003
+ "grad_norm": 1.5095759630203247,
3004
+ "learning_rate": 1.4162807922604014e-05,
3005
+ "loss": 0.0623,
3006
+ "step": 428
3007
+ },
3008
+ {
3009
+ "epoch": 0.02145,
3010
+ "grad_norm": 1.2446397542953491,
3011
+ "learning_rate": 1.413104429824542e-05,
3012
+ "loss": 0.0632,
3013
+ "step": 429
3014
+ },
3015
+ {
3016
+ "epoch": 0.0215,
3017
+ "grad_norm": 23.939973831176758,
3018
+ "learning_rate": 1.4099230338415728e-05,
3019
+ "loss": 0.0938,
3020
+ "step": 430
3021
+ },
3022
+ {
3023
+ "epoch": 0.02155,
3024
+ "grad_norm": 2.7718734741210938,
3025
+ "learning_rate": 1.4067366430758004e-05,
3026
+ "loss": 0.1157,
3027
+ "step": 431
3028
+ },
3029
+ {
3030
+ "epoch": 0.0216,
3031
+ "grad_norm": 1.762878656387329,
3032
+ "learning_rate": 1.4035452963523903e-05,
3033
+ "loss": 0.0837,
3034
+ "step": 432
3035
+ },
3036
+ {
3037
+ "epoch": 0.02165,
3038
+ "grad_norm": 1.1785478591918945,
3039
+ "learning_rate": 1.4003490325568953e-05,
3040
+ "loss": 0.0786,
3041
+ "step": 433
3042
+ },
3043
+ {
3044
+ "epoch": 0.0217,
3045
+ "grad_norm": 2.3212571144104004,
3046
+ "learning_rate": 1.3971478906347806e-05,
3047
+ "loss": 0.0795,
3048
+ "step": 434
3049
+ },
3050
+ {
3051
+ "epoch": 0.02175,
3052
+ "grad_norm": 61.90953826904297,
3053
+ "learning_rate": 1.3939419095909513e-05,
3054
+ "loss": 0.1883,
3055
+ "step": 435
3056
+ },
3057
+ {
3058
+ "epoch": 0.0218,
3059
+ "grad_norm": 2.4108712673187256,
3060
+ "learning_rate": 1.3907311284892737e-05,
3061
+ "loss": 0.101,
3062
+ "step": 436
3063
+ },
3064
+ {
3065
+ "epoch": 0.02185,
3066
+ "grad_norm": 18.406414031982422,
3067
+ "learning_rate": 1.3875155864521031e-05,
3068
+ "loss": 0.124,
3069
+ "step": 437
3070
+ },
3071
+ {
3072
+ "epoch": 0.0219,
3073
+ "grad_norm": 2.9103317260742188,
3074
+ "learning_rate": 1.3842953226598036e-05,
3075
+ "loss": 0.1076,
3076
+ "step": 438
3077
+ },
3078
+ {
3079
+ "epoch": 0.02195,
3080
+ "grad_norm": 3.6682307720184326,
3081
+ "learning_rate": 1.3810703763502744e-05,
3082
+ "loss": 0.1115,
3083
+ "step": 439
3084
+ },
3085
+ {
3086
+ "epoch": 0.022,
3087
+ "grad_norm": 2.4667904376983643,
3088
+ "learning_rate": 1.3778407868184674e-05,
3089
+ "loss": 0.0894,
3090
+ "step": 440
3091
+ },
3092
+ {
3093
+ "epoch": 0.02205,
3094
+ "grad_norm": 1.5204410552978516,
3095
+ "learning_rate": 1.3746065934159123e-05,
3096
+ "loss": 0.0696,
3097
+ "step": 441
3098
+ },
3099
+ {
3100
+ "epoch": 0.0221,
3101
+ "grad_norm": 2.2093870639801025,
3102
+ "learning_rate": 1.371367835550235e-05,
3103
+ "loss": 0.0988,
3104
+ "step": 442
3105
+ },
3106
+ {
3107
+ "epoch": 0.02215,
3108
+ "grad_norm": 1.1975420713424683,
3109
