Nexspear commited on
Commit
b88c602
·
verified ·
1 Parent(s): cb51dd7

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 sha256:0b6f2266e9a7e54d676df78fc77f23d97d99468e4e60243f06c2dd3ff7440096
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac8c743a16391ff79eeea0fb876716734fda0e32c4b7f7abb4b4e06bfdedbd9a
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:358425bd65c2a6988b68c2f6213d6277c04360bb7bffb596259a2d785f14aaa7
3
  size 85723284
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23661c08a9b86de2fcf47779a4dbf055734303447ed86d26e2a4878d26108c4f
3
  size 85723284
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e28411e83171f3c78c4425c84389ce7118ea6cadf71988b15c3be1e9067a0ff4
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0dc1eecf7759beab6629d72055a23b793964c0c7b876af875c22f5f50cfc8f28
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": 0.055944055944055944,
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": 10.039,
306
  "eval_steps_per_second": 1.256,
307
  "step": 90
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
308
  }
309
  ],
310
  "logging_steps": 3,
@@ -324,7 +353,7 @@
324
  "attributes": {}
325
  }
326
  },
327
- "total_flos": 1.8584276453189222e+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": 0.06153846153846154,
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": 10.039,
306
  "eval_steps_per_second": 1.256,
307
  "step": 90
308
+ },
309
+ {
310
+ "epoch": 0.05780885780885781,
311
+ "grad_norm": 2.821603298187256,
312
+ "learning_rate": 7.426068431000882e-07,
313
+ "loss": 3.0367,
314
+ "step": 93
315
+ },
316
+ {
317
+ "epoch": 0.059673659673659674,
318
+ "grad_norm": 2.2452235221862793,
319
+ "learning_rate": 2.4329828146074095e-07,
320
+ "loss": 2.7214,
321
+ "step": 96
322
+ },
323
+ {
324
+ "epoch": 0.06153846153846154,
325
+ "grad_norm": 2.7175397872924805,
326
+ "learning_rate": 1.522932452260595e-08,
327
+ "loss": 2.8909,
328
+ "step": 99
329
+ },
330
+ {
331
+ "epoch": 0.06153846153846154,
332
+ "eval_loss": 2.9674060344696045,
333
+ "eval_runtime": 269.5194,
334
+ "eval_samples_per_second": 10.055,
335
+ "eval_steps_per_second": 1.258,
336
+ "step": 99
337
  }
338
  ],
339
  "logging_steps": 3,
 
353
  "attributes": {}
354
  }
355
  },
356
+ "total_flos": 2.0476089026268365e+17,
357
  "train_batch_size": 8,
358
  "trial_name": null,
359
  "trial_params": null