BayesTensor commited on
Commit
46ebd4d
·
verified ·
1 Parent(s): 5fc0d0d

Training in progress, epoch 24, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ccaa285f634999614d76916fa26ad8586b367298697a9ba5d5674744d4bc4433
3
  size 598442860
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2bf762a1c693117661a2e6b5acd9ba79de90c623d4bbf4b865e56acdcdda157
3
  size 598442860
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2897be83473030817c6ff78446c8bb0dfc829bb54d41c6eb71287e1885905e70
3
  size 1196973562
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:207a6393b2e42b1dd59e4c718a34f25d22c300d23a0e6f1db931caddef4b10c3
3
  size 1196973562
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:23c03a4de3b86963ec287522a2181427c3374e2dc539cb28bf29e0a8cece77ca
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:618ef55f6c5423457249c94a2577645800716eebc494bf2745faa205a24bad51
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:483f4ecfb311e0d8ab1c4c2d39a345ad988e3534065d1820a6f78e949cfb8296
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d4a23bf331c10255c622291f489aea6f2f24812a9bd3d5febfd9dade1a88b34
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 0.685027729264332,
3
  "best_model_checkpoint": "modernbert-medical-classifier/checkpoint-2024",
4
- "epoch": 23.0,
5
  "eval_steps": 500,
6
- "global_step": 2116,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -361,6 +361,22 @@
361
  "eval_samples_per_second": 12.538,
362
  "eval_steps_per_second": 3.134,
363
  "step": 2116
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
364
  }
365
  ],
366
  "logging_steps": 100,
@@ -380,7 +396,7 @@
380
  "attributes": {}
381
  }
382
  },
383
- "total_flos": 1.4526900524214e+16,
384
  "train_batch_size": 4,
385
  "trial_name": null,
386
  "trial_params": null
 
1
  {
2
  "best_metric": 0.685027729264332,
3
  "best_model_checkpoint": "modernbert-medical-classifier/checkpoint-2024",
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,
 
361
  "eval_samples_per_second": 12.538,
362
  "eval_steps_per_second": 3.134,
363
  "step": 2116
364
+ },
365
+ {
366
+ "epoch": 23.91304347826087,
367
+ "grad_norm": 0.0006493396940641105,
368
+ "learning_rate": 9.66183574879227e-07,
369
+ "loss": 0.0001,
370
+ "step": 2200
371
+ },
372
+ {
373
+ "epoch": 24.0,
374
+ "eval_f1": 0.6675544814093237,
375
+ "eval_loss": 3.64399790763855,
376
+ "eval_runtime": 7.3823,
377
+ "eval_samples_per_second": 12.462,
378
+ "eval_steps_per_second": 3.116,
379
+ "step": 2208
380
  }
381
  ],
382
  "logging_steps": 100,
 
396
  "attributes": {}
397
  }
398
  },
399
+ "total_flos": 1.5158504894832e+16,
400
  "train_batch_size": 4,
401
  "trial_name": null,
402
  "trial_params": null