aee4 commited on
Commit
7ceb21d
·
verified ·
1 Parent(s): c9c53ca

Training in progress, step 31750, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dedd9aacdda348954bfbf9198afefb4e66266caa79489d13ace65b43db1a34eb
3
  size 76153420
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fe6cf44d4a60a4b01f83d348aefde599dd010516e7b47635e4b72532150e9e1
3
  size 76153420
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d72bcd3ef8b9a9e0f6f4414a0a29875a214381368a85e85a6e6c3c95f0d8f69
3
  size 152327371
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2325b75a0e09db7c2b328d127508ac7275893afdbd26c884f088d02c068cfec6
3
  size 152327371
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e1eb5d3edcb370711cf545dce77cd286cf5a332e6f6b1b84d670fd0cf8b7a6ca
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c522cfcda35326db8ec316aeb7015f0f34ee064fd611db9fe65a8193d5fae478
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b420740271eb81ad380f7d851e50a0acb0920fb5addeda6e7fcb98b508d375cf
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0771ff96276a7110458f23f22723f9432c881c5474dd979717aa5b336448478a
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -2,9 +2,9 @@
2
  "best_global_step": 18500,
3
  "best_metric": 0.7932397701166506,
4
  "best_model_checkpoint": "/kaggle/working/G17_amfu_paper_training/trainer_output/checkpoint-18500",
5
- "epoch": 177.96610169491527,
6
  "eval_steps": 250,
7
- "global_step": 31500,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -10340,6 +10340,88 @@
10340
  "eval_samples_per_second": 50.859,
10341
  "eval_steps_per_second": 12.715,
10342
  "step": 31500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
10343
  }
10344
  ],
10345
  "logging_steps": 25,
 
2
  "best_global_step": 18500,
3
  "best_metric": 0.7932397701166506,
4
  "best_model_checkpoint": "/kaggle/working/G17_amfu_paper_training/trainer_output/checkpoint-18500",
5
+ "epoch": 179.37853107344634,
6
  "eval_steps": 250,
7
+ "global_step": 31750,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
10340
  "eval_samples_per_second": 50.859,
10341
  "eval_steps_per_second": 12.715,
10342
  "step": 31500
10343
+ },
10344
+ {
10345
+ "epoch": 178.10734463276836,
10346
+ "grad_norm": 0.7718198299407959,
10347
+ "learning_rate": 7.62939453125e-09,
10348
+ "loss": 0.2515,
10349
+ "step": 31525
10350
+ },
10351
+ {
10352
+ "epoch": 178.24858757062148,
10353
+ "grad_norm": 1.6290037631988525,
10354
+ "learning_rate": 7.62939453125e-09,
10355
+ "loss": 0.2726,
10356
+ "step": 31550
10357
+ },
10358
+ {
10359
+ "epoch": 178.38983050847457,
10360
+ "grad_norm": 2.5522103309631348,
10361
+ "learning_rate": 7.62939453125e-09,
10362
+ "loss": 0.2537,
10363
+ "step": 31575
10364
+ },
10365
+ {
10366
+ "epoch": 178.5310734463277,
10367
+ "grad_norm": 2.0693769454956055,
10368
+ "learning_rate": 7.62939453125e-09,
10369
+ "loss": 0.2614,
10370
+ "step": 31600
10371
+ },
10372
+ {
10373
+ "epoch": 178.6723163841808,
10374
+ "grad_norm": 1.310135841369629,
10375
+ "learning_rate": 7.62939453125e-09,
10376
+ "loss": 0.2328,
10377
+ "step": 31625
10378
+ },
10379
+ {
10380
+ "epoch": 178.8135593220339,
10381
+ "grad_norm": 1.4671868085861206,
10382
+ "learning_rate": 7.62939453125e-09,
10383
+ "loss": 0.2855,
10384
+ "step": 31650
10385
+ },
10386
+ {
10387
+ "epoch": 178.954802259887,
10388
+ "grad_norm": 2.567404270172119,
10389
+ "learning_rate": 7.62939453125e-09,
10390
+ "loss": 0.2512,
10391
+ "step": 31675
10392
+ },
10393
+ {
10394
+ "epoch": 179.09604519774012,
10395
+ "grad_norm": 2.848036289215088,
10396
+ "learning_rate": 7.62939453125e-09,
10397
+ "loss": 0.2573,
10398
+ "step": 31700
10399
+ },
10400
+ {
10401
+ "epoch": 179.23728813559322,
10402
+ "grad_norm": 0.8092109560966492,
10403
+ "learning_rate": 7.62939453125e-09,
10404
+ "loss": 0.2685,
10405
+ "step": 31725
10406
+ },
10407
+ {
10408
+ "epoch": 179.37853107344634,
10409
+ "grad_norm": 2.89276385307312,
10410
+ "learning_rate": 7.62939453125e-09,
10411
+ "loss": 0.2531,
10412
+ "step": 31750
10413
+ },
10414
+ {
10415
+ "epoch": 179.37853107344634,
10416
+ "eval_asd": 10.179012076926757,
10417
+ "eval_dice": 0.7920001397486518,
10418
+ "eval_hd95": 30.8769639366725,
10419
+ "eval_jaccard": 0.6975573153606285,
10420
+ "eval_loss": 0.3459547460079193,
10421
+ "eval_runtime": 5.0953,
10422
+ "eval_samples_per_second": 51.028,
10423
+ "eval_steps_per_second": 12.757,
10424
+ "step": 31750
10425
  }
10426
  ],
10427
  "logging_steps": 25,