w-ahmad commited on
Commit
90fc66e
·
verified ·
1 Parent(s): ccba799

Upload entire model folder (part 2)

Browse files
wandb/debug-internal.log CHANGED
@@ -881,3 +881,39 @@
881
  {"time":"2026-08-03T01:56:13.766620862Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
882
  {"time":"2026-08-03T01:56:28.550658745Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":3779,"history_lines":3,"events_offset":871,"events_lines":2,"console_offset":4078,"console_lines":9}
883
  {"time":"2026-08-03T01:56:28.942217122Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
881
  {"time":"2026-08-03T01:56:13.766620862Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
882
  {"time":"2026-08-03T01:56:28.550658745Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":3779,"history_lines":3,"events_offset":871,"events_lines":2,"console_offset":4078,"console_lines":9}
883
  {"time":"2026-08-03T01:56:28.942217122Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
884
+ {"time":"2026-08-03T01:56:43.550276701Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":3782,"history_lines":10,"events_offset":873,"events_lines":2,"console_offset":4084,"console_lines":1}
885
+ {"time":"2026-08-03T01:56:43.870134841Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
886
+ {"time":"2026-08-03T01:56:58.550560434Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":3792,"history_lines":10,"events_offset":875,"events_lines":2,"console_offset":4084,"console_lines":1}
887
+ {"time":"2026-08-03T01:56:58.805307452Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
888
+ {"time":"2026-08-03T01:57:13.550239277Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":3802,"history_lines":11,"events_offset":877,"events_lines":2,"console_offset":4084,"console_lines":1}
889
+ {"time":"2026-08-03T01:57:13.715260475Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
890
+ {"time":"2026-08-03T01:57:28.550662766Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":3813,"history_lines":10,"events_offset":879,"events_lines":2,"console_offset":4087,"console_lines":41}
891
+ {"time":"2026-08-03T01:57:28.928462625Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
892
+ {"time":"2026-08-03T01:57:43.550225887Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":3823,"history_lines":7,"events_offset":881,"events_lines":2,"console_offset":4128,"console_lines":8}
893
+ {"time":"2026-08-03T01:57:43.800131275Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
894
+ {"time":"2026-08-03T01:57:58.550422994Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":3830,"history_lines":5,"events_offset":883,"events_lines":2,"console_offset":4135,"console_lines":6}
895
+ {"time":"2026-08-03T01:57:58.805706284Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
896
+ {"time":"2026-08-03T01:58:13.549885357Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":3835,"history_lines":11,"events_offset":885,"events_lines":2,"console_offset":4141,"console_lines":11}
897
+ {"time":"2026-08-03T01:58:13.712269171Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
898
+ {"time":"2026-08-03T01:58:28.550591544Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":3846,"history_lines":10,"events_offset":887,"events_lines":2,"console_offset":4152,"console_lines":10}
899
+ {"time":"2026-08-03T01:58:28.770157422Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
900
+ {"time":"2026-08-03T01:58:43.550671465Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":3856,"history_lines":10,"events_offset":889,"events_lines":2,"console_offset":4162,"console_lines":10}
901
+ {"time":"2026-08-03T01:58:43.78455609Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
902
+ {"time":"2026-08-03T01:58:58.550246569Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":3866,"history_lines":10,"events_offset":891,"events_lines":2,"console_offset":4172,"console_lines":10}
903
+ {"time":"2026-08-03T01:58:58.776779762Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
904
+ {"time":"2026-08-03T01:59:13.550472831Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":3876,"history_lines":5,"events_offset":893,"events_lines":2,"console_offset":4182,"console_lines":5}
905
+ {"time":"2026-08-03T01:59:13.757926044Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
906
+ {"time":"2026-08-03T01:59:28.550391713Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":3881,"history_lines":7,"events_offset":895,"events_lines":2,"console_offset":4187,"console_lines":13}
907
+ {"time":"2026-08-03T01:59:29.027920091Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
908
+ {"time":"2026-08-03T01:59:43.550715008Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":3888,"history_lines":10,"events_offset":897,"events_lines":2,"console_offset":4193,"console_lines":1}
909
+ {"time":"2026-08-03T01:59:43.975009654Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
910
+ {"time":"2026-08-03T01:59:58.550358662Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":3898,"history_lines":10,"events_offset":899,"events_lines":2,"console_offset":4193,"console_lines":1}
911
+ {"time":"2026-08-03T01:59:58.725210066Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
912
+ {"time":"2026-08-03T02:00:13.549998818Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":3908,"history_lines":11,"events_offset":901,"events_lines":2,"console_offset":4193,"console_lines":1}
913
+ {"time":"2026-08-03T02:00:13.829452162Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
914
+ {"time":"2026-08-03T02:00:28.549995799Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":3919,"history_lines":10,"events_offset":903,"events_lines":2,"console_offset":4200,"console_lines":41}
915
+ {"time":"2026-08-03T02:00:28.795194135Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
916
+ {"time":"2026-08-03T02:00:43.550452093Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":3929,"history_lines":3,"events_offset":905,"events_lines":2,"console_offset":4241,"console_lines":4}
917
+ {"time":"2026-08-03T02:00:43.734399312Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
918
+ {"time":"2026-08-03T02:00:58.550399722Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":3932,"history_lines":9,"events_offset":907,"events_lines":2,"console_offset":4244,"console_lines":10}
919
+ {"time":"2026-08-03T02:00:58.794953391Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
wandb/run-20260803_000712-b7gsa2kc/files/output.log CHANGED
@@ -4082,10 +4082,177 @@ Writing model shards: 100%|█████████████████
4082
  Writing model shards: 100%|██████████████████████| 1/1 [00:00<00:00, 6.44it/s]
4083
  /mnt/data/zainulabideen/zain-exp/notebooks/Activation/exp.py:402: UserWarning: std(): degrees of freedom is <= 0. Correction should be strictly less than the reduction factor (input numel divided by output numel). (Triggered internally at /pytorch/aten/src/ATen/native/ReduceOps.cpp:1831.)
4084
  "std": tensor.std().item(),
4085
- 71%|██████████████████████████▏ | 7064/10000 [20:32<07:06, 6.88it/s]
4086
  {'loss': '3.115', 'grad_norm': '0.7447', 'learning_rate': '0.0003', 'epoch': '0.4484', 'train/total_time_seconds': '692.5', 'train/time_per_step_avg': '0.09837', 'train/epoch_time_elapsed': '1224', 'train/estimated_remaining_minutes': '4.923', 'train/global/norm': '1.623e+05', 'train/global/mean': '-2.196', 'train/global/std': '0', 'train/global/max_abs': '26.97', 'train/global/frac_near_dtype_limit': '0', 'train/global/frac_near_user_limit': '0', 'train/layer__model_layers_2/norm': '51.47', 'train/layer__model_layers_2/mean': '0.0004086', 'train/layer__model_layers_2/std': '0.03447', 'train/layer__model_layers_2/max_abs': '1.076', 'train/layer__model_layers_2/frac_near_dtype_limit': '0', 'train/layer__model_layers_2/frac_near_user_limit': '0', 'train/layer__model_layers_4/norm': '54.06', 'train/layer__model_layers_4/mean': '0.0004333', 'train/layer__model_layers_4/std': '0.03621', 'train/layer__model_layers_4/max_abs': '1.139', 'train/layer__model_layers_4/frac_near_dtype_limit': '0', 'train/layer__model_layers_4/frac_near_user_limit': '0', 'train/layer_model_layers_3/norm': '9083', 'train/layer_model_layers_3/mean': '-0.007008', 'train/layer_model_layers_3/std': '0.8627', 'train/layer_model_layers_3/max_abs': '21.47', 'train/layer_model_layers_3/frac_near_dtype_limit': '0', 'train/layer_model_layers_3/frac_near_user_limit': '0', 'train/layer_model_layers_5/norm': '1.019e+04', 'train/layer_model_layers_5/mean': '-0.01245', 'train/layer_model_layers_5/std': '0.9674', 'train/layer_model_layers_5/max_abs': '25.78', 'train/layer_model_layers_5/frac_near_dtype_limit': '0', 'train/layer_model_layers_5/frac_near_user_limit': '0', 'train/layer_model_layers_0/norm': '8289', 'train/layer_model_layers_0/mean': '-0.01145', 'train/layer_model_layers_0/std': '0.7876', 'train/layer_model_layers_0/max_abs': '12.41', 'train/layer_model_layers_0/frac_near_dtype_limit': '0', 'train/layer_model_layers_0/frac_near_user_limit': '0', 'train/layer__model_layers_6/norm': '56.83', 'train/layer__model_layers_6/mean': '0.0004606', 'train/layer__model_layers_6/std': '0.03806', 'train/layer__model_layers_6/max_abs': '1.181', 'train/layer__model_layers_6/frac_near_dtype_limit': '0', 'train/layer__model_layers_6/frac_near_user_limit': '0', 'train/layer_model_layers_1/norm': '8333', 'train/layer_model_layers_1/mean': '-0.008844', 'train/layer_model_layers_1/std': '0.7917', 'train/layer_model_layers_1/max_abs': '16.37', 'train/layer_model_layers_1/frac_near_dtype_limit': '0', 'train/layer_model_layers_1/frac_near_user_limit': '0', 'train/layer__model_layers_1/norm': '49.7', 'train/layer__model_layers_1/mean': '0.0004351', 'train/layer__model_layers_1/std': '0.03328', 'train/layer__model_layers_1/max_abs': '1.022', 'train/layer__model_layers_1/frac_near_dtype_limit': '0', 'train/layer__model_layers_1/frac_near_user_limit': '0', 'train/layer_model_layers_7/norm': '1.149e+04', 'train/layer_model_layers_7/mean': '-0.00584', 'train/layer_model_layers_7/std': '1.091', 'train/layer_model_layers_7/max_abs': '26.97', 'train/layer_model_layers_7/frac_near_dtype_limit': '0', 'train/layer_model_layers_7/frac_near_user_limit': '0', 'train/layer__model_layers_0/norm': '52.14', 'train/layer__model_layers_0/mean': '0.0004665', 'train/layer__model_layers_0/std': '0.03492', 'train/layer__model_layers_0/max_abs': '1.089', 'train/layer__model_layers_0/frac_near_dtype_limit': '0', 'train/layer__model_layers_0/frac_near_user_limit': '0', 'train/layer_model_layers_2/norm': '8662', 'train/layer_model_layers_2/mean': '-0.001211', 'train/layer_model_layers_2/std': '0.8222', 'train/layer_model_layers_2/max_abs': '18.74', 'train/layer_model_layers_2/frac_near_dtype_limit': '0', 'train/layer_model_layers_2/frac_near_user_limit': '0', 'train/layer_model_layers_4/norm': '9865', 'train/layer_model_layers_4/mean': '-0.002752', 'train/layer_model_layers_4/std': '0.9373', 'train/layer_model_layers_4/max_abs': '25.06', 'train/layer_model_layers_4/frac_near_dtype_limit': '0', 'train/layer_model_layers_4/frac_near_user_limit': '0', 'train/layer__model_layers_5/norm': '56.36', 'train/layer__
4087
  {'loss': '3.13', 'grad_norm': '0.7995', 'learning_rate': '0.0003', 'epoch': '0.4491', 'train/total_time_seconds': '693.5', 'train/time_per_step_avg': '0.09833', 'train/epoch_time_elapsed': '1226', 'train/estimated_remaining_minutes': '4.907'}
4088
  {'loss': '3.104', 'grad_norm': '0.7444', 'learning_rate': '0.0003', 'epoch': '0.4497', 'train/total_time_seconds': '694.5', 'train/time_per_step_avg': '0.09843', 'train/epoch_time_elapsed': '1227', 'train/estimated_remaining_minutes': '4.89'}
4089
  {'loss': '3.142', 'grad_norm': '0.7233', 'learning_rate': '0.0003', 'epoch': '0.4504', 'train/total_time_seconds': '695.5', 'train/time_per_step_avg': '0.09858', 'train/epoch_time_elapsed': '1229', 'train/estimated_remaining_minutes': '4.874'}
4090
  {'loss': '3.093', 'grad_norm': '0.7554', 'learning_rate': '0.0003', 'epoch': '0.451', 'train/total_time_seconds': '696.5', 'train/time_per_step_avg': '0.09862', 'train/epoch_time_elapsed': '1230', 'train/estimated_remaining_minutes': '4.857'}
4091
  {'loss': '3.11', 'grad_norm': '0.765', 'learning_rate': '0.0003', 'epoch': '0.4516', 'train/total_time_seconds': '697.4', 'train/time_per_step_avg': '0.09867', 'train/epoch_time_elapsed': '1232', 'train/estimated_remaining_minutes': '4.84'}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4082
  Writing model shards: 100%|██████████████████████| 1/1 [00:00<00:00, 6.44it/s]
4083
  /mnt/data/zainulabideen/zain-exp/notebooks/Activation/exp.py:402: UserWarning: std(): degrees of freedom is <= 0. Correction should be strictly less than the reduction factor (input numel divided by output numel). (Triggered internally at /pytorch/aten/src/ATen/native/ReduceOps.cpp:1831.)
