TachyHealthResearch commited on
Commit
7af8588
1 Parent(s): 691d55b

Training in progress, step 100, 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:ad86822da69a83aaadc42b69b1bc0af15541f77718c3e7d9f00e66321a73a9b5
3
  size 125248064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f1cfb477142aa1a645084332e93d3df2f7050205e592da70d824f4190de332b
3
  size 125248064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8bc55b190ddf62af56285308303a85e0ae18412267bc27a046847c1542e9d2cc
3
  size 63350356
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2afb0816f23808a55f51d1cf0b446e87a8106440fd8d6ad4c78a0cd506620a18
3
  size 63350356
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4155835a2c0c408507441a4409ed2c6847f58a7d2fcf11f63e6cd6de754bef8b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ea9587f57d558858d9209d96d19ea2be1ea0213796d98d94e89cfd6c1b66c54
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ab3b539b8fc03731efbb7316c713d982e79a58e9287d0ae319d5bcf6c96f1b4
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a60c7d771c1fd156acee762fba03c724cb41829a3f71df370ecd1d20b134982
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": 0.038,
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,
@@ -577,13 +577,43 @@
577
  "learning_rate": 1.0309278350515464e-05,
578
  "loss": 1.4259,
579
  "step": 95
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
580
  }
581
  ],
582
  "logging_steps": 1,
583
  "max_steps": 100,
584
  "num_train_epochs": 1,
585
  "save_steps": 5,
586
- "total_flos": 1.147472100999168e+16,
587
  "trial_name": null,
588
  "trial_params": null
589
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.04,
5
  "eval_steps": 1000,
6
+ "global_step": 100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
577
  "learning_rate": 1.0309278350515464e-05,
578
  "loss": 1.4259,
579
  "step": 95
580
+ },
581
+ {
582
+ "epoch": 0.04,
583
+ "learning_rate": 8.247422680412371e-06,
584
+ "loss": 1.5112,
585
+ "step": 96
586
+ },
587
+ {
588
+ "epoch": 0.04,
589
+ "learning_rate": 6.185567010309279e-06,
590
+ "loss": 1.6401,
591
+ "step": 97
592
+ },
593
+ {
594
+ "epoch": 0.04,
595
+ "learning_rate": 4.123711340206186e-06,
596
+ "loss": 1.6328,
597
+ "step": 98
598
+ },
599
+ {
600
+ "epoch": 0.04,
601
+ "learning_rate": 2.061855670103093e-06,
602
+ "loss": 1.6182,
603
+ "step": 99
604
+ },
605
+ {
606
+ "epoch": 0.04,
607
+ "learning_rate": 0.0,
608
+ "loss": 1.4856,
609
+ "step": 100
610
  }
611
  ],
612
  "logging_steps": 1,
613
  "max_steps": 100,
614
  "num_train_epochs": 1,
615
  "save_steps": 5,
616
+ "total_flos": 1.236815439519744e+16,
617
  "trial_name": null,
618
  "trial_params": null
619
  }