Nexspear commited on
Commit
e3472c8
·
verified ·
1 Parent(s): ba31273

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:adf4d81665c463139b62940be68da8a0149ed478eee21eb621ffc41a12bf39c9
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69ae5e4403a9e09f2b0f5498335485624c79b90f315e2bed5346f49a1dccaf1a
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2ed2d1e3a6f1e5bf167533312c46c6163dfd85392d23f6fd02194800059054ae
3
  size 325339796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:448c2514a2e7bc592309a5aff2fe9b424ff5173b771e007c3946866b96e05188
3
  size 325339796
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 sha256:4ec0bb6efeeb25000ef7426abb9d88265daa212fa2a170e1fb3f58996efa27f6
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": 0.3220035778175313,
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": 11.063,
193
  "eval_steps_per_second": 1.406,
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": 5.987288966234112e+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": 0.35778175313059035,
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": 11.063,
193
  "eval_steps_per_second": 1.406,
194
  "step": 45
195
+ },
196
+ {
197
+ "epoch": 0.3434704830053667,
198
+ "grad_norm": 9.970080375671387,
199
+ "learning_rate": 6.15582970243117e-07,
200
+ "loss": 0.1613,
201
+ "step": 48
202
+ },
203
+ {
204
+ "epoch": 0.35778175313059035,
205
+ "eval_loss": 0.015444937162101269,
206
+ "eval_runtime": 21.3372,
207
+ "eval_samples_per_second": 11.06,
208
+ "eval_steps_per_second": 1.406,
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": 6.65254329581568e+16,
230
  "train_batch_size": 8,
231
  "trial_name": null,
232
  "trial_params": null