aee4 commited on
Commit
bd52ff8
·
verified ·
1 Parent(s): 5d618f9

Training in progress, step 24750, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aab79c92173e354e196f544c0de4e9ba890e5c3dca7d372a60e8f2c9829117cb
3
  size 76153420
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf6f92f5cead0b55e9039d86c2f34e56fac99de594be2c4e6242b11129eec63b
3
  size 76153420
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:38aef9fdab4585eabc82e791f0282bea03138952bd2061b1fe2b78ba677c95e9
3
  size 152327371
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e9c9e3c8eba8c3a23e8d1f5008742f827782029b429d807fcc0cb4464c12242
3
  size 152327371
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:386e72e61ed6c7cd07989aac8b73fc3a1fb31bd0bc49fbc79d7c84fe0c0ccaa6
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acb5cd8d790926f87a61764ced4598531d15a21dda0771e484b1d836b5c851e2
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e45ffeae492be284e875b386245d3f2a410c1a794de3df5d225ca3a6991944f
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef9add21fa268b698b3a5b76d6915a09037e3b69b20c46c261fec18f527f895a
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -2,9 +2,9 @@
2
  "best_global_step": 18500,
3
  "best_metric": 0.7932397701166506,
4
  "best_model_checkpoint": "/kaggle/working/G17_amfu_paper_training/trainer_output/checkpoint-18500",
5
- "epoch": 138.4180790960452,
6
  "eval_steps": 250,
7
- "global_step": 24500,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -8044,6 +8044,88 @@
8044
  "eval_samples_per_second": 51.035,
8045
  "eval_steps_per_second": 12.759,
8046
  "step": 24500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8047
  }
8048
  ],
8049
  "logging_steps": 25,
 
2
  "best_global_step": 18500,
3
  "best_metric": 0.7932397701166506,
4
  "best_model_checkpoint": "/kaggle/working/G17_amfu_paper_training/trainer_output/checkpoint-18500",
5
+ "epoch": 139.83050847457628,
6
  "eval_steps": 250,
7
+ "global_step": 24750,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
8044
  "eval_samples_per_second": 51.035,
8045
  "eval_steps_per_second": 12.759,
8046
  "step": 24500
8047
+ },
8048
+ {
8049
+ "epoch": 138.5593220338983,
8050
+ "grad_norm": 1.7911659479141235,
8051
+ "learning_rate": 1.220703125e-07,
8052
+ "loss": 0.2484,
8053
+ "step": 24525
8054
+ },
8055
+ {
8056
+ "epoch": 138.70056497175142,
8057
+ "grad_norm": 3.553830862045288,
8058
+ "learning_rate": 1.220703125e-07,
8059
+ "loss": 0.2399,
8060
+ "step": 24550
8061
+ },
8062
+ {
8063
+ "epoch": 138.8418079096045,
8064
+ "grad_norm": 1.9792214632034302,
8065
+ "learning_rate": 1.220703125e-07,
8066
+ "loss": 0.2745,
8067
+ "step": 24575
8068
+ },
8069
+ {
8070
+ "epoch": 138.98305084745763,
8071
+ "grad_norm": 3.0148303508758545,
8072
+ "learning_rate": 1.220703125e-07,
8073
+ "loss": 0.2651,
8074
+ "step": 24600
8075
+ },
8076
+ {
8077
+ "epoch": 139.12429378531073,
8078
+ "grad_norm": 1.3943380117416382,
8079
+ "learning_rate": 1.220703125e-07,
8080
+ "loss": 0.2686,
8081
+ "step": 24625
8082
+ },
8083
+ {
8084
+ "epoch": 139.26553672316385,
8085
+ "grad_norm": 1.6113567352294922,
8086
+ "learning_rate": 1.220703125e-07,
8087
+ "loss": 0.266,
8088
+ "step": 24650
8089
+ },
8090
+ {
8091
+ "epoch": 139.40677966101694,
8092
+ "grad_norm": 0.9839724898338318,
8093
+ "learning_rate": 1.220703125e-07,
8094
+ "loss": 0.2177,
8095
+ "step": 24675
8096
+ },
8097
+ {
8098
+ "epoch": 139.54802259887006,
8099
+ "grad_norm": 1.6616085767745972,
8100
+ "learning_rate": 1.220703125e-07,
8101
+ "loss": 0.2691,
8102
+ "step": 24700
8103
+ },
8104
+ {
8105
+ "epoch": 139.68926553672316,
8106
+ "grad_norm": 0.8645173907279968,
8107
+ "learning_rate": 1.220703125e-07,
8108
+ "loss": 0.267,
8109
+ "step": 24725
8110
+ },
8111
+ {
8112
+ "epoch": 139.83050847457628,
8113
+ "grad_norm": 1.3323326110839844,
8114
+ "learning_rate": 1.220703125e-07,
8115
+ "loss": 0.265,
8116
+ "step": 24750
8117
+ },
8118
+ {
8119
+ "epoch": 139.83050847457628,
8120
+ "eval_asd": 9.70710468047104,
8121
+ "eval_dice": 0.7915460670176017,
8122
+ "eval_hd95": 29.321639763462024,
8123
+ "eval_jaccard": 0.6981227697823843,
8124
+ "eval_loss": 0.3463759124279022,
8125
+ "eval_runtime": 5.1124,
8126
+ "eval_samples_per_second": 50.857,
8127
+ "eval_steps_per_second": 12.714,
8128
+ "step": 24750
8129
  }
8130
  ],
8131
  "logging_steps": 25,