TachyHealthResearch commited on
Commit
e8f6ba1
·
1 Parent(s): cfef509

Training in progress, step 65, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:492f62c36a1692ce068912b1d628ba12ae76234d0c198404d8ebdcc99d481a0c
3
  size 125248064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ad064f22dab87d3f89ed5c3c9a6228ec9671fe6c3881dc79eaf9164c1257ffa
3
  size 125248064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d7ff9e56c8601711ed636ec4fe19a91638ec31dae45461988c532ca4a51e34d8
3
  size 63350356
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7a7ba9645022e500d708b119cb844695141adf068dd664b9a374923a7589910
3
  size 63350356
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:78da1da061288012ca67a39eca3ceec230fb3877f3be89de615db089beb7984c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad16dda5b42ed1a3750dc7c5d4d95215438c97f721863ee8d5f5fbd09779cc98
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a1b67e0370258becf640b62b2d37ad76e97fbb2bcef2aed2b85f7b9a0e5265f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25af55feb1b9903fcca68f02f47bace5e1e3ee14f2adaa2a9b2e961c20b03a84
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": 0.024,
5
  "eval_steps": 1000,
6
- "global_step": 60,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -367,13 +367,43 @@
367
  "learning_rate": 8.247422680412371e-05,
368
  "loss": 1.7194,
369
  "step": 60
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
370
  }
371
  ],
372
  "logging_steps": 1,
373
  "max_steps": 100,
374
  "num_train_epochs": 1,
375
  "save_steps": 5,
376
- "total_flos": 6638833090068480.0,
377
  "trial_name": null,
378
  "trial_params": null
379
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.026,
5
  "eval_steps": 1000,
6
+ "global_step": 65,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
367
  "learning_rate": 8.247422680412371e-05,
368
  "loss": 1.7194,
369
  "step": 60
370
+ },
371
+ {
372
+ "epoch": 0.02,
373
+ "learning_rate": 8.041237113402063e-05,
374
+ "loss": 1.7635,
375
+ "step": 61
376
+ },
377
+ {
378
+ "epoch": 0.02,
379
+ "learning_rate": 7.835051546391753e-05,
380
+ "loss": 1.5533,
381
+ "step": 62
382
+ },
383
+ {
384
+ "epoch": 0.03,
385
+ "learning_rate": 7.628865979381443e-05,
386
+ "loss": 1.4684,
387
+ "step": 63
388
+ },
389
+ {
390
+ "epoch": 0.03,
391
+ "learning_rate": 7.422680412371135e-05,
392
+ "loss": 1.3388,
393
+ "step": 64
394
+ },
395
+ {
396
+ "epoch": 0.03,
397
+ "learning_rate": 7.216494845360825e-05,
398
+ "loss": 1.4259,
399
+ "step": 65
400
  }
401
  ],
402
  "logging_steps": 1,
403
  "max_steps": 100,
404
  "num_train_epochs": 1,
405
  "save_steps": 5,
406
+ "total_flos": 7198794280796160.0,
407
  "trial_name": null,
408
  "trial_params": null
409
  }