aee4 commited on
Commit
0dc59dd
·
verified ·
1 Parent(s): b18802a

Training in progress, step 25250, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:15fe9ca760adf8b1de6126c76774d044f365f87464c6fa823fa000f96890a98f
3
  size 76153420
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1448d02152017cc4b7b71084bd768c2c7649492b038d74adef4abce46b34a122
3
  size 76153420
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:48ec77486ad1f510c324b28c0af1e7048278cdd21e408c0ff6c1124dbdbc0c0f
3
  size 152327371
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e03361263e0b9d36ccd55faa0fd6032aee18f5d49b155fa90a183beef97ccb14
3
  size 152327371
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:53e89b4dd924821239ce07e4b1cd83255d84da817bd9ae57d609333ea61ca381
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ee7a198870b6e0e41e20dabe9fe9ec9af3e64455f9e58d83a3e6f1eb5e145d7
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b9fedbac6a4cb25b0146acd9217dd3b4e452b97ef5f47a75d8821ffbba633524
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c74eddcf861a76c51de05d341a8570fb8be33ceaea1216189f96b08370223d1
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": 141.24293785310735,
6
  "eval_steps": 250,
7
- "global_step": 25000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -8208,6 +8208,88 @@
8208
  "eval_samples_per_second": 50.59,
8209
  "eval_steps_per_second": 12.648,
8210
  "step": 25000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8211
  }
8212
  ],
8213
  "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": 142.65536723163842,
6
  "eval_steps": 250,
7
+ "global_step": 25250,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
8208
  "eval_samples_per_second": 50.59,
8209
  "eval_steps_per_second": 12.648,
8210
  "step": 25000
8211
+ },
8212
+ {
8213
+ "epoch": 141.38418079096044,
8214
+ "grad_norm": 2.0897176265716553,
8215
+ "learning_rate": 6.103515625e-08,
8216
+ "loss": 0.2759,
8217
+ "step": 25025
8218
+ },
8219
+ {
8220
+ "epoch": 141.52542372881356,
8221
+ "grad_norm": 1.684669852256775,
8222
+ "learning_rate": 6.103515625e-08,
8223
+ "loss": 0.2434,
8224
+ "step": 25050
8225
+ },
8226
+ {
8227
+ "epoch": 141.66666666666666,
8228
+ "grad_norm": 1.3040128946304321,
8229
+ "learning_rate": 6.103515625e-08,
8230
+ "loss": 0.269,
8231
+ "step": 25075
8232
+ },
8233
+ {
8234
+ "epoch": 141.80790960451978,
8235
+ "grad_norm": 2.624764919281006,
8236
+ "learning_rate": 6.103515625e-08,
8237
+ "loss": 0.2671,
8238
+ "step": 25100
8239
+ },
8240
+ {
8241
+ "epoch": 141.94915254237287,
8242
+ "grad_norm": 2.1109540462493896,
8243
+ "learning_rate": 6.103515625e-08,
8244
+ "loss": 0.2519,
8245
+ "step": 25125
8246
+ },
8247
+ {
8248
+ "epoch": 142.090395480226,
8249
+ "grad_norm": 9.619257926940918,
8250
+ "learning_rate": 6.103515625e-08,
8251
+ "loss": 0.2958,
8252
+ "step": 25150
8253
+ },
8254
+ {
8255
+ "epoch": 142.2316384180791,
8256
+ "grad_norm": 3.334533214569092,
8257
+ "learning_rate": 6.103515625e-08,
8258
+ "loss": 0.2505,
8259
+ "step": 25175
8260
+ },
8261
+ {
8262
+ "epoch": 142.3728813559322,
8263
+ "grad_norm": 1.3030273914337158,
8264
+ "learning_rate": 6.103515625e-08,
8265
+ "loss": 0.2506,
8266
+ "step": 25200
8267
+ },
8268
+ {
8269
+ "epoch": 142.5141242937853,
8270
+ "grad_norm": 1.5810096263885498,
8271
+ "learning_rate": 6.103515625e-08,
8272
+ "loss": 0.2577,
8273
+ "step": 25225
8274
+ },
8275
+ {
8276
+ "epoch": 142.65536723163842,
8277
+ "grad_norm": 1.7737849950790405,
8278
+ "learning_rate": 6.103515625e-08,
8279
+ "loss": 0.245,
8280
+ "step": 25250
8281
+ },
8282
+ {
8283
+ "epoch": 142.65536723163842,
8284
+ "eval_asd": 9.919983044588985,
8285
+ "eval_dice": 0.7907053525798633,
8286
+ "eval_hd95": 30.54021069264459,
8287
+ "eval_jaccard": 0.696669639727433,
8288
+ "eval_loss": 0.35015588998794556,
8289
+ "eval_runtime": 5.0909,
8290
+ "eval_samples_per_second": 51.072,
8291
+ "eval_steps_per_second": 12.768,
8292
+ "step": 25250
8293
  }
8294
  ],
8295
  "logging_steps": 25,