avsolatorio commited on
Commit
21c3d90
1 Parent(s): 8c383e1

Training in progress, step 12000, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a14ba6d631b491aedf133a76099b0070972351da82405b18ac3450de34336449
3
  size 567860028
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:791af0f71e3a9b8e8ae2ddc2902b7686c5f69824bf9684c694143cc9c7a516b2
3
  size 567860028
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:73ea4bb0360117a07d4f6423fa49546e2503080cd4f5396d578fe653c6c03609
3
  size 1135783354
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb49ff40fbf04fc597f1b5630850feb0b992849099b487836eadc12854f7d18d
3
  size 1135783354
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2ef6b86d20d6ecc4df3a0c586eaefe72e249b74f60cbccfafd813b5495f54c4f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a445c512a69801b68e319bfb3cb3702cfd8c222330cff7d4d1380aca05cd09b
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c3c3f1ac50882defeade258e77931f3038c02d6276451a81f8ef210f495feca4
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1600bc22796954bbfe2cfe1a5708dbdc0d32592a1fa22b6a9c5489c11d5fbd8c
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 0.037347666919231415,
3
  "best_model_checkpoint": "doc-topic-model_eval-01_train-03/checkpoint-11000",
4
- "epoch": 5.424063116370808,
5
  "eval_steps": 1000,
6
- "global_step": 11000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -293,6 +293,32 @@
293
  "eval_samples_per_second": 566.858,
294
  "eval_steps_per_second": 2.237,
295
  "step": 11000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
296
  }
297
  ],
298
  "logging_steps": 500,
@@ -321,7 +347,7 @@
321
  "attributes": {}
322
  }
323
  },
324
- "total_flos": 248019064848396.0,
325
  "train_batch_size": 4,
326
  "trial_name": null,
327
  "trial_params": null
 
1
  {
2
  "best_metric": 0.037347666919231415,
3
  "best_model_checkpoint": "doc-topic-model_eval-01_train-03/checkpoint-11000",
4
+ "epoch": 5.9171597633136095,
5
  "eval_steps": 1000,
6
+ "global_step": 12000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
293
  "eval_samples_per_second": 566.858,
294
  "eval_steps_per_second": 2.237,
295
  "step": 11000
296
+ },
297
+ {
298
+ "epoch": 5.670611439842209,
299
+ "grad_norm": 0.42573484778404236,
300
+ "learning_rate": 1.886597633136095e-05,
301
+ "loss": 0.0299,
302
+ "step": 11500
303
+ },
304
+ {
305
+ "epoch": 5.9171597633136095,
306
+ "grad_norm": 0.4632101058959961,
307
+ "learning_rate": 1.881666666666667e-05,
308
+ "loss": 0.0295,
309
+ "step": 12000
310
+ },
311
+ {
312
+ "epoch": 5.9171597633136095,
313
+ "eval_accuracy": 0.9875462392108508,
314
+ "eval_f1": 0.6107641196013289,
315
+ "eval_loss": 0.03775852918624878,
316
+ "eval_precision": 0.7302966101694915,
317
+ "eval_recall": 0.524857251617815,
318
+ "eval_runtime": 14.2377,
319
+ "eval_samples_per_second": 569.612,
320
+ "eval_steps_per_second": 2.248,
321
+ "step": 12000
322
  }
323
  ],
324
  "logging_steps": 500,
 
347
  "attributes": {}
348
  }
349
  },
350
+ "total_flos": 270583826069916.0,
351
  "train_batch_size": 4,
352
  "trial_name": null,
353
  "trial_params": null