4084
  "std": tensor.std().item(),
4085
+
4086
  {'loss': '3.115', 'grad_norm': '0.7447', 'learning_rate': '0.0003', 'epoch': '0.4484', 'train/total_time_seconds': '692.5', 'train/time_per_step_avg': '0.09837', 'train/epoch_time_elapsed': '1224', 'train/estimated_remaining_minutes': '4.923', 'train/global/norm': '1.623e+05', 'train/global/mean': '-2.196', 'train/global/std': '0', 'train/global/max_abs': '26.97', 'train/global/frac_near_dtype_limit': '0', 'train/global/frac_near_user_limit': '0', 'train/layer__model_layers_2/norm': '51.47', 'train/layer__model_layers_2/mean': '0.0004086', 'train/layer__model_layers_2/std': '0.03447', 'train/layer__model_layers_2/max_abs': '1.076', 'train/layer__model_layers_2/frac_near_dtype_limit': '0', 'train/layer__model_layers_2/frac_near_user_limit': '0', 'train/layer__model_layers_4/norm': '54.06', 'train/layer__model_layers_4/mean': '0.0004333', 'train/layer__model_layers_4/std': '0.03621', 'train/layer__model_layers_4/max_abs': '1.139', 'train/layer__model_layers_4/frac_near_dtype_limit': '0', 'train/layer__model_layers_4/frac_near_user_limit': '0', 'train/layer_model_layers_3/norm': '9083', 'train/layer_model_layers_3/mean': '-0.007008', 'train/layer_model_layers_3/std': '0.8627', 'train/layer_model_layers_3/max_abs': '21.47', 'train/layer_model_layers_3/frac_near_dtype_limit': '0', 'train/layer_model_layers_3/frac_near_user_limit': '0', 'train/layer_model_layers_5/norm': '1.019e+04', 'train/layer_model_layers_5/mean': '-0.01245', 'train/layer_model_layers_5/std': '0.9674', 'train/layer_model_layers_5/max_abs': '25.78', 'train/layer_model_layers_5/frac_near_dtype_limit': '0', 'train/layer_model_layers_5/frac_near_user_limit': '0', 'train/layer_model_layers_0/norm': '8289', 'train/layer_model_layers_0/mean': '-0.01145', 'train/layer_model_layers_0/std': '0.7876', 'train/layer_model_layers_0/max_abs': '12.41', 'train/layer_model_layers_0/frac_near_dtype_limit': '0', 'train/layer_model_layers_0/frac_near_user_limit': '0', 'train/layer__model_layers_6/norm': '56.83', 'train/layer__model_layers_6/mean': '0.0004606', 'train/layer__model_layers_6/std': '0.03806', 'train/layer__model_layers_6/max_abs': '1.181', 'train/layer__model_layers_6/frac_near_dtype_limit': '0', 'train/layer__model_layers_6/frac_near_user_limit': '0', 'train/layer_model_layers_1/norm': '8333', 'train/layer_model_layers_1/mean': '-0.008844', 'train/layer_model_layers_1/std': '0.7917', 'train/layer_model_layers_1/max_abs': '16.37', 'train/layer_model_layers_1/frac_near_dtype_limit': '0', 'train/layer_model_layers_1/frac_near_user_limit': '0', 'train/layer__model_layers_1/norm': '49.7', 'train/layer__model_layers_1/mean': '0.0004351', 'train/layer__model_layers_1/std': '0.03328', 'train/layer__model_layers_1/max_abs': '1.022', 'train/layer__model_layers_1/frac_near_dtype_limit': '0', 'train/layer__model_layers_1/frac_near_user_limit': '0', 'train/layer_model_layers_7/norm': '1.149e+04', 'train/layer_model_layers_7/mean': '-0.00584', 'train/layer_model_layers_7/std': '1.091', 'train/layer_model_layers_7/max_abs': '26.97', 'train/layer_model_layers_7/frac_near_dtype_limit': '0', 'train/layer_model_layers_7/frac_near_user_limit': '0', 'train/layer__model_layers_0/norm': '52.14', 'train/layer__model_layers_0/mean': '0.0004665', 'train/layer__model_layers_0/std': '0.03492', 'train/layer__model_layers_0/max_abs': '1.089', 'train/layer__model_layers_0/frac_near_dtype_limit': '0', 'train/layer__model_layers_0/frac_near_user_limit': '0', 'train/layer_model_layers_2/norm': '8662', 'train/layer_model_layers_2/mean': '-0.001211', 'train/layer_model_layers_2/std': '0.8222', 'train/layer_model_layers_2/max_abs': '18.74', 'train/layer_model_layers_2/frac_near_dtype_limit': '0', 'train/layer_model_layers_2/frac_near_user_limit': '0', 'train/layer_model_layers_4/norm': '9865', 'train/layer_model_layers_4/mean': '-0.002752', 'train/layer_model_layers_4/std': '0.9373', 'train/layer_model_layers_4/max_abs': '25.06', 'train/layer_model_layers_4/frac_near_dtype_limit': '0', 'train/layer_model_layers_4/frac_near_user_limit': '0', 'train/layer__model_layers_5/norm': '56.36', 'train/layer__
4087
  {'loss': '3.13', 'grad_norm': '0.7995', 'learning_rate': '0.0003', 'epoch': '0.4491', 'train/total_time_seconds': '693.5', 'train/time_per_step_avg': '0.09833', 'train/epoch_time_elapsed': '1226', 'train/estimated_remaining_minutes': '4.907'}
4088
  {'loss': '3.104', 'grad_norm': '0.7444', 'learning_rate': '0.0003', 'epoch': '0.4497', 'train/total_time_seconds': '694.5', 'train/time_per_step_avg': '0.09843', 'train/epoch_time_elapsed': '1227', 'train/estimated_remaining_minutes': '4.89'}
4089
  {'loss': '3.142', 'grad_norm': '0.7233', 'learning_rate': '0.0003', 'epoch': '0.4504', 'train/total_time_seconds': '695.5', 'train/time_per_step_avg': '0.09858', 'train/epoch_time_elapsed': '1229', 'train/estimated_remaining_minutes': '4.874'}
4090
  {'loss': '3.093', 'grad_norm': '0.7554', 'learning_rate': '0.0003', 'epoch': '0.451', 'train/total_time_seconds': '696.5', 'train/time_per_step_avg': '0.09862', 'train/epoch_time_elapsed': '1230', 'train/estimated_remaining_minutes': '4.857'}
4091
  {'loss': '3.11', 'grad_norm': '0.765', 'learning_rate': '0.0003', 'epoch': '0.4516', 'train/total_time_seconds': '697.4', 'train/time_per_step_avg': '0.09867', 'train/epoch_time_elapsed': '1232', 'train/estimated_remaining_minutes': '4.84'}
4092
+ {'loss': '3.079', 'grad_norm': '0.7695', 'learning_rate': '0.0003', 'epoch': '0.4523', 'train/total_time_seconds': '698.4', 'train/time_per_step_avg': '0.0987', 'train/epoch_time_elapsed': '1233', 'train/estimated_remaining_minutes': '4.824'}
4093
+ {'loss': '3.132', 'grad_norm': '0.7945', 'learning_rate': '0.0003', 'epoch': '0.4529', 'train/total_time_seconds': '699.4', 'train/time_per_step_avg': '0.09872', 'train/epoch_time_elapsed': '1235', 'train/estimated_remaining_minutes': '4.807'}
4094
+ {'loss': '3.114', 'grad_norm': '0.7773', 'learning_rate': '0.0003', 'epoch': '0.4536', 'train/total_time_seconds': '700.3', 'train/time_per_step_avg': '0.09874', 'train/epoch_time_elapsed': '1236', 'train/estimated_remaining_minutes': '4.791'}
4095
+ {'loss': '3.096', 'grad_norm': '0.7609', 'learning_rate': '0.0003', 'epoch': '0.4542', 'train/total_time_seconds': '701.3', 'train/time_per_step_avg': '0.09867', 'train/epoch_time_elapsed': '1238', 'train/estimated_remaining_minutes': '4.774'}
4096
+ {'loss': '3.141', 'grad_norm': '0.7433', 'learning_rate': '0.0003', 'epoch': '0.4548', 'train/total_time_seconds': '702.3', 'train/time_per_step_avg': '0.09756', 'train/epoch_time_elapsed': '1239', 'train/estimated_remaining_minutes': '4.758'}
4097
+ {'loss': '3.132', 'grad_norm': '0.7955', 'learning_rate': '0.0003', 'epoch': '0.4555', 'train/total_time_seconds': '703.3', 'train/time_per_step_avg': '0.09761', 'train/epoch_time_elapsed': '1240', 'train/estimated_remaining_minutes': '4.741'}
4098
+ {'loss': '3.154', 'grad_norm': '0.8101', 'learning_rate': '0.0003', 'epoch': '0.4561', 'train/total_time_seconds': '704.2', 'train/time_per_step_avg': '0.09751', 'train/epoch_time_elapsed': '1242', 'train/estimated_remaining_minutes': '4.725'}
4099
+ {'loss': '3.104', 'grad_norm': '0.7462', 'learning_rate': '0.0003', 'epoch': '0.4568', 'train/total_time_seconds': '705.2', 'train/time_per_step_avg': '0.09742', 'train/epoch_time_elapsed': '1243', 'train/estimated_remaining_minutes': '4.708'}
4100
+ {'loss': '3.096', 'grad_norm': '0.7493', 'learning_rate': '0.0003', 'epoch': '0.4574', 'train/total_time_seconds': '706.2', 'train/time_per_step_avg': '0.0974', 'train/epoch_time_elapsed': '1245', 'train/estimated_remaining_minutes': '4.691'}
4101
+ {'loss': '3.095', 'grad_norm': '0.7567', 'learning_rate': '0.0003', 'epoch': '0.458', 'train/total_time_seconds': '707.2', 'train/time_per_step_avg': '0.09751', 'train/epoch_time_elapsed': '1246', 'train/estimated_remaining_minutes': '4.675'}
4102
+ {'loss': '3.129', 'grad_norm': '0.7841', 'learning_rate': '0.0003', 'epoch': '0.4587', 'train/total_time_seconds': '708.2', 'train/time_per_step_avg': '0.09751', 'train/epoch_time_elapsed': '1248', 'train/estimated_remaining_minutes': '4.658'}
4103
+ {'loss': '3.149', 'grad_norm': '0.7611', 'learning_rate': '0.0003', 'epoch': '0.4593', 'train/total_time_seconds': '709.1', 'train/time_per_step_avg': '0.09759', 'train/epoch_time_elapsed': '1249', 'train/estimated_remaining_minutes': '4.642'}
4104
+ {'loss': '3.138', 'grad_norm': '0.7454', 'learning_rate': '0.0003', 'epoch': '0.46', 'train/total_time_seconds': '710.1', 'train/time_per_step_avg': '0.0976', 'train/epoch_time_elapsed': '1251', 'train/estimated_remaining_minutes': '4.625'}
4105
+ {'loss': '3.08', 'grad_norm': '0.7387', 'learning_rate': '0.0003', 'epoch': '0.4606', 'train/total_time_seconds': '711.1', 'train/time_per_step_avg': '0.09774', 'train/epoch_time_elapsed': '1252', 'train/estimated_remaining_minutes': '4.609'}
4106
+ {'loss': '3.139', 'grad_norm': '0.7731', 'learning_rate': '0.0003', 'epoch': '0.4612', 'train/total_time_seconds': '712.2', 'train/time_per_step_avg': '0.09902', 'train/epoch_time_elapsed': '1254', 'train/estimated_remaining_minutes': '4.593', 'train/global/norm': '1.642e+05', 'train/global/mean': '-2.228', 'train/global/std': '0', 'train/global/max_abs': '28.63', 'train/global/frac_near_dtype_limit': '0', 'train/global/frac_near_user_limit': '0', 'train/layer__model_layers_2/norm': '51.69', 'train/layer__model_layers_2/mean': '0.0004112', 'train/layer__model_layers_2/std': '0.03462', 'train/layer__model_layers_2/max_abs': '1.077', 'train/layer__model_layers_2/frac_near_dtype_limit': '0', 'train/layer__model_layers_2/frac_near_user_limit': '0', 'train/layer__model_layers_4/norm': '54.29', 'train/layer__model_layers_4/mean': '0.0004317', 'train/layer__model_layers_4/std': '0.03636', 'train/layer__model_layers_4/max_abs': '1.142', 'train/layer__model_layers_4/frac_near_dtype_limit': '0', 'train/layer__model_layers_4/frac_near_user_limit': '0', 'train/layer_model_layers_3/norm': '9109', 'train/layer_model_layers_3/mean': '-0.007245', 'train/layer_model_layers_3/std': '0.8659', 'train/layer_model_layers_3/max_abs': '21.93', 'train/layer_model_layers_3/frac_near_dtype_limit': '0', 'train/layer_model_layers_3/frac_near_user_limit': '0', 'train/layer_model_layers_5/norm': '1.019e+04', 'train/layer_model_layers_5/mean': '-0.009899', 'train/layer_model_layers_5/std': '0.9683', 'train/layer_model_layers_5/max_abs': '26.88', 'train/layer_model_layers_5/frac_near_dtype_limit': '0', 'train/layer_model_layers_5/frac_near_user_limit': '0', 'train/layer_model_layers_0/norm': '8315', 'train/layer_model_layers_0/mean': '-0.009449', 'train/layer_model_layers_0/std': '0.7899', 'train/layer_model_layers_0/max_abs': '12.2', 'train/layer_model_layers_0/frac_near_dtype_limit': '0', 'train/layer_model_layers_0/frac_near_user_limit': '0', 'train/layer__model_layers_6/norm': '57.08', 'train/layer__model_layers_6/mean': '0.0004614', 'train/layer__model_layers_6/std': '0.03823', 'train/layer__model_layers_6/max_abs': '1.182', 'train/layer__model_layers_6/frac_near_dtype_limit': '0', 'train/layer__model_layers_6/frac_near_user_limit': '0', 'train/layer_model_layers_1/norm': '8329', 'train/layer_model_layers_1/mean': '-0.008077', 'train/layer_model_layers_1/std': '0.7903', 'train/layer_model_layers_1/max_abs': '16.76', 'train/layer_model_layers_1/frac_near_dtype_limit': '0', 'train/layer_model_layers_1/frac_near_user_limit': '0', 'train/layer__model_layers_1/norm': '49.88', 'train/layer__model_layers_1/mean': '0.0004326', 'train/layer__model_layers_1/std': '0.0334', 'train/layer__model_layers_1/max_abs': '1.022', 'train/layer__model_layers_1/frac_near_dtype_limit': '0', 'train/layer__model_layers_1/frac_near_user_limit': '0', 'train/layer_model_layers_7/norm': '1.151e+04', 'train/layer_model_layers_7/mean': '-0.002651', 'train/layer_model_layers_7/std': '1.094', 'train/layer_model_layers_7/max_abs': '28.63', 'train/layer_model_layers_7/frac_near_dtype_limit': '0', 'train/layer_model_layers_7/frac_near_user_limit': '0', 'train/layer__model_layers_0/norm': '52.32', 'train/layer__model_layers_0/mean': '0.0004639', 'train/layer__model_layers_0/std': '0.03504', 'train/layer__model_layers_0/max_abs': '1.089', 'train/layer__model_layers_0/frac_near_dtype_limit': '0', 'train/layer__model_layers_0/frac_near_user_limit': '0', 'train/layer_model_layers_2/norm': '8667', 'train/layer_model_layers_2/mean': '-0.002043', 'train/layer_model_layers_2/std': '0.8234', 'train/layer_model_layers_2/max_abs': '19.47', 'train/layer_model_layers_2/frac_near_dtype_limit': '0', 'train/layer_model_layers_2/frac_near_user_limit': '0', 'train/layer_model_layers_4/norm': '9912', 'train/layer_model_layers_4/mean': '-0.002628', 'train/layer_model_layers_4/std': '0.9416', 'train/layer_model_layers_4/max_abs': '26.03', 'train/layer_model_layers_4/frac_near_dtype_limit': '0', 'train/layer_model_layers_4/frac_near_user_limit': '0', 'train/layer__model_layers_5/norm': '56.6', 'train/layer_
