ardaspear commited on
Commit
599f81f
1 Parent(s): a8a9f7a

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:ca8853fd10c42593ba458a656c81b3bbb1e4dbe03de7fec06fb5938c3a5e3152
3
  size 191968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:309c64fc7a5741a8d6a05be4d40ea22bd13ad35d1aad5bd73087e69aa92c02b6
3
  size 191968
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a87bccbafeee423590f7a4a274508d4c30036dbbfee8ca36260c9a7b89a50617
3
  size 253144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27afef69233f6ab7b0cff803649d7240c0cffa136111dd9e6989e76de0f628af
3
  size 253144
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f6aaadfc3a2995ea3bff4c91194faec2c49a54ff830cb39f07c142f67055ad8
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d1201220196b0eea01cc2e9383598f0df0fda082156bad64ee5af51ec629e09
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": 0.10158013544018059,
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": 531.663,
193
  "eval_steps_per_second": 66.903,
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": 5019779727360.0,
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": 0.11286681715575621,
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": 531.663,
193
  "eval_steps_per_second": 66.903,
194
  "step": 45
195
+ },
196
+ {
197
+ "epoch": 0.10835214446952596,
198
+ "grad_norm": 0.7388740181922913,
199
+ "learning_rate": 6.15582970243117e-07,
200
+ "loss": 10.3121,
201
+ "step": 48
202
+ },
203
+ {
204
+ "epoch": 0.11286681715575621,
205
+ "eval_loss": 10.314505577087402,
206
+ "eval_runtime": 1.3781,
207
+ "eval_samples_per_second": 542.057,
208
+ "eval_steps_per_second": 68.211,
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": 5577533030400.0,
230
  "train_batch_size": 8,
231
  "trial_name": null,
232
  "trial_params": null