ardaspear commited on
Commit
705bb98
·
verified ·
1 Parent(s): a0ba3c0

Training in progress, step 90, 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:fb3391cc964032c4f7bbececa19b46ffa89526608f10dc32217bf61d3203c27c
3
  size 247936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:037121f73a5ff6c01dfa5f8c106ac3433ff46de20fc9c44a46c247a85576de46
3
  size 247936
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e05c54bd7d150324fee7fb367dbf0999cb0f7383c79b063e43a7dea0435733e9
3
  size 263024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:496d9757580288d8509ddfe99b04e84ee3c3f6ccd1df9532fda74934a1ec9f68
3
  size 263024
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7e60026f80fd7f1a2958d0aa771127ff3ac2eee272a3f23e35c58ef19e35fd09
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f809f3a9bd317f6dc50b7c5d7a14135ab1c1e2d413bfb7e8872835b0a5d61e58
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:90f7a57653bcfdeb8d3e27706e79cc5f6e1f14bbd0ff72a8e33edaaa89ef8274
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f7d03f1dba06dbe949e0b7294b5a80e81e1c97413b12e930c7d1d62b4e569ba
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": 0.09207161125319693,
5
  "eval_steps": 9,
6
- "global_step": 81,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -276,6 +276,35 @@
276
  "eval_samples_per_second": 175.096,
277
  "eval_steps_per_second": 43.951,
278
  "step": 81
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
279
  }
280
  ],
281
  "logging_steps": 3,
@@ -295,7 +324,7 @@
295
  "attributes": {}
296
  }
297
  },
298
- "total_flos": 719774023680.0,
299
  "train_batch_size": 4,
300
  "trial_name": null,
301
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.10230179028132992,
5
  "eval_steps": 9,
6
+ "global_step": 90,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
276
  "eval_samples_per_second": 175.096,
277
  "eval_steps_per_second": 43.951,
278
  "step": 81
279
+ },
280
+ {
281
+ "epoch": 0.09548167092924126,
282
+ "grad_norm": 1.081790566444397,
283
+ "learning_rate": 7.597595192178702e-06,
284
+ "loss": 43.735,
285
+ "step": 84
286
+ },
287
+ {
288
+ "epoch": 0.0988917306052856,
289
+ "grad_norm": 0.8974946737289429,
290
+ "learning_rate": 5.060297685041659e-06,
291
+ "loss": 43.7617,
292
+ "step": 87
293
+ },
294
+ {
295
+ "epoch": 0.10230179028132992,
296
+ "grad_norm": 1.1310738325119019,
297
+ "learning_rate": 3.0153689607045845e-06,
298
+ "loss": 43.7058,
299
+ "step": 90
300
+ },
301
+ {
302
+ "epoch": 0.10230179028132992,
303
+ "eval_loss": 10.934582710266113,
304
+ "eval_runtime": 4.682,
305
+ "eval_samples_per_second": 158.267,
306
+ "eval_steps_per_second": 39.727,
307
+ "step": 90
308
  }
309
  ],
310
  "logging_steps": 3,
 
324
  "attributes": {}
325
  }
326
  },
327
+ "total_flos": 798370037760.0,
328
  "train_batch_size": 4,
329
  "trial_name": null,
330
  "trial_params": null