ardaspear commited on
Commit
9892ba7
·
verified ·
1 Parent(s): deff01b

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 sha256:9c83497329fb42af49da70fbc3c60c36b43dc83dd65c358fca5f048d008c168f
3
  size 1001465824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:550e9734ff446a8268c1a1fc936ade23019cc5ce0d40639b396d30a06fbd193d
3
  size 1001465824
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f4ba0b62f0ca73cf26460d7ea15aec677a396882d9b4f8029e11d7b4c2cb2668
3
  size 509176980
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e02cb5371b89bae377a36efbd5f7858b16fa2edaf5876fbd5290db1aa2b2d92b
3
  size 509176980
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:05022b5c93ac0c87641f83d2aeb7aee1afa0bbf65f75509e0da8ffce4e027801
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a847f2f57aef831dc09ae29e327eeff14e59b39e62f5656a7ef248f84e11a237
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": 0.7964601769911505,
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": 7.769,
306
  "eval_steps_per_second": 1.963,
307
  "step": 90
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
308
  }
309
  ],
310
  "logging_steps": 3,
@@ -324,7 +353,7 @@
324
  "attributes": {}
325
  }
326
  },
327
- "total_flos": 1.3073439686393856e+17,
328
  "train_batch_size": 4,
329
  "trial_name": null,
330
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.8761061946902655,
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": 7.769,
306
  "eval_steps_per_second": 1.963,
307
  "step": 90
308
+ },
309
+ {
310
+ "epoch": 0.8230088495575221,
311
+ "grad_norm": 7.868893590057269e-05,
312
+ "learning_rate": 1.4852136862001764e-06,
313
+ "loss": 0.0,
314
+ "step": 93
315
+ },
316
+ {
317
+ "epoch": 0.8495575221238938,
318
+ "grad_norm": 4.243826697347686e-05,
319
+ "learning_rate": 4.865965629214819e-07,
320
+ "loss": 0.0,
321
+ "step": 96
322
+ },
323
+ {
324
+ "epoch": 0.8761061946902655,
325
+ "grad_norm": 6.109167588874698e-05,
326
+ "learning_rate": 3.04586490452119e-08,
327
+ "loss": 0.0,
328
+ "step": 99
329
+ },
330
+ {
331
+ "epoch": 0.8761061946902655,
332
+ "eval_loss": 2.0830219682466122e-07,
333
+ "eval_runtime": 12.2672,
334
+ "eval_samples_per_second": 7.744,
335
+ "eval_steps_per_second": 1.956,
336
+ "step": 99
337
  }
338
  ],
339
  "logging_steps": 3,
 
353
  "attributes": {}
354
  }
355
  },
356
+ "total_flos": 1.4393663891177472e+17,
357
  "train_batch_size": 4,
358
  "trial_name": null,
359
  "trial_params": null