4107
+ {'loss': '3.076', 'grad_norm': '0.7587', 'learning_rate': '0.0003', 'epoch': '0.4619', 'train/total_time_seconds': '713.2', 'train/time_per_step_avg': '0.09907', 'train/epoch_time_elapsed': '1255', 'train/estimated_remaining_minutes': '4.577'}
4108
+ {'loss': '3.174', 'grad_norm': '0.7648', 'learning_rate': '0.0003', 'epoch': '0.4625', 'train/total_time_seconds': '714.1', 'train/time_per_step_avg': '0.09908', 'train/epoch_time_elapsed': '1257', 'train/estimated_remaining_minutes': '4.56'}
4109
+ {'loss': '3.153', 'grad_norm': '0.7649', 'learning_rate': '0.0003', 'epoch': '0.4632', 'train/total_time_seconds': '715.1', 'train/time_per_step_avg': '0.0991', 'train/epoch_time_elapsed': '1258', 'train/estimated_remaining_minutes': '4.544'}
4110
+ {'loss': '3.104', 'grad_norm': '0.7418', 'learning_rate': '0.0003', 'epoch': '0.4638', 'train/total_time_seconds': '716.1', 'train/time_per_step_avg': '0.09913', 'train/epoch_time_elapsed': '1260', 'train/estimated_remaining_minutes': '4.527'}
4111
+ {'loss': '3.1', 'grad_norm': '0.7541', 'learning_rate': '0.0003', 'epoch': '0.4644', 'train/total_time_seconds': '717.1', 'train/time_per_step_avg': '0.09897', 'train/epoch_time_elapsed': '1261', 'train/estimated_remaining_minutes': '4.511'}
4112
+ {'loss': '3.104', 'grad_norm': '0.7655', 'learning_rate': '0.0003', 'epoch': '0.4651', 'train/total_time_seconds': '718', 'train/time_per_step_avg': '0.09894', 'train/epoch_time_elapsed': '1262', 'train/estimated_remaining_minutes': '4.494'}
4113
+ {'loss': '3.096', 'grad_norm': '0.7935', 'learning_rate': '0.0003', 'epoch': '0.4657', 'train/total_time_seconds': '719', 'train/time_per_step_avg': '0.09891', 'train/epoch_time_elapsed': '1264', 'train/estimated_remaining_minutes': '4.477'}
4114
+ {'loss': '3.082', 'grad_norm': '0.7655', 'learning_rate': '0.0003', 'epoch': '0.4664', 'train/total_time_seconds': '720', 'train/time_per_step_avg': '0.09886', 'train/epoch_time_elapsed': '1265', 'train/estimated_remaining_minutes': '4.461'}
4115
+ {'loss': '3.115', 'grad_norm': '0.7568', 'learning_rate': '0.0003', 'epoch': '0.467', 'train/total_time_seconds': '721', 'train/time_per_step_avg': '0.09876', 'train/epoch_time_elapsed': '1267', 'train/estimated_remaining_minutes': '4.444'}
4116
+ {'loss': '3.124', 'grad_norm': '0.7544', 'learning_rate': '0.0003', 'epoch': '0.4676', 'train/total_time_seconds': '721.9', 'train/time_per_step_avg': '0.09746', 'train/epoch_time_elapsed': '1268', 'train/estimated_remaining_minutes': '4.428'}
4117
+ {'loss': '3.081', 'grad_norm': '0.7994', 'learning_rate': '0.0003', 'epoch': '0.4683', 'train/total_time_seconds': '722.9', 'train/time_per_step_avg': '0.09743', 'train/epoch_time_elapsed': '1270', 'train/estimated_remaining_minutes': '4.411'}
4118
+ {'loss': '3.126', 'grad_norm': '0.7796', 'learning_rate': '0.0003', 'epoch': '0.4689', 'train/total_time_seconds': '723.9', 'train/time_per_step_avg': '0.09741', 'train/epoch_time_elapsed': '1271', 'train/estimated_remaining_minutes': '4.395'}
4119
+ {'loss': '3.099', 'grad_norm': '0.7961', 'learning_rate': '0.0003', 'epoch': '0.4695', 'train/total_time_seconds': '724.9', 'train/time_per_step_avg': '0.0974', 'train/epoch_time_elapsed': '1273', 'train/estimated_remaining_minutes': '4.378'}
4120
+ {'loss': '3.101', 'grad_norm': '0.7498', 'learning_rate': '0.0003', 'epoch': '0.4702', 'train/total_time_seconds': '725.8', 'train/time_per_step_avg': '0.09734', 'train/epoch_time_elapsed': '1274', 'train/estimated_remaining_minutes': '4.362'}
4121
+ {'loss': '3.052', 'grad_norm': '0.7455', 'learning_rate': '0.0003', 'epoch': '0.4708', 'train/total_time_seconds': '726.8', 'train/time_per_step_avg': '0.09734', 'train/epoch_time_elapsed': '1276', 'train/estimated_remaining_minutes': '4.345'}
4122
+ {'loss': '3.136', 'grad_norm': '0.7458', 'learning_rate': '0.0003', 'epoch': '0.4715', 'train/total_time_seconds': '727.8', 'train/time_per_step_avg': '0.09742', 'train/epoch_time_elapsed': '1277', 'train/estimated_remaining_minutes': '4.329'}
4123
+ {'loss': '3.138', 'grad_norm': '0.8134', 'learning_rate': '0.0003', 'epoch': '0.4721', 'train/total_time_seconds': '728.8', 'train/time_per_step_avg': '0.0974', 'train/epoch_time_elapsed': '1278', 'train/estimated_remaining_minutes': '4.312'}
4124
+ {'loss': '3.05', 'grad_norm': '0.7532', 'learning_rate': '0.0003', 'epoch': '0.4727', 'train/total_time_seconds': '729.7', 'train/time_per_step_avg': '0.09745', 'train/epoch_time_elapsed': '1280', 'train/estimated_remaining_minutes': '4.295'}
4125
+ {'loss': '3.109', 'grad_norm': '0.8121', 'learning_rate': '0.0003', 'epoch': '0.4734', 'train/total_time_seconds': '730.7', 'train/time_per_step_avg': '0.0975', 'train/epoch_time_elapsed': '1281', 'train/estimated_remaining_minutes': '4.279'}
4126
+ {'loss': '3.091', 'grad_norm': '0.7669', 'learning_rate': '0.0003', 'epoch': '0.474', 'train/total_time_seconds': '731.8', 'train/time_per_step_avg': '0.09886', 'train/epoch_time_elapsed': '1283', 'train/estimated_remaining_minutes': '4.263', 'train/global/norm': '1.692e+05', 'train/global/mean': '-2.293', 'train/global/std': '0', 'train/global/max_abs': '28.28', 'train/global/frac_near_dtype_limit': '0', 'train/global/frac_near_user_limit': '0', 'train/layer__model_layers_2/norm': '51.91', 'train/layer__model_layers_2/mean': '0.000411', 'train/layer__model_layers_2/std': '0.03477', 'train/layer__model_layers_2/max_abs': '1.074', 'train/layer__model_layers_2/frac_near_dtype_limit': '0', 'train/layer__model_layers_2/frac_near_user_limit': '0', 'train/layer__model_layers_4/norm': '54.52', 'train/layer__model_layers_4/mean': '0.0004321', 'train/layer__model_layers_4/std': '0.03651', 'train/layer__model_layers_4/max_abs': '1.141', 'train/layer__model_layers_4/frac_near_dtype_limit': '0', 'train/layer__model_layers_4/frac_near_user_limit': '0', 'train/layer_model_layers_3/norm': '9170', 'train/layer_model_layers_3/mean': '-0.005143', 'train/layer_model_layers_3/std': '0.8703', 'train/layer_model_layers_3/max_abs': '22.97', 'train/layer_model_layers_3/frac_near_dtype_limit': '0', 'train/layer_model_layers_3/frac_near_user_limit': '0', 'train/layer_model_layers_5/norm': '1.029e+04', 'train/layer_model_layers_5/mean': '-0.009372', 'train/layer_model_layers_5/std': '0.9771', 'train/layer_model_layers_5/max_abs': '28.28', 'train/layer_model_layers_5/frac_near_dtype_limit': '0', 'train/layer_model_layers_5/frac_near_user_limit': '0', 'train/layer_model_layers_0/norm': '8363', 'train/layer_model_layers_0/mean': '-0.009826', 'train/layer_model_layers_0/std': '0.7941', 'train/layer_model_layers_0/max_abs': '12.9', 'train/layer_model_layers_0/frac_near_dtype_limit': '0', 'train/layer_model_layers_0/frac_near_user_limit': '0', 'train/layer__model_layers_6/norm': '57.33', 'train/layer__model_layers_6/mean': '0.0004607', 'train/layer__model_layers_6/std': '0.03839', 'train/layer__model_layers_6/max_abs': '1.185', 'train/layer__model_layers_6/frac_near_dtype_limit': '0', 'train/layer__model_layers_6/frac_near_user_limit': '0', 'train/layer_model_layers_1/norm': '8398', 'train/layer_model_layers_1/mean': '-0.007074', 'train/layer_model_layers_1/std': '0.7973', 'train/layer_model_layers_1/max_abs': '17.37', 'train/layer_model_layers_1/frac_near_dtype_limit': '0', 'train/layer_model_layers_1/frac_near_user_limit': '0', 'train/layer__model_layers_1/norm': '50.08', 'train/layer__model_layers_1/mean': '0.0004336', 'train/layer__model_layers_1/std': '0.03354', 'train/layer__model_layers_1/max_abs': '1.026', 'train/layer__model_layers_1/frac_near_dtype_limit': '0', 'train/layer__model_layers_1/frac_near_user_limit': '0', 'train/layer_model_layers_7/norm': '1.174e+04', 'train/layer_model_layers_7/mean': '-0.003151', 'train/layer_model_layers_7/std': '1.114', 'train/layer_model_layers_7/max_abs': '25.98', 'train/layer_model_layers_7/frac_near_dtype_limit': '0', 'train/layer_model_layers_7/frac_near_user_limit': '0', 'train/layer__model_layers_0/norm': '52.5', 'train/layer__model_layers_0/mean': '0.0004636', 'train/layer__model_layers_0/std': '0.03516', 'train/layer__model_layers_0/max_abs': '1.091', 'train/layer__model_layers_0/frac_near_dtype_limit': '0', 'train/layer__model_layers_0/frac_near_user_limit': '0', 'train/layer_model_layers_2/norm': '8730', 'train/layer_model_layers_2/mean': '-0.0002001', 'train/layer_model_layers_2/std': '0.8287', 'train/layer_model_layers_2/max_abs': '20.68', 'train/layer_model_layers_2/frac_near_dtype_limit': '0', 'train/layer_model_layers_2/frac_near_user_limit': '0', 'train/layer_model_layers_4/norm': '1e+04', 'train/layer_model_layers_4/mean': '0.0008348', 'train/layer_model_layers_4/std': '0.9493', 'train/layer_model_layers_4/max_abs': '27.51', 'train/layer_model_layers_4/frac_near_dtype_limit': '0', 'train/layer_model_layers_4/frac_near_user_limit': '0', 'train/layer__model_layers_5/norm': '56.85', 'train/layer
4127
+ {'loss': '3.103', 'grad_norm': '0.7571', 'learning_rate': '0.0003', 'epoch': '0.4747', 'train/total_time_seconds': '732.8', 'train/time_per_step_avg': '0.09885', 'train/epoch_time_elapsed': '1284', 'train/estimated_remaining_minutes': '4.247'}
4128
+ {'loss': '3.091', 'grad_norm': '0.7185', 'learning_rate': '0.0003', 'epoch': '0.4753', 'train/total_time_seconds': '733.8', 'train/time_per_step_avg': '0.09889', 'train/epoch_time_elapsed': '1286', 'train/estimated_remaining_minutes': '4.23'}
4129
+ {'loss': '3.101', 'grad_norm': '0.7646', 'learning_rate': '0.0003', 'epoch': '0.4759', 'train/total_time_seconds': '734.8', 'train/time_per_step_avg': '0.09889', 'train/epoch_time_elapsed': '1287', 'train/estimated_remaining_minutes': '4.214'}
4130
+ {'loss': '3.138', 'grad_norm': '0.7322', 'learning_rate': '0.0003', 'epoch': '0.4766', 'train/total_time_seconds': '735.7', 'train/time_per_step_avg': '0.09889', 'train/epoch_time_elapsed': '1289', 'train/estimated_remaining_minutes': '4.197'}
