aee4 commited on
Commit
02f649f
·
verified ·
1 Parent(s): b3764b5

Training in progress, step 28250, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:29544c5ff17a6103a2f0e5709d8f6bb1ef53532c16fd2f6816ae796e48499013
3
  size 76153420
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d2e0b72ecfef259626389d372140189f305fb334c72bb54c21c852563d135c6
3
  size 76153420
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:65e953de80a645914e8357c4b151484a23eadc6ab61e5d99da40afc77a58b928
3
  size 152327371
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f67a68c43643a6709bd0d7e4b80f492d69ec5fab884d4d2b13384a4c5de799f
3
  size 152327371
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4736301ba415f4a17e7f309321fc583a7d4c049193ba906552bff155a5a4dfa8
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35eb65031bbaf87296bc1af82f0e4c1cca31517e853f8c848f65c220945b183f
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2ccca3db7f0195546020b0924701e30a64a44b4e8079b0e18595ce0dd64cf75e
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:150822977e05de7f4b84498a822120f935757b6a9ffe817525c136b719ac8dfc
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": 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,
@@ -9192,6 +9192,88 @@
9192
  "eval_samples_per_second": 51.152,
9193
  "eval_steps_per_second": 12.788,
9194
  "step": 28000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9195
  }
9196
  ],
9197
  "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": 159.6045197740113,
6
  "eval_steps": 250,
7
+ "global_step": 28250,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
9192
  "eval_samples_per_second": 51.152,
9193
  "eval_steps_per_second": 12.788,
9194
  "step": 28000
9195
+ },
9196
+ {
9197
+ "epoch": 158.33333333333334,
9198
+ "grad_norm": 1.5999171733856201,
9199
+ "learning_rate": 3.0517578125e-08,
9200
+ "loss": 0.2517,
9201
+ "step": 28025
9202
+ },
9203
+ {
9204
+ "epoch": 158.47457627118644,
9205
+ "grad_norm": 1.3441364765167236,
9206
+ "learning_rate": 3.0517578125e-08,
9207
+ "loss": 0.2455,
9208
+ "step": 28050
9209
+ },
9210
+ {
9211
+ "epoch": 158.61581920903956,
9212
+ "grad_norm": 3.2164599895477295,
9213
+ "learning_rate": 3.0517578125e-08,
9214
+ "loss": 0.2765,
9215
+ "step": 28075
9216
+ },
9217
+ {
9218
+ "epoch": 158.75706214689265,
9219
+ "grad_norm": 0.9148532152175903,
9220
+ "learning_rate": 3.0517578125e-08,
9221
+ "loss": 0.2502,
9222
+ "step": 28100
9223
+ },
9224
+ {
9225
+ "epoch": 158.89830508474577,
9226
+ "grad_norm": 0.799048662185669,
9227
+ "learning_rate": 3.0517578125e-08,
9228
+ "loss": 0.2391,
9229
+ "step": 28125
9230
+ },
9231
+ {
9232
+ "epoch": 159.03954802259886,
9233
+ "grad_norm": 2.3579928874969482,
9234
+ "learning_rate": 3.0517578125e-08,
9235
+ "loss": 0.2845,
9236
+ "step": 28150
9237
+ },
9238
+ {
9239
+ "epoch": 159.180790960452,
9240
+ "grad_norm": 1.7993416786193848,
9241
+ "learning_rate": 3.0517578125e-08,
9242
+ "loss": 0.2335,
9243
+ "step": 28175
9244
+ },
9245
+ {
9246
+ "epoch": 159.32203389830508,
9247
+ "grad_norm": 1.1014084815979004,
9248
+ "learning_rate": 3.0517578125e-08,
9249
+ "loss": 0.266,
9250
+ "step": 28200
9251
+ },
9252
+ {
9253
+ "epoch": 159.4632768361582,
9254
+ "grad_norm": 1.4245517253875732,
9255
+ "learning_rate": 3.0517578125e-08,
9256
+ "loss": 0.2719,
9257
+ "step": 28225
9258
+ },
9259
+ {
9260
+ "epoch": 159.6045197740113,
9261
+ "grad_norm": 2.324073076248169,
9262
+ "learning_rate": 3.0517578125e-08,
9263
+ "loss": 0.2576,
9264
+ "step": 28250
9265
+ },
9266
+ {
9267
+ "epoch": 159.6045197740113,
9268
+ "eval_asd": 10.116352721376701,
9269
+ "eval_dice": 0.792037941236608,
9270
+ "eval_hd95": 31.598652783435487,
9271
+ "eval_jaccard": 0.6980539908747615,
9272
+ "eval_loss": 0.3468816876411438,
9273
+ "eval_runtime": 5.1135,
9274
+ "eval_samples_per_second": 50.846,
9275
+ "eval_steps_per_second": 12.712,
9276
+ "step": 28250
9277
  }
9278
  ],
9279
  "logging_steps": 25,