aee4 commited on
Commit
9c69386
·
verified ·
1 Parent(s): 50846ca

Training in progress, step 12250, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a84677645787821cf00465dd9ab3ef72a4faf8501805c93800d4f02a2a5a121e
3
  size 24995616
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb83ede8c0deca402ab087e4b16160023d10302f114f209880b20ab327f3cca9
3
  size 24995616
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:16b1e59744bab368988e3457c6cb3359dfc156c04508408b72ebedde10b02b1e
3
  size 49993547
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63637056ae4f2e3221abde7568fc659920f6e4ae57ae0fca9af892be4876f8d4
3
  size 49993547
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:28494c3041d98dbcb14f8e8a7ed3cf88db042ec3db7b93f94070a85bb863bc96
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d701f47e319ba7f92c6db14b6e2d0b5008b605c0be1c072bc0820b39a36a7394
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0622c92f08fd12b122eff11afe6c887783d3648a4425c7e425b4864c2a368f9e
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af62e79aed357a259b43bfa38d78819ea14ffaceca979ecafe531cfa838a875c
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -2,9 +2,9 @@
2
  "best_global_step": 10000,
3
  "best_metric": 0.8396956422654931,
4
  "best_model_checkpoint": "/kaggle/working/G17_training/trainer_output/checkpoint-10000",
5
- "epoch": 56.872037914691944,
6
  "eval_steps": 250,
7
- "global_step": 12000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -3992,6 +3992,89 @@
3992
  "eval_specificity": 0.98814271282744,
3993
  "eval_steps_per_second": 26.105,
3994
  "step": 12000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3995
  }
3996
  ],
3997
  "logging_steps": 25,
@@ -4006,7 +4089,7 @@
4006
  "early_stopping_threshold": 0.0
4007
  },
4008
  "attributes": {
4009
- "early_stopping_patience_counter": 8
4010
  }
4011
  },
4012
  "TrainerControl": {
@@ -4015,7 +4098,7 @@
4015
  "should_evaluate": false,
4016
  "should_log": false,
4017
  "should_save": true,
4018
- "should_training_stop": true
4019
  },
4020
  "attributes": {}
4021
  }
 
2
  "best_global_step": 10000,
3
  "best_metric": 0.8396956422654931,
4
  "best_model_checkpoint": "/kaggle/working/G17_training/trainer_output/checkpoint-10000",
5
+ "epoch": 58.056872037914694,
6
  "eval_steps": 250,
7
+ "global_step": 12250,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
3992
  "eval_specificity": 0.98814271282744,
3993
  "eval_steps_per_second": 26.105,
3994
  "step": 12000
3995
+ },
3996
+ {
3997
+ "epoch": 56.99052132701422,
3998
+ "grad_norm": 3.2021896839141846,
3999
+ "learning_rate": 1.5071090047393363e-05,
4000
+ "loss": 0.2225,
4001
+ "step": 12025
4002
+ },
4003
+ {
4004
+ "epoch": 57.10900473933649,
4005
+ "grad_norm": 2.9559223651885986,
4006
+ "learning_rate": 1.447867298578199e-05,
4007
+ "loss": 0.1925,
4008
+ "step": 12050
4009
+ },
4010
+ {
4011
+ "epoch": 57.22748815165877,
4012
+ "grad_norm": 2.2703027725219727,
4013
+ "learning_rate": 1.3886255924170615e-05,
4014
+ "loss": 0.2583,
4015
+ "step": 12075
4016
+ },
4017
+ {
4018
+ "epoch": 57.345971563981045,
4019
+ "grad_norm": 2.6159918308258057,
4020
+ "learning_rate": 1.3293838862559241e-05,
4021
+ "loss": 0.2087,
4022
+ "step": 12100
4023
+ },
4024
+ {
4025
+ "epoch": 57.464454976303315,
4026
+ "grad_norm": 1.8098419904708862,
4027
+ "learning_rate": 1.2701421800947868e-05,
4028
+ "loss": 0.2226,
4029
+ "step": 12125
4030
+ },
4031
+ {
4032
+ "epoch": 57.58293838862559,
4033
+ "grad_norm": 1.6202045679092407,
4034
+ "learning_rate": 1.210900473933649e-05,
4035
+ "loss": 0.2119,
4036
+ "step": 12150
4037
+ },
4038
+ {
4039
+ "epoch": 57.70142180094787,
4040
+ "grad_norm": 0.47480809688568115,
4041
+ "learning_rate": 1.1516587677725117e-05,
4042
+ "loss": 0.2003,
4043
+ "step": 12175
4044
+ },
4045
+ {
4046
+ "epoch": 57.81990521327014,
4047
+ "grad_norm": 2.292057991027832,
4048
+ "learning_rate": 1.0924170616113742e-05,
4049
+ "loss": 0.1892,
4050
+ "step": 12200
4051
+ },
4052
+ {
4053
+ "epoch": 57.93838862559242,
4054
+ "grad_norm": 1.525924563407898,
4055
+ "learning_rate": 1.0331753554502368e-05,
4056
+ "loss": 0.211,
4057
+ "step": 12225
4058
+ },
4059
+ {
4060
+ "epoch": 58.056872037914694,
4061
+ "grad_norm": 1.9131159782409668,
4062
+ "learning_rate": 9.739336492890995e-06,
4063
+ "loss": 0.2523,
4064
+ "step": 12250
4065
+ },
4066
+ {
4067
+ "epoch": 58.056872037914694,
4068
+ "eval_dice": 0.8319437839931644,
4069
+ "eval_iou": 0.7533251756894057,
4070
+ "eval_loss": 0.29047533869743347,
4071
+ "eval_precision": 0.8658964547328264,
4072
+ "eval_recall": 0.8451036792670125,
4073
+ "eval_runtime": 3.9961,
4074
+ "eval_samples_per_second": 105.102,
4075
+ "eval_specificity": 0.9870378125679844,
4076
+ "eval_steps_per_second": 26.276,
4077
+ "step": 12250
4078
  }
4079
  ],
4080
  "logging_steps": 25,
 
4089
  "early_stopping_threshold": 0.0
4090
  },
4091
  "attributes": {
4092
+ "early_stopping_patience_counter": 1
4093
  }
4094
  },
4095
  "TrainerControl": {
 
4098
  "should_evaluate": false,
4099
  "should_log": false,
4100
  "should_save": true,
4101
+ "should_training_stop": false
4102
  },
4103
  "attributes": {}
4104
  }