aee4 commited on
Commit
3149591
·
verified ·
1 Parent(s): 50c1927

Training in progress, step 7000, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:15816a6f6b36555f6ecd628cbdfe22b603bde1b7c3abc6c0a84f92e0abdc2cd6
3
  size 24995616
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53dc020b8cd2d3893ca1bfadebb967b6315fba2e25acd6f22a48a11ce668bb9b
3
  size 24995616
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c7f1184ba45991b7126ffdd98444e70154b8049a5de0ed6eebb272e8ceb6fa4
3
  size 49993547
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddbe6f4194ab9c0eaaab68e9191e7491742fddb3001f661c43982ed7dcd2f103
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:ef9acad5dfe6355012be16c2854f2d692974d86e83413f9cfdf1067fc122d44c
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d87bd3f15dcb8032d69873d42adc3da815ef2633016c90a44a9a2ae2ea8f94d
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3326d11ec8c0873ad769ec8c5134fca32533b7d5abec2c627273e0f32d2b8716
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c402afa65569dd6a20c903334eb01d95fbbb68bcc35208a657e78ada897b2992
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -2,9 +2,9 @@
2
  "best_global_step": 6750,
3
  "best_metric": 0.8330850752448713,
4
  "best_model_checkpoint": "/kaggle/working/G17_training/trainer_output/checkpoint-6750",
5
- "epoch": 31.990521327014218,
6
  "eval_steps": 250,
7
- "global_step": 6750,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -2249,6 +2249,89 @@
2249
  "eval_specificity": 0.9803297796811287,
2250
  "eval_steps_per_second": 26.264,
2251
  "step": 6750
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2252
  }
2253
  ],
2254
  "logging_steps": 25,
@@ -2263,7 +2346,7 @@
2263
  "early_stopping_threshold": 0.0
2264
  },
2265
  "attributes": {
2266
- "early_stopping_patience_counter": 0
2267
  }
2268
  },
2269
  "TrainerControl": {
 
2
  "best_global_step": 6750,
3
  "best_metric": 0.8330850752448713,
4
  "best_model_checkpoint": "/kaggle/working/G17_training/trainer_output/checkpoint-6750",
5
+ "epoch": 33.175355450236964,
6
  "eval_steps": 250,
7
+ "global_step": 7000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
2249
  "eval_specificity": 0.9803297796811287,
2250
  "eval_steps_per_second": 26.264,
2251
  "step": 6750
2252
+ },
2253
+ {
2254
+ "epoch": 32.10900473933649,
2255
+ "grad_norm": 5.636173248291016,
2256
+ "learning_rate": 0.000139478672985782,
2257
+ "loss": 0.3169,
2258
+ "step": 6775
2259
+ },
2260
+ {
2261
+ "epoch": 32.22748815165877,
2262
+ "grad_norm": 1.0934466123580933,
2263
+ "learning_rate": 0.00013888625592417062,
2264
+ "loss": 0.2385,
2265
+ "step": 6800
2266
+ },
2267
+ {
2268
+ "epoch": 32.345971563981045,
2269
+ "grad_norm": 7.592465400695801,
2270
+ "learning_rate": 0.00013829383886255922,
2271
+ "loss": 0.3178,
2272
+ "step": 6825
2273
+ },
2274
+ {
2275
+ "epoch": 32.464454976303315,
2276
+ "grad_norm": 0.9197977781295776,
2277
+ "learning_rate": 0.00013770142180094785,
2278
+ "loss": 0.2916,
2279
+ "step": 6850
2280
+ },
2281
+ {
2282
+ "epoch": 32.58293838862559,
2283
+ "grad_norm": 1.2327977418899536,
2284
+ "learning_rate": 0.00013710900473933648,
2285
+ "loss": 0.2788,
2286
+ "step": 6875
2287
+ },
2288
+ {
2289
+ "epoch": 32.70142180094787,
2290
+ "grad_norm": 1.1535913944244385,
2291
+ "learning_rate": 0.0001365165876777251,
2292
+ "loss": 0.266,
2293
+ "step": 6900
2294
+ },
2295
+ {
2296
+ "epoch": 32.81990521327014,
2297
+ "grad_norm": 3.4096062183380127,
2298
+ "learning_rate": 0.00013592417061611373,
2299
+ "loss": 0.2689,
2300
+ "step": 6925
2301
+ },
2302
+ {
2303
+ "epoch": 32.93838862559242,
2304
+ "grad_norm": 2.372750997543335,
2305
+ "learning_rate": 0.00013533175355450236,
2306
+ "loss": 0.2495,
2307
+ "step": 6950
2308
+ },
2309
+ {
2310
+ "epoch": 33.056872037914694,
2311
+ "grad_norm": 5.562926292419434,
2312
+ "learning_rate": 0.000134739336492891,
2313
+ "loss": 0.2604,
2314
+ "step": 6975
2315
+ },
2316
+ {
2317
+ "epoch": 33.175355450236964,
2318
+ "grad_norm": 4.015929222106934,
2319
+ "learning_rate": 0.0001341469194312796,
2320
+ "loss": 0.2563,
2321
+ "step": 7000
2322
+ },
2323
+ {
2324
+ "epoch": 33.175355450236964,
2325
+ "eval_dice": 0.829018473311588,
2326
+ "eval_iou": 0.7430530567698698,
2327
+ "eval_loss": 0.2998183071613312,
2328
+ "eval_precision": 0.8390963626252012,
2329
+ "eval_recall": 0.856689398152752,
2330
+ "eval_runtime": 3.9986,
2331
+ "eval_samples_per_second": 105.038,
2332
+ "eval_specificity": 0.9842851711684156,
2333
+ "eval_steps_per_second": 26.259,
2334
+ "step": 7000
2335
  }
2336
  ],
2337
  "logging_steps": 25,
 
2346
  "early_stopping_threshold": 0.0
2347
  },
2348
  "attributes": {
2349
+ "early_stopping_patience_counter": 1
2350
  }
2351
  },
2352
  "TrainerControl": {