ramdhanfirdaus commited on
Commit
4381c41
1 Parent(s): 0a00984

Training in progress, step 2700, 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:fb90b4a01c2b1f6a1dee1a7ee71eee274538d61adb1808da614d4b82be99c789
3
  size 75507072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1c69e0a024d6505c17255e34483719ad08d7d6393ac25061d160f2f0da882e4
3
  size 75507072
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:72931b28bd75ed18775198c2152512ff9b31630990ab6c77e8e49354210c1960
3
  size 151034501
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:612e26221044539294665a9713613ae5f15ebacfc38fce426bb948c6321bccc9
3
  size 151034501
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:442bafcbf0d292ca19eedeb960e51c5d7ecd5eec12507df91524cb8e1081a81b
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89071e526b1b7beed654269a10a336d28a5d83cc28ed2dc62051376c98906e08
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ee2eceee28d7a299780008f817c050eb9e87b0d18fb8d8f19062cda68b3e10f9
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d747a341abc7681ba1384e20b96e3fad64e2a0f72aee64e5047f8f5bba229c8f
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.216168999671936,
3
- "best_model_checkpoint": "./outputs/checkpoint-2600",
4
- "epoch": 1.8943533697632058,
5
  "eval_steps": 100,
6
- "global_step": 2600,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -371,13 +371,27 @@
371
  "eval_samples_per_second": 15.02,
372
  "eval_steps_per_second": 1.879,
373
  "step": 2600
 
 
 
 
 
 
 
 
 
 
 
 
 
 
374
  }
375
  ],
376
  "logging_steps": 100,
377
  "max_steps": 4116,
378
  "num_train_epochs": 3,
379
  "save_steps": 100,
380
- "total_flos": 8.428488053895383e+17,
381
  "trial_name": null,
382
  "trial_params": null
383
  }
 
1
  {
2
+ "best_metric": 1.2053289413452148,
3
+ "best_model_checkpoint": "./outputs/checkpoint-2700",
4
+ "epoch": 1.9672131147540983,
5
  "eval_steps": 100,
6
+ "global_step": 2700,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
371
  "eval_samples_per_second": 15.02,
372
  "eval_steps_per_second": 1.879,
373
  "step": 2600
374
+ },
375
+ {
376
+ "epoch": 1.97,
377
+ "learning_rate": 0.0002,
378
+ "loss": 1.2034,
379
+ "step": 2700
380
+ },
381
+ {
382
+ "epoch": 1.97,
383
+ "eval_loss": 1.2053289413452148,
384
+ "eval_runtime": 417.5961,
385
+ "eval_samples_per_second": 15.024,
386
+ "eval_steps_per_second": 1.88,
387
+ "step": 2700
388
  }
389
  ],
390
  "logging_steps": 100,
391
  "max_steps": 4116,
392
  "num_train_epochs": 3,
393
  "save_steps": 100,
394
+ "total_flos": 8.753264069241692e+17,
395
  "trial_name": null,
396
  "trial_params": null
397
  }