aee4 commited on
Commit
6fb8332
·
verified ·
1 Parent(s): a9294cd

Training in progress, step 9250, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4fd5b4ae808fdb2752f49379ad06420f8f5a81937496f0ed1d1a900e3a856909
3
  size 24995616
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb0c23dff6bd9220c73ba4da223046b8097e761c55cc14221709a7c434fa881e
3
  size 24995616
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:de0464ac57aa359b6eb57b5a1e897f169f45ce3a1bcea3940fe5021434e98bed
3
  size 49993547
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b6cb0d971f152771d1d4d134c8321e0dbc6e6d7b02a3ea5dcde686a7f608855
3
  size 49993547
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1ee34062530866a754b7d215e3569f051455e042c0dd4cfdd40d63ebd3a659e8
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56b5277cd7bffb656bc0ecc1846b211f3bcdacf429f47cb6024198d6634c591d
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:631f01a8f155f83975aa0c5b53bc0eb0a8787a37646c3816c93a7c0986ab01d0
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd52c170da3e34004bdf2fad6595e20d1abfe37157f551534d57687fa82919c5
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -1,10 +1,10 @@
1
  {
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,
@@ -2996,6 +2996,89 @@
2996
  "eval_specificity": 0.990112645359611,
2997
  "eval_steps_per_second": 26.082,
2998
  "step": 9000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2999
  }
3000
  ],
3001
  "logging_steps": 25,
@@ -3010,7 +3093,7 @@
3010
  "early_stopping_threshold": 0.0
3011
  },
3012
  "attributes": {
3013
- "early_stopping_patience_counter": 3
3014
  }
3015
  },
3016
  "TrainerControl": {
 
1
  {
2
+ "best_global_step": 9250,
3
+ "best_metric": 0.8331254935254058,
4
+ "best_model_checkpoint": "/kaggle/working/G17_training/trainer_output/checkpoint-9250",
5
+ "epoch": 43.838862559241704,
6
  "eval_steps": 250,
7
+ "global_step": 9250,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
2996
  "eval_specificity": 0.990112645359611,
2997
  "eval_steps_per_second": 26.082,
2998
  "step": 9000
2999
+ },
3000
+ {
3001
+ "epoch": 42.77251184834123,
3002
+ "grad_norm": 1.2376387119293213,
3003
+ "learning_rate": 8.61611374407583e-05,
3004
+ "loss": 0.275,
3005
+ "step": 9025
3006
+ },
3007
+ {
3008
+ "epoch": 42.89099526066351,
3009
+ "grad_norm": 1.3053178787231445,
3010
+ "learning_rate": 8.556872037914691e-05,
3011
+ "loss": 0.2477,
3012
+ "step": 9050
3013
+ },
3014
+ {
3015
+ "epoch": 43.00947867298578,
3016
+ "grad_norm": 0.9519197344779968,
3017
+ "learning_rate": 8.497630331753554e-05,
3018
+ "loss": 0.2308,
3019
+ "step": 9075
3020
+ },
3021
+ {
3022
+ "epoch": 43.127962085308056,
3023
+ "grad_norm": 1.6234074831008911,
3024
+ "learning_rate": 8.438388625592417e-05,
3025
+ "loss": 0.229,
3026
+ "step": 9100
3027
+ },
3028
+ {
3029
+ "epoch": 43.24644549763033,
3030
+ "grad_norm": 0.8277037143707275,
3031
+ "learning_rate": 8.379146919431278e-05,
3032
+ "loss": 0.2196,
3033
+ "step": 9125
3034
+ },
3035
+ {
3036
+ "epoch": 43.36492890995261,
3037
+ "grad_norm": 3.1412487030029297,
3038
+ "learning_rate": 8.319905213270142e-05,
3039
+ "loss": 0.2717,
3040
+ "step": 9150
3041
+ },
3042
+ {
3043
+ "epoch": 43.48341232227488,
3044
+ "grad_norm": 0.7409705519676208,
3045
+ "learning_rate": 8.260663507109004e-05,
3046
+ "loss": 0.2374,
3047
+ "step": 9175
3048
+ },
3049
+ {
3050
+ "epoch": 43.60189573459716,
3051
+ "grad_norm": 4.343459129333496,
3052
+ "learning_rate": 8.201421800947867e-05,
3053
+ "loss": 0.2551,
3054
+ "step": 9200
3055
+ },
3056
+ {
3057
+ "epoch": 43.720379146919434,
3058
+ "grad_norm": 14.049575805664062,
3059
+ "learning_rate": 8.14218009478673e-05,
3060
+ "loss": 0.2195,
3061
+ "step": 9225
3062
+ },
3063
+ {
3064
+ "epoch": 43.838862559241704,
3065
+ "grad_norm": 0.43131211400032043,
3066
+ "learning_rate": 8.082938388625591e-05,
3067
+ "loss": 0.2468,
3068
+ "step": 9250
3069
+ },
3070
+ {
3071
+ "epoch": 43.838862559241704,
3072
+ "eval_dice": 0.8331254935254058,
3073
+ "eval_iou": 0.7514759957138237,
3074
+ "eval_loss": 0.29890671372413635,
3075
+ "eval_precision": 0.8791162248825162,
3076
+ "eval_recall": 0.8301214565261319,
3077
+ "eval_runtime": 4.0211,
3078
+ "eval_samples_per_second": 104.45,
3079
+ "eval_specificity": 0.9897418947828769,
3080
+ "eval_steps_per_second": 26.112,
3081
+ "step": 9250
3082
  }
3083
  ],
3084
  "logging_steps": 25,
 
3093
  "early_stopping_threshold": 0.0
3094
  },
3095
  "attributes": {
3096
+ "early_stopping_patience_counter": 0
3097
  }
3098
  },
3099
  "TrainerControl": {