ardaspear commited on
Commit
c77004c
1 Parent(s): f774e81

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 sha256:2d85f12ce431a51ec6f19c695da5add1448192090ed55a47fc09ae90c2fb9452
3
  size 645975704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:846d973dd42d843c754887a60b0baa2a9d4eb464a90adfcd521c35c02cc6bca0
3
  size 645975704
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:79cad39bf69db8f514344133dd55d98ad17085d5f340ea24465e790540a80460
3
  size 328468404
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30b7b4d8a18eafa63f54299fd804628dcf58ed98c8592ca5a3069a07556ef039
3
  size 328468404
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cbd2f6e463444356bddac32968462fbb7d07302b4789c6151e3ff1ab681295d1
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84e8f605c2d931c93cdfd9fce8aa9bc642f057803e755232882ae97f067b9943
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": 0.33771106941838647,
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": 13.659,
306
  "eval_steps_per_second": 3.46,
307
  "step": 90
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
308
  }
309
  ],
310
  "logging_steps": 3,
@@ -324,7 +353,7 @@
324
  "attributes": {}
325
  }
326
  },
327
- "total_flos": 6.39849908404224e+16,
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": 0.3714821763602251,
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": 13.659,
306
  "eval_steps_per_second": 3.46,
307
  "step": 90
308
+ },
309
+ {
310
+ "epoch": 0.34896810506566606,
311
+ "grad_norm": 0.005139649845659733,
312
+ "learning_rate": 1.4852136862001764e-06,
313
+ "loss": 0.0003,
314
+ "step": 93
315
+ },
316
+ {
317
+ "epoch": 0.3602251407129456,
318
+ "grad_norm": 0.0025040253531187773,
319
+ "learning_rate": 4.865965629214819e-07,
320
+ "loss": 0.0007,
321
+ "step": 96
322
+ },
323
+ {
324
+ "epoch": 0.3714821763602251,
325
+ "grad_norm": 0.0036368141882121563,
326
+ "learning_rate": 3.04586490452119e-08,
327
+ "loss": 0.0003,
328
+ "step": 99
329
+ },
330
+ {
331
+ "epoch": 0.3714821763602251,
332
+ "eval_loss": 0.0012390989577397704,
333
+ "eval_runtime": 16.4714,
334
+ "eval_samples_per_second": 13.66,
335
+ "eval_steps_per_second": 3.461,
336
+ "step": 99
337
  }
338
  ],
339
  "logging_steps": 3,
 
353
  "attributes": {}
354
  }
355
  },
356
+ "total_flos": 7.038348992446464e+16,
357
  "train_batch_size": 4,
358
  "trial_name": null,
359
  "trial_params": null