leixa commited on
Commit
ba56ba0
·
verified ·
1 Parent(s): eaca1eb

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:c91e72a3e318d4dd79ad1a3f60541d41c8fc9c519c11d05121e4b9d511b7b9a5
3
  size 891333320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01ff5d77e03385f2dffc5cacd7a84ffb1145ad068fd5d6346d139833c27979c6
3
  size 891333320
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:133d7b7a67f93577f1b2433ec8874d898e8b054406f84e33299d60a60da77663
3
  size 452984596
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8701dbc721a671da916b35327f7b740e5ce5be3cfb4be93f8331cd2978dd147c
3
  size 452984596
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b0ea16f6cbc3482bc244d205dbea74f7ab7b04b6705a0543758bcce72fbf13ce
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9fb3cab2d8f5b95d82cb6c27b6d664393952cfe75dec9c286e83184c159d693
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ec0bb6efeeb25000ef7426abb9d88265daa212fa2a170e1fb3f58996efa27f6
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
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": 0.0049810443589672635,
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": 6.647,
193
  "eval_steps_per_second": 0.831,
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": 1.24030191403008e+17,
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": 0.005534493732185848,
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": 6.647,
193
  "eval_steps_per_second": 0.831,
194
  "step": 45
195
+ },
196
+ {
197
+ "epoch": 0.005313113982898414,
198
+ "grad_norm": 4.175896644592285,
199
+ "learning_rate": 6.15582970243117e-07,
200
+ "loss": 1.3884,
201
+ "step": 48
202
+ },
203
+ {
204
+ "epoch": 0.005534493732185848,
205
+ "eval_loss": 0.3020959794521332,
206
+ "eval_runtime": 2290.7826,
207
+ "eval_samples_per_second": 6.642,
208
+ "eval_steps_per_second": 0.83,
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": 1.3781132378112e+17,
230
  "train_batch_size": 8,
231
  "trial_name": null,
232
  "trial_params": null