aee4 commited on
Commit
f424be1
·
verified ·
1 Parent(s): dbfb8d1

Training in progress, step 31500, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e37f910b465b56e1bc8d20f9ff416a964b569456f8a4a910ebb66581ee8bdd0a
3
  size 76153420
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dedd9aacdda348954bfbf9198afefb4e66266caa79489d13ace65b43db1a34eb
3
  size 76153420
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:76ca7d3c71f83dbd9a8ad4f763e93a3eb0b6753bd3a030e18500a0faaaee80da
3
  size 152327371
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d72bcd3ef8b9a9e0f6f4414a0a29875a214381368a85e85a6e6c3c95f0d8f69
3
  size 152327371
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:13f146793c59423e9597805cd1a13a50a20b076c62d500cc4dd13aa89eabea47
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1eb5d3edcb370711cf545dce77cd286cf5a332e6f6b1b84d670fd0cf8b7a6ca
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b734abfe5d8a81cb0b84a84897dcc97cbc43638dce90cf3c14164ab1a35d5e02
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b420740271eb81ad380f7d851e50a0acb0920fb5addeda6e7fcb98b508d375cf
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": 176.5536723163842,
6
  "eval_steps": 250,
7
- "global_step": 31250,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -10258,6 +10258,88 @@
10258
  "eval_samples_per_second": 50.493,
10259
  "eval_steps_per_second": 12.623,
10260
  "step": 31250
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
10261
  }
10262
  ],
10263
  "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": 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,
 
10258
  "eval_samples_per_second": 50.493,
10259
  "eval_steps_per_second": 12.623,
10260
  "step": 31250
10261
+ },
10262
+ {
10263
+ "epoch": 176.6949152542373,
10264
+ "grad_norm": 1.3705204725265503,
10265
+ "learning_rate": 7.62939453125e-09,
10266
+ "loss": 0.2343,
10267
+ "step": 31275
10268
+ },
10269
+ {
10270
+ "epoch": 176.8361581920904,
10271
+ "grad_norm": 1.2656540870666504,
10272
+ "learning_rate": 7.62939453125e-09,
10273
+ "loss": 0.2587,
10274
+ "step": 31300
10275
+ },
10276
+ {
10277
+ "epoch": 176.9774011299435,
10278
+ "grad_norm": 1.3624602556228638,
10279
+ "learning_rate": 7.62939453125e-09,
10280
+ "loss": 0.2464,
10281
+ "step": 31325
10282
+ },
10283
+ {
10284
+ "epoch": 177.11864406779662,
10285
+ "grad_norm": 1.7263494729995728,
10286
+ "learning_rate": 7.62939453125e-09,
10287
+ "loss": 0.2788,
10288
+ "step": 31350
10289
+ },
10290
+ {
10291
+ "epoch": 177.25988700564972,
10292
+ "grad_norm": 1.3279907703399658,
10293
+ "learning_rate": 7.62939453125e-09,
10294
+ "loss": 0.235,
10295
+ "step": 31375
10296
+ },
10297
+ {
10298
+ "epoch": 177.40112994350284,
10299
+ "grad_norm": 3.0990030765533447,
10300
+ "learning_rate": 7.62939453125e-09,
10301
+ "loss": 0.2632,
10302
+ "step": 31400
10303
+ },
10304
+ {
10305
+ "epoch": 177.54237288135593,
10306
+ "grad_norm": 1.4206148386001587,
10307
+ "learning_rate": 7.62939453125e-09,
10308
+ "loss": 0.2649,
10309
+ "step": 31425
10310
+ },
10311
+ {
10312
+ "epoch": 177.68361581920905,
10313
+ "grad_norm": 0.6275918483734131,
10314
+ "learning_rate": 7.62939453125e-09,
10315
+ "loss": 0.2501,
10316
+ "step": 31450
10317
+ },
10318
+ {
10319
+ "epoch": 177.82485875706215,
10320
+ "grad_norm": 0.529276430606842,
10321
+ "learning_rate": 7.62939453125e-09,
10322
+ "loss": 0.2542,
10323
+ "step": 31475
10324
+ },
10325
+ {
10326
+ "epoch": 177.96610169491527,
10327
+ "grad_norm": 1.1462534666061401,
10328
+ "learning_rate": 7.62939453125e-09,
10329
+ "loss": 0.2574,
10330
+ "step": 31500
10331
+ },
10332
+ {
10333
+ "epoch": 177.96610169491527,
10334
+ "eval_asd": 9.969696959335995,
10335
+ "eval_dice": 0.7924465851866783,
10336
+ "eval_hd95": 30.314947315664433,
10337
+ "eval_jaccard": 0.6986915690798318,
10338
+ "eval_loss": 0.3467029929161072,
10339
+ "eval_runtime": 5.1122,
10340
+ "eval_samples_per_second": 50.859,
10341
+ "eval_steps_per_second": 12.715,
10342
+ "step": 31500
10343
  }
10344
  ],
10345
  "logging_steps": 25,