4131
+ {'loss': '3.145', 'grad_norm': '0.7509', 'learning_rate': '0.0003', 'epoch': '0.4772', 'train/total_time_seconds': '736.7', 'train/time_per_step_avg': '0.09889', 'train/epoch_time_elapsed': '1290', 'train/estimated_remaining_minutes': '4.181'}
4132
+ {'loss': '3.094', 'grad_norm': '0.7164', 'learning_rate': '0.0003', 'epoch': '0.4779', 'train/total_time_seconds': '737.7', 'train/time_per_step_avg': '0.0988', 'train/epoch_time_elapsed': '1292', 'train/estimated_remaining_minutes': '4.164'}
4133
+ {'loss': '3.068', 'grad_norm': '0.716', 'learning_rate': '0.0003', 'epoch': '0.4785', 'train/total_time_seconds': '738.6', 'train/time_per_step_avg': '0.09879', 'train/epoch_time_elapsed': '1293', 'train/estimated_remaining_minutes': '4.147'}
4134
+ {'loss': '3.122', 'grad_norm': '0.7315', 'learning_rate': '0.0003', 'epoch': '0.4791', 'train/total_time_seconds': '739.6', 'train/time_per_step_avg': '0.09875', 'train/epoch_time_elapsed': '1295', 'train/estimated_remaining_minutes': '4.131'}
4135
+ {'loss': '3.053', 'grad_norm': '0.7249', 'learning_rate': '0.0003', 'epoch': '0.4798', 'train/total_time_seconds': '740.6', 'train/time_per_step_avg': '0.09866', 'train/epoch_time_elapsed': '1296', 'train/estimated_remaining_minutes': '4.114'}
4136
+
4137
+ {'eval_loss': '1.554', 'eval_runtime': '13.15', 'eval_samples_per_second': '765', 'eval_steps_per_second': '23.95', 'epoch': '0.4798', 'train/total_time_seconds': '740.6', 'train/time_per_step_avg': '0.09866', 'train/epoch_time_elapsed': '1309', 'train/estimated_remaining_minutes': '4.114'}
4138
+ {'loss': '3.149', 'grad_norm': '0.7944', 'learning_rate': '0.0003', 'epoch': '0.4804', 'train/total_time_seconds': '741.6', 'train/time_per_step_avg': '0.09731', 'train/epoch_time_elapsed': '1311', 'train/estimated_remaining_minutes': '4.098'}
4139
+ {'loss': '3.088', 'grad_norm': '0.7482', 'learning_rate': '0.0003', 'epoch': '0.4811', 'train/total_time_seconds': '742.5', 'train/time_per_step_avg': '0.09735', 'train/epoch_time_elapsed': '1312', 'train/estimated_remaining_minutes': '4.081'}
4140
+ {'loss': '3.086', 'grad_norm': '0.7347', 'learning_rate': '0.0003', 'epoch': '0.4817', 'train/total_time_seconds': '743.5', 'train/time_per_step_avg': '0.09747', 'train/epoch_time_elapsed': '1314', 'train/estimated_remaining_minutes': '4.065'}
4141
+ {'loss': '3.114', 'grad_norm': '0.7275', 'learning_rate': '0.0003', 'epoch': '0.4823', 'train/total_time_seconds': '744.5', 'train/time_per_step_avg': '0.09748', 'train/epoch_time_elapsed': '1315', 'train/estimated_remaining_minutes': '4.048'}
4142
+ {'loss': '3.078', 'grad_norm': '0.7493', 'learning_rate': '0.0003', 'epoch': '0.483', 'train/total_time_seconds': '745.5', 'train/time_per_step_avg': '0.0975', 'train/epoch_time_elapsed': '1316', 'train/estimated_remaining_minutes': '4.032'}
4143
+ {'loss': '3.068', 'grad_norm': '0.764', 'learning_rate': '0.0003', 'epoch': '0.4836', 'train/total_time_seconds': '746.5', 'train/time_per_step_avg': '0.09757', 'train/epoch_time_elapsed': '1318', 'train/estimated_remaining_minutes': '4.015'}
4144
+ {'loss': '3.071', 'grad_norm': '0.7425', 'learning_rate': '0.0003', 'epoch': '0.4843', 'train/total_time_seconds': '747.4', 'train/time_per_step_avg': '0.09764', 'train/epoch_time_elapsed': '1319', 'train/estimated_remaining_minutes': '3.999'}
4145
+ {'loss': '3.082', 'grad_norm': '0.7545', 'learning_rate': '0.0003', 'epoch': '0.4849', 'train/total_time_seconds': '748.4', 'train/time_per_step_avg': '0.09765', 'train/epoch_time_elapsed': '1321', 'train/estimated_remaining_minutes': '3.982'}
4146
+ {'loss': '3.117', 'grad_norm': '0.7715', 'learning_rate': '0.0003', 'epoch': '0.4855', 'train/total_time_seconds': '749.4', 'train/time_per_step_avg': '0.09767', 'train/epoch_time_elapsed': '1322', 'train/estimated_remaining_minutes': '3.966'}
4147
+ {'loss': '3.139', 'grad_norm': '0.7636', 'learning_rate': '0.0003', 'epoch': '0.4862', 'train/total_time_seconds': '750.4', 'train/time_per_step_avg': '0.09772', 'train/epoch_time_elapsed': '1324', 'train/estimated_remaining_minutes': '3.949'}
4148
+ {'loss': '3.08', 'grad_norm': '0.7683', 'learning_rate': '0.0003', 'epoch': '0.4868', 'train/total_time_seconds': '751.5', 'train/time_per_step_avg': '0.099', 'train/epoch_time_elapsed': '1325', 'train/estimated_remaining_minutes': '3.933', 'train/global/norm': '1.668e+05', 'train/global/mean': '-2.261', 'train/global/std': '0', 'train/global/max_abs': '28.11', 'train/global/frac_near_dtype_limit': '0', 'train/global/frac_near_user_limit': '0', 'train/layer__model_layers_2/norm': '52.12', 'train/layer__model_layers_2/mean': '0.0004091', 'train/layer__model_layers_2/std': '0.03491', 'train/layer__model_layers_2/max_abs': '1.078', 'train/layer__model_layers_2/frac_near_dtype_limit': '0', 'train/layer__model_layers_2/frac_near_user_limit': '0', 'train/layer__model_layers_4/norm': '54.74', 'train/layer__model_layers_4/mean': '0.0004342', 'train/layer__model_layers_4/std': '0.03666', 'train/layer__model_layers_4/max_abs': '1.142', 'train/layer__model_layers_4/frac_near_dtype_limit': '0', 'train/layer__model_layers_4/frac_near_user_limit': '0', 'train/layer_model_layers_3/norm': '9231', 'train/layer_model_layers_3/mean': '-0.007359', 'train/layer_model_layers_3/std': '0.8768', 'train/layer_model_layers_3/max_abs': '23.14', 'train/layer_model_layers_3/frac_near_dtype_limit': '0', 'train/layer_model_layers_3/frac_near_user_limit': '0', 'train/layer_model_layers_5/norm': '1.035e+04', 'train/layer_model_layers_5/mean': '-0.01111', 'train/layer_model_layers_5/std': '0.9831', 'train/layer_model_layers_5/max_abs': '26.58', 'train/layer_model_layers_5/frac_near_dtype_limit': '0', 'train/layer_model_layers_5/frac_near_user_limit': '0', 'train/layer_model_layers_0/norm': '8403', 'train/layer_model_layers_0/mean': '-0.01118', 'train/layer_model_layers_0/std': '0.7977', 'train/layer_model_layers_0/max_abs': '12.89', 'train/layer_model_layers_0/frac_near_dtype_limit': '0', 'train/layer_model_layers_0/frac_near_user_limit': '0', 'train/layer__model_layers_6/norm': '57.58', 'train/layer__model_layers_6/mean': '0.00046', 'train/layer__model_layers_6/std': '0.03856', 'train/layer__model_layers_6/max_abs': '1.187', 'train/layer__model_layers_6/frac_near_dtype_limit': '0', 'train/layer__model_layers_6/frac_near_user_limit': '0', 'train/layer_model_layers_1/norm': '8432', 'train/layer_model_layers_1/mean': '-0.008993', 'train/layer_model_layers_1/std': '0.8016', 'train/layer_model_layers_1/max_abs': '17.56', 'train/layer_model_layers_1/frac_near_dtype_limit': '0', 'train/layer_model_layers_1/frac_near_user_limit': '0', 'train/layer__model_layers_1/norm': '50.27', 'train/layer__model_layers_1/mean': '0.0004348', 'train/layer__model_layers_1/std': '0.03366', 'train/layer__model_layers_1/max_abs': '1.02', 'train/layer__model_layers_1/frac_near_dtype_limit': '0', 'train/layer__model_layers_1/frac_near_user_limit': '0', 'train/layer_model_layers_7/norm': '1.17e+04', 'train/layer_model_layers_7/mean': '-0.004109', 'train/layer_model_layers_7/std': '1.111', 'train/layer_model_layers_7/max_abs': '28.11', 'train/layer_model_layers_7/frac_near_dtype_limit': '0', 'train/layer_model_layers_7/frac_near_user_limit': '0', 'train/layer__model_layers_0/norm': '52.69', 'train/layer__model_layers_0/mean': '0.000465', 'train/layer__model_layers_0/std': '0.03528', 'train/layer__model_layers_0/max_abs': '1.091', 'train/layer__model_layers_0/frac_near_dtype_limit': '0', 'train/layer__model_layers_0/frac_near_user_limit': '0', 'train/layer_model_layers_2/norm': '8801', 'train/layer_model_layers_2/mean': '-0.002584', 'train/layer_model_layers_2/std': '0.8359', 'train/layer_model_layers_2/max_abs': '20.14', 'train/layer_model_layers_2/frac_near_dtype_limit': '0', 'train/layer_model_layers_2/frac_near_user_limit': '0', 'train/layer_model_layers_4/norm': '1.006e+04', 'train/layer_model_layers_4/mean': '-0.002625', 'train/layer_model_layers_4/std': '0.9552', 'train/layer_model_layers_4/max_abs': '27.45', 'train/layer_model_layers_4/frac_near_dtype_limit': '0', 'train/layer_model_layers_4/frac_near_user_limit': '0', 'train/layer__model_layers_5/norm': '57.09', 'train/layer__m
4149
+ {'loss': '3.073', 'grad_norm': '0.7704', 'learning_rate': '0.0003', 'epoch': '0.4875', 'train/total_time_seconds': '752.4', 'train/time_per_step_avg': '0.09895', 'train/epoch_time_elapsed': '1327', 'train/estimated_remaining_minutes': '3.917'}
4150
+ {'loss': '3.096', 'grad_norm': '0.7425', 'learning_rate': '0.0003', 'epoch': '0.4881', 'train/total_time_seconds': '753.4', 'train/time_per_step_avg': '0.09879', 'train/epoch_time_elapsed': '1328', 'train/estimated_remaining_minutes': '3.9'}
4151
+ {'loss': '3.1', 'grad_norm': '0.7715', 'learning_rate': '0.0003', 'epoch': '0.4887', 'train/total_time_seconds': '754.4', 'train/time_per_step_avg': '0.09871', 'train/epoch_time_elapsed': '1330', 'train/estimated_remaining_minutes': '3.884'}
4152
+ {'loss': '3.1', 'grad_norm': '0.7283', 'learning_rate': '0.0003', 'epoch': '0.4894', 'train/total_time_seconds': '755.3', 'train/time_per_step_avg': '0.09871', 'train/epoch_time_elapsed': '1331', 'train/estimated_remaining_minutes': '3.867'}
4153
+ {'loss': '3.056', 'grad_norm': '0.726', 'learning_rate': '0.0003', 'epoch': '0.49', 'train/total_time_seconds': '756.3', 'train/time_per_step_avg': '0.09876', 'train/epoch_time_elapsed': '1333', 'train/estimated_remaining_minutes': '3.851'}
4154
+ {'loss': '3.099', 'grad_norm': '0.727', 'learning_rate': '0.0003', 'epoch': '0.4907', 'train/total_time_seconds': '757.3', 'train/time_per_step_avg': '0.09871', 'train/epoch_time_elapsed': '1334', 'train/estimated_remaining_minutes': '3.834'}
4155
+ {'loss': '3.136', 'grad_norm': '0.7588', 'learning_rate': '0.0003', 'epoch': '0.4913', 'train/total_time_seconds': '758.3', 'train/time_per_step_avg': '0.09875', 'train/epoch_time_elapsed': '1335', 'train/estimated_remaining_minutes': '3.818'}
4156
+ {'loss': '3.079', 'grad_norm': '0.7646', 'learning_rate': '0.0003', 'epoch': '0.4919', 'train/total_time_seconds': '759.3', 'train/time_per_step_avg': '0.0988', 'train/epoch_time_elapsed': '1337', 'train/estimated_remaining_minutes': '3.801'}
4157
+ {'loss': '3.103', 'grad_norm': '0.7326', 'learning_rate': '0.0003', 'epoch': '0.4926', 'train/total_time_seconds': '760.2', 'train/time_per_step_avg': '0.09886', 'train/epoch_time_elapsed': '1338', 'train/estimated_remaining_minutes': '3.785'}
4158
+ {'loss': '3.106', 'grad_norm': '0.787', 'learning_rate': '0.0003', 'epoch': '0.4932', 'train/total_time_seconds': '761.2', 'train/time_per_step_avg': '0.09784', 'train/epoch_time_elapsed': '1340', 'train/estimated_remaining_minutes': '3.768'}
4159
+ {'loss': '3.074', 'grad_norm': '0.7591', 'learning_rate': '0.0003', 'epoch': '0.4939', 'train/total_time_seconds': '762.2', 'train/time_per_step_avg': '0.09801', 'train/epoch_time_elapsed': '1341', 'train/estimated_remaining_minutes': '3.752'}
4160
+ {'loss': '3.098', 'grad_norm': '0.7503', 'learning_rate': '0.0003', 'epoch': '0.4945', 'train/total_time_seconds': '763.2', 'train/time_per_step_avg': '0.09815', 'train/epoch_time_elapsed': '1343', 'train/estimated_remaining_minutes': '3.735'}
4161
+ {'loss': '3.087', 'grad_norm': '0.7557', 'learning_rate': '0.0003', 'epoch': '0.4951', 'train/total_time_seconds': '764.2', 'train/time_per_step_avg': '0.09832', 'train/epoch_time_elapsed': '1344', 'train/estimated_remaining_minutes': '3.719'}
