ardaspear commited on
Commit
abb262f
·
verified ·
1 Parent(s): 7e4a0ce

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:b502e19105e8e4324eb822c2cb279ebc41823b0d5775653e7c90d3dfb312964e
3
  size 72396376
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a63f33d0edf964e98b1d1231892185a8c017f3d946ce84e1f5c94981d7cf3d1b
3
  size 72396376
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d599903f1e48d5e966b11907fa9bd4da4a8adfed06de75f9055bebf8a55eb1f
3
  size 37134420
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c672324c07ad2df18f204afefe385c29b85ae5dd7907d57fa61020334f12d1a
3
  size 37134420
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:57fcc930ed6aa822432f240a0030f67a2b3c586a79bdd7dc125c1ff972778eec
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa200d5341a0170ee99ee0d658ce47896459e3d989a4e7bfd0345fb1ee145124
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": 0.1815431164901664,
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": 17.581,
306
  "eval_steps_per_second": 2.211,
307
  "step": 90
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
308
  }
309
  ],
310
  "logging_steps": 3,
@@ -324,7 +353,7 @@
324
  "attributes": {}
325
  }
326
  },
327
- "total_flos": 5.764235611078656e+16,
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": 0.19969742813918306,
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": 17.581,
306
  "eval_steps_per_second": 2.211,
307
  "step": 90
308
+ },
309
+ {
310
+ "epoch": 0.1875945537065053,
311
+ "grad_norm": 0.07828027755022049,
312
+ "learning_rate": 7.426068431000882e-07,
313
+ "loss": 1.3319,
314
+ "step": 93
315
+ },
316
+ {
317
+ "epoch": 0.19364599092284418,
318
+ "grad_norm": 0.07713537663221359,
319
+ "learning_rate": 2.4329828146074095e-07,
320
+ "loss": 1.3671,
321
+ "step": 96
322
+ },
323
+ {
324
+ "epoch": 0.19969742813918306,
325
+ "grad_norm": 0.07717742770910263,
326
+ "learning_rate": 1.522932452260595e-08,
327
+ "loss": 1.2967,
328
+ "step": 99
329
+ },
330
+ {
331
+ "epoch": 0.19969742813918306,
332
+ "eval_loss": 1.3039239645004272,
333
+ "eval_runtime": 47.4866,
334
+ "eval_samples_per_second": 17.584,
335
+ "eval_steps_per_second": 2.211,
336
+ "step": 99
337
  }
338
  ],
339
  "logging_steps": 3,
 
353
  "attributes": {}
354
  }
355
  },
356
+ "total_flos": 6.340659172186522e+16,
357
  "train_batch_size": 8,
358
  "trial_name": null,
359
  "trial_params": null