auxyus commited on
Commit
8fd99e8
·
verified ·
1 Parent(s): 531b800

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 sha256:02577884df611dd60fb80159ae1b4cb618d3349cf8a0e1f0edb1299190b6c053
3
  size 125918320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a69f467bae445edb83cdc93110ee1d39380676f28a114d0280ed3c40cc00dcdb
3
  size 125918320
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:088cb11e750be1a66564f07e39bd8bad6a9171e0a0bad3c8f69fd81a00a8e9ef
3
  size 64683604
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6921e1855b9b87d250af8c258829c3aa968408b7edacb36d411edd29d8fc6d57
3
  size 64683604
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:68a8635fca5b7ec0840a5ada15e48cb6c62127c493cd074297b231a796d1174e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8de9f15cb7cf16a613c75ae673fe065d6d3ea271f16870a12211dedaaf4137b6
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5dcc5b33f65fdaffd6a8f394a182adc55f95c04061e1e53640018b07b2b89f10
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90f7a57653bcfdeb8d3e27706e79cc5f6e1f14bbd0ff72a8e33edaaa89ef8274
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": 0.027298578199052133,
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": 7.859,
248
  "eval_steps_per_second": 0.984,
249
  "step": 72
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
250
  }
251
  ],
252
  "logging_steps": 3,
@@ -266,7 +295,7 @@
266
  "attributes": {}
267
  }
268
  },
269
- "total_flos": 1.917867167412388e+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": 0.03071090047393365,
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": 7.859,
248
  "eval_steps_per_second": 0.984,
249
  "step": 72
250
+ },
251
+ {
252
+ "epoch": 0.02843601895734597,
253
+ "grad_norm": 4.369206428527832,
254
+ "learning_rate": 1.7860619515673033e-05,
255
+ "loss": 2.1532,
256
+ "step": 75
257
+ },
258
+ {
259
+ "epoch": 0.02957345971563981,
260
+ "grad_norm": 4.181845664978027,
261
+ "learning_rate": 1.4033009983067452e-05,
262
+ "loss": 2.0465,
263
+ "step": 78
264
+ },
265
+ {
266
+ "epoch": 0.03071090047393365,
267
+ "grad_norm": 4.068225383758545,
268
+ "learning_rate": 1.0599462319663905e-05,
269
+ "loss": 1.9805,
270
+ "step": 81
271
+ },
272
+ {
273
+ "epoch": 0.03071090047393365,
274
+ "eval_loss": 0.48237505555152893,
275
+ "eval_runtime": 565.3076,
276
+ "eval_samples_per_second": 7.858,
277
+ "eval_steps_per_second": 0.984,
278
+ "step": 81
279
  }
280
  ],
281
  "logging_steps": 3,
 
295
  "attributes": {}
296
  }
297
  },
298
+ "total_flos": 2.1634795839474893e+17,
299
  "train_batch_size": 8,
300
  "trial_name": null,
301
  "trial_params": null