ramdhanfirdaus commited on
Commit
29a77c8
1 Parent(s): 4757f2e

Training in progress, step 3000, 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:b31b4a00a58b78fe2a07a65de9d4800daafad305a40c731ec7818259b4f4e152
3
  size 75507072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30abfb839cec746369ea13a06b600a7b92f0e9f40f2d6f943ae0a64dd0b1711e
3
  size 75507072
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f88ce03d03ef0ab0ab5aaf2b800b48d66beb2b623d9605c54480fc317792db7
3
  size 151034501
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7cf416a1e8e2bb3ecbc2d7d94875ff3ca17723c05072d4dd2b338a8bb3a1d66
3
  size 151034501
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0113ad93500b070ec629f543dd5608478106668e37e4a31f0489501e14482509
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01f685e2bfdf120cb9f33f03b5cfc13afc255a166c60899a27a5d70125a9a675
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:097f95efaf3ced711759e9e49c3b8b3ef906ff28483e958d227db85b3ea360b9
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb57538b0fddb988f32d5e33311bcf25efee1aa4001ec3e33ef4a2dd884d77d3
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.1863473653793335,
3
- "best_model_checkpoint": "./outputs/checkpoint-2900",
4
- "epoch": 2.1129326047358834,
5
  "eval_steps": 100,
6
- "global_step": 2900,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -413,13 +413,27 @@
413
  "eval_samples_per_second": 15.024,
414
  "eval_steps_per_second": 1.88,
415
  "step": 2900
 
 
 
 
 
 
 
 
 
 
 
 
 
 
416
  }
417
  ],
418
  "logging_steps": 100,
419
  "max_steps": 4116,
420
  "num_train_epochs": 3,
421
  "save_steps": 100,
422
- "total_flos": 9.401047433193892e+17,
423
  "trial_name": null,
424
  "trial_params": null
425
  }
 
1
  {
2
+ "best_metric": 1.17583167552948,
3
+ "best_model_checkpoint": "./outputs/checkpoint-3000",
4
+ "epoch": 2.185792349726776,
5
  "eval_steps": 100,
6
+ "global_step": 3000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
413
  "eval_samples_per_second": 15.024,
414
  "eval_steps_per_second": 1.88,
415
  "step": 2900
416
+ },
417
+ {
418
+ "epoch": 2.19,
419
+ "learning_rate": 0.0002,
420
+ "loss": 1.1567,
421
+ "step": 3000
422
+ },
423
+ {
424
+ "epoch": 2.19,
425
+ "eval_loss": 1.17583167552948,
426
+ "eval_runtime": 417.6171,
427
+ "eval_samples_per_second": 15.023,
428
+ "eval_steps_per_second": 1.88,
429
+ "step": 3000
430
  }
431
  ],
432
  "logging_steps": 100,
433
  "max_steps": 4116,
434
  "num_train_epochs": 3,
435
  "save_steps": 100,
436
+ "total_flos": 9.726295518292378e+17,
437
  "trial_name": null,
438
  "trial_params": null
439
  }