ardaspear commited on
Commit
f8fc435
·
verified ·
1 Parent(s): 19ac4f3

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 sha256:037121f73a5ff6c01dfa5f8c106ac3433ff46de20fc9c44a46c247a85576de46
3
  size 247936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ada8edb6dc25553741c9b54f8223846e1b72122c098de7dea394d367dbe7db17
3
  size 247936
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:496d9757580288d8509ddfe99b04e84ee3c3f6ccd1df9532fda74934a1ec9f68
3
  size 263024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c93633bbdf52cba909606941874c9b7ce43ce70c22af5d77b66342ba7068a776
3
  size 263024
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f809f3a9bd317f6dc50b7c5d7a14135ab1c1e2d413bfb7e8872835b0a5d61e58
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3de63c6bc3d65cbbf3f68336ee000886d3c69f9b6aabfd55d8747d2e7debede0
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": 0.10230179028132992,
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": 158.267,
306
  "eval_steps_per_second": 39.727,
307
  "step": 90
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
308
  }
309
  ],
310
  "logging_steps": 3,
@@ -324,7 +353,7 @@
324
  "attributes": {}
325
  }
326
  },
327
- "total_flos": 798370037760.0,
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": 0.11253196930946291,
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": 158.267,
306
  "eval_steps_per_second": 39.727,
307
  "step": 90
308
+ },
309
+ {
310
+ "epoch": 0.10571184995737426,
311
+ "grad_norm": 1.0372346639633179,
312
+ "learning_rate": 1.4852136862001764e-06,
313
+ "loss": 43.758,
314
+ "step": 93
315
+ },
316
+ {
317
+ "epoch": 0.10912190963341858,
318
+ "grad_norm": 1.142467737197876,
319
+ "learning_rate": 4.865965629214819e-07,
320
+ "loss": 43.7437,
321
+ "step": 96
322
+ },
323
+ {
324
+ "epoch": 0.11253196930946291,
325
+ "grad_norm": 1.0426071882247925,
326
+ "learning_rate": 3.04586490452119e-08,
327
+ "loss": 43.7267,
328
+ "step": 99
329
+ },
330
+ {
331
+ "epoch": 0.11253196930946291,
332
+ "eval_loss": 10.934452056884766,
333
+ "eval_runtime": 4.6402,
334
+ "eval_samples_per_second": 159.693,
335
+ "eval_steps_per_second": 40.085,
336
+ "step": 99
337
  }
338
  ],
339
  "logging_steps": 3,
 
353
  "attributes": {}
354
  }
355
  },
356
+ "total_flos": 874897735680.0,
357
  "train_batch_size": 4,
358
  "trial_name": null,
359
  "trial_params": null