oldiday commited on
Commit
6ead66a
·
verified ·
1 Parent(s): 245255e

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 sha256:99d0c9bd199202667ea6ddbff77fe3ae44382dbee87987c33da7a5166a176c83
3
  size 73911112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8084f2694e163a264197d7917f8d6fbea3e2ec65874835e7d4e56335957eb8c
3
  size 73911112
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b1e71b573c3bf82448bdee7bdd69394a5e893e8bf4a6afc29744347d8da35762
3
  size 37965300
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:848e7d31a743661e7df912c621c94a4704b71638c5d095b79f9ff7d8ed390f9c
3
  size 37965300
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ba011c9e555bcbe3ac2f8124b37661b41ac93648fa02f025e3ad48558449cb1d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c95ca45a493e6ca4c3e96903e02caca906defc4426d872c5bf2434b8480c5e21
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": 0.0024285148114106467,
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": 30.138,
248
  "eval_steps_per_second": 3.768,
249
  "step": 72
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
250
  }
251
  ],
252
  "logging_steps": 3,
@@ -266,7 +295,7 @@
266
  "attributes": {}
267
  }
268
  },
269
- "total_flos": 2.2337197109673984e+16,
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": 0.0027320791628369775,
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": 30.138,
248
  "eval_steps_per_second": 3.768,
249
  "step": 72
250
+ },
251
+ {
252
+ "epoch": 0.002529702928552757,
253
+ "grad_norm": 0.21596688032150269,
254
+ "learning_rate": 8.930309757836517e-06,
255
+ "loss": 0.785,
256
+ "step": 75
257
+ },
258
+ {
259
+ "epoch": 0.0026308910456948674,
260
+ "grad_norm": 0.2620626389980316,
261
+ "learning_rate": 7.016504991533726e-06,
262
+ "loss": 0.8722,
263
+ "step": 78
264
+ },
265
+ {
266
+ "epoch": 0.0027320791628369775,
267
+ "grad_norm": 0.29990634322166443,
268
+ "learning_rate": 5.299731159831953e-06,
269
+ "loss": 0.8015,
270
+ "step": 81
271
+ },
272
+ {
273
+ "epoch": 0.0027320791628369775,
274
+ "eval_loss": 0.8147459030151367,
275
+ "eval_runtime": 1656.7133,
276
+ "eval_samples_per_second": 30.14,
277
+ "eval_steps_per_second": 3.768,
278
+ "step": 81
279
  }
280
  ],
281
  "logging_steps": 3,
 
295
  "attributes": {}
296
  }
297
  },
298
+ "total_flos": 2.514567510884352e+16,
299
  "train_batch_size": 8,
300
  "trial_name": null,
301
  "trial_params": null