ardaspear commited on
Commit
64f362a
·
verified ·
1 Parent(s): c9951cf

Training in progress, step 50, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:89e5ec929a682f97f7a13dca1fbedfae442596450072376d826c8737e1abe091
3
  size 159967880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fda91db90e8033d278b3ad72a07f9e95d0b620154781a58f07426c9ef900fb64
3
  size 159967880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:616e2d330f75688d41851622885c80eac2ebfde7d4687f8bbb98231e0b6d400b
3
  size 81730196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:100d357025a14d0d4af84037b5f508887304da7ac016abcc74b287e26f7745d4
3
  size 81730196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:71b07cdafd3b5e2145088a8972b9442b008f1502e71d5096045be99cb1c123be
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b1dd6c4cc69e984f6149a8a0a86ca1652090c8b6b039bc0544bc845c636f554
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a8be797a494f7bdae3ea44e950170e2b372b107c6dbe1015cbf67e384b5238e
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:439e51f57871ee9c2bc8b35458a0c03f9b948af7a0d15ffe5e1cf9789955c6c8
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": 0.06620080912100036,
5
  "eval_steps": 5,
6
- "global_step": 45,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -192,6 +192,21 @@
192
  "eval_samples_per_second": 11.031,
193
  "eval_steps_per_second": 1.387,
194
  "step": 45
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
195
  }
196
  ],
197
  "logging_steps": 3,
@@ -206,12 +221,12 @@
206
  "should_evaluate": false,
207
  "should_log": false,
208
  "should_save": true,
209
- "should_training_stop": false
210
  },
211
  "attributes": {}
212
  }
213
  },
214
- "total_flos": 5.881181799186432e+16,
215
  "train_batch_size": 8,
216
  "trial_name": null,
217
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.07355645457888929,
5
  "eval_steps": 5,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
192
  "eval_samples_per_second": 11.031,
193
  "eval_steps_per_second": 1.387,
194
  "step": 45
195
+ },
196
+ {
197
+ "epoch": 0.07061419639573373,
198
+ "grad_norm": 1.3296202421188354,
199
+ "learning_rate": 3.077914851215585e-07,
200
+ "loss": 6.9776,
201
+ "step": 48
202
+ },
203
+ {
204
+ "epoch": 0.07355645457888929,
205
+ "eval_loss": 1.742841124534607,
206
+ "eval_runtime": 103.7854,
207
+ "eval_samples_per_second": 11.032,
208
+ "eval_steps_per_second": 1.387,
209
+ "step": 50
210
  }
211
  ],
212
  "logging_steps": 3,
 
221
  "should_evaluate": false,
222
  "should_log": false,
223
  "should_save": true,
224
+ "should_training_stop": true
225
  },
226
  "attributes": {}
227
  }
228
  },
229
+ "total_flos": 6.53464644354048e+16,
230
  "train_batch_size": 8,
231
  "trial_name": null,
232
  "trial_params": null