dixedus commited on
Commit
11696ae
·
verified ·
1 Parent(s): 17d5604

Training in progress, step 72, 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:fb97d9d163a73ea7f9751d1416577a26bb4b0dd126962fec44a06677503ff529
3
  size 34793120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4db804d5174d336b6f9629d4f70964a54f0fbb4b06ca277c59a799dac6d2306c
3
  size 34793120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0227abca3d752bb4f21e6bead416e0d844ff970d3c99e49714c2d6eb85f9f259
3
  size 18132116
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13f0be0df0a9bcd16c86c6dc461bb8b70554fa5d76c9eefedc9a36aa0d686186
3
  size 18132116
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a505b6f4b73db6520699af0051d1b07d67320ce5266a6dfbde7ef46ef8dab4d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07a8a9bdd862ce991dd45800936ca731700f83e2a539b63be29d121aacf28815
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:922634a168fad3088c2a461ec82359f2941891b1472f492b835996e27c3cba9d
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d899e046e5eb8fee9b81979db8db7b88d6dc92f30a13d049b906f3a3be1dfc0f
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": 0.8904593639575972,
5
  "eval_steps": 9,
6
- "global_step": 63,
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": 39.684,
219
  "eval_steps_per_second": 4.96,
220
  "step": 63
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
221
  }
222
  ],
223
  "logging_steps": 3,
@@ -237,7 +266,7 @@
237
  "attributes": {}
238
  }
239
  },
240
- "total_flos": 8009447909621760.0,
241
  "train_batch_size": 8,
242
  "trial_name": null,
243
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.017667844522968,
5
  "eval_steps": 9,
6
+ "global_step": 72,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
218
  "eval_samples_per_second": 39.684,
219
  "eval_steps_per_second": 4.96,
220
  "step": 63
221
+ },
222
+ {
223
+ "epoch": 0.9328621908127208,
224
+ "grad_norm": 0.06605750322341919,
225
+ "learning_rate": 1.56348351646022e-05,
226
+ "loss": 2.4754,
227
+ "step": 66
228
+ },
229
+ {
230
+ "epoch": 0.9752650176678446,
231
+ "grad_norm": 0.05665251612663269,
232
+ "learning_rate": 1.3263210930352737e-05,
233
+ "loss": 2.5084,
234
+ "step": 69
235
+ },
236
+ {
237
+ "epoch": 1.017667844522968,
238
+ "grad_norm": 0.051736362278461456,
239
+ "learning_rate": 1.1020177413231334e-05,
240
+ "loss": 2.591,
241
+ "step": 72
242
+ },
243
+ {
244
+ "epoch": 1.017667844522968,
245
+ "eval_loss": 2.3466386795043945,
246
+ "eval_runtime": 2.9973,
247
+ "eval_samples_per_second": 40.037,
248
+ "eval_steps_per_second": 5.005,
249
+ "step": 72
250
  }
251
  ],
252
  "logging_steps": 3,
 
266
  "attributes": {}
267
  }
268
  },
269
+ "total_flos": 9153654753853440.0,
270
  "train_batch_size": 8,
271
  "trial_name": null,
272
  "trial_params": null