DuongTrongChi commited on
Commit
f6832ec
1 Parent(s): c425dbb

Training in progress, step 37, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c4c2c5b373f6a50d462b25c2a377562f91b4389f0e2d101d2feb433346495d8
3
  size 100198584
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:884cc4e8aa6c9621e8b91e5cd70760d8455b34dbf5b7ef4b5d1d8f041c31e5f1
3
  size 100198584
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f9a26df27a852fcc25a43cec6ed5388e796c14c8dee9596a8fd6a85722b9a531
3
  size 50675156
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85d0be838345ed7a8da9240dcc6a94880a0713205f9886770aec70b397d28ef8
3
  size 50675156
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cc45c09e66fd942f81d3e1a2a005793e3b66657aac967cab369d222230d52fd0
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:936ee85bcb507716e18474dc9cdf2a95bc2e2f298bec38ce951a907f92c6a06e
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": 0.09876543209876543,
5
  "eval_steps": 500,
6
- "global_step": 36,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -259,6 +259,13 @@
259
  "learning_rate": 7.2e-05,
260
  "loss": 1.3956,
261
  "step": 36
 
 
 
 
 
 
 
262
  }
263
  ],
264
  "logging_steps": 1,
@@ -278,7 +285,7 @@
278
  "attributes": {}
279
  }
280
  },
281
- "total_flos": 1.029250509239255e+17,
282
  "train_batch_size": 16,
283
  "trial_name": null,
284
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.10150891632373114,
5
  "eval_steps": 500,
6
+ "global_step": 37,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
259
  "learning_rate": 7.2e-05,
260
  "loss": 1.3956,
261
  "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.10150891632373114,
265
+ "grad_norm": 0.4032560884952545,
266
+ "learning_rate": 7.4e-05,
267
+ "loss": 1.3773,
268
+ "step": 37
269
  }
270
  ],
271
  "logging_steps": 1,
 
285
  "attributes": {}
286
  }
287
  },
288
+ "total_flos": 1.0569755640338842e+17,
289
  "train_batch_size": 16,
290
  "trial_name": null,
291
  "trial_params": null