ardaspear commited on
Commit
1842968
·
verified ·
1 Parent(s): 70eb30b

Training in progress, step 81, 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:bbb1e70325f43adf8edad114cc78cce2713e46b0f3df2b009e42d681ba074d09
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9eeafb9edc855ed511c6afcb94a19efc84775dc67fc4c61a2c598c34c6dcaf9d
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:794635d61c7123f681d7316631cd07d570b66792ec92510adc081b2436e7c885
3
  size 85723284
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4579ec690ddb8cb216f30c82b626a09d64561ba85cfe45edbb141442c052649
3
  size 85723284
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e516afdcdb9527b92acb9135dcaef8efd04a59ef48eae429f8862424dca0ac8
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b53abc7e570e04f329d31359238d4aaad5393b7c224043d2ef4e3a88f19578e2
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5dcc5b33f65fdaffd6a8f394a182adc55f95c04061e1e53640018b07b2b89f10
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90f7a57653bcfdeb8d3e27706e79cc5f6e1f14bbd0ff72a8e33edaaa89ef8274
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": 1.3457943925233644,
5
  "eval_steps": 9,
6
- "global_step": 72,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -247,6 +247,35 @@
247
  "eval_samples_per_second": 13.969,
248
  "eval_steps_per_second": 1.863,
249
  "step": 72
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
250
  }
251
  ],
252
  "logging_steps": 3,
@@ -266,7 +295,7 @@
266
  "attributes": {}
267
  }
268
  },
269
- "total_flos": 1.0191068692532429e+17,
270
  "train_batch_size": 8,
271
  "trial_name": null,
272
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.514018691588785,
5
  "eval_steps": 9,
6
+ "global_step": 81,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
247
  "eval_samples_per_second": 13.969,
248
  "eval_steps_per_second": 1.863,
249
  "step": 72
250
+ },
251
+ {
252
+ "epoch": 1.4018691588785046,
253
+ "grad_norm": 3.333451509475708,
254
+ "learning_rate": 1.7860619515673033e-05,
255
+ "loss": 2.3143,
256
+ "step": 75
257
+ },
258
+ {
259
+ "epoch": 1.4579439252336448,
260
+ "grad_norm": 3.3543541431427,
261
+ "learning_rate": 1.4033009983067452e-05,
262
+ "loss": 2.3838,
263
+ "step": 78
264
+ },
265
+ {
266
+ "epoch": 1.514018691588785,
267
+ "grad_norm": 3.3445632457733154,
268
+ "learning_rate": 1.0599462319663905e-05,
269
+ "loss": 2.1699,
270
+ "step": 81
271
+ },
272
+ {
273
+ "epoch": 1.514018691588785,
274
+ "eval_loss": 0.6209324598312378,
275
+ "eval_runtime": 6.4415,
276
+ "eval_samples_per_second": 13.972,
277
+ "eval_steps_per_second": 1.863,
278
+ "step": 81
279
  }
280
  ],
281
  "logging_steps": 3,
 
295
  "attributes": {}
296
  }
297
  },
298
+ "total_flos": 1.1492430354736742e+17,
299
  "train_batch_size": 8,
300
  "trial_name": null,
301
  "trial_params": null