mamung commited on
Commit
ff81aad
·
verified ·
1 Parent(s): d8e83df

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:edba9a659ea2d15ac08f4abd527696aac0edf94cd18d20f20194b671f1d182a8
3
  size 335604696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa50e1f7ccd6df960bc1f68aabcc023812e055fcc6b0ee54f36bc372c9f589fd
3
  size 335604696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eddea9273d1ba676c8532d2df9e4c68891427843af29bf94d3d5de2dcf187c92
3
  size 671466706
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc5be2e7234679dbb3388f6b9170e8c01944b28c04d75f6cc17d3ee90f68436e
3
  size 671466706
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:05d2bfe38cfda32d48c4b91fa50be61b10a17efeab1ffd415b2ffd38352c57e4
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3777963747e4f66ada1c48bff38ad1c5a6150500ace0874207d1c842b982744
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f6b7babead6c4be4368caff2650e543461856d401ff242b042a60fc57cd3bcca
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7041fa0be7432c15ac468c1425bc3b5d595e4b5b769cfa7728743ab80ef12291
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": 0.21636240703177823,
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": 8.957,
306
  "eval_steps_per_second": 4.478,
307
  "step": 90
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
308
  }
309
  ],
310
  "logging_steps": 3,
@@ -324,7 +353,7 @@
324
  "attributes": {}
325
  }
326
  },
327
- "total_flos": 5.373140281715589e+17,
328
  "train_batch_size": 2,
329
  "trial_name": null,
330
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.23799864773495605,
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": 8.957,
306
  "eval_steps_per_second": 4.478,
307
  "step": 90
308
+ },
309
+ {
310
+ "epoch": 0.22357448726617082,
311
+ "grad_norm": 0.9879840016365051,
312
+ "learning_rate": 3.7544763546352834e-06,
313
+ "loss": 1.1005,
314
+ "step": 93
315
+ },
316
+ {
317
+ "epoch": 0.23078656750056345,
318
+ "grad_norm": 0.884789764881134,
319
+ "learning_rate": 1.231165940486234e-06,
320
+ "loss": 1.0352,
321
+ "step": 96
322
+ },
323
+ {
324
+ "epoch": 0.23799864773495605,
325
+ "grad_norm": 1.1920340061187744,
326
+ "learning_rate": 7.709637592770991e-08,
327
+ "loss": 1.117,
328
+ "step": 99
329
+ },
330
+ {
331
+ "epoch": 0.23799864773495605,
332
+ "eval_loss": 1.0599479675292969,
333
+ "eval_runtime": 156.5531,
334
+ "eval_samples_per_second": 8.955,
335
+ "eval_steps_per_second": 4.478,
336
+ "step": 99
337
  }
338
  ],
339
  "logging_steps": 3,
 
353
  "attributes": {}
354
  }
355
  },
356
+ "total_flos": 5.910267807274107e+17,
357
  "train_batch_size": 2,
358
  "trial_name": null,
359
  "trial_params": null