TachyHealthResearch commited on
Commit
42907b4
·
1 Parent(s): f040c43

Training in progress, step 95, 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:b9ce0d5b909ffd7b29231ec089aa95b795da59614a9dee8c8790678c6ec04a35
3
  size 125248064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79b5512edb2dab2e5262a8b32e2ace46b0e307acedbfb8dacced3cb08fcc2816
3
  size 125248064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:865724214c1d6d853eef94fba17f1a7c80dda30457c4f5186d20cac483aed0d2
3
  size 63350356
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:273126e84c3940e91ef1046bf2d8ecf250412dcca07eb78877d2c252dff0102d
3
  size 63350356
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8bb115e5ab94d968710c7b1278747dfbb15e5fca1a53624a1aa871bb9a0a1c7b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4155835a2c0c408507441a4409ed2c6847f58a7d2fcf11f63e6cd6de754bef8b
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8872fbc255580a4a595781a6a22e1bdc87218e472bb5b2b3113647f32836029f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6108f4faef547664ffc49f24479d791d4a8a5a6cda6f7c8b0f62fd8408e62a4f
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": 0.036,
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,
@@ -547,13 +547,43 @@
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
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.038,
5
  "eval_steps": 1000,
6
+ "global_step": 95,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
547
  "learning_rate": 8.163265306122449e-05,
548
  "loss": 1.8656,
549
  "step": 90
550
+ },
551
+ {
552
+ "epoch": 0.04,
553
+ "learning_rate": 8.027210884353742e-05,
554
+ "loss": 1.465,
555
+ "step": 91
556
+ },
557
+ {
558
+ "epoch": 0.04,
559
+ "learning_rate": 7.891156462585034e-05,
560
+ "loss": 1.0163,
561
+ "step": 92
562
+ },
563
+ {
564
+ "epoch": 0.04,
565
+ "learning_rate": 7.755102040816327e-05,
566
+ "loss": 1.61,
567
+ "step": 93
568
+ },
569
+ {
570
+ "epoch": 0.04,
571
+ "learning_rate": 7.619047619047618e-05,
572
+ "loss": 2.0532,
573
+ "step": 94
574
+ },
575
+ {
576
+ "epoch": 0.04,
577
+ "learning_rate": 7.482993197278913e-05,
578
+ "loss": 1.4248,
579
+ "step": 95
580
  }
581
  ],
582
  "logging_steps": 1,
583
  "max_steps": 150,
584
  "num_train_epochs": 1,
585
  "save_steps": 5,
586
+ "total_flos": 1.147472100999168e+16,
587
  "trial_name": null,
588
  "trial_params": null
589
  }