ramdhanfirdaus commited on
Commit
ccfeecd
1 Parent(s): ab522c3

Training in progress, step 2900, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9558ffacb1406cf319cb4564cd910ab2eb5c43f2c3fdad67a59a22f993d61909
3
  size 75507072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b31b4a00a58b78fe2a07a65de9d4800daafad305a40c731ec7818259b4f4e152
3
  size 75507072
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:deadd118a49b60af187a6021b932f75dab37d56200bfa634238d4e39da3da637
3
  size 151034501
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f88ce03d03ef0ab0ab5aaf2b800b48d66beb2b623d9605c54480fc317792db7
3
  size 151034501
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:84bb513a36255f7d8ac49c282923197f8cd306767f0110ec7b93a182523a1deb
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0113ad93500b070ec629f543dd5608478106668e37e4a31f0489501e14482509
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:79c08a7148c570c3d4c87a735e3acef3af52d256eb019f3a3f3feeab8a656949
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:097f95efaf3ced711759e9e49c3b8b3ef906ff28483e958d227db85b3ea360b9
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.1963659524917603,
3
- "best_model_checkpoint": "./outputs/checkpoint-2800",
4
- "epoch": 2.040072859744991,
5
  "eval_steps": 100,
6
- "global_step": 2800,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -399,13 +399,27 @@
399
  "eval_samples_per_second": 15.019,
400
  "eval_steps_per_second": 1.879,
401
  "step": 2800
 
 
 
 
 
 
 
 
 
 
 
 
 
 
402
  }
403
  ],
404
  "logging_steps": 100,
405
  "max_steps": 4116,
406
  "num_train_epochs": 3,
407
  "save_steps": 100,
408
- "total_flos": 9.077493057814364e+17,
409
  "trial_name": null,
410
  "trial_params": null
411
  }
 
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,
 
399
  "eval_samples_per_second": 15.019,
400
  "eval_steps_per_second": 1.879,
401
  "step": 2800
402
+ },
403
+ {
404
+ "epoch": 2.11,
405
+ "learning_rate": 0.0002,
406
+ "loss": 1.1541,
407
+ "step": 2900
408
+ },
409
+ {
410
+ "epoch": 2.11,
411
+ "eval_loss": 1.1863473653793335,
412
+ "eval_runtime": 417.6096,
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
  }