dimasik87 commited on
Commit
3e912d4
·
verified ·
1 Parent(s): b0c00eb

Training in progress, step 24, 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:f5e74f2c0f6c8718bfb11db555903b3311629e8a1d6aaa3955497c1d1b2861b3
3
  size 767856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fedda0e97e830103c40f700f4873855bbadc6e072a7633e5d19307123b1919fb
3
  size 767856
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d1f6c8c7837757a9a61314e82f7d54a6b2778e683a9c519822e1304d5feec53a
3
  size 1601338
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:815dbaf33c54ccf6aca94a1a868eea78ef23b0cd589f78171d3beb60101910fd
3
  size 1601338
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d6f8c1bb44b3bf7f6dd68732a83f5e01a15949b2ddeff8197272f5b012b6e34e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:067f8b0f85e5ac448631bc4ef4291d838ac65f22fa74b4f23300ecb47979612e
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cfc868d168373f518aa3d81b0bcf5eaf44208e53fb25d46f5a39136146621a60
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9be43866b7a112efbf8125d7bbc11610819a4fb8c7f205bdfffb33dc32734ab8
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": 0.006797216378054701,
5
  "eval_steps": 3,
6
- "global_step": 21,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -218,6 +218,35 @@
218
  "eval_samples_per_second": 80.033,
219
  "eval_steps_per_second": 40.017,
220
  "step": 21
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
221
  }
222
  ],
223
  "logging_steps": 1,
@@ -237,7 +266,7 @@
237
  "attributes": {}
238
  }
239
  },
240
- "total_flos": 17104197648384.0,
241
  "train_batch_size": 2,
242
  "trial_name": null,
243
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.007768247289205373,
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,
 
218
  "eval_samples_per_second": 80.033,
219
  "eval_steps_per_second": 40.017,
220
  "step": 21
221
+ },
222
+ {
223
+ "epoch": 0.007120893348438259,
224
+ "grad_norm": 3.710598945617676,
225
+ "learning_rate": 1.9098300562505266e-05,
226
+ "loss": 9.5764,
227
+ "step": 22
228
+ },
229
+ {
230
+ "epoch": 0.0074445703188218155,
231
+ "grad_norm": 4.25644063949585,
232
+ "learning_rate": 8.645454235739903e-06,
233
+ "loss": 9.0068,
234
+ "step": 23
235
+ },
236
+ {
237
+ "epoch": 0.007768247289205373,
238
+ "grad_norm": 4.236860275268555,
239
+ "learning_rate": 2.1852399266194314e-06,
240
+ "loss": 10.1768,
241
+ "step": 24
242
+ },
243
+ {
244
+ "epoch": 0.007768247289205373,
245
+ "eval_loss": 9.696382522583008,
246
+ "eval_runtime": 24.3495,
247
+ "eval_samples_per_second": 80.166,
248
+ "eval_steps_per_second": 40.083,
249
+ "step": 24
250
  }
251
  ],
252
  "logging_steps": 1,
 
266
  "attributes": {}
267
  }
268
  },
269
+ "total_flos": 19547654455296.0,
270
  "train_batch_size": 2,
271
  "trial_name": null,
272
  "trial_params": null