4162
+ {'loss': '3.081', 'grad_norm': '0.723', 'learning_rate': '0.0003', 'epoch': '0.4958', 'train/total_time_seconds': '765.2', 'train/time_per_step_avg': '0.09847', 'train/epoch_time_elapsed': '1346', 'train/estimated_remaining_minutes': '3.703'}
4163
+ {'loss': '3.117', 'grad_norm': '0.7133', 'learning_rate': '0.0003', 'epoch': '0.4964', 'train/total_time_seconds': '766.2', 'train/time_per_step_avg': '0.09855', 'train/epoch_time_elapsed': '1347', 'train/estimated_remaining_minutes': '3.686'}
4164
+ {'loss': '3.103', 'grad_norm': '0.7397', 'learning_rate': '0.0003', 'epoch': '0.4971', 'train/total_time_seconds': '767.2', 'train/time_per_step_avg': '0.09866', 'train/epoch_time_elapsed': '1349', 'train/estimated_remaining_minutes': '3.67'}
4165
+ {'loss': '3.062', 'grad_norm': '0.7233', 'learning_rate': '0.0003', 'epoch': '0.4977', 'train/total_time_seconds': '768.2', 'train/time_per_step_avg': '0.0987', 'train/epoch_time_elapsed': '1350', 'train/estimated_remaining_minutes': '3.653'}
4166
+ {'loss': '3.094', 'grad_norm': '0.7559', 'learning_rate': '0.0003', 'epoch': '0.4983', 'train/total_time_seconds': '769.1', 'train/time_per_step_avg': '0.09871', 'train/epoch_time_elapsed': '1352', 'train/estimated_remaining_minutes': '3.637'}
4167
+ {'loss': '3.073', 'grad_norm': '0.7303', 'learning_rate': '0.0003', 'epoch': '0.499', 'train/total_time_seconds': '770.1', 'train/time_per_step_avg': '0.09873', 'train/epoch_time_elapsed': '1353', 'train/estimated_remaining_minutes': '3.62'}
4168
+ {'loss': '3.12', 'grad_norm': '0.7322', 'learning_rate': '0.0003', 'epoch': '0.4996', 'train/total_time_seconds': '771.2', 'train/time_per_step_avg': '0.0998', 'train/epoch_time_elapsed': '1355', 'train/estimated_remaining_minutes': '3.604', 'train/global/norm': '1.698e+05', 'train/global/mean': '-2.306', 'train/global/std': '0', 'train/global/max_abs': '32.6', 'train/global/frac_near_dtype_limit': '0', 'train/global/frac_near_user_limit': '0', 'train/layer__model_layers_2/norm': '52.36', 'train/layer__model_layers_2/mean': '0.0004091', 'train/layer__model_layers_2/std': '0.03506', 'train/layer__model_layers_2/max_abs': '1.078', 'train/layer__model_layers_2/frac_near_dtype_limit': '0', 'train/layer__model_layers_2/frac_near_user_limit': '0', 'train/layer__model_layers_4/norm': '54.97', 'train/layer__model_layers_4/mean': '0.0004319', 'train/layer__model_layers_4/std': '0.03681', 'train/layer__model_layers_4/max_abs': '1.14', 'train/layer__model_layers_4/frac_near_dtype_limit': '0', 'train/layer__model_layers_4/frac_near_user_limit': '0', 'train/layer_model_layers_3/norm': '9254', 'train/layer_model_layers_3/mean': '-0.007598', 'train/layer_model_layers_3/std': '0.8786', 'train/layer_model_layers_3/max_abs': '24.9', 'train/layer_model_layers_3/frac_near_dtype_limit': '0', 'train/layer_model_layers_3/frac_near_user_limit': '0', 'train/layer_model_layers_5/norm': '1.038e+04', 'train/layer_model_layers_5/mean': '-0.01374', 'train/layer_model_layers_5/std': '0.9859', 'train/layer_model_layers_5/max_abs': '30.16', 'train/layer_model_layers_5/frac_near_dtype_limit': '0', 'train/layer_model_layers_5/frac_near_user_limit': '0', 'train/layer_model_layers_0/norm': '8432', 'train/layer_model_layers_0/mean': '-0.0113', 'train/layer_model_layers_0/std': '0.8004', 'train/layer_model_layers_0/max_abs': '13.34', 'train/layer_model_layers_0/frac_near_dtype_limit': '0', 'train/layer_model_layers_0/frac_near_user_limit': '0', 'train/layer__model_layers_6/norm': '57.82', 'train/layer__model_layers_6/mean': '0.0004596', 'train/layer__model_layers_6/std': '0.03872', 'train/layer__model_layers_6/max_abs': '1.187', 'train/layer__model_layers_6/frac_near_dtype_limit': '0', 'train/layer__model_layers_6/frac_near_user_limit': '0', 'train/layer_model_layers_1/norm': '8457', 'train/layer_model_layers_1/mean': '-0.007699', 'train/layer_model_layers_1/std': '0.8027', 'train/layer_model_layers_1/max_abs': '19.31', 'train/layer_model_layers_1/frac_near_dtype_limit': '0', 'train/layer_model_layers_1/frac_near_user_limit': '0', 'train/layer__model_layers_1/norm': '50.46', 'train/layer__model_layers_1/mean': '0.0004344', 'train/layer__model_layers_1/std': '0.03379', 'train/layer__model_layers_1/max_abs': '1.021', 'train/layer__model_layers_1/frac_near_dtype_limit': '0', 'train/layer__model_layers_1/frac_near_user_limit': '0', 'train/layer_model_layers_7/norm': '1.183e+04', 'train/layer_model_layers_7/mean': '-0.007984', 'train/layer_model_layers_7/std': '1.123', 'train/layer_model_layers_7/max_abs': '32.6', 'train/layer_model_layers_7/frac_near_dtype_limit': '0', 'train/layer_model_layers_7/frac_near_user_limit': '0', 'train/layer__model_layers_0/norm': '52.85', 'train/layer__model_layers_0/mean': '0.0004664', 'train/layer__model_layers_0/std': '0.03539', 'train/layer__model_layers_0/max_abs': '1.092', 'train/layer__model_layers_0/frac_near_dtype_limit': '0', 'train/layer__model_layers_0/frac_near_user_limit': '0', 'train/layer_model_layers_2/norm': '8817', 'train/layer_model_layers_2/mean': '-0.001678', 'train/layer_model_layers_2/std': '0.8382', 'train/layer_model_layers_2/max_abs': '22.65', 'train/layer_model_layers_2/frac_near_dtype_limit': '0', 'train/layer_model_layers_2/frac_near_user_limit': '0', 'train/layer_model_layers_4/norm': '1.01e+04', 'train/layer_model_layers_4/mean': '-0.002165', 'train/layer_model_layers_4/std': '0.9594', 'train/layer_model_layers_4/max_abs': '29.45', 'train/layer_model_layers_4/frac_near_dtype_limit': '0', 'train/layer_model_layers_4/frac_near_user_limit': '0', 'train/layer__model_layers_5/norm': '57.34', 'train/layer__m
4169
+ {'loss': '3.097', 'grad_norm': '0.7402', 'learning_rate': '0.0003', 'epoch': '0.5003', 'train/total_time_seconds': '772.2', 'train/time_per_step_avg': '0.09976', 'train/epoch_time_elapsed': '1356', 'train/estimated_remaining_minutes': '3.588'}
4170
+ {'loss': '3.097', 'grad_norm': '0.7905', 'learning_rate': '0.0003', 'epoch': '0.5009', 'train/total_time_seconds': '773.2', 'train/time_per_step_avg': '0.09969', 'train/epoch_time_elapsed': '1358', 'train/estimated_remaining_minutes': '3.571'}
4171
+ {'loss': '3.126', 'grad_norm': '0.8013', 'learning_rate': '0.0003', 'epoch': '0.5015', 'train/total_time_seconds': '774.2', 'train/time_per_step_avg': '0.09961', 'train/epoch_time_elapsed': '1359', 'train/estimated_remaining_minutes': '3.555'}
4172
+ {'loss': '3.074', 'grad_norm': '0.7634', 'learning_rate': '0.0003', 'epoch': '0.5022', 'train/total_time_seconds': '775.1', 'train/time_per_step_avg': '0.09952', 'train/epoch_time_elapsed': '1361', 'train/estimated_remaining_minutes': '3.538'}
4173
+ {'loss': '3.088', 'grad_norm': '0.7817', 'learning_rate': '0.0003', 'epoch': '0.5028', 'train/total_time_seconds': '776.1', 'train/time_per_step_avg': '0.09951', 'train/epoch_time_elapsed': '1362', 'train/estimated_remaining_minutes': '3.522'}
4174
+ {'loss': '3.073', 'grad_norm': '0.7545', 'learning_rate': '0.0003', 'epoch': '0.5035', 'train/total_time_seconds': '777.1', 'train/time_per_step_avg': '0.09955', 'train/epoch_time_elapsed': '1364', 'train/estimated_remaining_minutes': '3.505'}
4175
+ {'loss': '3.046', 'grad_norm': '0.7587', 'learning_rate': '0.0003', 'epoch': '0.5041', 'train/total_time_seconds': '778.1', 'train/time_per_step_avg': '0.09963', 'train/epoch_time_elapsed': '1365', 'train/estimated_remaining_minutes': '3.489'}
4176
+ {'loss': '3.113', 'grad_norm': '0.728', 'learning_rate': '0.0003', 'epoch': '0.5047', 'train/total_time_seconds': '779.1', 'train/time_per_step_avg': '0.09967', 'train/epoch_time_elapsed': '1367', 'train/estimated_remaining_minutes': '3.473'}
4177
+ {'loss': '3.105', 'grad_norm': '0.7225', 'learning_rate': '0.0003', 'epoch': '0.5054', 'train/total_time_seconds': '780.1', 'train/time_per_step_avg': '0.09967', 'train/epoch_time_elapsed': '1368', 'train/estimated_remaining_minutes': '3.456'}
4178
+ {'loss': '3.098', 'grad_norm': '0.7516', 'learning_rate': '0.0003', 'epoch': '0.506', 'train/total_time_seconds': '781.1', 'train/time_per_step_avg': '0.09849', 'train/epoch_time_elapsed': '1370', 'train/estimated_remaining_minutes': '3.44'}
4179
+ {'loss': '3.112', 'grad_norm': '0.7497', 'learning_rate': '0.0003', 'epoch': '0.5067', 'train/total_time_seconds': '782', 'train/time_per_step_avg': '0.09843', 'train/epoch_time_elapsed': '1371', 'train/estimated_remaining_minutes': '3.423'}
4180
+ {'loss': '3.081', 'grad_norm': '0.7259', 'learning_rate': '0.0003', 'epoch': '0.5073', 'train/total_time_seconds': '783', 'train/time_per_step_avg': '0.09857', 'train/epoch_time_elapsed': '1373', 'train/estimated_remaining_minutes': '3.407'}
4181
+ {'loss': '3.047', 'grad_norm': '0.7274', 'learning_rate': '0.0003', 'epoch': '0.5079', 'train/total_time_seconds': '784', 'train/time_per_step_avg': '0.09865', 'train/epoch_time_elapsed': '1374', 'train/estimated_remaining_minutes': '3.39'}
4182
+ {'loss': '3.056', 'grad_norm': '0.7358', 'learning_rate': '0.0003', 'epoch': '0.5086', 'train/total_time_seconds': '785', 'train/time_per_step_avg': '0.09868', 'train/epoch_time_elapsed': '1376', 'train/estimated_remaining_minutes': '3.374'}
4183
+ {'loss': '3.078', 'grad_norm': '0.7427', 'learning_rate': '0.0003', 'epoch': '0.5092', 'train/total_time_seconds': '786', 'train/time_per_step_avg': '0.09858', 'train/epoch_time_elapsed': '1377', 'train/estimated_remaining_minutes': '3.357'}
4184
+ {'loss': '3.097', 'grad_norm': '0.7614', 'learning_rate': '0.0003', 'epoch': '0.5099', 'train/total_time_seconds': '787', 'train/time_per_step_avg': '0.09848', 'train/epoch_time_elapsed': '1378', 'train/estimated_remaining_minutes': '3.341'}
4185
+ {'loss': '3.044', 'grad_norm': '0.7919', 'learning_rate': '0.0003', 'epoch': '0.5105', 'train/total_time_seconds': '788', 'train/time_per_step_avg': '0.09841', 'train/epoch_time_elapsed': '1380', 'train/estimated_remaining_minutes': '3.324'}
4186
+ {'loss': '3.097', 'grad_norm': '0.712', 'learning_rate': '0.0003', 'epoch': '0.5111', 'train/total_time_seconds': '788.9', 'train/time_per_step_avg': '0.09836', 'train/epoch_time_elapsed': '1381', 'train/estimated_remaining_minutes': '3.308'}
4187
+ {'loss': '3.095', 'grad_norm': '0.722', 'learning_rate': '0.0003', 'epoch': '0.5118', 'train/total_time_seconds': '789.9', 'train/time_per_step_avg': '0.09836', 'train/epoch_time_elapsed': '1383', 'train/estimated_remaining_minutes': '3.291'}
4188
+ {'eval_loss': '1.543', 'eval_runtime': '13.28', 'eval_samples_per_second': '757.4', 'eval_steps_per_second': '23.71', 'epoch': '0.5118', 'train/total_time_seconds': '789.9', 'train/time_per_step_avg': '0.09836', 'train/epoch_time_elapsed': '1396', 'train/estimated_remaining_minutes': '3.291'}
4189
+ - If you are the owner of the model architecture code, please modify your model class such that it inherits from `GenerationMixin` (after `PreTrainedModel`, otherwise you'll get an exception).
4190
+ - If you are not the owner of the model architecture class, please contact the model code owner to update it.
4191
+ Writing model shards: 100%|██████████████████████| 1/1 [00:00<00:00, 6.37it/s]
4192
+ /mnt/data/zainulabideen/zain-exp/notebooks/Activation/exp.py:402: UserWarning: std(): degrees of freedom is <= 0. Correction should be strictly less than the reduction factor (input numel divided by output numel). (Triggered internally at /pytorch/aten/src/ATen/native/ReduceOps.cpp:1831.)
