aee4 commited on
Commit
f22d887
·
verified ·
1 Parent(s): 6354b27

Training in progress, step 10000, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b180fc6d30dcf9abb50b34fcee909c23aadcbeb2673aff09639d0d9e61422359
3
  size 24995616
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2ed21ae35e3800e155600064f0537e7d53a82ceff85c753854caddcfd967cc5
3
  size 24995616
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fd63bda680518b9c4f3523ed26858fd9ae9cff5630163f1e5eeb714b8ed357a9
3
  size 49993547
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9ac24dc7542c921cbb9dc421392b94c58297151767adc33b6767e7667e9a11d
3
  size 49993547
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e7210af27fe26778f7d9ac5f4057eac07457a093e7a0242f3d26fcc633de849c
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6dbb90f03320796635b26281f9a3921d95277c32e6673e792faf729c478a88b
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:74cc218938d202b7443905d3c4e4f0a010b063ba9a4eb1e2105a96b666dc68b1
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23335f3b21225accd4782ef3c4a924d72aff54feef3d38251342660850309f15
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "best_global_step": 9250,
3
- "best_metric": 0.838824375147426,
4
- "best_model_checkpoint": "/kaggle/working/G17_training/trainer_output/checkpoint-9250",
5
- "epoch": 46.208530805687204,
6
  "eval_steps": 250,
7
- "global_step": 9750,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -3245,6 +3245,89 @@
3245
  "eval_specificity": 0.9855094003578792,
3246
  "eval_steps_per_second": 26.25,
3247
  "step": 9750
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3248
  }
3249
  ],
3250
  "logging_steps": 25,
@@ -3259,7 +3342,7 @@
3259
  "early_stopping_threshold": 0.0
3260
  },
3261
  "attributes": {
3262
- "early_stopping_patience_counter": 2
3263
  }
3264
  },
3265
  "TrainerControl": {
 
1
  {
2
+ "best_global_step": 10000,
3
+ "best_metric": 0.8403776925789292,
4
+ "best_model_checkpoint": "/kaggle/working/G17_training/trainer_output/checkpoint-10000",
5
+ "epoch": 47.39336492890995,
6
  "eval_steps": 250,
7
+ "global_step": 10000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
3245
  "eval_specificity": 0.9855094003578792,
3246
  "eval_steps_per_second": 26.25,
3247
  "step": 9750
3248
+ },
3249
+ {
3250
+ "epoch": 46.32701421800948,
3251
+ "grad_norm": 1.6559125185012817,
3252
+ "learning_rate": 6.838862559241706e-05,
3253
+ "loss": 0.2237,
3254
+ "step": 9775
3255
+ },
3256
+ {
3257
+ "epoch": 46.44549763033175,
3258
+ "grad_norm": 1.5927103757858276,
3259
+ "learning_rate": 6.779620853080569e-05,
3260
+ "loss": 0.2192,
3261
+ "step": 9800
3262
+ },
3263
+ {
3264
+ "epoch": 46.56398104265403,
3265
+ "grad_norm": 9.687053680419922,
3266
+ "learning_rate": 6.72037914691943e-05,
3267
+ "loss": 0.2472,
3268
+ "step": 9825
3269
+ },
3270
+ {
3271
+ "epoch": 46.682464454976305,
3272
+ "grad_norm": 2.2457642555236816,
3273
+ "learning_rate": 6.661137440758293e-05,
3274
+ "loss": 0.255,
3275
+ "step": 9850
3276
+ },
3277
+ {
3278
+ "epoch": 46.800947867298575,
3279
+ "grad_norm": 10.048160552978516,
3280
+ "learning_rate": 6.601895734597156e-05,
3281
+ "loss": 0.2149,
3282
+ "step": 9875
3283
+ },
3284
+ {
3285
+ "epoch": 46.91943127962085,
3286
+ "grad_norm": 1.5694763660430908,
3287
+ "learning_rate": 6.542654028436019e-05,
3288
+ "loss": 0.2838,
3289
+ "step": 9900
3290
+ },
3291
+ {
3292
+ "epoch": 47.03791469194313,
3293
+ "grad_norm": 2.075925827026367,
3294
+ "learning_rate": 6.483412322274881e-05,
3295
+ "loss": 0.2328,
3296
+ "step": 9925
3297
+ },
3298
+ {
3299
+ "epoch": 47.156398104265406,
3300
+ "grad_norm": 3.465050220489502,
3301
+ "learning_rate": 6.424170616113743e-05,
3302
+ "loss": 0.2223,
3303
+ "step": 9950
3304
+ },
3305
+ {
3306
+ "epoch": 47.274881516587676,
3307
+ "grad_norm": 0.4745011627674103,
3308
+ "learning_rate": 6.364928909952606e-05,
3309
+ "loss": 0.1925,
3310
+ "step": 9975
3311
+ },
3312
+ {
3313
+ "epoch": 47.39336492890995,
3314
+ "grad_norm": 1.6556150913238525,
3315
+ "learning_rate": 6.305687203791468e-05,
3316
+ "loss": 0.243,
3317
+ "step": 10000
3318
+ },
3319
+ {
3320
+ "epoch": 47.39336492890995,
3321
+ "eval_dice": 0.8403776925789292,
3322
+ "eval_iou": 0.7570883607364053,
3323
+ "eval_loss": 0.28017136454582214,
3324
+ "eval_precision": 0.8452902582706101,
3325
+ "eval_recall": 0.8726460354149849,
3326
+ "eval_runtime": 4.0217,
3327
+ "eval_samples_per_second": 104.434,
3328
+ "eval_specificity": 0.9828701914870307,
3329
+ "eval_steps_per_second": 26.108,
3330
+ "step": 10000
3331
  }
3332
  ],
3333
  "logging_steps": 25,
 
3342
  "early_stopping_threshold": 0.0
3343
  },
3344
  "attributes": {
3345
+ "early_stopping_patience_counter": 0
3346
  }
3347
  },
3348
  "TrainerControl": {