aee4 commited on
Commit
5efe207
·
verified ·
1 Parent(s): 9a187ba

Training in progress, step 34500, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a52a80efabfb02c2766e3b6fed8178bf1e3420a1ad3f5095e1718445c1b02f4b
3
  size 76153420
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df48f3da88cc053504d2cae4febd01448212d2bb38d9db28e68c9ea2247fdfb3
3
  size 76153420
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ba5469c2fe5d77b747e9959705a743023a8cb4032d30ffa36e094f75943b62d3
3
  size 152327371
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b3534efc3270214c2b368dacdb4b515ef12bdbbc4e20d54faa05b6a6e14f0cb
3
  size 152327371
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:38e289876bb0bb83024a660c49dc0549b9c7e6849ec628afac69af62772bc1bb
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39897af14e11c1a12d582090be09c2a4d728f65a236e152a92bb9ee752dc9d1b
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:93820086d109aacd918c31c3c646a145c713246798f31b807cb4454bc07f3820
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfa8fa70c80047c0b9f131b3217bbc1baaa6f296af5e7d3c469ae2a4ce111749
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": 193.50282485875707,
6
  "eval_steps": 250,
7
- "global_step": 34250,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -11242,6 +11242,88 @@
11242
  "eval_samples_per_second": 50.861,
11243
  "eval_steps_per_second": 12.715,
11244
  "step": 34250
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11245
  }
11246
  ],
11247
  "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": 194.91525423728814,
6
  "eval_steps": 250,
7
+ "global_step": 34500,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
11242
  "eval_samples_per_second": 50.861,
11243
  "eval_steps_per_second": 12.715,
11244
  "step": 34250
11245
+ },
11246
+ {
11247
+ "epoch": 193.64406779661016,
11248
+ "grad_norm": 0.8605188727378845,
11249
+ "learning_rate": 1.9073486328125e-09,
11250
+ "loss": 0.2405,
11251
+ "step": 34275
11252
+ },
11253
+ {
11254
+ "epoch": 193.78531073446328,
11255
+ "grad_norm": 1.2505837678909302,
11256
+ "learning_rate": 1.9073486328125e-09,
11257
+ "loss": 0.2453,
11258
+ "step": 34300
11259
+ },
11260
+ {
11261
+ "epoch": 193.92655367231637,
11262
+ "grad_norm": 0.9287299513816833,
11263
+ "learning_rate": 1.9073486328125e-09,
11264
+ "loss": 0.2476,
11265
+ "step": 34325
11266
+ },
11267
+ {
11268
+ "epoch": 194.0677966101695,
11269
+ "grad_norm": 1.4540334939956665,
11270
+ "learning_rate": 1.9073486328125e-09,
11271
+ "loss": 0.2583,
11272
+ "step": 34350
11273
+ },
11274
+ {
11275
+ "epoch": 194.2090395480226,
11276
+ "grad_norm": 1.361136555671692,
11277
+ "learning_rate": 1.9073486328125e-09,
11278
+ "loss": 0.2733,
11279
+ "step": 34375
11280
+ },
11281
+ {
11282
+ "epoch": 194.3502824858757,
11283
+ "grad_norm": 2.6395156383514404,
11284
+ "learning_rate": 1.9073486328125e-09,
11285
+ "loss": 0.2579,
11286
+ "step": 34400
11287
+ },
11288
+ {
11289
+ "epoch": 194.4915254237288,
11290
+ "grad_norm": 1.0137184858322144,
11291
+ "learning_rate": 1.9073486328125e-09,
11292
+ "loss": 0.2331,
11293
+ "step": 34425
11294
+ },
11295
+ {
11296
+ "epoch": 194.63276836158192,
11297
+ "grad_norm": 1.529662847518921,
11298
+ "learning_rate": 1.9073486328125e-09,
11299
+ "loss": 0.272,
11300
+ "step": 34450
11301
+ },
11302
+ {
11303
+ "epoch": 194.77401129943502,
11304
+ "grad_norm": 1.5772504806518555,
11305
+ "learning_rate": 1.9073486328125e-09,
11306
+ "loss": 0.2407,
11307
+ "step": 34475
11308
+ },
11309
+ {
11310
+ "epoch": 194.91525423728814,
11311
+ "grad_norm": 1.5300109386444092,
11312
+ "learning_rate": 1.9073486328125e-09,
11313
+ "loss": 0.2514,
11314
+ "step": 34500
11315
+ },
11316
+ {
11317
+ "epoch": 194.91525423728814,
11318
+ "eval_asd": 9.99685792602786,
11319
+ "eval_dice": 0.7916359885395614,
11320
+ "eval_hd95": 30.694877742734196,
11321
+ "eval_jaccard": 0.6978240407658445,
11322
+ "eval_loss": 0.3472123146057129,
11323
+ "eval_runtime": 5.1214,
11324
+ "eval_samples_per_second": 50.767,
11325
+ "eval_steps_per_second": 12.692,
11326
+ "step": 34500
11327
  }
11328
  ],
11329
  "logging_steps": 25,