ardaspear commited on
Commit
84f8034
·
verified ·
1 Parent(s): ac881fe

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 sha256:4639593f8883f131f9091f1e294cb45c49812ff12739c77f86d31c0d3c4b3588
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a9901cb66d3f5e6bf76970d9a6cf88e4beeb03d99b47f505d2a06cf657dd054
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:35e57bf01f0fb7c5c64b6e13badf461b6a877db8393cd0f1319cda39c4aa6a37
3
  size 85723284
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d04fbf002ee6751ceae950b0c3e63d8482559947c12842871529908cf254d420
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:b202cc35d4d82828b46ac25c2aa3b0d5b24c9fdd644bb03957f013b307cbc71d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ca5ed7077b7e80b15b5b40bb67c00bb6aeb10626f97d2892620cc3f79d1da45
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": 0.026503717882647427,
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": 14.491,
306
  "eval_steps_per_second": 1.811,
307
  "step": 90
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
308
  }
309
  ],
310
  "logging_steps": 3,
@@ -324,7 +353,7 @@
324
  "attributes": {}
325
  }
326
  },
327
- "total_flos": 1.2661897253879808e+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": 0.02915408967091217,
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": 14.491,
306
  "eval_steps_per_second": 1.811,
307
  "step": 90
308
+ },
309
+ {
310
+ "epoch": 0.027387175145402343,
311
+ "grad_norm": 5.856942653656006,
312
+ "learning_rate": 1.4852136862001764e-06,
313
+ "loss": 3.0394,
314
+ "step": 93
315
+ },
316
+ {
317
+ "epoch": 0.028270632408157255,
318
+ "grad_norm": 5.515998363494873,
319
+ "learning_rate": 4.865965629214819e-07,
320
+ "loss": 3.1025,
321
+ "step": 96
322
+ },
323
+ {
324
+ "epoch": 0.02915408967091217,
325
+ "grad_norm": 5.73545503616333,
326
+ "learning_rate": 3.04586490452119e-08,
327
+ "loss": 3.2693,
328
+ "step": 99
329
+ },
330
+ {
331
+ "epoch": 0.02915408967091217,
332
+ "eval_loss": 0.8529771566390991,
333
+ "eval_runtime": 394.735,
334
+ "eval_samples_per_second": 14.491,
335
+ "eval_steps_per_second": 1.811,
336
+ "step": 99
337
  }
338
  ],
339
  "logging_steps": 3,
 
353
  "attributes": {}
354
  }
355
  },
356
+ "total_flos": 1.3928086979267789e+17,
357
  "train_batch_size": 8,
358
  "trial_name": null,
359
  "trial_params": null