dixedus commited on
Commit
b50217b
·
verified ·
1 Parent(s): 1cf4358

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 sha256:33116f53cd2af9d2453ad151a9cb859b87d2920e96cd5c9a5b32fe5427efdf52
3
  size 159967880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b20134bb8d6f0f46e8f7db83c26e12679211525c9e335ced58a0f0c5e61b2b78
3
  size 159967880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a061a58ac6d3c360b3986c8cf928c53ee385dec3c173e39a371a89c430a68013
3
  size 81730196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37d4b0bf6232ba28f4fef882c84d98e0f19d853b8c631ea4c5d6cb6ee4f8895e
3
  size 81730196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e17e59518a33349d3e7ccb2a3d6202e23618632431c2022d3d7024a72198bc7
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad97e92012eab34b088960899e55a1e0fd6af3e7e6f80ae09df5b37044f193ea
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f7d03f1dba06dbe949e0b7294b5a80e81e1c97413b12e930c7d1d62b4e569ba
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43444b0a2aaeda40531bf13a694e8a3eeeb489f81435e9521c012609a5be4dc4
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": 0.009723685276719877,
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": 6.93,
306
  "eval_steps_per_second": 0.866,
307
  "step": 90
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
308
  }
309
  ],
310
  "logging_steps": 3,
@@ -324,7 +353,7 @@
324
  "attributes": {}
325
  }
326
  },
327
- "total_flos": 2.3732317461676032e+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": 0.010696053804391864,
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": 6.93,
306
  "eval_steps_per_second": 0.866,
307
  "step": 90
308
+ },
309
+ {
310
+ "epoch": 0.010047808119277206,
311
+ "grad_norm": 0.8895863890647888,
312
+ "learning_rate": 1.4852136862001764e-06,
313
+ "loss": 1.722,
314
+ "step": 93
315
+ },
316
+ {
317
+ "epoch": 0.010371930961834535,
318
+ "grad_norm": 0.8872703909873962,
319
+ "learning_rate": 4.865965629214819e-07,
320
+ "loss": 1.71,
321
+ "step": 96
322
+ },
323
+ {
324
+ "epoch": 0.010696053804391864,
325
+ "grad_norm": 0.9046586751937866,
326
+ "learning_rate": 3.04586490452119e-08,
327
+ "loss": 1.7767,
328
+ "step": 99
329
+ },
330
+ {
331
+ "epoch": 0.010696053804391864,
332
+ "eval_loss": 1.769021987915039,
333
+ "eval_runtime": 2250.6578,
334
+ "eval_samples_per_second": 6.926,
335
+ "eval_steps_per_second": 0.866,
336
+ "step": 99
337
  }
338
  ],
339
  "logging_steps": 3,
 
353
  "attributes": {}
354
  }
355
  },
356
+ "total_flos": 2.6105549207843635e+17,
357
  "train_batch_size": 8,
358
  "trial_name": null,
359
  "trial_params": null