clarxus commited on
Commit
fb22dc7
·
verified ·
1 Parent(s): 23652c1

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 sha256:993aff0d616f08ed583ec7c732efc989a542cf8cebf9d98347703d267646f68b
3
  size 161533192
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfd5afce7348151819c0fd9dc2b22dc5f859dd6fcac0662afa81383ff8c4a698
3
  size 161533192
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:57b285bf5ad6cf6b9cea547ac2fd5562d6d03592e0a4c91fadc5c1eefd109e36
3
  size 82460660
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43f4fad86dc10a669aa6ac202151c9d47ea9911b8025eefd006f339499dcb91e
3
  size 82460660
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:66a117ea053aab6fa5cc98c0bc1598d57e433e7e150af316d9ef492cf6161b89
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:809515f485ff8339ea759cadf35a9cf928f6fc34958e3f872da46cb4afcba971
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": 0.8181818181818182,
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": 8.683,
248
  "eval_steps_per_second": 1.115,
249
  "step": 72
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
250
  }
251
  ],
252
  "logging_steps": 3,
@@ -266,7 +295,7 @@
266
  "attributes": {}
267
  }
268
  },
269
- "total_flos": 1.705654411717509e+17,
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": 0.9204545454545454,
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": 8.683,
248
  "eval_steps_per_second": 1.115,
249
  "step": 72
250
+ },
251
+ {
252
+ "epoch": 0.8522727272727273,
253
+ "grad_norm": 1.535409688949585,
254
+ "learning_rate": 8.930309757836517e-06,
255
+ "loss": 2.0856,
256
+ "step": 75
257
+ },
258
+ {
259
+ "epoch": 0.8863636363636364,
260
+ "grad_norm": 1.479998230934143,
261
+ "learning_rate": 7.016504991533726e-06,
262
+ "loss": 1.9215,
263
+ "step": 78
264
+ },
265
+ {
266
+ "epoch": 0.9204545454545454,
267
+ "grad_norm": 1.4978396892547607,
268
+ "learning_rate": 5.299731159831953e-06,
269
+ "loss": 2.0011,
270
+ "step": 81
271
+ },
272
+ {
273
+ "epoch": 0.9204545454545454,
274
+ "eval_loss": 1.9259672164916992,
275
+ "eval_runtime": 17.0378,
276
+ "eval_samples_per_second": 8.687,
277
+ "eval_steps_per_second": 1.115,
278
+ "step": 81
279
  }
280
  ],
281
  "logging_steps": 3,
 
295
  "attributes": {}
296
  }
297
  },
298
+ "total_flos": 1.9258516001154662e+17,
299
  "train_batch_size": 8,
300
  "trial_name": null,
301
  "trial_params": null