brixeus commited on
Commit
5a07c1e
·
verified ·
1 Parent(s): d808e88

Training in progress, step 81, 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:c37a24adf9c3e8af6a36a77732ea1a02518b265bc1b7459422d625668ac3f691
3
  size 25192688
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4abe0a462c1e0ca5a3b68930944cef3583c76709996ffad6724268682a769300
3
  size 25192688
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:976a83bf0bcea90c0bc7cca5efd9f40f43b8226e527d4d641f9645232fdc0683
3
  size 13005178
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2eee3d652a9893091cef4e326884c2885c2b9c9485c28aa000522b99e12b1c9
3
  size 13005178
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d586ff3a365cea90dd140eb51f5d7760b8f6a0b293d7fb243ca3e748ea6a51a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5066b7dfe731942be4af3b1b28e679d0bf8d4a2fa0007add9f33d22921a55916
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d899e046e5eb8fee9b81979db8db7b88d6dc92f30a13d049b906f3a3be1dfc0f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bec84b33191b76a1f66109f05ca2863b65ba9c0ae66be6a4921ad95ad9f1a38e
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": 0.02392225267879392,
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,
@@ -247,6 +247,35 @@
247
  "eval_samples_per_second": 22.906,
248
  "eval_steps_per_second": 2.865,
249
  "step": 72
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
250
  }
251
  ],
252
  "logging_steps": 3,
@@ -266,7 +295,7 @@
266
  "attributes": {}
267
  }
268
  },
269
- "total_flos": 5961239922475008.0,
270
  "train_batch_size": 8,
271
  "trial_name": null,
272
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.02691253426364316,
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,
 
247
  "eval_samples_per_second": 22.906,
248
  "eval_steps_per_second": 2.865,
249
  "step": 72
250
+ },
251
+ {
252
+ "epoch": 0.024919013207076998,
253
+ "grad_norm": 3.9145100116729736,
254
+ "learning_rate": 8.930309757836517e-06,
255
+ "loss": 5.9105,
256
+ "step": 75
257
+ },
258
+ {
259
+ "epoch": 0.02591577373536008,
260
+ "grad_norm": 4.379709720611572,
261
+ "learning_rate": 7.016504991533726e-06,
262
+ "loss": 7.0362,
263
+ "step": 78
264
+ },
265
+ {
266
+ "epoch": 0.02691253426364316,
267
+ "grad_norm": 4.382705211639404,
268
+ "learning_rate": 5.299731159831953e-06,
269
+ "loss": 5.4184,
270
+ "step": 81
271
+ },
272
+ {
273
+ "epoch": 0.02691253426364316,
274
+ "eval_loss": 1.537489891052246,
275
+ "eval_runtime": 221.2804,
276
+ "eval_samples_per_second": 22.908,
277
+ "eval_steps_per_second": 2.865,
278
+ "step": 81
279
  }
280
  ],
281
  "logging_steps": 3,
 
295
  "attributes": {}
296
  }
297
  },
298
+ "total_flos": 6704498844106752.0,
299
  "train_batch_size": 8,
300
  "trial_name": null,
301
  "trial_params": null