+ "learning_rate": 1.3681245526846782e-05,
3110
+ "loss": 0.075,
3111
+ "step": 443
3112
+ },
3113
+ {
3114
+ "epoch": 0.0222,
3115
+ "grad_norm": 41.98251724243164,
3116
+ "learning_rate": 1.3648767843376196e-05,
3117
+ "loss": 0.4722,
3118
+ "step": 444
3119
+ },
3120
+ {
3121
+ "epoch": 0.02225,
3122
+ "grad_norm": 2.698796272277832,
3123
+ "learning_rate": 1.3616245700820922e-05,
3124
+ "loss": 0.093,
3125
+ "step": 445
3126
+ },
3127
+ {
3128
+ "epoch": 0.0223,
3129
+ "grad_norm": 25.365121841430664,
3130
+ "learning_rate": 1.3583679495453e-05,
3131
+ "loss": 0.6883,
3132
+ "step": 446
3133
+ },
3134
+ {
3135
+ "epoch": 0.02235,
3136
+ "grad_norm": 26.637304306030273,
3137
+ "learning_rate": 1.3551069624081372e-05,
3138
+ "loss": 0.2127,
3139
+ "step": 447
3140
+ },
3141
+ {
3142
+ "epoch": 0.0224,
3143
+ "grad_norm": 1.6217232942581177,
3144
+ "learning_rate": 1.3518416484047018e-05,
3145
+ "loss": 0.0728,
3146
+ "step": 448
3147
+ },
3148
+ {
3149
+ "epoch": 0.02245,
3150
+ "grad_norm": 2.7400615215301514,
3151
+ "learning_rate": 1.3485720473218153e-05,
3152
+ "loss": 0.0927,
3153
+ "step": 449
3154
+ },
3155
+ {
3156
+ "epoch": 0.0225,
3157
+ "grad_norm": 2.490354537963867,
3158
+ "learning_rate": 1.3452981989985347e-05,
3159
+ "loss": 0.0998,
3160
+ "step": 450
3161
+ },
3162
+ {
3163
+ "epoch": 0.02255,
3164
+ "grad_norm": 3.2277610301971436,
3165
+ "learning_rate": 1.342020143325669e-05,
3166
+ "loss": 0.1005,
3167
+ "step": 451
3168
+ },
3169
+ {
3170
+ "epoch": 0.0226,
3171
+ "grad_norm": 1.15992271900177,
3172
+ "learning_rate": 1.3387379202452917e-05,
3173
+ "loss": 0.0646,
3174
+ "step": 452
3175
+ },
3176
+ {
3177
+ "epoch": 0.02265,
3178
+ "grad_norm": 2.447103261947632,
3179
+ "learning_rate": 1.3354515697502552e-05,
3180
+ "loss": 0.0893,
3181
+ "step": 453
3182
+ },
3183
+ {
3184
+ "epoch": 0.0227,
3185
+ "grad_norm": 3.7397661209106445,
3186
+ "learning_rate": 1.3321611318837033e-05,
3187
+ "loss": 0.0956,
3188
+ "step": 454
3189
+ },
3190
+ {
3191
+ "epoch": 0.02275,
3192
+ "grad_norm": 1.829380989074707,
3193
+ "learning_rate": 1.3288666467385834e-05,
3194
+ "loss": 0.0824,
3195
+ "step": 455
3196
+ },
3197
+ {
3198
+ "epoch": 0.0228,
3199
+ "grad_norm": 1.3651745319366455,
3200
+ "learning_rate": 1.3255681544571568e-05,
3201
+ "loss": 0.0723,
3202
+ "step": 456
3203
+ },
3204
+ {
3205
+ "epoch": 0.02285,
3206
+ "grad_norm": 1.840768575668335,
3207
+ "learning_rate": 1.3222656952305113e-05,
3208
+ "loss": 0.0835,
3209
+ "step": 457
3210
+ },
3211
+ {
3212
+ "epoch": 0.0229,
3213
+ "grad_norm": 34.218894958496094,
3214
+ "learning_rate": 1.3189593092980701e-05,
3215
+ "loss": 0.4912,
3216
+ "step": 458
