ramdhanfirdaus commited on
Commit
6e7047c
1 Parent(s): ef0003b

Training in progress, step 3100, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:30abfb839cec746369ea13a06b600a7b92f0e9f40f2d6f943ae0a64dd0b1711e
3
  size 75507072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fde2cd0cf6d40cb850b65d1bc5d18b30cd332d6d9c120818d3fc4a0e538baa40
3
  size 75507072
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f7cf416a1e8e2bb3ecbc2d7d94875ff3ca17723c05072d4dd2b338a8bb3a1d66
3
  size 151034501
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:665a1e527fd239417ff50a71f133d7f3a3697d1ea1306dacc8961dd283167746
3
  size 151034501
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:01f685e2bfdf120cb9f33f03b5cfc13afc255a166c60899a27a5d70125a9a675
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab6b545b6dd6418e570a8474ea31c45a1baed67ab97da8014ad68491fbcf9bed
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cb57538b0fddb988f32d5e33311bcf25efee1aa4001ec3e33ef4a2dd884d77d3
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f4766a50a63740d51a19c983a4de442d7f62ff1e951fc016c44cc6c58fb9db1
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
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,
@@ -427,13 +427,27 @@
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
  }
 
1
  {
2
+ "best_metric": 1.1677733659744263,
3
+ "best_model_checkpoint": "./outputs/checkpoint-3100",
4
+ "epoch": 2.2586520947176685,
5
  "eval_steps": 100,
6
+ "global_step": 3100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
427
  "eval_samples_per_second": 15.023,
428
  "eval_steps_per_second": 1.88,
429
  "step": 3000
430
+ },
431
+ {
432
+ "epoch": 2.26,
433
+ "learning_rate": 0.0002,
434
+ "loss": 1.1395,
435
+ "step": 3100
436
+ },
437
+ {
438
+ "epoch": 2.26,
439
+ "eval_loss": 1.1677733659744263,
440
+ "eval_runtime": 417.4863,
441
+ "eval_samples_per_second": 15.028,
442
+ "eval_steps_per_second": 1.88,
443
+ "step": 3100
444
  }
445
  ],
446
  "logging_steps": 100,
447
  "max_steps": 4116,
448
  "num_train_epochs": 3,
449
  "save_steps": 100,
450
+ "total_flos": 1.0050782869364552e+18,
451
  "trial_name": null,
452
  "trial_params": null
453
  }