TachyHealthResearch commited on
Commit
be98d68
1 Parent(s): 46d79c2

Training in progress, step 90, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ab02d753e42b32738a575ceb3d47ce069ba4d019eb9f69aef75b66382b07765
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb1361a8c98d22dbf42344dd633a462078c2fd5a89751b8618cbb6d4b7fd5bd1
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:34f6c10e9299ce96dec9a3383a4b5ac95a7b7f4f90b0756e9a256996865d7035
3
  size 42545748
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0de11ffa8e9a4df736ba11322bd4021586ad28b2c09e0f770171519f460711b
3
  size 42545748
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6eb5c56ad7f28c08ba6a65f011db11d829b6a7b17048bf037654e46884108234
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a547a76271f1c64e2d7367c4322cb2512e489925ea0a7e0f9d1cd2d7ba6973b
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f33415f176b8a48691d03ed7dab3f1b327d681c8c56b2a0baf4a0c917f18d582
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b296677280182a88e75c28cc855364d568a9149408830a5cd922e45719e62ac
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.032,
5
  "eval_steps": 1000,
6
- "global_step": 80,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -487,13 +487,73 @@
487
  "learning_rate": 4.210526315789474e-05,
488
  "loss": 1.573,
489
  "step": 80
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
490
  }
491
  ],
492
  "logging_steps": 1,
493
  "max_steps": 100,
494
  "num_train_epochs": 1,
495
  "save_steps": 10,
496
- "total_flos": 4814878295752704.0,
497
  "trial_name": null,
498
  "trial_params": null
499
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.036,
5
  "eval_steps": 1000,
6
+ "global_step": 90,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
487
  "learning_rate": 4.210526315789474e-05,
488
  "loss": 1.573,
489
  "step": 80
490
+ },
491
+ {
492
+ "epoch": 0.03,
493
+ "learning_rate": 4e-05,
494
+ "loss": 1.4032,
495
+ "step": 81
496
+ },
497
+ {
498
+ "epoch": 0.03,
499
+ "learning_rate": 3.789473684210527e-05,
500
+ "loss": 1.6532,
501
+ "step": 82
502
+ },
503
+ {
504
+ "epoch": 0.03,
505
+ "learning_rate": 3.578947368421053e-05,
506
+ "loss": 1.3414,
507
+ "step": 83
508
+ },
509
+ {
510
+ "epoch": 0.03,
511
+ "learning_rate": 3.368421052631579e-05,
512
+ "loss": 2.0307,
513
+ "step": 84
514
+ },
515
+ {
516
+ "epoch": 0.03,
517
+ "learning_rate": 3.157894736842105e-05,
518
+ "loss": 1.6258,
519
+ "step": 85
520
+ },
521
+ {
522
+ "epoch": 0.03,
523
+ "learning_rate": 2.9473684210526314e-05,
524
+ "loss": 1.5653,
525
+ "step": 86
526
+ },
527
+ {
528
+ "epoch": 0.03,
529
+ "learning_rate": 2.7368421052631583e-05,
530
+ "loss": 1.3957,
531
+ "step": 87
532
+ },
533
+ {
534
+ "epoch": 0.04,
535
+ "learning_rate": 2.5263157894736845e-05,
536
+ "loss": 1.7757,
537
+ "step": 88
538
+ },
539
+ {
540
+ "epoch": 0.04,
541
+ "learning_rate": 2.3157894736842107e-05,
542
+ "loss": 1.7531,
543
+ "step": 89
544
+ },
545
+ {
546
+ "epoch": 0.04,
547
+ "learning_rate": 2.105263157894737e-05,
548
+ "loss": 1.7966,
549
+ "step": 90
550
  }
551
  ],
552
  "logging_steps": 1,
553
  "max_steps": 100,
554
  "num_train_epochs": 1,
555
  "save_steps": 10,
556
+ "total_flos": 5562330342162432.0,
557
  "trial_name": null,
558
  "trial_params": null
559
  }