aee4 commited on
Commit
ee47c12
·
verified ·
1 Parent(s): 5548b2a

Training in progress, step 28500, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5d2e0b72ecfef259626389d372140189f305fb334c72bb54c21c852563d135c6
3
  size 76153420
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13920c61c2d8b4abf45f3c6bc1942d7ca707ed62c52c9f8f84a168be15e24c54
3
  size 76153420
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f67a68c43643a6709bd0d7e4b80f492d69ec5fab884d4d2b13384a4c5de799f
3
  size 152327371
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ea2b43e889f90dc3e37402c29466b5a58de9be2902617b492ff0b5c6004914e
3
  size 152327371
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:35eb65031bbaf87296bc1af82f0e4c1cca31517e853f8c848f65c220945b183f
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:597b46883f0f0db427c56a5a3074dca6e6dd7c02754509311acf0d0c7b7c1e75
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:150822977e05de7f4b84498a822120f935757b6a9ffe817525c136b719ac8dfc
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad687cc833a102a219d1deceb07e92491bc411c93f49421a8e10df28a99c082b
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": 159.6045197740113,
6
  "eval_steps": 250,
7
- "global_step": 28250,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -9274,6 +9274,88 @@
9274
  "eval_samples_per_second": 50.846,
9275
  "eval_steps_per_second": 12.712,
9276
  "step": 28250
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9277
  }
9278
  ],
9279
  "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": 161.01694915254237,
6
  "eval_steps": 250,
7
+ "global_step": 28500,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
9274
  "eval_samples_per_second": 50.846,
9275
  "eval_steps_per_second": 12.712,
9276
  "step": 28250
9277
+ },
9278
+ {
9279
+ "epoch": 159.74576271186442,
9280
+ "grad_norm": 1.9132059812545776,
9281
+ "learning_rate": 3.0517578125e-08,
9282
+ "loss": 0.2641,
9283
+ "step": 28275
9284
+ },
9285
+ {
9286
+ "epoch": 159.8870056497175,
9287
+ "grad_norm": 0.8357412815093994,
9288
+ "learning_rate": 3.0517578125e-08,
9289
+ "loss": 0.2584,
9290
+ "step": 28300
9291
+ },
9292
+ {
9293
+ "epoch": 160.02824858757063,
9294
+ "grad_norm": 0.9180699586868286,
9295
+ "learning_rate": 1.52587890625e-08,
9296
+ "loss": 0.2753,
9297
+ "step": 28325
9298
+ },
9299
+ {
9300
+ "epoch": 160.16949152542372,
9301
+ "grad_norm": 1.9907315969467163,
9302
+ "learning_rate": 1.52587890625e-08,
9303
+ "loss": 0.2401,
9304
+ "step": 28350
9305
+ },
9306
+ {
9307
+ "epoch": 160.31073446327684,
9308
+ "grad_norm": 2.6685564517974854,
9309
+ "learning_rate": 1.52587890625e-08,
9310
+ "loss": 0.2751,
9311
+ "step": 28375
9312
+ },
9313
+ {
9314
+ "epoch": 160.45197740112994,
9315
+ "grad_norm": 3.085446834564209,
9316
+ "learning_rate": 1.52587890625e-08,
9317
+ "loss": 0.2608,
9318
+ "step": 28400
9319
+ },
9320
+ {
9321
+ "epoch": 160.59322033898306,
9322
+ "grad_norm": 1.4601061344146729,
9323
+ "learning_rate": 1.52587890625e-08,
9324
+ "loss": 0.2614,
9325
+ "step": 28425
9326
+ },
9327
+ {
9328
+ "epoch": 160.73446327683615,
9329
+ "grad_norm": 1.8298653364181519,
9330
+ "learning_rate": 1.52587890625e-08,
9331
+ "loss": 0.2565,
9332
+ "step": 28450
9333
+ },
9334
+ {
9335
+ "epoch": 160.87570621468927,
9336
+ "grad_norm": 1.5453938245773315,
9337
+ "learning_rate": 1.52587890625e-08,
9338
+ "loss": 0.257,
9339
+ "step": 28475
9340
+ },
9341
+ {
9342
+ "epoch": 161.01694915254237,
9343
+ "grad_norm": 2.2380871772766113,
9344
+ "learning_rate": 1.52587890625e-08,
9345
+ "loss": 0.2452,
9346
+ "step": 28500
9347
+ },
9348
+ {
9349
+ "epoch": 161.01694915254237,
9350
+ "eval_asd": 10.138622435979396,
9351
+ "eval_dice": 0.7903840422983693,
9352
+ "eval_hd95": 31.278252063301554,
9353
+ "eval_jaccard": 0.6961206258040024,
9354
+ "eval_loss": 0.3500337600708008,
9355
+ "eval_runtime": 5.1366,
9356
+ "eval_samples_per_second": 50.617,
9357
+ "eval_steps_per_second": 12.654,
9358
+ "step": 28500
9359
  }
9360
  ],
9361
  "logging_steps": 25,