TachyHealthResearch commited on
Commit
ef03979
1 Parent(s): 7ffe5b1

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:ee40a63c153af0b9f73825f7f38fef512f1ace91e267526b36cc1f6946bd0795
3
  size 125248064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad86822da69a83aaadc42b69b1bc0af15541f77718c3e7d9f00e66321a73a9b5
3
  size 125248064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5056f228f865430bfe4e00440c0f8934a8e1fc1e938d3a02996b9d09898a2bb1
3
  size 63350356
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bc55b190ddf62af56285308303a85e0ae18412267bc27a046847c1542e9d2cc
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 sha256:479698cf1fa3e8710aea592da04136d35bad3d39e7bddbd54c7d7b87963a2cf4
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ab3b539b8fc03731efbb7316c713d982e79a58e9287d0ae319d5bcf6c96f1b4
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": 2.0618556701030927e-05,
548
  "loss": 1.872,
549
  "step": 90
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
550
  }
551
  ],
552
  "logging_steps": 1,
553
  "max_steps": 100,
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": 2.0618556701030927e-05,
548
  "loss": 1.872,
549
  "step": 90
550
+ },
551
+ {
552
+ "epoch": 0.04,
553
+ "learning_rate": 1.8556701030927837e-05,
554
+ "loss": 1.4659,
555
+ "step": 91
556
+ },
557
+ {
558
+ "epoch": 0.04,
559
+ "learning_rate": 1.6494845360824743e-05,
560
+ "loss": 1.0273,
561
+ "step": 92
562
+ },
563
+ {
564
+ "epoch": 0.04,
565
+ "learning_rate": 1.4432989690721649e-05,
566
+ "loss": 1.5946,
567
+ "step": 93
568
+ },
569
+ {
570
+ "epoch": 0.04,
571
+ "learning_rate": 1.2371134020618558e-05,
572
+ "loss": 2.0506,
573
+ "step": 94
574
+ },
575
+ {
576
+ "epoch": 0.04,
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
  }