mamung commited on
Commit
8494aa1
·
verified ·
1 Parent(s): 0aeebe2

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 sha256:1a578e9521a9ab15d4f40115992f62619f58b6d43bb0f7dc335d4b3f47103097
3
  size 319876032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00bbeab6943a0fa937a98e954fd84f2fb514cc61ff22654325f059e3945e5475
3
  size 319876032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:258574fc95c474270a3a1b9fb326a794c444e7bb209be9cd0a9f2c97e9c987c8
3
  size 640009682
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7add0487458a6e4a9632064b9b09bfe6e30c5bbbf7e25a265a06937f35948179
3
  size 640009682
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e18e668860aa083adef211013189cd3d58c25adbb67cd9b0e99f8ed5231c4495
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d63d25d2bb4b8f7e38ba5db2a209d7024c91b0aec7921a156027cefe066d98db
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:429c9f0a4ff1909f8cc1cafc3bf6eb6ff29e4592139b5344f1aee9b75eae7379
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1eef4c60eef56c59d148e4191bea64e9a3bf517b29f5a413c536dcdc8e61edf1
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": 1.0626151012891345,
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": 5.921,
306
  "eval_steps_per_second": 2.961,
307
  "step": 90
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
308
  }
309
  ],
310
  "logging_steps": 3,
@@ -324,7 +353,7 @@
324
  "attributes": {}
325
  }
326
  },
327
- "total_flos": 4.7332406838951936e+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": 1.1686924493554327,
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": 5.921,
306
  "eval_steps_per_second": 2.961,
307
  "step": 90
308
+ },
309
+ {
310
+ "epoch": 1.097974217311234,
311
+ "grad_norm": 27.65435791015625,
312
+ "learning_rate": 2.815857265976462e-06,
313
+ "loss": 48.2304,
314
+ "step": 93
315
+ },
316
+ {
317
+ "epoch": 1.1333333333333333,
318
+ "grad_norm": 22.98744773864746,
319
+ "learning_rate": 9.233744553646754e-07,
320
+ "loss": 42.7889,
321
+ "step": 96
322
+ },
323
+ {
324
+ "epoch": 1.1686924493554327,
325
+ "grad_norm": 29.46680450439453,
326
+ "learning_rate": 5.7822281945782424e-08,
327
+ "loss": 47.1437,
328
+ "step": 99
329
+ },
330
+ {
331
+ "epoch": 1.1686924493554327,
332
+ "eval_loss": 1.5387442111968994,
333
+ "eval_runtime": 48.2916,
334
+ "eval_samples_per_second": 5.922,
335
+ "eval_steps_per_second": 2.961,
336
+ "step": 99
337
  }
338
  ],
339
  "logging_steps": 3,
 
353
  "attributes": {}
354
  }
355
  },
356
+ "total_flos": 5.206564752284713e+17,
357
  "train_batch_size": 2,
358
  "trial_name": null,
359
  "trial_params": null