oldiday commited on
Commit
dd5739d
·
verified ·
1 Parent(s): d2fb45c

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 sha256:512f494c5aadb7f06522ea5ccf364c27b1034a318d7f8151d450f5c7bfaa34d2
3
  size 19593064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce8f27aa0f6b6b19087b2aa8cb86f67af56381ae7f7af757d82e45744344d0a6
3
  size 19593064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:146fa6143c10c0e9bb32b923385e55ff05907aa1c5d062e8d1bc5a9e1885d024
3
  size 11469420
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7087af5f97d7d7906afafb935d3ee52b9b072cad4fd786052c35df1624be625c
3
  size 11469420
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4eb2a57ee880a7e5e6816a3da3a29ffebab989146dd73c02addd843781aa88c3
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3649573dd9faf4273ccd11cd6f21c7c44fdb86a72123c4c88faa22c2bc17d638
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": 0.05868927290511901,
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": 72.775,
306
  "eval_steps_per_second": 9.1,
307
  "step": 90
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
308
  }
309
  ],
310
  "logging_steps": 3,
@@ -324,7 +353,7 @@
324
  "attributes": {}
325
  }
326
  },
327
- "total_flos": 3024947603570688.0,
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": 0.06455820019563091,
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": 72.775,
306
  "eval_steps_per_second": 9.1,
307
  "step": 90
308
+ },
309
+ {
310
+ "epoch": 0.06064558200195631,
311
+ "grad_norm": 0.1278517246246338,
312
+ "learning_rate": 7.426068431000882e-07,
313
+ "loss": 1.4409,
314
+ "step": 93
315
+ },
316
+ {
317
+ "epoch": 0.0626018910987936,
318
+ "grad_norm": 0.10912717878818512,
319
+ "learning_rate": 2.4329828146074095e-07,
320
+ "loss": 1.331,
321
+ "step": 96
322
+ },
323
+ {
324
+ "epoch": 0.06455820019563091,
325
+ "grad_norm": 0.143110990524292,
326
+ "learning_rate": 1.522932452260595e-08,
327
+ "loss": 1.3777,
328
+ "step": 99
329
+ },
330
+ {
331
+ "epoch": 0.06455820019563091,
332
+ "eval_loss": 1.3658305406570435,
333
+ "eval_runtime": 35.5981,
334
+ "eval_samples_per_second": 72.56,
335
+ "eval_steps_per_second": 9.074,
336
+ "step": 99
337
  }
338
  ],
339
  "logging_steps": 3,
 
353
  "attributes": {}
354
  }
355
  },
356
+ "total_flos": 3325258286235648.0,
357
  "train_batch_size": 8,
358
  "trial_name": null,
359
  "trial_params": null