ardaspear commited on
Commit
7af8cce
·
verified ·
1 Parent(s): 001b1e7

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 sha256:07c5d57c8f0d70ca706116e121388b3fe2b274f02bf39c33c17e778d6e65bcf9
3
  size 72396376
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97e8a8952f73d2de3c9937eb66e02c0caba0209aa530067ed8009db0db11eae7
3
  size 72396376
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:467d975348b6d16ae8bd98009a854eab0e063288a2eff4bc0ffb94bae397798c
3
  size 37134420
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e0ca58e4737955cde008c943a33123b50c1f3a4fe93ae9f0669254abae92b61
3
  size 37134420
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eb26646051d6ad9589b97bde1959db9d8644550abb439500c6e4a7bc67aad86d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d172a0977011fc38ea0b9291c2bd1ee51a83d8ae7d2ba7da8eb9820d958ff65e
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0569f9f06b6a114946825bdc699040cc55958cfef46aba8eb5fb625896d49025
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b64833e2721bfb57dae2a544bde34ace02492c2f80bfbff48034c9946dc6b4a
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": 0.3373945641986879,
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": 34.628,
306
  "eval_steps_per_second": 4.386,
307
  "step": 90
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
308
  }
309
  ],
310
  "logging_steps": 3,
@@ -324,7 +353,7 @@
324
  "attributes": {}
325
  }
326
  },
327
- "total_flos": 2.9381589850914816e+16,
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": 0.3711340206185567,
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": 34.628,
306
  "eval_steps_per_second": 4.386,
307
  "step": 90
308
+ },
309
+ {
310
+ "epoch": 0.3486410496719775,
311
+ "grad_norm": 0.21853309869766235,
312
+ "learning_rate": 7.426068431000882e-07,
313
+ "loss": 1.8859,
314
+ "step": 93
315
+ },
316
+ {
317
+ "epoch": 0.3598875351452671,
318
+ "grad_norm": 0.24381911754608154,
319
+ "learning_rate": 2.4329828146074095e-07,
320
+ "loss": 1.8836,
321
+ "step": 96
322
+ },
323
+ {
324
+ "epoch": 0.3711340206185567,
325
+ "grad_norm": 0.24009494483470917,
326
+ "learning_rate": 1.522932452260595e-08,
327
+ "loss": 1.8607,
328
+ "step": 99
329
+ },
330
+ {
331
+ "epoch": 0.3711340206185567,
332
+ "eval_loss": 1.9197931289672852,
333
+ "eval_runtime": 12.9903,
334
+ "eval_samples_per_second": 34.641,
335
+ "eval_steps_per_second": 4.388,
336
+ "step": 99
337
  }
338
  ],
339
  "logging_steps": 3,
 
353
  "attributes": {}
354
  }
355
  },
356
+ "total_flos": 3.250388414024909e+16,
357
  "train_batch_size": 8,
358
  "trial_name": null,
359
  "trial_params": null