avsolatorio commited on
Commit
a1bc998
1 Parent(s): 7e853bb

Training in progress, step 17000, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:75f25d8ad92f875a53659d2aa604eab54bc9083bbbead781aa5da3c192cfdc81
3
  size 567860028
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9b0baeb960dd305488b4d620acbbe73944acf2f3aee6f39ab4f9f2ace9146da
3
  size 567860028
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8883bcd809b17855f5bd75fa68a9ed04c375ce0e9e0384257d097e9cf8c0ddd9
3
  size 1135783354
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aae5503ebaf112403941b4ddfc161ae2d74499963b425aa493869fdb99502c7b
3
  size 1135783354
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:257882d778b7ee81778c5c372a17241451c183798e27c011c1764580527db4bc
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d909219cbdd70599a7be8a42aba4df5d7065f7b997b0075bce4834affe89f840
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b383cee6a8b310b70be569cfc8af334eaeb0c2fb37d6fe24dbd7ccca37a08dab
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd937dc5ca4c62f5f5a023ee1555a7a5e140540c1dc517f73c54011163ae049e
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 0.0379740335047245,
3
  "best_model_checkpoint": "doc-topic-model_eval-03_train-01/checkpoint-16000",
4
- "epoch": 7.889546351084813,
5
  "eval_steps": 1000,
6
- "global_step": 16000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -423,6 +423,32 @@
423
  "eval_samples_per_second": 555.63,
424
  "eval_steps_per_second": 2.192,
425
  "step": 16000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
426
  }
427
  ],
428
  "logging_steps": 500,
@@ -451,7 +477,7 @@
451
  "attributes": {}
452
  }
453
  },
454
- "total_flos": 361937940787440.0,
455
  "train_batch_size": 4,
456
  "trial_name": null,
457
  "trial_params": null
 
1
  {
2
  "best_metric": 0.0379740335047245,
3
  "best_model_checkpoint": "doc-topic-model_eval-03_train-01/checkpoint-16000",
4
+ "epoch": 8.382642998027613,
5
  "eval_steps": 1000,
6
+ "global_step": 17000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
423
  "eval_samples_per_second": 555.63,
424
  "eval_steps_per_second": 2.192,
425
  "step": 16000
426
+ },
427
+ {
428
+ "epoch": 8.136094674556213,
429
+ "grad_norm": 0.13463503122329712,
430
+ "learning_rate": 1.8373076923076926e-05,
431
+ "loss": 0.0224,
432
+ "step": 16500
433
+ },
434
+ {
435
+ "epoch": 8.382642998027613,
436
+ "grad_norm": 0.25073572993278503,
437
+ "learning_rate": 1.8323865877712033e-05,
438
+ "loss": 0.0214,
439
+ "step": 17000
440
+ },
441
+ {
442
+ "epoch": 8.382642998027613,
443
+ "eval_accuracy": 0.9875703332057769,
444
+ "eval_f1": 0.6291754756871036,
445
+ "eval_loss": 0.03818249702453613,
446
+ "eval_precision": 0.7049459920409323,
447
+ "eval_recall": 0.5681124007330483,
448
+ "eval_runtime": 14.6338,
449
+ "eval_samples_per_second": 554.198,
450
+ "eval_steps_per_second": 2.187,
451
+ "step": 17000
452
  }
453
  ],
454
  "logging_steps": 500,
 
477
  "attributes": {}
478
  }
479
  },
480
+ "total_flos": 384458650453980.0,
481
  "train_batch_size": 4,
482
  "trial_name": null,
483
  "trial_params": null