clarxus commited on
Commit
eb0b5ad
·
verified ·
1 Parent(s): 03e2b17

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 sha256:8c7f9356eb32fa848d5be29cdd7b4f5c93742c19c282b8dac9445551a61b9c69
3
  size 34793120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab919a913881991fb357210b41d1c70a6748b72ce89d6724e6a9e7450206cd18
3
  size 34793120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3da4b43998cc262088e7c2d966ef40123bfe05149e62a282f435f1661cfcdeb0
3
  size 18132116
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:989b384461e280b729efabe642defef709c90c2ebdaa61e95b4bf5ac4499cc06
3
  size 18132116
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:624f33a8825fe91cf75494eb380d78794d533169c1a0c48e642c8c4930913984
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9134cf4636ee0e156a5ccb78f67e0d6537e097c0604a30e16aa9819b3bfd1040
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": 0.033413773900129944,
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": 44.348,
306
  "eval_steps_per_second": 5.552,
307
  "step": 90
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
308
  }
309
  ],
310
  "logging_steps": 3,
@@ -324,7 +353,7 @@
324
  "attributes": {}
325
  }
326
  },
327
- "total_flos": 8994737136599040.0,
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": 0.03675515129014294,
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": 44.348,
306
  "eval_steps_per_second": 5.552,
307
  "step": 90
308
+ },
309
+ {
310
+ "epoch": 0.034527566363467606,
311
+ "grad_norm": 0.8410691022872925,
312
+ "learning_rate": 7.426068431000882e-07,
313
+ "loss": 2.5786,
314
+ "step": 93
315
+ },
316
+ {
317
+ "epoch": 0.035641358826805275,
318
+ "grad_norm": 0.9793163537979126,
319
+ "learning_rate": 2.4329828146074095e-07,
320
+ "loss": 2.6365,
321
+ "step": 96
322
+ },
323
+ {
324
+ "epoch": 0.03675515129014294,
325
+ "grad_norm": 0.8763136267662048,
326
+ "learning_rate": 1.522932452260595e-08,
327
+ "loss": 2.9456,
328
+ "step": 99
329
+ },
330
+ {
331
+ "epoch": 0.03675515129014294,
332
+ "eval_loss": 2.747492551803589,
333
+ "eval_runtime": 102.3186,
334
+ "eval_samples_per_second": 44.342,
335
+ "eval_steps_per_second": 5.551,
336
+ "step": 99
337
  }
338
  ],
339
  "logging_steps": 3,
 
353
  "attributes": {}
354
  }
355
  },
356
+ "total_flos": 9852892269772800.0,
357
  "train_batch_size": 8,
358
  "trial_name": null,
359
  "trial_params": null