brixeus commited on
Commit
1e1bf80
·
verified ·
1 Parent(s): 84632f6

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 sha256:04d441fe58ae18d54ff114a06bbc0c0ffd3150eb8e35332e45166d952293a38c
3
  size 25192592
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97f4f6cb1225c71a38cdd9fcc95ab75dca01b99f0ca82d2a95909b0cc7866727
3
  size 25192592
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a9b408fabbfdb94f3fba4949059fc28605272238fd54a54fb1b1328cbe9effe9
3
  size 13005178
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c65359393e116659102f27c8bad07dc53a95c70f1c964fb31a6cb33f3a37594
3
  size 13005178
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d2197cddd6589f1765bb48131c86ecd29e7a72e43e811e8a33c0558dee96a8af
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a670cb7e282ec2b386f760c13cfa928205073e43114f22892f013945b0015291
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": 0.18711018711018712,
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": 47.638,
306
  "eval_steps_per_second": 5.991,
307
  "step": 90
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
308
  }
309
  ],
310
  "logging_steps": 3,
@@ -324,7 +353,7 @@
324
  "attributes": {}
325
  }
326
  },
327
- "total_flos": 1.274423902470144e+16,
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": 0.20582120582120583,
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": 47.638,
306
  "eval_steps_per_second": 5.991,
307
  "step": 90
308
+ },
309
+ {
310
+ "epoch": 0.19334719334719336,
311
+ "grad_norm": 15.008647918701172,
312
+ "learning_rate": 7.426068431000882e-07,
313
+ "loss": 5.7227,
314
+ "step": 93
315
+ },
316
+ {
317
+ "epoch": 0.1995841995841996,
318
+ "grad_norm": 14.886467933654785,
319
+ "learning_rate": 2.4329828146074095e-07,
320
+ "loss": 5.7242,
321
+ "step": 96
322
+ },
323
+ {
324
+ "epoch": 0.20582120582120583,
325
+ "grad_norm": 12.942763328552246,
326
+ "learning_rate": 1.522932452260595e-08,
327
+ "loss": 5.7465,
328
+ "step": 99
329
+ },
330
+ {
331
+ "epoch": 0.20582120582120583,
332
+ "eval_loss": 1.4416875839233398,
333
+ "eval_runtime": 17.0119,
334
+ "eval_samples_per_second": 47.672,
335
+ "eval_steps_per_second": 5.996,
336
+ "step": 99
337
  }
338
  ],
339
  "logging_steps": 3,
 
353
  "attributes": {}
354
  }
355
  },
356
+ "total_flos": 1.4018662927171584e+16,
357
  "train_batch_size": 8,
358
  "trial_name": null,
359
  "trial_params": null