4193
+ "std": tensor.std().item(),
4194
+
4195
+ {'loss': '3.084', 'grad_norm': '0.7577', 'learning_rate': '0.0003', 'epoch': '0.5124', 'train/total_time_seconds': '791', 'train/time_per_step_avg': '0.09962', 'train/epoch_time_elapsed': '1398', 'train/estimated_remaining_minutes': '3.275', 'train/global/norm': '1.693e+05', 'train/global/mean': '-2.294', 'train/global/std': '0', 'train/global/max_abs': '32.75', 'train/global/frac_near_dtype_limit': '0', 'train/global/frac_near_user_limit': '0', 'train/layer__model_layers_2/norm': '52.57', 'train/layer__model_layers_2/mean': '0.0004073', 'train/layer__model_layers_2/std': '0.03521', 'train/layer__model_layers_2/max_abs': '1.079', 'train/layer__model_layers_2/frac_near_dtype_limit': '0', 'train/layer__model_layers_2/frac_near_user_limit': '0', 'train/layer__model_layers_4/norm': '55.2', 'train/layer__model_layers_4/mean': '0.0004324', 'train/layer__model_layers_4/std': '0.03697', 'train/layer__model_layers_4/max_abs': '1.138', 'train/layer__model_layers_4/frac_near_dtype_limit': '0', 'train/layer__model_layers_4/frac_near_user_limit': '0', 'train/layer_model_layers_3/norm': '9276', 'train/layer_model_layers_3/mean': '-0.006225', 'train/layer_model_layers_3/std': '0.8813', 'train/layer_model_layers_3/max_abs': '25.03', 'train/layer_model_layers_3/frac_near_dtype_limit': '0', 'train/layer_model_layers_3/frac_near_user_limit': '0', 'train/layer_model_layers_5/norm': '1.045e+04', 'train/layer_model_layers_5/mean': '-0.01043', 'train/layer_model_layers_5/std': '0.9918', 'train/layer_model_layers_5/max_abs': '29.75', 'train/layer_model_layers_5/frac_near_dtype_limit': '0', 'train/layer_model_layers_5/frac_near_user_limit': '0', 'train/layer_model_layers_0/norm': '8477', 'train/layer_model_layers_0/mean': '-0.01178', 'train/layer_model_layers_0/std': '0.8053', 'train/layer_model_layers_0/max_abs': '13.93', 'train/layer_model_layers_0/frac_near_dtype_limit': '0', 'train/layer_model_layers_0/frac_near_user_limit': '0', 'train/layer__model_layers_6/norm': '58.06', 'train/layer__model_layers_6/mean': '0.000459', 'train/layer__model_layers_6/std': '0.03889', 'train/layer__model_layers_6/max_abs': '1.187', 'train/layer__model_layers_6/frac_near_dtype_limit': '0', 'train/layer__model_layers_6/frac_near_user_limit': '0', 'train/layer_model_layers_1/norm': '8501', 'train/layer_model_layers_1/mean': '-0.008163', 'train/layer_model_layers_1/std': '0.8069', 'train/layer_model_layers_1/max_abs': '19.87', 'train/layer_model_layers_1/frac_near_dtype_limit': '0', 'train/layer_model_layers_1/frac_near_user_limit': '0', 'train/layer__model_layers_1/norm': '50.65', 'train/layer__model_layers_1/mean': '0.0004319', 'train/layer__model_layers_1/std': '0.03392', 'train/layer__model_layers_1/max_abs': '1.023', 'train/layer__model_layers_1/frac_near_dtype_limit': '0', 'train/layer__model_layers_1/frac_near_user_limit': '0', 'train/layer_model_layers_7/norm': '1.187e+04', 'train/layer_model_layers_7/mean': '-0.00692', 'train/layer_model_layers_7/std': '1.127', 'train/layer_model_layers_7/max_abs': '32.75', 'train/layer_model_layers_7/frac_near_dtype_limit': '0', 'train/layer_model_layers_7/frac_near_user_limit': '0', 'train/layer__model_layers_0/norm': '53.03', 'train/layer__model_layers_0/mean': '0.000467', 'train/layer__model_layers_0/std': '0.03551', 'train/layer__model_layers_0/max_abs': '1.092', 'train/layer__model_layers_0/frac_near_dtype_limit': '0', 'train/layer__model_layers_0/frac_near_user_limit': '0', 'train/layer_model_layers_2/norm': '8830', 'train/layer_model_layers_2/mean': '-0.0009152', 'train/layer_model_layers_2/std': '0.838', 'train/layer_model_layers_2/max_abs': '22.76', 'train/layer_model_layers_2/frac_near_dtype_limit': '0', 'train/layer_model_layers_2/frac_near_user_limit': '0', 'train/layer_model_layers_4/norm': '1.014e+04', 'train/layer_model_layers_4/mean': '-0.0009612', 'train/layer_model_layers_4/std': '0.9624', 'train/layer_model_layers_4/max_abs': '29.08', 'train/layer_model_layers_4/frac_near_dtype_limit': '0', 'train/layer_model_layers_4/frac_near_user_limit': '0', 'train/layer__model_layers_5/norm': '57.57', 'train/layer
4196
+ {'loss': '3.052', 'grad_norm': '0.8091', 'learning_rate': '0.0003', 'epoch': '0.5131', 'train/total_time_seconds': '792', 'train/time_per_step_avg': '0.09963', 'train/epoch_time_elapsed': '1400', 'train/estimated_remaining_minutes': '3.259'}
4197
+ {'loss': '3.071', 'grad_norm': '0.7467', 'learning_rate': '0.0003', 'epoch': '0.5137', 'train/total_time_seconds': '793', 'train/time_per_step_avg': '0.09962', 'train/epoch_time_elapsed': '1401', 'train/estimated_remaining_minutes': '3.242'}
4198
+ {'loss': '3.104', 'grad_norm': '0.764', 'learning_rate': '0.0003', 'epoch': '0.5143', 'train/total_time_seconds': '794', 'train/time_per_step_avg': '0.09968', 'train/epoch_time_elapsed': '1403', 'train/estimated_remaining_minutes': '3.226'}
4199
+ {'loss': '3.079', 'grad_norm': '0.745', 'learning_rate': '0.0003', 'epoch': '0.515', 'train/total_time_seconds': '795', 'train/time_per_step_avg': '0.09972', 'train/epoch_time_elapsed': '1404', 'train/estimated_remaining_minutes': '3.21'}
4200
+ {'loss': '3.098', 'grad_norm': '0.7522', 'learning_rate': '0.0003', 'epoch': '0.5156', 'train/total_time_seconds': '796', 'train/time_per_step_avg': '0.09976', 'train/epoch_time_elapsed': '1406', 'train/estimated_remaining_minutes': '3.193'}
4201
+ {'loss': '3.094', 'grad_norm': '0.7517', 'learning_rate': '0.0003', 'epoch': '0.5162', 'train/total_time_seconds': '797', 'train/time_per_step_avg': '0.09995', 'train/epoch_time_elapsed': '1407', 'train/estimated_remaining_minutes': '3.177'}
4202
+ {'loss': '3.121', 'grad_norm': '0.7683', 'learning_rate': '0.0003', 'epoch': '0.5169', 'train/total_time_seconds': '798', 'train/time_per_step_avg': '0.09997', 'train/epoch_time_elapsed': '1409', 'train/estimated_remaining_minutes': '3.16'}
4203
+ {'loss': '3.092', 'grad_norm': '0.7465', 'learning_rate': '0.0003', 'epoch': '0.5175', 'train/total_time_seconds': '798.9', 'train/time_per_step_avg': '0.1', 'train/epoch_time_elapsed': '1410', 'train/estimated_remaining_minutes': '3.144'}
4204
+ {'loss': '3.08', 'grad_norm': '0.7735', 'learning_rate': '0.0003', 'epoch': '0.5182', 'train/total_time_seconds': '799.9', 'train/time_per_step_avg': '0.1001', 'train/epoch_time_elapsed': '1412', 'train/estimated_remaining_minutes': '3.127'}
4205
+ {'loss': '3.084', 'grad_norm': '0.7458', 'learning_rate': '0.0003', 'epoch': '0.5188', 'train/total_time_seconds': '800.9', 'train/time_per_step_avg': '0.09883', 'train/epoch_time_elapsed': '1413', 'train/estimated_remaining_minutes': '3.111'}
4206
+ {'loss': '3.072', 'grad_norm': '0.7591', 'learning_rate': '0.0003', 'epoch': '0.5194', 'train/total_time_seconds': '801.9', 'train/time_per_step_avg': '0.09884', 'train/epoch_time_elapsed': '1415', 'train/estimated_remaining_minutes': '3.094'}
4207
+ {'loss': '3.099', 'grad_norm': '0.7457', 'learning_rate': '0.0003', 'epoch': '0.5201', 'train/total_time_seconds': '802.9', 'train/time_per_step_avg': '0.09877', 'train/epoch_time_elapsed': '1416', 'train/estimated_remaining_minutes': '3.078'}
4208
+ {'loss': '3.117', 'grad_norm': '0.7769', 'learning_rate': '0.0003', 'epoch': '0.5207', 'train/total_time_seconds': '803.9', 'train/time_per_step_avg': '0.09866', 'train/epoch_time_elapsed': '1417', 'train/estimated_remaining_minutes': '3.061'}
4209
+ {'loss': '3.061', 'grad_norm': '0.7196', 'learning_rate': '0.0003', 'epoch': '0.5214', 'train/total_time_seconds': '804.8', 'train/time_per_step_avg': '0.09864', 'train/epoch_time_elapsed': '1419', 'train/estimated_remaining_minutes': '3.045'}
4210
+ {'loss': '3.086', 'grad_norm': '0.7419', 'learning_rate': '0.0003', 'epoch': '0.522', 'train/total_time_seconds': '805.8', 'train/time_per_step_avg': '0.09861', 'train/epoch_time_elapsed': '1420', 'train/estimated_remaining_minutes': '3.028'}
4211
+ {'loss': '3.078', 'grad_norm': '0.7533', 'learning_rate': '0.0003', 'epoch': '0.5226', 'train/total_time_seconds': '806.8', 'train/time_per_step_avg': '0.09844', 'train/epoch_time_elapsed': '1422', 'train/estimated_remaining_minutes': '3.012'}
4212
+ {'loss': '3.073', 'grad_norm': '0.7303', 'learning_rate': '0.0003', 'epoch': '0.5233', 'train/total_time_seconds': '807.8', 'train/time_per_step_avg': '0.09852', 'train/epoch_time_elapsed': '1423', 'train/estimated_remaining_minutes': '2.996'}
4213
+ {'loss': '3.051', 'grad_norm': '0.7137', 'learning_rate': '0.0003', 'epoch': '0.5239', 'train/total_time_seconds': '808.8', 'train/time_per_step_avg': '0.09851', 'train/epoch_time_elapsed': '1425', 'train/estimated_remaining_minutes': '2.979'}
4214
+ {'loss': '3.064', 'grad_norm': '0.7106', 'learning_rate': '0.0003', 'epoch': '0.5246', 'train/total_time_seconds': '809.8', 'train/time_per_step_avg': '0.09847', 'train/epoch_time_elapsed': '1426', 'train/estimated_remaining_minutes': '2.963'}
4215
+ {'loss': '3.031', 'grad_norm': '0.7481', 'learning_rate': '0.0003', 'epoch': '0.5252', 'train/total_time_seconds': '810.9', 'train/time_per_step_avg': '0.0997', 'train/epoch_time_elapsed': '1428', 'train/estimated_remaining_minutes': '2.947', 'train/global/norm': '1.716e+05', 'train/global/mean': '-2.328', 'train/global/std': '0', 'train/global/max_abs': '32.77', 'train/global/frac_near_dtype_limit': '0', 'train/global/frac_near_user_limit': '0', 'train/layer__model_layers_2/norm': '52.8', 'train/layer__model_layers_2/mean': '0.0004081', 'train/layer__model_layers_2/std': '0.03536', 'train/layer__model_layers_2/max_abs': '1.082', 'train/layer__model_layers_2/frac_near_dtype_limit': '0', 'train/layer__model_layers_2/frac_near_user_limit': '0', 'train/layer__model_layers_4/norm': '55.43', 'train/layer__model_layers_4/mean': '0.0004329', 'train/layer__model_layers_4/std': '0.03712', 'train/layer__model_layers_4/max_abs': '1.14', 'train/layer__model_layers_4/frac_near_dtype_limit': '0', 'train/layer__model_layers_4/frac_near_user_limit': '0', 'train/layer_model_layers_3/norm': '9297', 'train/layer_model_layers_3/mean': '-0.008664', 'train/layer_model_layers_3/std': '0.8832', 'train/layer_model_layers_3/max_abs': '26.53', 'train/layer_model_layers_3/frac_near_dtype_limit': '0', 'train/layer_model_layers_3/frac_near_user_limit': '0', 'train/layer_model_layers_5/norm': '1.047e+04', 'train/layer_model_layers_5/mean': '-0.01214', 'train/layer_model_layers_5/std': '0.9946', 'train/layer_model_layers_5/max_abs': '31.51', 'train/layer_model_layers_5/frac_near_dtype_limit': '0', 'train/layer_model_layers_5/frac_near_user_limit': '0', 'train/layer_model_layers_0/norm': '8514', 'train/layer_model_layers_0/mean': '-0.01258', 'train/layer_model_layers_0/std': '0.8083', 'train/layer_model_layers_0/max_abs': '15.13', 'train/layer_model_layers_0/frac_near_dtype_limit': '0', 'train/layer_model_layers_0/frac_near_user_limit': '0', 'train/layer__model_layers_6/norm': '58.29', 'train/layer__model_layers_6/mean': '0.0004579', 'train/layer__model_layers_6/std': '0.03904', 'train/layer__model_layers_6/max_abs': '1.188', 'train/layer__model_layers_6/frac_near_dtype_limit': '0', 'train/layer__model_layers_6/frac_near_user_limit': '0', 'train/layer_model_layers_1/norm': '8513', 'train/layer_model_layers_1/mean': '-0.00952', 'train/layer_model_layers_1/std': '0.8077', 'train/layer_model_layers_1/max_abs': '20.78', 'train/layer_model_layers_1/frac_near_dtype_limit': '0', 'train/layer_model_layers_1/frac_near_user_limit': '0', 'train/layer__model_layers_1/norm': '50.85', 'train/layer__model_layers_1/mean': '0.0004306', 'train/layer__model_layers_1/std': '0.03405', 'train/layer__model_layers_1/max_abs': '1.027', 'train/layer__model_layers_1/frac_near_dtype_limit': '0', 'train/layer__model_layers_1/frac_near_user_limit': '0', 'train/layer_model_layers_7/norm': '1.192e+04', 'train/layer_model_layers_7/mean': '-0.006521', 'train/layer_model_layers_7/std': '1.133', 'train/layer_model_layers_7/max_abs': '32.77', 'train/layer_model_layers_7/frac_near_dtype_limit': '0', 'train/layer_model_layers_7/frac_near_user_limit': '0', 'train/layer__model_layers_0/norm': '53.21', 'train/layer__model_layers_0/mean': '0.0004646', 'train/layer__model_layers_0/std': '0.03563', 'train/layer__model_layers_0/max_abs': '1.094', 'train/layer__model_layers_0/frac_near_dtype_limit': '0', 'train/layer__model_layers_0/frac_near_user_limit': '0', 'train/layer_model_layers_2/norm': '8857', 'train/layer_model_layers_2/mean': '-0.002495', 'train/layer_model_layers_2/std': '0.8403', 'train/layer_model_layers_2/max_abs': '23.66', 'train/layer_model_layers_2/frac_near_dtype_limit': '0', 'train/layer_model_layers_2/frac_near_user_limit': '0', 'train/layer_model_layers_4/norm': '1.016e+04', 'train/layer_model_layers_4/mean': '-0.002232', 'train/layer_model_layers_4/std': '0.9648', 'train/layer_model_layers_4/max_abs': '30.89', 'train/layer_model_layers_4/frac_near_dtype_limit': '0', 'train/layer_model_layers_4/frac_near_user_limit': '0', 'train/layer__model_layers_5/norm': '57.81', 'train/laye
