dixedus commited on
Commit
cb5f800
·
verified ·
1 Parent(s): a38b8bb

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:a9647adb27981853b26d82eeddc723e36144f864d61580d416f699ea91dcaefa
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c96b23a5abc6d444bbf737f062e61b3d56d6fbd261e5f31f51af51ed2474a3a
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e47f36ad78f6f7604e3268f59728911c1aa62156f46a6c659ac6efcfed066dc7
3
  size 85723284
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d129f7652ffccf9657cff2b8e680d015c800cd0c45953434c07e2331df92d718
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:d7e8c1b8811cba42117d1c35bab2d6e9ca27ecfe61350e3c045dcd0814b8dbb5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18651b26b99f01dd12dc2e4037897ec27129ab1025f84e5ea4fd1c12352cc455
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f7d03f1dba06dbe949e0b7294b5a80e81e1c97413b12e930c7d1d62b4e569ba
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43444b0a2aaeda40531bf13a694e8a3eeeb489f81435e9521c012609a5be4dc4
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": 2.3684210526315788,
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": 14.232,
306
  "eval_steps_per_second": 1.779,
307
  "step": 90
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
308
  }
309
  ],
310
  "logging_steps": 3,
@@ -324,7 +353,7 @@
324
  "attributes": {}
325
  }
326
  },
327
- "total_flos": 1.2594821570179891e+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": 2.6052631578947367,
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": 14.232,
306
  "eval_steps_per_second": 1.779,
307
  "step": 90
308
+ },
309
+ {
310
+ "epoch": 2.4473684210526314,
311
+ "grad_norm": 7.044579982757568,
312
+ "learning_rate": 1.4852136862001764e-06,
313
+ "loss": 1.5221,
314
+ "step": 93
315
+ },
316
+ {
317
+ "epoch": 2.526315789473684,
318
+ "grad_norm": 7.962366580963135,
319
+ "learning_rate": 4.865965629214819e-07,
320
+ "loss": 1.4521,
321
+ "step": 96
322
+ },
323
+ {
324
+ "epoch": 2.6052631578947367,
325
+ "grad_norm": 7.687761306762695,
326
+ "learning_rate": 3.04586490452119e-08,
327
+ "loss": 1.473,
328
+ "step": 99
329
+ },
330
+ {
331
+ "epoch": 2.6052631578947367,
332
+ "eval_loss": 0.8015087842941284,
333
+ "eval_runtime": 4.5008,
334
+ "eval_samples_per_second": 14.22,
335
+ "eval_steps_per_second": 1.777,
336
+ "step": 99
337
  }
338
  ],
339
  "logging_steps": 3,
 
353
  "attributes": {}
354
  }
355
  },
356
+ "total_flos": 1.3860456117357773e+17,
357
  "train_batch_size": 8,
358
  "trial_name": null,
359
  "trial_params": null