avsolatorio commited on
Commit
65c80aa
1 Parent(s): d552d3f

Training in progress, step 14000, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f49c46fc02975a8bcfad45e5a8dfb4264dc7f7e5fe1f7927bf0228959114e677
3
  size 567860028
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98617680d962c5113705e2fbad186edd60eeedfd294fa6fa24932d2327dfa47f
3
  size 567860028
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e254ff0234e4863ebedc13e8f132a91ede7f26982d93888d6f3556126a451f62
3
  size 1135783354
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7bfefb58a92140d2482dbcb2f412ecf1fdbdfec6f5ea8b787a6d35eaec393b7
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:a9b5b8eb805933fe8f900e32fd375bcc66cfa8e06b254a11fc2a80b5c9b6018d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3067b28aa64de4757065dd8a01a67d3704c9818184e3b87673b274005079225
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ac5cca03c5fb2105d752b6c1034ca2d26b6b19fd729ff034cb671359a651884
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33ec0c6c7881febe86af83de0fd1c05de3d6b8cdacbf1d5a88958d9ee8777f33
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 0.03706079348921776,
3
  "best_model_checkpoint": "doc-topic-model_eval-04_train-03/checkpoint-11000",
4
- "epoch": 6.410256410256411,
5
  "eval_steps": 1000,
6
- "global_step": 13000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -345,6 +345,32 @@
345
  "eval_samples_per_second": 555.394,
346
  "eval_steps_per_second": 2.191,
347
  "step": 13000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
348
  }
349
  ],
350
  "logging_steps": 500,
@@ -373,7 +399,7 @@
373
  "attributes": {}
374
  }
375
  },
376
- "total_flos": 292968753296400.0,
377
  "train_batch_size": 4,
378
  "trial_name": null,
379
  "trial_params": null
 
1
  {
2
  "best_metric": 0.03706079348921776,
3
  "best_model_checkpoint": "doc-topic-model_eval-04_train-03/checkpoint-11000",
4
+ "epoch": 6.903353057199211,
5
  "eval_steps": 1000,
6
+ "global_step": 14000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
345
  "eval_samples_per_second": 555.394,
346
  "eval_steps_per_second": 2.191,
347
  "step": 13000
348
+ },
349
+ {
350
+ "epoch": 6.65680473372781,
351
+ "grad_norm": 0.7562135457992554,
352
+ "learning_rate": 1.8668836291913217e-05,
353
+ "loss": 0.0265,
354
+ "step": 13500
355
+ },
356
+ {
357
+ "epoch": 6.903353057199211,
358
+ "grad_norm": 0.5237112641334534,
359
+ "learning_rate": 1.8619526627218937e-05,
360
+ "loss": 0.0257,
361
+ "step": 14000
362
+ },
363
+ {
364
+ "epoch": 6.903353057199211,
365
+ "eval_accuracy": 0.9877591094752143,
366
+ "eval_f1": 0.6171231055570328,
367
+ "eval_loss": 0.03727097436785698,
368
+ "eval_precision": 0.73248474647591,
369
+ "eval_recall": 0.5331546707503828,
370
+ "eval_runtime": 14.3608,
371
+ "eval_samples_per_second": 564.941,
372
+ "eval_steps_per_second": 2.228,
373
+ "step": 14000
374
  }
375
  ],
376
  "logging_steps": 500,
 
399
  "attributes": {}
400
  }
401
  },
402
+ "total_flos": 315603997005888.0,
403
  "train_batch_size": 4,
404
  "trial_name": null,
405
  "trial_params": null