ramdhanfirdaus commited on
Commit
5f55321
1 Parent(s): 9730a0d

Training in progress, step 2400, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b224bb2144b166ed0f3223f5de34c9a9ae294eff60b66b723c7a6b541a045cf
3
  size 75507072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3de14f08f155ab5012317e0ab6ca05907566ba28980ed01d299c07246532e37
3
  size 75507072
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:20d523a25eb3995eb7b033b67953af8ff66244daec4522a6d2b2f5c78796dd36
3
  size 151034501
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f96ba4d51ba642e51959e86f9bb4544c4930e899c92070faa515407fa6283f32
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:c0ecaa372dca690ec2f6181df8c7b03d3248836d0042c5e635eada8af4366c91
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6df3c3e6d66c14ab5f979071ad4f8c384c7c65af069e4b3c79758858b3a854dc
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:58c098aa199ff890a6444b804a3fbc89c9468b8e4fb7f53db1b50396e4ed0c2d
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a78e728336b77d3305afe2734acb1241c76f8f2c33b35460bc07397abc49ba2
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.2497906684875488,
3
- "best_model_checkpoint": "./outputs/checkpoint-2300",
4
- "epoch": 1.6757741347905282,
5
  "eval_steps": 100,
6
- "global_step": 2300,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -329,13 +329,27 @@
329
  "eval_samples_per_second": 15.019,
330
  "eval_steps_per_second": 1.879,
331
  "step": 2300
 
 
 
 
 
 
 
 
 
 
 
 
 
 
332
  }
333
  ],
334
  "logging_steps": 100,
335
  "max_steps": 4116,
336
  "num_train_epochs": 3,
337
  "save_steps": 100,
338
- "total_flos": 7.457059409239757e+17,
339
  "trial_name": null,
340
  "trial_params": null
341
  }
 
1
  {
2
+ "best_metric": 1.2375760078430176,
3
+ "best_model_checkpoint": "./outputs/checkpoint-2400",
4
+ "epoch": 1.748633879781421,
5
  "eval_steps": 100,
6
+ "global_step": 2400,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
329
  "eval_samples_per_second": 15.019,
330
  "eval_steps_per_second": 1.879,
331
  "step": 2300
332
+ },
333
+ {
334
+ "epoch": 1.75,
335
+ "learning_rate": 0.0002,
336
+ "loss": 1.2412,
337
+ "step": 2400
338
+ },
339
+ {
340
+ "epoch": 1.75,
341
+ "eval_loss": 1.2375760078430176,
342
+ "eval_runtime": 417.7184,
343
+ "eval_samples_per_second": 15.02,
344
+ "eval_steps_per_second": 1.879,
345
+ "step": 2400
346
  }
347
  ],
348
  "logging_steps": 100,
349
  "max_steps": 4116,
350
  "num_train_epochs": 3,
351
  "save_steps": 100,
352
+ "total_flos": 7.781170380374385e+17,
353
  "trial_name": null,
354
  "trial_params": null
355
  }