aee4 commited on
Commit
f1e1b1e
·
verified ·
1 Parent(s): 94613ce

Training in progress, step 28000, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:11423187e1331fc94deb0bf135744867620fc9b21408610008b928d09c9147f8
3
  size 76153420
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29544c5ff17a6103a2f0e5709d8f6bb1ef53532c16fd2f6816ae796e48499013
3
  size 76153420
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cebd3ca7c2fa506a5f2d4807c3e718be4240e9471a01e0f1cf324e0a8ecbb2d0
3
  size 152327371
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65e953de80a645914e8357c4b151484a23eadc6ab61e5d99da40afc77a58b928
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:d82dd5e2ad13d2cef7043f2cd1d3696abb2b240d4b0f342524b279387c889418
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4736301ba415f4a17e7f309321fc583a7d4c049193ba906552bff155a5a4dfa8
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ec485a156b6f127d16c572a2bf80911b4937d51d34a5c555fd7a53f85eca3e3
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ccca3db7f0195546020b0924701e30a64a44b4e8079b0e18595ce0dd64cf75e
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": 156.77966101694915,
6
  "eval_steps": 250,
7
- "global_step": 27750,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -9110,6 +9110,88 @@
9110
  "eval_samples_per_second": 51.343,
9111
  "eval_steps_per_second": 12.836,
9112
  "step": 27750
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9113
  }
9114
  ],
9115
  "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": 158.19209039548022,
6
  "eval_steps": 250,
7
+ "global_step": 28000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
9110
  "eval_samples_per_second": 51.343,
9111
  "eval_steps_per_second": 12.836,
9112
  "step": 27750
9113
+ },
9114
+ {
9115
+ "epoch": 156.92090395480227,
9116
+ "grad_norm": 0.5020657181739807,
9117
+ "learning_rate": 3.0517578125e-08,
9118
+ "loss": 0.2712,
9119
+ "step": 27775
9120
+ },
9121
+ {
9122
+ "epoch": 157.06214689265536,
9123
+ "grad_norm": 1.5506677627563477,
9124
+ "learning_rate": 3.0517578125e-08,
9125
+ "loss": 0.2617,
9126
+ "step": 27800
9127
+ },
9128
+ {
9129
+ "epoch": 157.20338983050848,
9130
+ "grad_norm": 0.8360307812690735,
9131
+ "learning_rate": 3.0517578125e-08,
9132
+ "loss": 0.2687,
9133
+ "step": 27825
9134
+ },
9135
+ {
9136
+ "epoch": 157.34463276836158,
9137
+ "grad_norm": 0.8615549802780151,
9138
+ "learning_rate": 3.0517578125e-08,
9139
+ "loss": 0.2376,
9140
+ "step": 27850
9141
+ },
9142
+ {
9143
+ "epoch": 157.4858757062147,
9144
+ "grad_norm": 1.4960042238235474,
9145
+ "learning_rate": 3.0517578125e-08,
9146
+ "loss": 0.2759,
9147
+ "step": 27875
9148
+ },
9149
+ {
9150
+ "epoch": 157.6271186440678,
9151
+ "grad_norm": 1.6164301633834839,
9152
+ "learning_rate": 3.0517578125e-08,
9153
+ "loss": 0.272,
9154
+ "step": 27900
9155
+ },
9156
+ {
9157
+ "epoch": 157.7683615819209,
9158
+ "grad_norm": 0.9965801239013672,
9159
+ "learning_rate": 3.0517578125e-08,
9160
+ "loss": 0.242,
9161
+ "step": 27925
9162
+ },
9163
+ {
9164
+ "epoch": 157.909604519774,
9165
+ "grad_norm": 0.8680419921875,
9166
+ "learning_rate": 3.0517578125e-08,
9167
+ "loss": 0.258,
9168
+ "step": 27950
9169
+ },
9170
+ {
9171
+ "epoch": 158.05084745762713,
9172
+ "grad_norm": 1.219549298286438,
9173
+ "learning_rate": 3.0517578125e-08,
9174
+ "loss": 0.2547,
9175
+ "step": 27975
9176
+ },
9177
+ {
9178
+ "epoch": 158.19209039548022,
9179
+ "grad_norm": 2.8840699195861816,
9180
+ "learning_rate": 3.0517578125e-08,
9181
+ "loss": 0.2693,
9182
+ "step": 28000
9183
+ },
9184
+ {
9185
+ "epoch": 158.19209039548022,
9186
+ "eval_asd": 9.984678223294726,
9187
+ "eval_dice": 0.7914670821123254,
9188
+ "eval_hd95": 30.71606911694114,
9189
+ "eval_jaccard": 0.6974675325093858,
9190
+ "eval_loss": 0.34817832708358765,
9191
+ "eval_runtime": 5.0829,
9192
+ "eval_samples_per_second": 51.152,
9193
+ "eval_steps_per_second": 12.788,
9194
+ "step": 28000
9195
  }
9196
  ],
9197
  "logging_steps": 25,