DuongTrongChi commited on
Commit
607684a
1 Parent(s): 6e13282

Training in progress, step 45, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a4ff1d0bd6ac86edfcec5edcaf85802e9d94f98dc66173056b7c39d0ea91f20
3
  size 100198584
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:672f916bebd7a5d3bc18cb32b38eef5409ec4970a4f0e264344d1d898aed73c7
3
  size 100198584
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4224b11968d7a1169054c9405ec53b5db31b399e6bb57a32f4adc100f7284d92
3
  size 50675156
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68ecb70cde7af6cfe8d984e2a09352a923bdbcdd1e80a416a9e4a53e0f1b6389
3
  size 50675156
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c134361f6786d848c90ab6fe56c7855e1e48d2d09ca3556b281b17aa210f9d50
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cc121e67e70577df944161a080afe74f5e848cfee5c8b258778d6cec57833eb
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.12071330589849108,
5
  "eval_steps": 500,
6
- "global_step": 44,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -315,6 +315,13 @@
315
  "learning_rate": 8.800000000000001e-05,
316
  "loss": 1.3378,
317
  "step": 44
 
 
 
 
 
 
 
318
  }
319
  ],
320
  "logging_steps": 1,
@@ -334,7 +341,7 @@
334
  "attributes": {}
335
  }
336
  },
337
- "total_flos": 1.2527009113994035e+17,
338
  "train_batch_size": 16,
339
  "trial_name": null,
340
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.12345679012345678,
5
  "eval_steps": 500,
6
+ "global_step": 45,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
315
  "learning_rate": 8.800000000000001e-05,
316
  "loss": 1.3378,
317
  "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.12345679012345678,
321
+ "grad_norm": 0.12385573983192444,
322
+ "learning_rate": 9e-05,
323
+ "loss": 1.2032,
324
+ "step": 45
325
  }
326
  ],
327
  "logging_steps": 1,
 
341
  "attributes": {}
342
  }
343
  },
344
+ "total_flos": 1.279779880523858e+17,
345
  "train_batch_size": 16,
346
  "trial_name": null,
347
  "trial_params": null