Nexspear commited on
Commit
5667bb0
1 Parent(s): 4a68e2d

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:c71e33a5debc3c4df2a757522ef142d20c3595371956e5a37d90551f25c82754
3
  size 800116456
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21d45853cbd2b34f8c36016892276406d3b0289700e4eccbfa79e0b5c5c2a500
3
  size 800116456
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dbc79f753b6a657bc036c59ff3a86671d57a3be4ec21947f6712e72c39986ed2
3
  size 406743412
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3b05163e70f87868c87c36dfd9c6296991d8342cde5db60a7b1e0fe1277ad7f
3
  size 406743412
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4789c106969b99c08f3baf5e5d541de9a8461ea0366289912967be9907174268
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eaf02895b834a33e05be338cb10af146c2170b1e50919fc9991bee91a28f6199
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": 0.011384479160078426,
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": 11.249,
193
  "eval_steps_per_second": 1.407,
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": 7.034770185781248e+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": 0.01264942128897603,
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": 11.249,
193
  "eval_steps_per_second": 1.407,
194
  "step": 45
195
+ },
196
+ {
197
+ "epoch": 0.012143444437416988,
198
+ "grad_norm": 9.111993789672852,
199
+ "learning_rate": 6.15582970243117e-07,
200
+ "loss": 3.0088,
201
+ "step": 48
202
+ },
203
+ {
204
+ "epoch": 0.01264942128897603,
205
+ "eval_loss": 3.237314462661743,
206
+ "eval_runtime": 592.0112,
207
+ "eval_samples_per_second": 11.246,
208
+ "eval_steps_per_second": 1.407,
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": 7.81641131753472e+16,
230
  "train_batch_size": 8,
231
  "trial_name": null,
232
  "trial_params": null