Nexspear commited on
Commit
2defd8e
·
verified ·
1 Parent(s): c88c562

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 sha256:5fc78ef22866ba72ae579e35c73a169c895aca49a6efca7716da7119bf17b822
3
  size 130583912
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccaaae6dc0ce650238d5059b9a0ed629a98fccb077cfdb3aedb17ca9576427a1
3
  size 130583912
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1a2e6aab7eac6ded0b5aabc5720b8964e6b39d9c994abfe99563c26c1a3be920
3
  size 66578772
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:269ffe167e1f54cc2b2edd9285532288764a36fbe23442b07c882d96a488b03b
3
  size 66578772
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:18a55733c512b33a1d8d4cc1387f7f6f5a8dcc0f715abbe53c564c0d6e191dc6
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee30e1de861cb5d531a3ca06c5b85c789d099fe249b46222ebbd707f4f8516c0
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": 0.4161849710982659,
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": 15.617,
306
  "eval_steps_per_second": 1.968,
307
  "step": 90
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
308
  }
309
  ],
310
  "logging_steps": 3,
@@ -324,7 +353,7 @@
324
  "attributes": {}
325
  }
326
  },
327
- "total_flos": 1.1782716886351872e+17,
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": 0.4578034682080925,
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": 15.617,
306
  "eval_steps_per_second": 1.968,
307
  "step": 90
308
+ },
309
+ {
310
+ "epoch": 0.4300578034682081,
311
+ "grad_norm": 11.400464057922363,
312
+ "learning_rate": 7.426068431000882e-07,
313
+ "loss": 8.8267,
314
+ "step": 93
315
+ },
316
+ {
317
+ "epoch": 0.4439306358381503,
318
+ "grad_norm": 13.761180877685547,
319
+ "learning_rate": 2.4329828146074095e-07,
320
+ "loss": 8.0885,
321
+ "step": 96
322
+ },
323
+ {
324
+ "epoch": 0.4578034682080925,
325
+ "grad_norm": 11.87588882446289,
326
+ "learning_rate": 1.522932452260595e-08,
327
+ "loss": 9.3402,
328
+ "step": 99
329
+ },
330
+ {
331
+ "epoch": 0.4578034682080925,
332
+ "eval_loss": 2.1476869583129883,
333
+ "eval_runtime": 23.3804,
334
+ "eval_samples_per_second": 15.611,
335
+ "eval_steps_per_second": 1.967,
336
+ "step": 99
337
  }
338
  ],
339
  "logging_steps": 3,
 
353
  "attributes": {}
354
  }
355
  },
356
+ "total_flos": 1.296098857498706e+17,
357
  "train_batch_size": 8,
358
  "trial_name": null,
359
  "trial_params": null