aee4 commited on
Commit
2ff10c4
·
verified ·
1 Parent(s): cacb4cf

Training in progress, step 8250, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:57c3a806ceb57a603185c329dfce7c73fe176d2608f2afeea558faef3de197ae
3
  size 24995616
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee8dd2a1c1e7fd30b8196dda6f5d6e5e487468a8b6d03cc949529afe003fbe4f
3
  size 24995616
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:386688408327994b0b32fec15565593fee297461fb7ee5b1d929d8d80a1e6692
3
  size 49993547
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:681f021f756e0c8ef1ca0691d0031608756fd298badda7759f7a58624bd0e446
3
  size 49993547
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:19b7a514d05f6a7c89ccb1853511875a242ed4e21ec8e66d0ff6d1045bbd0cf7
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e941508923cd238a158e089701c3a5d9237a6f100cb9cc013831ed50af3f4129
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:34b61eb094715052b9ea197e43838a1241561d6b263cefb944c409d984ff663c
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff8ed4f157a95beb6e874446159aa1cfe59db7ea884d28ba3f5480ea61c0ce93
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": 37.91469194312796,
6
  "eval_steps": 250,
7
- "global_step": 8000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -2664,6 +2664,89 @@
2664
  "eval_specificity": 0.9881697620252113,
2665
  "eval_steps_per_second": 26.169,
2666
  "step": 8000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2667
  }
2668
  ],
2669
  "logging_steps": 25,
@@ -2678,7 +2761,7 @@
2678
  "early_stopping_threshold": 0.0
2679
  },
2680
  "attributes": {
2681
- "early_stopping_patience_counter": 5
2682
  }
2683
  },
2684
  "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": 39.09952606635071,
6
  "eval_steps": 250,
7
+ "global_step": 8250,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
2664
  "eval_specificity": 0.9881697620252113,
2665
  "eval_steps_per_second": 26.169,
2666
  "step": 8000
2667
+ },
2668
+ {
2669
+ "epoch": 38.03317535545024,
2670
+ "grad_norm": 3.505401372909546,
2671
+ "learning_rate": 0.00010985781990521326,
2672
+ "loss": 0.2645,
2673
+ "step": 8025
2674
+ },
2675
+ {
2676
+ "epoch": 38.15165876777251,
2677
+ "grad_norm": 9.370362281799316,
2678
+ "learning_rate": 0.00010926540284360189,
2679
+ "loss": 0.2553,
2680
+ "step": 8050
2681
+ },
2682
+ {
2683
+ "epoch": 38.27014218009479,
2684
+ "grad_norm": 2.0583865642547607,
2685
+ "learning_rate": 0.00010867298578199051,
2686
+ "loss": 0.2419,
2687
+ "step": 8075
2688
+ },
2689
+ {
2690
+ "epoch": 38.388625592417064,
2691
+ "grad_norm": 0.5414301753044128,
2692
+ "learning_rate": 0.00010808056872037914,
2693
+ "loss": 0.2557,
2694
+ "step": 8100
2695
+ },
2696
+ {
2697
+ "epoch": 38.507109004739334,
2698
+ "grad_norm": 8.323583602905273,
2699
+ "learning_rate": 0.00010748815165876776,
2700
+ "loss": 0.3078,
2701
+ "step": 8125
2702
+ },
2703
+ {
2704
+ "epoch": 38.62559241706161,
2705
+ "grad_norm": 5.577996730804443,
2706
+ "learning_rate": 0.00010689573459715639,
2707
+ "loss": 0.2701,
2708
+ "step": 8150
2709
+ },
2710
+ {
2711
+ "epoch": 38.74407582938389,
2712
+ "grad_norm": 3.2807199954986572,
2713
+ "learning_rate": 0.00010630331753554502,
2714
+ "loss": 0.2424,
2715
+ "step": 8175
2716
+ },
2717
+ {
2718
+ "epoch": 38.86255924170616,
2719
+ "grad_norm": 1.8570042848587036,
2720
+ "learning_rate": 0.00010571090047393363,
2721
+ "loss": 0.2508,
2722
+ "step": 8200
2723
+ },
2724
+ {
2725
+ "epoch": 38.981042654028435,
2726
+ "grad_norm": 1.1301829814910889,
2727
+ "learning_rate": 0.00010511848341232226,
2728
+ "loss": 0.2554,
2729
+ "step": 8225
2730
+ },
2731
+ {
2732
+ "epoch": 39.09952606635071,
2733
+ "grad_norm": 2.6987528800964355,
2734
+ "learning_rate": 0.00010452606635071089,
2735
+ "loss": 0.2733,
2736
+ "step": 8250
2737
+ },
2738
+ {
2739
+ "epoch": 39.09952606635071,
2740
+ "eval_dice": 0.826025449067974,
2741
+ "eval_iou": 0.7461114951820224,
2742
+ "eval_loss": 0.29837414622306824,
2743
+ "eval_precision": 0.8715382479972166,
2744
+ "eval_recall": 0.8288175320710666,
2745
+ "eval_runtime": 4.02,
2746
+ "eval_samples_per_second": 104.479,
2747
+ "eval_specificity": 0.9887285001486302,
2748
+ "eval_steps_per_second": 26.12,
2749
+ "step": 8250
2750
  }
2751
  ],
2752
  "logging_steps": 25,
 
2761
  "early_stopping_threshold": 0.0
2762
  },
2763
  "attributes": {
2764
+ "early_stopping_patience_counter": 6
2765
  }
2766
  },
2767
  "TrainerControl": {