BayesTensor commited on
Commit
3e46531
·
verified ·
1 Parent(s): 4eb933e

Training in progress, epoch 14, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb6099b26484dcdc5882c934997be8ef652f09f24e4e3c8b9259641204db7271
3
  size 737722356
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fce2ce73ecb98cdcd08c1529fac53bc81efbe323299810a310b9dc503df3b96f
3
  size 737722356
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:42d7c22f3db24f63a9818736fbcbfc342409bf9ddaa7c1800e579be44c7b72a1
3
  size 1475564538
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f9f49c5eb20a477ea2177ceba542f474d12dd1694f64402a5c59de5d23e49ac
3
  size 1475564538
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:40105344871e6865600e248503be12c043bc99c76811b1b10664961dd30b5937
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3dc5be276d8f15b8e433244ccc4671ac29fb73c57d872124bed36588fa08a11
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2be7dc1d219acbd2f0efe1381e52b307e7734916897f0a941960c9fecdf13a99
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f13d01ee166bb96056eb90e8efbef49312aa82c63214dbdf297f81d2b908da20
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": 13.0,
5
  "eval_steps": 500,
6
- "global_step": 2379,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -285,6 +285,29 @@
285
  "eval_samples_per_second": 7.044,
286
  "eval_steps_per_second": 3.522,
287
  "step": 2379
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
288
  }
289
  ],
290
  "logging_steps": 100,
@@ -304,7 +327,7 @@
304
  "attributes": {}
305
  }
306
  },
307
- "total_flos": 6340016499570000.0,
308
  "train_batch_size": 2,
309
  "trial_name": null,
310
  "trial_params": null
 
1
  {
2
  "best_metric": 0.2747629944426283,
3
  "best_model_checkpoint": "debertalarge-medical-classifier/checkpoint-366",
4
+ "epoch": 14.0,
5
  "eval_steps": 500,
6
+ "global_step": 2562,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
285
  "eval_samples_per_second": 7.044,
286
  "eval_steps_per_second": 3.522,
287
  "step": 2379
288
+ },
289
+ {
290
+ "epoch": 13.114754098360656,
291
+ "grad_norm": 2.422586441040039,
292
+ "learning_rate": 2.377049180327869e-05,
293
+ "loss": 1.0433,
294
+ "step": 2400
295
+ },
296
+ {
297
+ "epoch": 13.66120218579235,
298
+ "grad_norm": 2.4954915046691895,
299
+ "learning_rate": 2.2677595628415303e-05,
300
+ "loss": 1.09,
301
+ "step": 2500
302
+ },
303
+ {
304
+ "epoch": 14.0,
305
+ "eval_f1": 0.2747629944426283,
306
+ "eval_loss": 1.110988974571228,
307
+ "eval_runtime": 13.0548,
308
+ "eval_samples_per_second": 7.047,
309
+ "eval_steps_per_second": 3.524,
310
+ "step": 2562
311
  }
312
  ],
313
  "logging_steps": 100,
 
327
  "attributes": {}
328
  }
329
  },
330
+ "total_flos": 6827710076460000.0,
331
  "train_batch_size": 2,
332
  "trial_name": null,
333
  "trial_params": null