3217
+ },
3218
+ {
3219
+ "epoch": 0.02295,
3220
+ "grad_norm": 1.4367423057556152,
3221
+ "learning_rate": 1.3156490369471026e-05,
3222
+ "loss": 0.0654,
3223
+ "step": 459
3224
+ },
3225
+ {
3226
+ "epoch": 0.023,
3227
+ "grad_norm": 1.4354041814804077,
3228
+ "learning_rate": 1.3123349185122328e-05,
3229
+ "loss": 0.0607,
3230
+ "step": 460
3231
+ },
3232
+ {
3233
+ "epoch": 0.02305,
3234
+ "grad_norm": 8.959512710571289,
3235
+ "learning_rate": 1.3090169943749475e-05,
3236
+ "loss": 0.0942,
3237
+ "step": 461
3238
+ },
3239
+ {
3240
+ "epoch": 0.0231,
3241
+ "grad_norm": 12.93722152709961,
3242
+ "learning_rate": 1.3056953049631059e-05,
3243
+ "loss": 0.2287,
3244
+ "step": 462
3245
+ },
3246
+ {
3247
+ "epoch": 0.02315,
3248
+ "grad_norm": 0.9477676749229431,
3249
+ "learning_rate": 1.3023698907504447e-05,
3250
+ "loss": 0.0627,
3251
+ "step": 463
3252
+ },
3253
+ {
3254
+ "epoch": 0.0232,
3255
+ "grad_norm": 21.566787719726562,
3256
+ "learning_rate": 1.2990407922560869e-05,
3257
+ "loss": 0.1503,
3258
+ "step": 464
3259
+ },
3260
+ {
3261
+ "epoch": 0.02325,
3262
+ "grad_norm": 1.426946997642517,
3263
+ "learning_rate": 1.2957080500440469e-05,
3264
+ "loss": 0.0806,
3265
+ "step": 465
3266
+ },
3267
+ {
3268
+ "epoch": 0.0233,
3269
+ "grad_norm": 24.813554763793945,
3270
+ "learning_rate": 1.2923717047227368e-05,
3271
+ "loss": 0.4477,
3272
+ "step": 466
3273
+ },
3274
+ {
3275
+ "epoch": 0.02335,
3276
+ "grad_norm": 1.1683995723724365,
3277
+ "learning_rate": 1.2890317969444716e-05,
3278
+ "loss": 0.0683,
3279
+ "step": 467
3280
+ },
3281
+ {
3282
+ "epoch": 0.0234,
3283
+ "grad_norm": 26.862457275390625,
3284
+ "learning_rate": 1.2856883674049736e-05,
3285
+ "loss": 0.2431,
3286
+ "step": 468
3287
+ },
3288
+ {
3289
+ "epoch": 0.02345,
3290
+ "grad_norm": 1.4641770124435425,
3291
+ "learning_rate": 1.2823414568428767e-05,
3292
+ "loss": 0.08,
3293
+ "step": 469
3294
+ },
3295
+ {
3296
+ "epoch": 0.0235,
3297
+ "grad_norm": 1.9108537435531616,
3298
+ "learning_rate": 1.2789911060392295e-05,
3299
+ "loss": 0.0797,
3300
+ "step": 470
3301
+ },
3302
+ {
3303
+ "epoch": 0.02355,
3304
+ "grad_norm": 18.305461883544922,
3305
+ "learning_rate": 1.2756373558169992e-05,
3306
+ "loss": 0.2025,
3307
+ "step": 471
3308
+ },
3309
+ {
3310
+ "epoch": 0.0236,
3311
+ "grad_norm": 9.38343334197998,
3312
+ "learning_rate": 1.2722802470405744e-05,
3313
+ "loss": 0.1712,
3314
+ "step": 472
3315
+ },
3316
+ {
3317
+ "epoch": 0.02365,
3318
+ "grad_norm": 0.9332784414291382,
3319
+ "learning_rate": 1.2689198206152657e-05,
3320
+ "loss": 0.061,
3321
+ "step": 473
3322
+ },
3323
+ {
3324
+ "epoch": 0.0237,
3325
