leixa commited on
Commit
4c542ab
·
verified ·
1 Parent(s): a0d3bcb

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 sha256:204ef28525b69547cb3eece54ba7cab7ef99b4a4d739bf9c0cd00820eaa20f7e
3
  size 406863720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33d987b11b0b06de891bfddc5ff9dca27385a494e786132b9db6afed2bd48c1b
3
  size 406863720
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd3e28a91f83d04fa437b90db432002bc0a76569a1e7c381374ba7fcea4ba815
3
  size 207013892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d02523229bdd718451ed85bcf4ab40cdf79bee898f98118ed01ca96a32967604
3
  size 207013892
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:495313cc5fe4d4d0b10caf54db3b277c47deeb18c57d30aa783f3f08b98a0f35
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9edf1cab18a885c802e0990cac1c2dcd8857feff20afd7cf42435a2b85a2da59
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": 0.0029215562156108487,
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": 5.348,
193
  "eval_steps_per_second": 0.669,
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": 5.068352526483456e+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": 0.003246173572900943,
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": 5.348,
193
  "eval_steps_per_second": 0.669,
194
  "step": 45
195
+ },
196
+ {
197
+ "epoch": 0.0031163266299849054,
198
+ "grad_norm": 0.2729395627975464,
199
+ "learning_rate": 6.15582970243117e-07,
200
+ "loss": 0.9525,
201
+ "step": 48
202
+ },
203
+ {
204
+ "epoch": 0.003246173572900943,
205
+ "eval_loss": 0.9448450207710266,
206
+ "eval_runtime": 4847.1505,
207
+ "eval_samples_per_second": 5.352,
208
+ "eval_steps_per_second": 0.669,
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": 5.590342321569792e+16,
230
  "train_batch_size": 8,
231
  "trial_name": null,
232
  "trial_params": null