TachyHealthResearch commited on
Commit
bd37ebd
·
1 Parent(s): 2cb618f

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:fa51538c0fee57c20d3cf0e5731daee81d09fdaecb65b37354cbfbb0b5f8907b
3
  size 125248064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9ce0d5b909ffd7b29231ec089aa95b795da59614a9dee8c8790678c6ec04a35
3
  size 125248064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:68efcc9d57f32ad2e4b4bce16e4b755288014677e1b23a6b972ef3ed184ea2a8
3
  size 63350356
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:865724214c1d6d853eef94fba17f1a7c80dda30457c4f5186d20cac483aed0d2
3
  size 63350356
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3fa0224b8fb2b0426a129f41a0666ecf84d9b716217e39a5d1bf97eabc1d4486
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bb115e5ab94d968710c7b1278747dfbb15e5fca1a53624a1aa871bb9a0a1c7b
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a7277563b68f0a25594bd8f04a2297ddade7a93c1062f094bae84be2463e566
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8872fbc255580a4a595781a6a22e1bdc87218e472bb5b2b3113647f32836029f
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": 0.034,
5
  "eval_steps": 1000,
6
- "global_step": 85,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -517,13 +517,43 @@
517
  "learning_rate": 8.843537414965987e-05,
518
  "loss": 1.5353,
519
  "step": 85
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
520
  }
521
  ],
522
  "logging_steps": 1,
523
  "max_steps": 150,
524
  "num_train_epochs": 1,
525
  "save_steps": 5,
526
- "total_flos": 9498160042721280.0,
527
  "trial_name": null,
528
  "trial_params": null
529
  }
 
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,
 
517
  "learning_rate": 8.843537414965987e-05,
518
  "loss": 1.5353,
519
  "step": 85
520
+ },
521
+ {
522
+ "epoch": 0.03,
523
+ "learning_rate": 8.70748299319728e-05,
524
+ "loss": 1.5158,
525
+ "step": 86
526
+ },
527
+ {
528
+ "epoch": 0.03,
529
+ "learning_rate": 8.571428571428571e-05,
530
+ "loss": 1.3898,
531
+ "step": 87
532
+ },
533
+ {
534
+ "epoch": 0.04,
535
+ "learning_rate": 8.435374149659864e-05,
536
+ "loss": 1.6535,
537
+ "step": 88
538
+ },
539
+ {
540
+ "epoch": 0.04,
541
+ "learning_rate": 8.299319727891157e-05,
542
+ "loss": 1.6544,
543
+ "step": 89
544
+ },
545
+ {
546
+ "epoch": 0.04,
547
+ "learning_rate": 8.163265306122449e-05,
548
+ "loss": 1.8656,
549
+ "step": 90
550
  }
551
  ],
552
  "logging_steps": 1,
553
  "max_steps": 150,
554
  "num_train_epochs": 1,
555
  "save_steps": 5,
556
+ "total_flos": 1.043070722727936e+16,
557
  "trial_name": null,
558
  "trial_params": null
559
  }