aee4 commited on
Commit
f9671a3
·
verified ·
1 Parent(s): 7f99a6c

Training in progress, step 7500, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:297a4fd35ed1d123061e51c5711746ea953694870b846415b69c4d69b34b4a48
3
  size 24995616
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a108f117db0849c20c25b913e7597435e4e49fceb9df91d6e4cd66e76718f9c
3
  size 24995616
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1533fe775255ffe26a67ac095cef68bcd5787214cc81cd635f89988e597bf7c1
3
  size 49993547
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52c4f2c96151abfd0e2d8c793641f62de7cb8af8898b4f5183fb953d08f39fba
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:e98a4d8c0c4e29b0b758beb6399a00d56002789e50d1b86cc3bd051e439ead97
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4b46b3455ffeeacf84a21caf4dd951357daf08659b57b97c0fb2d9eb819f875
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:54e56b08becc42adf9e3984dc2ddcd5e63c10de8458ac04acc6e8bf9d7689264
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d1f6821a23e549d35e1a3f8404bd0942e351259b7dff42764723c51488ea23f
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": 34.360189573459714,
6
  "eval_steps": 250,
7
- "global_step": 7250,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -2415,6 +2415,89 @@
2415
  "eval_specificity": 0.9916211649089091,
2416
  "eval_steps_per_second": 26.215,
2417
  "step": 7250
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2418
  }
2419
  ],
2420
  "logging_steps": 25,
@@ -2429,7 +2512,7 @@
2429
  "early_stopping_threshold": 0.0
2430
  },
2431
  "attributes": {
2432
- "early_stopping_patience_counter": 2
2433
  }
2434
  },
2435
  "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": 35.54502369668246,
6
  "eval_steps": 250,
7
+ "global_step": 7500,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
2415
  "eval_specificity": 0.9916211649089091,
2416
  "eval_steps_per_second": 26.215,
2417
  "step": 7250
2418
+ },
2419
+ {
2420
+ "epoch": 34.47867298578199,
2421
+ "grad_norm": 2.7973670959472656,
2422
+ "learning_rate": 0.0001276303317535545,
2423
+ "loss": 0.2692,
2424
+ "step": 7275
2425
+ },
2426
+ {
2427
+ "epoch": 34.59715639810427,
2428
+ "grad_norm": 3.7266221046447754,
2429
+ "learning_rate": 0.00012703791469194313,
2430
+ "loss": 0.2487,
2431
+ "step": 7300
2432
+ },
2433
+ {
2434
+ "epoch": 34.71563981042654,
2435
+ "grad_norm": 1.4115891456604004,
2436
+ "learning_rate": 0.00012644549763033173,
2437
+ "loss": 0.3176,
2438
+ "step": 7325
2439
+ },
2440
+ {
2441
+ "epoch": 34.834123222748815,
2442
+ "grad_norm": 3.848600149154663,
2443
+ "learning_rate": 0.00012585308056872036,
2444
+ "loss": 0.2663,
2445
+ "step": 7350
2446
+ },
2447
+ {
2448
+ "epoch": 34.95260663507109,
2449
+ "grad_norm": 0.6887936592102051,
2450
+ "learning_rate": 0.000125260663507109,
2451
+ "loss": 0.2649,
2452
+ "step": 7375
2453
+ },
2454
+ {
2455
+ "epoch": 35.07109004739336,
2456
+ "grad_norm": 2.590745210647583,
2457
+ "learning_rate": 0.00012466824644549761,
2458
+ "loss": 0.2686,
2459
+ "step": 7400
2460
+ },
2461
+ {
2462
+ "epoch": 35.18957345971564,
2463
+ "grad_norm": 2.942915201187134,
2464
+ "learning_rate": 0.00012407582938388624,
2465
+ "loss": 0.2714,
2466
+ "step": 7425
2467
+ },
2468
+ {
2469
+ "epoch": 35.308056872037916,
2470
+ "grad_norm": 1.3223179578781128,
2471
+ "learning_rate": 0.00012348341232227487,
2472
+ "loss": 0.315,
2473
+ "step": 7450
2474
+ },
2475
+ {
2476
+ "epoch": 35.426540284360186,
2477
+ "grad_norm": 1.1740903854370117,
2478
+ "learning_rate": 0.0001228909952606635,
2479
+ "loss": 0.309,
2480
+ "step": 7475
2481
+ },
2482
+ {
2483
+ "epoch": 35.54502369668246,
2484
+ "grad_norm": 1.2406233549118042,
2485
+ "learning_rate": 0.00012229857819905213,
2486
+ "loss": 0.2489,
2487
+ "step": 7500
2488
+ },
2489
+ {
2490
+ "epoch": 35.54502369668246,
2491
+ "eval_dice": 0.8191264687947266,
2492
+ "eval_iou": 0.733062071114117,
2493
+ "eval_loss": 0.30964383482933044,
2494
+ "eval_precision": 0.8293702874855964,
2495
+ "eval_recall": 0.8540272490618607,
2496
+ "eval_runtime": 4.0129,
2497
+ "eval_samples_per_second": 104.663,
2498
+ "eval_specificity": 0.9829102752853924,
2499
+ "eval_steps_per_second": 26.166,
2500
+ "step": 7500
2501
  }
2502
  ],
2503
  "logging_steps": 25,
 
2512
  "early_stopping_threshold": 0.0
2513
  },
2514
  "attributes": {
2515
+ "early_stopping_patience_counter": 3
2516
  }
2517
  },
2518
  "TrainerControl": {