4216
+ {'loss': '3.024', 'grad_norm': '0.7314', 'learning_rate': '0.0003', 'epoch': '0.5258', 'train/total_time_seconds': '811.9', 'train/time_per_step_avg': '0.09973', 'train/epoch_time_elapsed': '1429', 'train/estimated_remaining_minutes': '2.93'}
4217
+ {'loss': '3.059', 'grad_norm': '0.7503', 'learning_rate': '0.0003', 'epoch': '0.5265', 'train/total_time_seconds': '812.9', 'train/time_per_step_avg': '0.09973', 'train/epoch_time_elapsed': '1431', 'train/estimated_remaining_minutes': '2.914'}
4218
+ {'loss': '3.056', 'grad_norm': '0.7635', 'learning_rate': '0.0003', 'epoch': '0.5271', 'train/total_time_seconds': '813.8', 'train/time_per_step_avg': '0.09978', 'train/epoch_time_elapsed': '1432', 'train/estimated_remaining_minutes': '2.897'}
4219
+ {'loss': '3.083', 'grad_norm': '0.7811', 'learning_rate': '0.0003', 'epoch': '0.5278', 'train/total_time_seconds': '814.8', 'train/time_per_step_avg': '0.09978', 'train/epoch_time_elapsed': '1434', 'train/estimated_remaining_minutes': '2.881'}
4220
+ {'loss': '3.095', 'grad_norm': '0.8416', 'learning_rate': '0.0003', 'epoch': '0.5284', 'train/total_time_seconds': '815.8', 'train/time_per_step_avg': '0.09986', 'train/epoch_time_elapsed': '1435', 'train/estimated_remaining_minutes': '2.864'}
4221
+ {'loss': '3.017', 'grad_norm': '0.7709', 'learning_rate': '0.0003', 'epoch': '0.529', 'train/total_time_seconds': '816.8', 'train/time_per_step_avg': '0.09989', 'train/epoch_time_elapsed': '1437', 'train/estimated_remaining_minutes': '2.848'}
4222
+ {'loss': '3.064', 'grad_norm': '0.7384', 'learning_rate': '0.0003', 'epoch': '0.5297', 'train/total_time_seconds': '817.8', 'train/time_per_step_avg': '0.09983', 'train/epoch_time_elapsed': '1438', 'train/estimated_remaining_minutes': '2.831'}
4223
+ {'loss': '3.07', 'grad_norm': '0.7621', 'learning_rate': '0.0003', 'epoch': '0.5303', 'train/total_time_seconds': '818.8', 'train/time_per_step_avg': '0.09982', 'train/epoch_time_elapsed': '1440', 'train/estimated_remaining_minutes': '2.815'}
4224
+ {'loss': '3.083', 'grad_norm': '0.7359', 'learning_rate': '0.0003', 'epoch': '0.531', 'train/total_time_seconds': '819.8', 'train/time_per_step_avg': '0.09976', 'train/epoch_time_elapsed': '1441', 'train/estimated_remaining_minutes': '2.798'}
4225
+ {'loss': '3.084', 'grad_norm': '0.7407', 'learning_rate': '0.0003', 'epoch': '0.5316', 'train/total_time_seconds': '820.7', 'train/time_per_step_avg': '0.09849', 'train/epoch_time_elapsed': '1443', 'train/estimated_remaining_minutes': '2.782'}
4226
+ {'loss': '3.067', 'grad_norm': '0.7575', 'learning_rate': '0.0003', 'epoch': '0.5322', 'train/total_time_seconds': '821.7', 'train/time_per_step_avg': '0.09845', 'train/epoch_time_elapsed': '1444', 'train/estimated_remaining_minutes': '2.765'}
4227
+ {'loss': '3.06', 'grad_norm': '0.7529', 'learning_rate': '0.0003', 'epoch': '0.5329', 'train/total_time_seconds': '822.7', 'train/time_per_step_avg': '0.09847', 'train/epoch_time_elapsed': '1446', 'train/estimated_remaining_minutes': '2.749'}
4228
+ {'loss': '3.033', 'grad_norm': '0.7367', 'learning_rate': '0.0003', 'epoch': '0.5335', 'train/total_time_seconds': '823.7', 'train/time_per_step_avg': '0.09838', 'train/epoch_time_elapsed': '1447', 'train/estimated_remaining_minutes': '2.732'}
4229
+ {'loss': '3.072', 'grad_norm': '0.7477', 'learning_rate': '0.0003', 'epoch': '0.5342', 'train/total_time_seconds': '824.7', 'train/time_per_step_avg': '0.09834', 'train/epoch_time_elapsed': '1448', 'train/estimated_remaining_minutes': '2.716'}
4230
+ {'loss': '3.118', 'grad_norm': '0.7601', 'learning_rate': '0.0003', 'epoch': '0.5348', 'train/total_time_seconds': '825.6', 'train/time_per_step_avg': '0.09822', 'train/epoch_time_elapsed': '1450', 'train/estimated_remaining_minutes': '2.699'}
4231
+ {'loss': '3.079', 'grad_norm': '0.7172', 'learning_rate': '0.0003', 'epoch': '0.5354', 'train/total_time_seconds': '826.6', 'train/time_per_step_avg': '0.09815', 'train/epoch_time_elapsed': '1451', 'train/estimated_remaining_minutes': '2.683'}
4232
+ {'loss': '3.108', 'grad_norm': '0.7256', 'learning_rate': '0.0003', 'epoch': '0.5361', 'train/total_time_seconds': '827.6', 'train/time_per_step_avg': '0.09817', 'train/epoch_time_elapsed': '1453', 'train/estimated_remaining_minutes': '2.667'}
4233
+ {'loss': '3.1', 'grad_norm': '0.7655', 'learning_rate': '0.0003', 'epoch': '0.5367', 'train/total_time_seconds': '828.6', 'train/time_per_step_avg': '0.09813', 'train/epoch_time_elapsed': '1454', 'train/estimated_remaining_minutes': '2.65'}
4234
+ {'loss': '3.055', 'grad_norm': '0.7456', 'learning_rate': '0.0003', 'epoch': '0.5374', 'train/total_time_seconds': '829.6', 'train/time_per_step_avg': '0.09812', 'train/epoch_time_elapsed': '1456', 'train/estimated_remaining_minutes': '2.634'}
4235
+ {'loss': '3.045', 'grad_norm': '0.7489', 'learning_rate': '0.0003', 'epoch': '0.538', 'train/total_time_seconds': '830.7', 'train/time_per_step_avg': '0.09958', 'train/epoch_time_elapsed': '1457', 'train/estimated_remaining_minutes': '2.618', 'train/global/norm': '1.72e+05', 'train/global/mean': '-2.328', 'train/global/std': '0', 'train/global/max_abs': '32.8', 'train/global/frac_near_dtype_limit': '0', 'train/global/frac_near_user_limit': '0', 'train/layer__model_layers_2/norm': '53.02', 'train/layer__model_layers_2/mean': '0.0004105', 'train/layer__model_layers_2/std': '0.03551', 'train/layer__model_layers_2/max_abs': '1.079', 'train/layer__model_layers_2/frac_near_dtype_limit': '0', 'train/layer__model_layers_2/frac_near_user_limit': '0', 'train/layer__model_layers_4/norm': '55.64', 'train/layer__model_layers_4/mean': '0.0004327', 'train/layer__model_layers_4/std': '0.03726', 'train/layer__model_layers_4/max_abs': '1.141', 'train/layer__model_layers_4/frac_near_dtype_limit': '0', 'train/layer__model_layers_4/frac_near_user_limit': '0', 'train/layer_model_layers_3/norm': '9349', 'train/layer_model_layers_3/mean': '-0.008241', 'train/layer_model_layers_3/std': '0.8885', 'train/layer_model_layers_3/max_abs': '27.73', 'train/layer_model_layers_3/frac_near_dtype_limit': '0', 'train/layer_model_layers_3/frac_near_user_limit': '0', 'train/layer_model_layers_5/norm': '1.052e+04', 'train/layer_model_layers_5/mean': '-0.01235', 'train/layer_model_layers_5/std': '0.9988', 'train/layer_model_layers_5/max_abs': '32.61', 'train/layer_model_layers_5/frac_near_dtype_limit': '0', 'train/layer_model_layers_5/frac_near_user_limit': '0', 'train/layer_model_layers_0/norm': '8548', 'train/layer_model_layers_0/mean': '-0.01114', 'train/layer_model_layers_0/std': '0.8114', 'train/layer_model_layers_0/max_abs': '15.35', 'train/layer_model_layers_0/frac_near_dtype_limit': '0', 'train/layer_model_layers_0/frac_near_user_limit': '0', 'train/layer__model_layers_6/norm': '58.54', 'train/layer__model_layers_6/mean': '0.0004587', 'train/layer__model_layers_6/std': '0.03921', 'train/layer__model_layers_6/max_abs': '1.191', 'train/layer__model_layers_6/frac_near_dtype_limit': '0', 'train/layer__model_layers_6/frac_near_user_limit': '0', 'train/layer_model_layers_1/norm': '8581', 'train/layer_model_layers_1/mean': '-0.009432', 'train/layer_model_layers_1/std': '0.8144', 'train/layer_model_layers_1/max_abs': '21.31', 'train/layer_model_layers_1/frac_near_dtype_limit': '0', 'train/layer_model_layers_1/frac_near_user_limit': '0', 'train/layer__model_layers_1/norm': '51.05', 'train/layer__model_layers_1/mean': '0.0004296', 'train/layer__model_layers_1/std': '0.03419', 'train/layer__model_layers_1/max_abs': '1.026', 'train/layer__model_layers_1/frac_near_dtype_limit': '0', 'train/layer__model_layers_1/frac_near_user_limit': '0', 'train/layer_model_layers_7/norm': '1.199e+04', 'train/layer_model_layers_7/mean': '-0.007032', 'train/layer_model_layers_7/std': '1.139', 'train/layer_model_layers_7/max_abs': '32.8', 'train/layer_model_layers_7/frac_near_dtype_limit': '0', 'train/layer_model_layers_7/frac_near_user_limit': '0', 'train/layer__model_layers_0/norm': '53.38', 'train/layer__model_layers_0/mean': '0.0004644', 'train/layer__model_layers_0/std': '0.03575', 'train/layer__model_layers_0/max_abs': '1.095', 'train/layer__model_layers_0/frac_near_dtype_limit': '0', 'train/layer__model_layers_0/frac_near_user_limit': '0', 'train/layer_model_layers_2/norm': '8911', 'train/layer_model_layers_2/mean': '-0.002581', 'train/layer_model_layers_2/std': '0.8458', 'train/layer_model_layers_2/max_abs': '24.64', 'train/layer_model_layers_2/frac_near_dtype_limit': '0', 'train/layer_model_layers_2/frac_near_user_limit': '0', 'train/layer_model_layers_4/norm': '1.021e+04', 'train/layer_model_layers_4/mean': '-0.003565', 'train/layer_model_layers_4/std': '0.9685', 'train/layer_model_layers_4/max_abs': '31.85', 'train/layer_model_layers_4/frac_near_dtype_limit': '0', 'train/layer_model_layers_4/frac_near_user_limit': '0', 'train/layer__model_layers_5/norm': '58.05', 'train/laye
4236
+ {'loss': '3.024', 'grad_norm': '0.7469', 'learning_rate': '0.0003', 'epoch': '0.5386', 'train/total_time_seconds': '831.7', 'train/time_per_step_avg': '0.09959', 'train/epoch_time_elapsed': '1459', 'train/estimated_remaining_minutes': '2.601'}
4237
+ {'loss': '3.046', 'grad_norm': '0.7605', 'learning_rate': '0.0003', 'epoch': '0.5393', 'train/total_time_seconds': '832.7', 'train/time_per_step_avg': '0.09954', 'train/epoch_time_elapsed': '1460', 'train/estimated_remaining_minutes': '2.585'}
4238
+ {'loss': '3.084', 'grad_norm': '0.7174', 'learning_rate': '0.0003', 'epoch': '0.5399', 'train/total_time_seconds': '833.6', 'train/time_per_step_avg': '0.09956', 'train/epoch_time_elapsed': '1462', 'train/estimated_remaining_minutes': '2.568'}
4239
+ {'loss': '3.039', 'grad_norm': '0.7341', 'learning_rate': '0.0003', 'epoch': '0.5406', 'train/total_time_seconds': '834.6', 'train/time_per_step_avg': '0.09966', 'train/epoch_time_elapsed': '1463', 'train/estimated_remaining_minutes': '2.552'}
4240
+ {'loss': '3.079', 'grad_norm': '0.7248', 'learning_rate': '0.0003', 'epoch': '0.5412', 'train/total_time_seconds': '835.6', 'train/time_per_step_avg': '0.09967', 'train/epoch_time_elapsed': '1465', 'train/estimated_remaining_minutes': '2.535'}
4241
+ {'loss': '3.079', 'grad_norm': '0.7487', 'learning_rate': '0.0003', 'epoch': '0.5418', 'train/total_time_seconds': '836.6', 'train/time_per_step_avg': '0.09973', 'train/epoch_time_elapsed': '1466', 'train/estimated_remaining_minutes': '2.519'}
4242
+ {'loss': '3.054', 'grad_norm': '0.711', 'learning_rate': '0.0003', 'epoch': '0.5425', 'train/total_time_seconds': '837.6', 'train/time_per_step_avg': '0.09966', 'train/epoch_time_elapsed': '1468', 'train/estimated_remaining_minutes': '2.502'}
4243
+ {'loss': '3.039', 'grad_norm': '0.7715', 'learning_rate': '0.0003', 'epoch': '0.5431', 'train/total_time_seconds': '838.6', 'train/time_per_step_avg': '0.09964', 'train/epoch_time_elapsed': '1469', 'train/estimated_remaining_minutes': '2.486'}
4244
+ {'loss': '3.053', 'grad_norm': '0.7143', 'learning_rate': '0.0003', 'epoch': '0.5438', 'train/total_time_seconds': '839.5', 'train/time_per_step_avg': '0.09958', 'train/epoch_time_elapsed': '1471', 'train/estimated_remaining_minutes': '2.469'}
4245
+
4246
+ {'eval_loss': '1.537', 'eval_runtime': '13.32', 'eval_samples_per_second': '755.2', 'eval_steps_per_second': '23.65', 'epoch': '0.5438', 'train/total_time_seconds': '839.5', 'train/time_per_step_avg': '0.09958', 'train/epoch_time_elapsed': '1484', 'train/estimated_remaining_minutes': '2.469'}
4247
+ {'loss': '3.054', 'grad_norm': '0.7473', 'learning_rate': '0.0003', 'epoch': '0.5444', 'train/total_time_seconds': '840.5', 'train/time_per_step_avg': '0.09816', 'train/epoch_time_elapsed': '1485', 'train/estimated_remaining_minutes': '2.453'}
4248
+ {'loss': '3.075', 'grad_norm': '0.7757', 'learning_rate': '0.0003', 'epoch': '0.545', 'train/total_time_seconds': '841.5', 'train/time_per_step_avg': '0.09815', 'train/epoch_time_elapsed': '1487', 'train/estimated_remaining_minutes': '2.436'}
4249
+ {'loss': '3.079', 'grad_norm': '0.7507', 'learning_rate': '0.0003', 'epoch': '0.5457', 'train/total_time_seconds': '842.5', 'train/time_per_step_avg': '0.09815', 'train/epoch_time_elapsed': '1488', 'train/estimated_remaining_minutes': '2.42'}
4250
