leixa commited on
Commit
7d64ac9
1 Parent(s): 3a327bd

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 sha256:4530420825b598bf2c6fd3b32f80270e26a33cb751bf8bff025ed92b5b9996c0
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a53f1e408f63f4602a7326bc53c303313a33d3ec91b87fcddf743352088f04fa
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dc1c2b4c026d401c8d40a1ffba631f36d188427fac2ed462f67058b31ef1e2e7
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41c2a36657df23aab0d7b5a0838083851efa626869ee35f0224c237c0108e837
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:29843bac3ae7f15549b97859e26d118657b48715b2439ab9d58c3760f6e8b44c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d17fc37c391a80ab23fdd3242c6537b2ecbe7c719b558bb8412abea5cbaccadb
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": 0.3879310344827586,
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": 10.861,
193
  "eval_steps_per_second": 1.392,
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": 6.439491040444416e+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": 0.43103448275862066,
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": 10.861,
193
  "eval_steps_per_second": 1.392,
194
  "step": 45
195
+ },
196
+ {
197
+ "epoch": 0.41379310344827586,
198
+ "grad_norm": 11.72185230255127,
199
+ "learning_rate": 6.15582970243117e-07,
200
+ "loss": 2.7245,
201
+ "step": 48
202
+ },
203
+ {
204
+ "epoch": 0.43103448275862066,
205
+ "eval_loss": 0.6354005336761475,
206
+ "eval_runtime": 17.9512,
207
+ "eval_samples_per_second": 10.863,
208
+ "eval_steps_per_second": 1.393,
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": 7.15499004493824e+16,
230
  "train_batch_size": 8,
231
  "trial_name": null,
232
  "trial_params": null