TachyHealthResearch commited on
Commit
f6459b2
·
1 Parent(s): 6ea2049

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:d93f3d709b62a0801581eb275f1cf2b02019d04bcb1a08b2885550214f5215c5
3
  size 75012288
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba5c7f9943c7dbb338249739a96077e17b2518bed57247cb41754a5b1b56dac3
3
  size 75012288
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:84381402825991379f5ff82e4a69d8a8b4f9fd4188f826e7d8e70bc4266421be
3
  size 38034724
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1956add00bedcb5481023acba701758668db7925bd3d88f3c7a5e6a28fdd65d
3
  size 38034724
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a03205bd2befa025d120b19664f9407743b66ea492f2d94e9cbbdfbf2f7a9336
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4824af45392bc11d08c4cc392f4c9b82f8692e1fea5b438937d088e9b802692
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": 1.9541,
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": 4131013396463616.0,
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": 1.9541,
519
  "step": 85
520
+ },
521
+ {
522
+ "epoch": 0.03,
523
+ "learning_rate": 8.70748299319728e-05,
524
+ "loss": 1.9938,
525
+ "step": 86
526
+ },
527
+ {
528
+ "epoch": 0.03,
529
+ "learning_rate": 8.571428571428571e-05,
530
+ "loss": 1.7522,
531
+ "step": 87
532
+ },
533
+ {
534
+ "epoch": 0.04,
535
+ "learning_rate": 8.435374149659864e-05,
536
+ "loss": 2.1434,
537
+ "step": 88
538
+ },
539
+ {
540
+ "epoch": 0.04,
541
+ "learning_rate": 8.299319727891157e-05,
542
+ "loss": 2.1333,
543
+ "step": 89
544
+ },
545
+ {
546
+ "epoch": 0.04,
547
+ "learning_rate": 8.163265306122449e-05,
548
+ "loss": 2.2407,
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": 4531280261873664.0,
557
  "trial_name": null,
558
  "trial_params": null
559
  }