+ {'loss': '3.116', 'grad_norm': '0.7378', 'learning_rate': '0.0003', 'epoch': '0.5463', 'train/total_time_seconds': '843.4', 'train/time_per_step_avg': '0.09813', 'train/epoch_time_elapsed': '1490', 'train/estimated_remaining_minutes': '2.403'}
4251
+ {'loss': '3.046', 'grad_norm': '0.7336', 'learning_rate': '0.0003', 'epoch': '0.547', 'train/total_time_seconds': '844.4', 'train/time_per_step_avg': '0.09804', 'train/epoch_time_elapsed': '1491', 'train/estimated_remaining_minutes': '2.387'}
4252
+ {'loss': '3.048', 'grad_norm': '0.7088', 'learning_rate': '0.0003', 'epoch': '0.5476', 'train/total_time_seconds': '845.4', 'train/time_per_step_avg': '0.09807', 'train/epoch_time_elapsed': '1493', 'train/estimated_remaining_minutes': '2.37'}
4253
+ {'loss': '3.073', 'grad_norm': '0.7157', 'learning_rate': '0.0003', 'epoch': '0.5482', 'train/total_time_seconds': '846.4', 'train/time_per_step_avg': '0.09817', 'train/epoch_time_elapsed': '1494', 'train/estimated_remaining_minutes': '2.354'}
4254
+ {'loss': '3.079', 'grad_norm': '0.7158', 'learning_rate': '0.0003', 'epoch': '0.5489', 'train/total_time_seconds': '847.4', 'train/time_per_step_avg': '0.09819', 'train/epoch_time_elapsed': '1496', 'train/estimated_remaining_minutes': '2.337'}
4255
+ {'loss': '3.082', 'grad_norm': '0.7732', 'learning_rate': '0.0003', 'epoch': '0.5495', 'train/total_time_seconds': '848.4', 'train/time_per_step_avg': '0.09831', 'train/epoch_time_elapsed': '1497', 'train/estimated_remaining_minutes': '2.321'}
4256
+ {'loss': '3.073', 'grad_norm': '0.7541', 'learning_rate': '0.0003', 'epoch': '0.5502', 'train/total_time_seconds': '849.4', 'train/time_per_step_avg': '0.09845', 'train/epoch_time_elapsed': '1499', 'train/estimated_remaining_minutes': '2.304'}
4257
+ {'loss': '3.081', 'grad_norm': '0.7709', 'learning_rate': '0.0003', 'epoch': '0.5508', 'train/total_time_seconds': '850.5', 'train/time_per_step_avg': '0.09966', 'train/epoch_time_elapsed': '1500', 'train/estimated_remaining_minutes': '2.288', 'train/global/norm': '1.776e+05', 'train/global/mean': '-2.417', 'train/global/std': '0', 'train/global/max_abs': '35.37', 'train/global/frac_near_dtype_limit': '0', 'train/global/frac_near_user_limit': '0', 'train/layer__model_layers_2/norm': '53.24', 'train/layer__model_layers_2/mean': '0.0004066', 'train/layer__model_layers_2/std': '0.03566', 'train/layer__model_layers_2/max_abs': '1.079', 'train/layer__model_layers_2/frac_near_dtype_limit': '0', 'train/layer__model_layers_2/frac_near_user_limit': '0', 'train/layer__model_layers_4/norm': '55.87', 'train/layer__model_layers_4/mean': '0.0004326', 'train/layer__model_layers_4/std': '0.03742', 'train/layer__model_layers_4/max_abs': '1.141', 'train/layer__model_layers_4/frac_near_dtype_limit': '0', 'train/layer__model_layers_4/frac_near_user_limit': '0', 'train/layer_model_layers_3/norm': '9383', 'train/layer_model_layers_3/mean': '-0.008335', 'train/layer_model_layers_3/std': '0.891', 'train/layer_model_layers_3/max_abs': '29.38', 'train/layer_model_layers_3/frac_near_dtype_limit': '0', 'train/layer_model_layers_3/frac_near_user_limit': '0', 'train/layer_model_layers_5/norm': '1.056e+04', 'train/layer_model_layers_5/mean': '-0.01388', 'train/layer_model_layers_5/std': '1.003', 'train/layer_model_layers_5/max_abs': '35.37', 'train/layer_model_layers_5/frac_near_dtype_limit': '0', 'train/layer_model_layers_5/frac_near_user_limit': '0', 'train/layer_model_layers_0/norm': '8600', 'train/layer_model_layers_0/mean': '-0.01127', 'train/layer_model_layers_0/std': '0.8161', 'train/layer_model_layers_0/max_abs': '15.77', 'train/layer_model_layers_0/frac_near_dtype_limit': '0', 'train/layer_model_layers_0/frac_near_user_limit': '0', 'train/layer__model_layers_6/norm': '58.78', 'train/layer__model_layers_6/mean': '0.000462', 'train/layer__model_layers_6/std': '0.03937', 'train/layer__model_layers_6/max_abs': '1.189', 'train/layer__model_layers_6/frac_near_dtype_limit': '0', 'train/layer__model_layers_6/frac_near_user_limit': '0', 'train/layer_model_layers_1/norm': '8608', 'train/layer_model_layers_1/mean': '-0.00838', 'train/layer_model_layers_1/std': '0.8177', 'train/layer_model_layers_1/max_abs': '22.14', 'train/layer_model_layers_1/frac_near_dtype_limit': '0', 'train/layer_model_layers_1/frac_near_user_limit': '0', 'train/layer__model_layers_1/norm': '51.24', 'train/layer__model_layers_1/mean': '0.0004303', 'train/layer__model_layers_1/std': '0.03432', 'train/layer__model_layers_1/max_abs': '1.025', 'train/layer__model_layers_1/frac_near_dtype_limit': '0', 'train/layer__model_layers_1/frac_near_user_limit': '0', 'train/layer_model_layers_7/norm': '1.218e+04', 'train/layer_model_layers_7/mean': '-0.009196', 'train/layer_model_layers_7/std': '1.156', 'train/layer_model_layers_7/max_abs': '35.24', 'train/layer_model_layers_7/frac_near_dtype_limit': '0', 'train/layer_model_layers_7/frac_near_user_limit': '0', 'train/layer__model_layers_0/norm': '53.56', 'train/layer__model_layers_0/mean': '0.0004637', 'train/layer__model_layers_0/std': '0.03587', 'train/layer__model_layers_0/max_abs': '1.094', 'train/layer__model_layers_0/frac_near_dtype_limit': '0', 'train/layer__model_layers_0/frac_near_user_limit': '0', 'train/layer_model_layers_2/norm': '8952', 'train/layer_model_layers_2/mean': '-0.001844', 'train/layer_model_layers_2/std': '0.8504', 'train/layer_model_layers_2/max_abs': '25.74', 'train/layer_model_layers_2/frac_near_dtype_limit': '0', 'train/layer_model_layers_2/frac_near_user_limit': '0', 'train/layer_model_layers_4/norm': '1.026e+04', 'train/layer_model_layers_4/mean': '-0.003354', 'train/layer_model_layers_4/std': '0.9742', 'train/layer_model_layers_4/max_abs': '34.81', 'train/layer_model_layers_4/frac_near_dtype_limit': '0', 'train/layer_model_layers_4/frac_near_user_limit': '0', 'train/layer__model_layers_5/norm': '58.29', 'train/laye
4258
+ {'loss': '3.046', 'grad_norm': '0.7132', 'learning_rate': '0.0003', 'epoch': '0.5514', 'train/total_time_seconds': '851.5', 'train/time_per_step_avg': '0.09967', 'train/epoch_time_elapsed': '1502', 'train/estimated_remaining_minutes': '2.272'}
wandb/run-20260803_000712-b7gsa2kc/logs/debug-internal.log CHANGED
@@ -881,3 +881,39 @@
881
  {"time":"2026-08-03T01:56:13.766620862Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
882
  {"time":"2026-08-03T01:56:28.550658745Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":3779,"history_lines":3,"events_offset":871,"events_lines":2,"console_offset":4078,"console_lines":9}
883
  {"time":"2026-08-03T01:56:28.942217122Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
881
  {"time":"2026-08-03T01:56:13.766620862Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
882
  {"time":"2026-08-03T01:56:28.550658745Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":3779,"history_lines":3,"events_offset":871,"events_lines":2,"console_offset":4078,"console_lines":9}
883
  {"time":"2026-08-03T01:56:28.942217122Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
884
+ {"time":"2026-08-03T01:56:43.550276701Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":3782,"history_lines":10,"events_offset":873,"events_lines":2,"console_offset":4084,"console_lines":1}
885
+ {"time":"2026-08-03T01:56:43.870134841Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
886
+ {"time":"2026-08-03T01:56:58.550560434Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":3792,"history_lines":10,"events_offset":875,"events_lines":2,"console_offset":4084,"console_lines":1}
887
+ {"time":"2026-08-03T01:56:58.805307452Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
888
+ {"time":"2026-08-03T01:57:13.550239277Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":3802,"history_lines":11,"events_offset":877,"events_lines":2,"console_offset":4084,"console_lines":1}
889
+ {"time":"2026-08-03T01:57:13.715260475Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
890
+ {"time":"2026-08-03T01:57:28.550662766Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":3813,"history_lines":10,"events_offset":879,"events_lines":2,"console_offset":4087,"console_lines":41}
891
+ {"time":"2026-08-03T01:57:28.928462625Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
892
+ {"time":"2026-08-03T01:57:43.550225887Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":3823,"history_lines":7,"events_offset":881,"events_lines":2,"console_offset":4128,"console_lines":8}
893
+ {"time":"2026-08-03T01:57:43.800131275Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
894
+ {"time":"2026-08-03T01:57:58.550422994Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":3830,"history_lines":5,"events_offset":883,"events_lines":2,"console_offset":4135,"console_lines":6}
895
+ {"time":"2026-08-03T01:57:58.805706284Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
896
+ {"time":"2026-08-03T01:58:13.549885357Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":3835,"history_lines":11,"events_offset":885,"events_lines":2,"console_offset":4141,"console_lines":11}
897
+ {"time":"2026-08-03T01:58:13.712269171Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
898
+ {"time":"2026-08-03T01:58:28.550591544Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":3846,"history_lines":10,"events_offset":887,"events_lines":2,"console_offset":4152,"console_lines":10}
899
+ {"time":"2026-08-03T01:58:28.770157422Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
900
+ {"time":"2026-08-03T01:58:43.550671465Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":3856,"history_lines":10,"events_offset":889,"events_lines":2,"console_offset":4162,"console_lines":10}
901
+ {"time":"2026-08-03T01:58:43.78455609Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
902
+ {"time":"2026-08-03T01:58:58.550246569Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":3866,"history_lines":10,"events_offset":891,"events_lines":2,"console_offset":4172,"console_lines":10}
903
+ {"time":"2026-08-03T01:58:58.776779762Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
904
+ {"time":"2026-08-03T01:59:13.550472831Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":3876,"history_lines":5,"events_offset":893,"events_lines":2,"console_offset":4182,"console_lines":5}
905
+ {"time":"2026-08-03T01:59:13.757926044Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
906
+ {"time":"2026-08-03T01:59:28.550391713Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":3881,"history_lines":7,"events_offset":895,"events_lines":2,"console_offset":4187,"console_lines":13}
907
+ {"time":"2026-08-03T01:59:29.027920091Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
908
+ {"time":"2026-08-03T01:59:43.550715008Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":3888,"history_lines":10,"events_offset":897,"events_lines":2,"console_offset":4193,"console_lines":1}
909
+ {"time":"2026-08-03T01:59:43.975009654Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
910
+ {"time":"2026-08-03T01:59:58.550358662Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":3898,"history_lines":10,"events_offset":899,"events_lines":2,"console_offset":4193,"console_lines":1}
911
+ {"time":"2026-08-03T01:59:58.725210066Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
912
+ {"time":"2026-08-03T02:00:13.549998818Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":3908,"history_lines":11,"events_offset":901,"events_lines":2,"console_offset":4193,"console_lines":1}
913
+ {"time":"2026-08-03T02:00:13.829452162Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
914
+ {"time":"2026-08-03T02:00:28.549995799Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":3919,"history_lines":10,"events_offset":903,"events_lines":2,"console_offset":4200,"console_lines":41}
915
+ {"time":"2026-08-03T02:00:28.795194135Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
916
+ {"time":"2026-08-03T02:00:43.550452093Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":3929,"history_lines":3,"events_offset":905,"events_lines":2,"console_offset":4241,"console_lines":4}
917
+ {"time":"2026-08-03T02:00:43.734399312Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
918
+ {"time":"2026-08-03T02:00:58.550399722Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":3932,"history_lines":9,"events_offset":907,"events_lines":2,"console_offset":4244,"console_lines":10}
919
+ {"time":"2026-08-03T02:00:58.794953391Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
wandb/run-20260803_000712-b7gsa2kc/run-b7gsa2kc.wandb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6316a91bff9ec4c451d125aeffd95ca50db2d5e0385cce1b02c7c1ea6655c2c4
3
- size 16941056
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71feafb122b19fef5e75ac16168b87c91dbcedf082d31cdcb15094b097589748
3
+ size 17727488