aee4 commited on
Commit
dc5a1f2
·
verified ·
1 Parent(s): 63ee830

Training in progress, step 9000, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b33a7c03a6316094bcd94a720f3efea5e3372a23f4a476272ac4db8bfe686686
3
  size 24995616
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b3094e4463b2aee11d7b00fdf499fc5becea923c67ff8fdb28b1bf8d9c58bd5
3
  size 24995616
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2f57222a459c64708d936609c879244ed92d02e7b70279115385fc01f8eee526
3
  size 49993547
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1366213310b912b481cee09b7c79e215821c7cb53ff7bd5c9a6fdf9fd906e39
3
  size 49993547
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3975fc4d6754f467f428709b46bbf97a817e551a7a491b0d525252c1ca6bdc25
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ee34062530866a754b7d215e3569f051455e042c0dd4cfdd40d63ebd3a659e8
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:83a8a4c49c4217259f73234628d7c3baa02bfa43ce235ff8852ac20aa246ff09
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:631f01a8f155f83975aa0c5b53bc0eb0a8787a37646c3816c93a7c0986ab01d0
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": 41.46919431279621,
6
  "eval_steps": 250,
7
- "global_step": 8750,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -2913,6 +2913,89 @@
2913
  "eval_specificity": 0.9846463500194629,
2914
  "eval_steps_per_second": 26.206,
2915
  "step": 8750
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2916
  }
2917
  ],
2918
  "logging_steps": 25,
@@ -2927,7 +3010,7 @@
2927
  "early_stopping_threshold": 0.0
2928
  },
2929
  "attributes": {
2930
- "early_stopping_patience_counter": 8
2931
  }
2932
  },
2933
  "TrainerControl": {
@@ -2936,7 +3019,7 @@
2936
  "should_evaluate": false,
2937
  "should_log": false,
2938
  "should_save": true,
2939
- "should_training_stop": true
2940
  },
2941
  "attributes": {}
2942
  }
 
2
  "best_global_step": 6750,
3
  "best_metric": 0.8330850752448713,
4
  "best_model_checkpoint": "/kaggle/working/G17_training/trainer_output/checkpoint-6750",
5
+ "epoch": 42.654028436018955,
6
  "eval_steps": 250,
7
+ "global_step": 9000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
2913
  "eval_specificity": 0.9846463500194629,
2914
  "eval_steps_per_second": 26.206,
2915
  "step": 8750
2916
+ },
2917
+ {
2918
+ "epoch": 41.58767772511848,
2919
+ "grad_norm": 1.3263804912567139,
2920
+ "learning_rate": 9.208530805687204e-05,
2921
+ "loss": 0.2555,
2922
+ "step": 8775
2923
+ },
2924
+ {
2925
+ "epoch": 41.70616113744076,
2926
+ "grad_norm": 1.3473795652389526,
2927
+ "learning_rate": 9.149289099526066e-05,
2928
+ "loss": 0.2634,
2929
+ "step": 8800
2930
+ },
2931
+ {
2932
+ "epoch": 41.824644549763036,
2933
+ "grad_norm": 1.0343571901321411,
2934
+ "learning_rate": 9.090047393364928e-05,
2935
+ "loss": 0.2142,
2936
+ "step": 8825
2937
+ },
2938
+ {
2939
+ "epoch": 41.943127962085306,
2940
+ "grad_norm": 0.4155985116958618,
2941
+ "learning_rate": 9.03080568720379e-05,
2942
+ "loss": 0.2388,
2943
+ "step": 8850
2944
+ },
2945
+ {
2946
+ "epoch": 42.06161137440758,
2947
+ "grad_norm": 2.6496362686157227,
2948
+ "learning_rate": 8.971563981042653e-05,
2949
+ "loss": 0.2905,
2950
+ "step": 8875
2951
+ },
2952
+ {
2953
+ "epoch": 42.18009478672986,
2954
+ "grad_norm": 2.962233543395996,
2955
+ "learning_rate": 8.912322274881517e-05,
2956
+ "loss": 0.2611,
2957
+ "step": 8900
2958
+ },
2959
+ {
2960
+ "epoch": 42.29857819905213,
2961
+ "grad_norm": 0.9569677114486694,
2962
+ "learning_rate": 8.853080568720378e-05,
2963
+ "loss": 0.2516,
2964
+ "step": 8925
2965
+ },
2966
+ {
2967
+ "epoch": 42.41706161137441,
2968
+ "grad_norm": 0.6476653218269348,
2969
+ "learning_rate": 8.793838862559241e-05,
2970
+ "loss": 0.2392,
2971
+ "step": 8950
2972
+ },
2973
+ {
2974
+ "epoch": 42.535545023696685,
2975
+ "grad_norm": 1.9572572708129883,
2976
+ "learning_rate": 8.734597156398103e-05,
2977
+ "loss": 0.2564,
2978
+ "step": 8975
2979
+ },
2980
+ {
2981
+ "epoch": 42.654028436018955,
2982
+ "grad_norm": 1.9159420728683472,
2983
+ "learning_rate": 8.675355450236965e-05,
2984
+ "loss": 0.2226,
2985
+ "step": 9000
2986
+ },
2987
+ {
2988
+ "epoch": 42.654028436018955,
2989
+ "eval_dice": 0.8305104479197745,
2990
+ "eval_iou": 0.7500260790332562,
2991
+ "eval_loss": 0.29034939408302307,
2992
+ "eval_precision": 0.8825015404218443,
2993
+ "eval_recall": 0.8280170800106101,
2994
+ "eval_runtime": 3.9657,
2995
+ "eval_samples_per_second": 105.907,
2996
+ "eval_specificity": 0.9896662973121493,
2997
+ "eval_steps_per_second": 26.477,
2998
+ "step": 9000
2999
  }
3000
  ],
3001
  "logging_steps": 25,
 
3010
  "early_stopping_threshold": 0.0
3011
  },
3012
  "attributes": {
3013
+ "early_stopping_patience_counter": 1
3014
  }
3015
  },
3016
  "TrainerControl": {
 
3019
  "should_evaluate": false,
3020
  "should_log": false,
3021
  "should_save": true,
3022
+ "should_training_stop": false
3023
  },
3024
  "attributes": {}
3025
  }