BayesTensor commited on
Commit
22206a4
·
verified ·
1 Parent(s): 701dd20

Training in progress, epoch 25, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:219eccff007c0e370835316bb089b78b72b5f14b76be94392f3dc75728fe9e39
3
  size 598439784
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5919f93a54e495db48430b26521c73296b72218c64567785916850110de37ebc
3
  size 598439784
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fafdb36da12f76514a9bb8248fa0988c9ede29267cdc790d678b9194974ccfd7
3
  size 1196967418
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93a2cd2ffdeb33f31515c6d1503fdcbab2c355b120aa38e58e6900180d66de4d
3
  size 1196967418
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:572ed1aa15ce8f8aed234d431c888a5ee9318c9ef239c3f25a51346de4c681db
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4072b83269ebc4b1da2b842071bc665a20b5984e7d5702db20859234b16cca1c
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dadbb0c2548c50b49bb39f2ba86a4c33336520be2d6c262605200619683d2787
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:986eda8c046a738c9ab307d04bc623a8d8d1875086ca4a111c8f884ca4b836ba
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 0.8181082820112143,
3
  "best_model_checkpoint": "modernbert-medical-classifier/checkpoint-1196",
4
- "epoch": 24.0,
5
  "eval_steps": 500,
6
- "global_step": 2208,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -377,6 +377,22 @@
377
  "eval_samples_per_second": 12.867,
378
  "eval_steps_per_second": 3.217,
379
  "step": 2208
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
380
  }
381
  ],
382
  "logging_steps": 100,
@@ -391,12 +407,12 @@
391
  "should_evaluate": false,
392
  "should_log": false,
393
  "should_save": true,
394
- "should_training_stop": false
395
  },
396
  "attributes": {}
397
  }
398
  },
399
- "total_flos": 1.5158399806368e+16,
400
  "train_batch_size": 4,
401
  "trial_name": null,
402
  "trial_params": null
 
1
  {
2
  "best_metric": 0.8181082820112143,
3
  "best_model_checkpoint": "modernbert-medical-classifier/checkpoint-1196",
4
+ "epoch": 25.0,
5
  "eval_steps": 500,
6
+ "global_step": 2300,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
377
  "eval_samples_per_second": 12.867,
378
  "eval_steps_per_second": 3.217,
379
  "step": 2208
380
+ },
381
+ {
382
+ "epoch": 25.0,
383
+ "grad_norm": 0.0016703982837498188,
384
+ "learning_rate": 0.0,
385
+ "loss": 0.0,
386
+ "step": 2300
387
+ },
388
+ {
389
+ "epoch": 25.0,
390
+ "eval_f1": 0.7634584417193113,
391
+ "eval_loss": 1.8875935077667236,
392
+ "eval_runtime": 7.3972,
393
+ "eval_samples_per_second": 12.437,
394
+ "eval_steps_per_second": 3.109,
395
+ "step": 2300
396
  }
397
  ],
398
  "logging_steps": 100,
 
407
  "should_evaluate": false,
408
  "should_log": false,
409
  "should_save": true,
410
+ "should_training_stop": true
411
  },
412
  "attributes": {}
413
  }
414
  },
415
+ "total_flos": 1.57899997983e+16,
416
  "train_batch_size": 4,
417
  "trial_name": null,
418
  "trial_params": null