+ "grad_norm": 2.740528106689453,
3326
+ "learning_rate": 1.265556117486809e-05,
3327
+ "loss": 0.0643,
3328
+ "step": 474
3329
+ },
3330
+ {
3331
+ "epoch": 0.02375,
3332
+ "grad_norm": 2.050279378890991,
3333
+ "learning_rate": 1.2621891786408648e-05,
3334
+ "loss": 0.0739,
3335
+ "step": 475
3336
+ },
3337
+ {
3338
+ "epoch": 0.0238,
3339
+ "grad_norm": 4.4667558670043945,
3340
+ "learning_rate": 1.2588190451025209e-05,
3341
+ "loss": 0.0964,
3342
+ "step": 476
3343
+ },
3344
+ {
3345
+ "epoch": 0.02385,
3346
+ "grad_norm": 1.703878402709961,
3347
+ "learning_rate": 1.2554457579357906e-05,
3348
+ "loss": 0.0775,
3349
+ "step": 477
3350
+ },
3351
+ {
3352
+ "epoch": 0.0239,
3353
+ "grad_norm": 1.2993277311325073,
3354
+ "learning_rate": 1.252069358243114e-05,
3355
+ "loss": 0.0627,
3356
+ "step": 478
3357
+ },
3358
+ {
3359
+ "epoch": 0.02395,
3360
+ "grad_norm": 21.238073348999023,
3361
+ "learning_rate": 1.2486898871648552e-05,
3362
+ "loss": 0.188,
3363
+ "step": 479
3364
+ },
3365
+ {
3366
+ "epoch": 0.024,
3367
+ "grad_norm": 1.4124360084533691,
3368
+ "learning_rate": 1.2453073858788027e-05,
3369
+ "loss": 0.0864,
3370
+ "step": 480
3371
+ },
3372
+ {
3373
+ "epoch": 0.02405,
3374
+ "grad_norm": 14.426772117614746,
3375
+ "learning_rate": 1.2419218955996677e-05,
3376
+ "loss": 0.4066,
3377
+ "step": 481
3378
+ },
3379
+ {
3380
+ "epoch": 0.0241,
3381
+ "grad_norm": 2.3008742332458496,
3382
+ "learning_rate": 1.238533457578581e-05,
3383
+ "loss": 0.109,
3384
+ "step": 482
3385
+ },
3386
+ {
3387
+ "epoch": 0.02415,
3388
+ "grad_norm": 3.065260648727417,
3389
+ "learning_rate": 1.23514211310259e-05,
3390
+ "loss": 0.1144,
3391
+ "step": 483
3392
+ },
3393
+ {
3394
+ "epoch": 0.0242,
3395
+ "grad_norm": 3.2149078845977783,
3396
+ "learning_rate": 1.2317479034941572e-05,
3397
+ "loss": 0.1031,
3398
+ "step": 484
3399
+ },
3400
+ {
3401
+ "epoch": 0.02425,
3402
+ "grad_norm": 1.5617332458496094,
3403
+ "learning_rate": 1.2283508701106559e-05,
3404
+ "loss": 0.0558,
3405
+ "step": 485
3406
+ },
3407
+ {
3408
+ "epoch": 0.0243,
3409
+ "grad_norm": 21.832523345947266,
3410
+ "learning_rate": 1.2249510543438652e-05,
3411
+ "loss": 0.1919,
3412
+ "step": 486
3413
+ },
3414
+ {
3415
+ "epoch": 0.02435,
3416
+ "grad_norm": 2.4033219814300537,
3417
+ "learning_rate": 1.2215484976194675e-05,
3418
+ "loss": 0.0682,
3419
+ "step": 487
3420
+ },
3421
+ {
3422
+ "epoch": 0.0244,
3423
+ "grad_norm": 17.43706512451172,
3424
+ "learning_rate": 1.2181432413965428e-05,
3425
+ "loss": 0.4117,
3426
+ "step": 488
3427
+ },
3428
+ {
3429
+ "epoch": 0.02445,
3430
+ "grad_norm": 3.9174792766571045,
3431
+ "learning_rate": 1.2147353271670634e-05,
