BayesTensor commited on
Commit
ec79437
·
verified ·
1 Parent(s): 10f8d90

Training in progress, epoch 11, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0bdc41551b933d2fe35ea88d82d13eed280c2522e7af67d11f12c0282ae42fc0
3
  size 737722356
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:139ff089bb8abd16b767616edf7f45e9998d333389a98a23829b92514a5444ba
3
  size 737722356
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d6c397791ac92763f9e205e8ef510b47ad59bb375050c4e30ca36015500cc44
3
  size 1475564538
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a252e7e0e5065aab81693a783d4f8322dc109e6a924ed959746b8987a14af312
3
  size 1475564538
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:be99df8b3f53af28592d8cdccf7f2c01662135503a2081ac70bb1f25ea2abfac
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eec6befc66b9e00335f341333474f86f512da5548c42ed27dbc746d7e663d8f2
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:86ccb6d05c02edfe77c4f50beefff43ca85a79779bf84844c9dc8a1cdba8b680
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:931df331b7d50554d4357a63089fd71d02b22e6f87cd334ee816cc0ea0bf6dad
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 0.2747629944426283,
3
  "best_model_checkpoint": "debertalarge-medical-classifier/checkpoint-366",
4
- "epoch": 10.0,
5
  "eval_steps": 500,
6
- "global_step": 1830,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -223,6 +223,29 @@
223
  "eval_samples_per_second": 7.038,
224
  "eval_steps_per_second": 3.519,
225
  "step": 1830
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
226
  }
227
  ],
228
  "logging_steps": 100,
@@ -242,7 +265,7 @@
242
  "attributes": {}
243
  }
244
  },
245
- "total_flos": 4876935768900000.0,
246
  "train_batch_size": 2,
247
  "trial_name": null,
248
  "trial_params": null
 
1
  {
2
  "best_metric": 0.2747629944426283,
3
  "best_model_checkpoint": "debertalarge-medical-classifier/checkpoint-366",
4
+ "epoch": 11.0,
5
  "eval_steps": 500,
6
+ "global_step": 2013,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
223
  "eval_samples_per_second": 7.038,
224
  "eval_steps_per_second": 3.519,
225
  "step": 1830
226
+ },
227
+ {
228
+ "epoch": 10.382513661202186,
229
+ "grad_norm": 2.3387579917907715,
230
+ "learning_rate": 2.9234972677595628e-05,
231
+ "loss": 1.0349,
232
+ "step": 1900
233
+ },
234
+ {
235
+ "epoch": 10.92896174863388,
236
+ "grad_norm": 4.286855697631836,
237
+ "learning_rate": 2.814207650273224e-05,
238
+ "loss": 1.0849,
239
+ "step": 2000
240
+ },
241
+ {
242
+ "epoch": 11.0,
243
+ "eval_f1": 0.2747629944426283,
244
+ "eval_loss": 1.093202829360962,
245
+ "eval_runtime": 13.0444,
246
+ "eval_samples_per_second": 7.053,
247
+ "eval_steps_per_second": 3.526,
248
+ "step": 2013
249
  }
250
  ],
251
  "logging_steps": 100,
 
265
  "attributes": {}
266
  }
267
  },
268
+ "total_flos": 5364629345790000.0,
269
  "train_batch_size": 2,
270
  "trial_name": null,
271
  "trial_params": null