clarxus commited on
Commit
bcf64d5
·
verified ·
1 Parent(s): 125191e

Training in progress, step 99, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:282639d610792c276672138f2de55fc28c5a8fb44a285147342df6216bd85baf
3
  size 159967880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04103639c17678edb58d385753a6f141982ddffd33c68ba11c40ae230b0dfab4
3
  size 159967880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a7c49acc240924ce405899014142552a60a9b088a15cdcd422796eda55ad8249
3
  size 81730196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1f0ee9181440a06d942bedec23bf649ce525f2a5ef286f37c6c97f80aab7203
3
  size 81730196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f65d33f8dbb303a0d5f68445f3c91506d6bca32bb2475114b5510685edbdcace
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a002c35283ee15865b652908226f5a02d99c68599148fb6605a660ea5c853706
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0569f9f06b6a114946825bdc699040cc55958cfef46aba8eb5fb625896d49025
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b64833e2721bfb57dae2a544bde34ace02492c2f80bfbff48034c9946dc6b4a
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": 0.0073554951678483135,
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,
@@ -305,6 +305,35 @@
305
  "eval_samples_per_second": 13.942,
306
  "eval_steps_per_second": 1.743,
307
  "step": 90
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
308
  }
309
  ],
310
  "logging_steps": 3,
@@ -324,7 +353,7 @@
324
  "attributes": {}
325
  }
326
  },
327
- "total_flos": 1.2632210439929856e+17,
328
  "train_batch_size": 8,
329
  "trial_name": null,
330
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.008091044684633144,
5
  "eval_steps": 9,
6
+ "global_step": 99,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
305
  "eval_samples_per_second": 13.942,
306
  "eval_steps_per_second": 1.743,
307
  "step": 90
308
+ },
309
+ {
310
+ "epoch": 0.007600678340109924,
311
+ "grad_norm": 1.427655577659607,
312
+ "learning_rate": 7.426068431000882e-07,
313
+ "loss": 1.6916,
314
+ "step": 93
315
+ },
316
+ {
317
+ "epoch": 0.007845861512371535,
318
+ "grad_norm": 1.4828401803970337,
319
+ "learning_rate": 2.4329828146074095e-07,
320
+ "loss": 1.7312,
321
+ "step": 96
322
+ },
323
+ {
324
+ "epoch": 0.008091044684633144,
325
+ "grad_norm": 1.8109315633773804,
326
+ "learning_rate": 1.522932452260595e-08,
327
+ "loss": 1.8273,
328
+ "step": 99
329
+ },
330
+ {
331
+ "epoch": 0.008091044684633144,
332
+ "eval_loss": 1.8446593284606934,
333
+ "eval_runtime": 1477.5292,
334
+ "eval_samples_per_second": 13.948,
335
+ "eval_steps_per_second": 1.743,
336
+ "step": 99
337
  }
338
  ],
339
  "logging_steps": 3,
 
353
  "attributes": {}
354
  }
355
  },
356
+ "total_flos": 1.3895431483922842e+17,
357
  "train_batch_size": 8,
358
  "trial_name": null,
359
  "trial_params": null