dimasik87 commited on
Commit
ecad262
1 Parent(s): a153e9a

Training in progress, step 25, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7218447982eff110f849b470233fc4a6d276fed4f1c7ddac27d3905dc8dc40cf
3
  size 27024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:417e664fb27e10049bc564cbb0ac9b046e9bd404d7b3c11b95be8cbcdea2957d
3
  size 27024
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dc0b81dc68d12bd72222a18ddd1d7ff6e0c3c13f2afdc5364d487a263591e3bb
3
  size 70922
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:733e3340a51a130168a1f82a8be5b952a7fbc2edb66c7b3ffd89e3a7b188b451
3
  size 70922
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab594e810d8ab32046a6e307046228ac632e78669c4e55927f43fe5185a83078
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6483ca195bd59928c1f00a9166e770b271a5cda1143798c54df975ec34031428
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9be43866b7a112efbf8125d7bbc11610819a4fb8c7f205bdfffb33dc32734ab8
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4521b8db9cc205e54aa606d85e707c024abd2d8ad4a20bec4b2cff365dc59cdf
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": 0.0017012227538543328,
5
  "eval_steps": 3,
6
- "global_step": 24,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -247,6 +247,13 @@
247
  "eval_samples_per_second": 127.262,
248
  "eval_steps_per_second": 127.262,
249
  "step": 24
 
 
 
 
 
 
 
250
  }
251
  ],
252
  "logging_steps": 1,
@@ -261,12 +268,12 @@
261
  "should_evaluate": false,
262
  "should_log": false,
263
  "should_save": true,
264
- "should_training_stop": false
265
  },
266
  "attributes": {}
267
  }
268
  },
269
- "total_flos": 620683591680.0,
270
  "train_batch_size": 1,
271
  "trial_name": null,
272
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.00177210703526493,
5
  "eval_steps": 3,
6
+ "global_step": 25,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
247
  "eval_samples_per_second": 127.262,
248
  "eval_steps_per_second": 127.262,
249
  "step": 24
250
+ },
251
+ {
252
+ "epoch": 0.00177210703526493,
253
+ "grad_norm": 0.07770507037639618,
254
+ "learning_rate": 0.0,
255
+ "loss": 10.3784,
256
+ "step": 25
257
  }
258
  ],
259
  "logging_steps": 1,
 
268
  "should_evaluate": false,
269
  "should_log": false,
270
  "should_save": true,
271
+ "should_training_stop": true
272
  },
273
  "attributes": {}
274
  }
275
  },
276
+ "total_flos": 646545408000.0,
277
  "train_batch_size": 1,
278
  "trial_name": null,
279
  "trial_params": null