3432
+ "loss": 0.0823,
3433
+ "step": 489
3434
+ },
3435
+ {
3436
+ "epoch": 0.0245,
3437
+ "grad_norm": 46.03153610229492,
3438
+ "learning_rate": 1.211324796455389e-05,
3439
+ "loss": 0.3065,
3440
+ "step": 490
3441
+ },
3442
+ {
3443
+ "epoch": 0.02455,
3444
+ "grad_norm": 1.6286877393722534,
3445
+ "learning_rate": 1.2079116908177592e-05,
3446
+ "loss": 0.0705,
3447
+ "step": 491
3448
+ },
3449
+ {
3450
+ "epoch": 0.0246,
3451
+ "grad_norm": 39.38934326171875,
3452
+ "learning_rate": 1.2044960518417902e-05,
3453
+ "loss": 0.412,
3454
+ "step": 492
3455
+ },
3456
+ {
3457
+ "epoch": 0.02465,
3458
+ "grad_norm": 18.489652633666992,
3459
+ "learning_rate": 1.2010779211459649e-05,
3460
+ "loss": 0.1775,
3461
+ "step": 493
3462
+ },
3463
+ {
3464
+ "epoch": 0.0247,
3465
+ "grad_norm": 1.5449779033660889,
3466
+ "learning_rate": 1.1976573403791263e-05,
3467
+ "loss": 0.0777,
3468
+ "step": 494
3469
+ },
3470
+ {
3471
+ "epoch": 0.02475,
3472
+ "grad_norm": 1.7571698427200317,
3473
+ "learning_rate": 1.194234351219972e-05,
3474
+ "loss": 0.0909,
3475
+ "step": 495
3476
+ },
3477
+ {
3478
+ "epoch": 0.0248,
3479
+ "grad_norm": 1.4077978134155273,
3480
+ "learning_rate": 1.190808995376545e-05,
3481
+ "loss": 0.0665,
3482
+ "step": 496
3483
+ },
3484
+ {
3485
+ "epoch": 0.02485,
3486
+ "grad_norm": 4.160821437835693,
3487
+ "learning_rate": 1.187381314585725e-05,
3488
+ "loss": 0.0962,
3489
+ "step": 497
3490
+ },
3491
+ {
3492
+ "epoch": 0.0249,
3493
+ "grad_norm": 2.014230728149414,
3494
+ "learning_rate": 1.1839513506127202e-05,
3495
+ "loss": 0.0773,
3496
+ "step": 498
3497
+ },
3498
+ {
3499
+ "epoch": 0.02495,
3500
+ "grad_norm": 2.2846667766571045,
3501
+ "learning_rate": 1.1805191452505602e-05,
3502
+ "loss": 0.113,
3503
+ "step": 499
3504
+ },
3505
+ {
3506
+ "epoch": 0.025,
3507
+ "grad_norm": 1.8118311166763306,
3508
+ "learning_rate": 1.1770847403195836e-05,
3509
+ "loss": 0.0598,
3510
+ "step": 500
3511
+ }
3512
+ ],
3513
+ "logging_steps": 1,
3514
+ "max_steps": 1000,
3515
+ "num_input_tokens_seen": 0,
3516
+ "num_train_epochs": 1,
3517
+ "save_steps": 200,
3518
+ "stateful_callbacks": {
3519
+ "TrainerControl": {
3520
+ "args": {
3521
+ "should_epoch_stop": false,
3522
+ "should_evaluate": false,
3523
+ "should_log": false,
3524
+ "should_save": false,
3525
+ "should_training_stop": false
3526
+ },
3527
+ "attributes": {}
3528
+ }
3529
+ },
3530
+ "total_flos": 0.0,
3531
+ "train_batch_size": 8,
3532
+ "trial_name": null,
3533
+ "trial_params": null
3534
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:146cefd13fd5d69db471454c874c947c9e8f345427d1dd56b1b7dc21d9e0acc4
3
+ size 5841