oldiday commited on
Commit
23c288f
·
verified ·
1 Parent(s): b89c7f0

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 sha256:424a3df412cf8c918ef0a8e92eca1c66eae42c30a32d6ce71544d5ee966f5989
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02084396003419c73b94cfd6b7b82609dad8aa44999bb42e85b2688fb2c513c5
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c494268409b65803dfc49cec96f6902874637c488c64ba4527e1a39031ded2c7
3
  size 85723284
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d99e349b66a926c0130f22ea6d4bdf81c0bcf3cb58ae2410a2891dabf8889a92
3
  size 85723284
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0170ac6e43387e4421d0f20421c57b816b53cdb93b7e860b5657d28983a51482
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8484e8b92048ccc424572b7476e3b63c15a73998dad67876e6ddae7332afdf1
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": 0.15273652948663555,
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": 13.683,
306
  "eval_steps_per_second": 1.722,
307
  "step": 90
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
308
  }
309
  ],
310
  "logging_steps": 3,
@@ -324,7 +353,7 @@
324
  "attributes": {}
325
  }
326
  },
327
- "total_flos": 1.3391065468266086e+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": 0.1680101824352991,
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": 13.683,
306
  "eval_steps_per_second": 1.722,
307
  "step": 90
308
+ },
309
+ {
310
+ "epoch": 0.15782774713619008,
311
+ "grad_norm": 0.5294960141181946,
312
+ "learning_rate": 7.426068431000882e-07,
313
+ "loss": 0.3643,
314
+ "step": 93
315
+ },
316
+ {
317
+ "epoch": 0.16291896478574458,
318
+ "grad_norm": 0.4545383155345917,
319
+ "learning_rate": 2.4329828146074095e-07,
320
+ "loss": 0.3463,
321
+ "step": 96
322
+ },
323
+ {
324
+ "epoch": 0.1680101824352991,
325
+ "grad_norm": 0.6580240726470947,
326
+ "learning_rate": 1.522932452260595e-08,
327
+ "loss": 0.3619,
328
+ "step": 99
329
+ },
330
+ {
331
+ "epoch": 0.1680101824352991,
332
+ "eval_loss": 0.364297091960907,
333
+ "eval_runtime": 72.5705,
334
+ "eval_samples_per_second": 13.683,
335
+ "eval_steps_per_second": 1.722,
336
+ "step": 99
337
  }
338
  ],
339
  "logging_steps": 3,
 
353
  "attributes": {}
354
  }
355
  },
356
+ "total_flos": 1.4726462578674893e+17,
357
  "train_batch_size": 8,
358
  "trial_name": null,
359
  "trial_params": null