brixeus commited on
Commit
cbc1d60
·
verified ·
1 Parent(s): 50940da

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 sha256:96d74015691f4d81e671974fa14038368ae12b384c68e4ba4e51d03e24a5e52d
3
  size 25192688
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3606854651b8e074d1f366c3167bbd7c4470f2610399297c3af88717c3fdeebd
3
  size 25192688
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1cf204f0186f0ab5641d62694c8e7e000410b3cc652da871914c0618d2d47d59
3
  size 13005178
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85c19f8a2e08eeffc499b9d9f4606c4915442b63cefe0a7af8792b413c69ff3c
3
  size 13005178
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ee04cda361f6941c5803fef5b388c8b8630c38a5748503a508eaf64a60fe897b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b29dd384d340b9ad2e9bc0d4e436142281339628c474cd1e5893f02985d68b62
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": 0.0299028158484924,
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": 22.904,
306
  "eval_steps_per_second": 2.865,
307
  "step": 90
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
308
  }
309
  ],
310
  "logging_steps": 3,
@@ -324,7 +353,7 @@
324
  "attributes": {}
325
  }
326
  },
327
- "total_flos": 7402252117475328.0,
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": 0.032893097433341636,
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": 22.904,
306
  "eval_steps_per_second": 2.865,
307
  "step": 90
308
+ },
309
+ {
310
+ "epoch": 0.03089957637677548,
311
+ "grad_norm": 4.082184314727783,
312
+ "learning_rate": 7.426068431000882e-07,
313
+ "loss": 6.4988,
314
+ "step": 93
315
+ },
316
+ {
317
+ "epoch": 0.03189633690505856,
318
+ "grad_norm": 5.3565568923950195,
319
+ "learning_rate": 2.4329828146074095e-07,
320
+ "loss": 5.9101,
321
+ "step": 96
322
+ },
323
+ {
324
+ "epoch": 0.032893097433341636,
325
+ "grad_norm": 4.958103656768799,
326
+ "learning_rate": 1.522932452260595e-08,
327
+ "loss": 5.5128,
328
+ "step": 99
329
+ },
330
+ {
331
+ "epoch": 0.032893097433341636,
332
+ "eval_loss": 1.5341731309890747,
333
+ "eval_runtime": 221.3156,
334
+ "eval_samples_per_second": 22.904,
335
+ "eval_steps_per_second": 2.865,
336
+ "step": 99
337
  }
338
  ],
339
  "logging_steps": 3,
 
353
  "attributes": {}
354
  }
355
  },
356
+ "total_flos": 8115173940264960.0,
357
  "train_batch_size": 8,
358
  "trial_name": null,
359
  "trial_params": null