ardaspear commited on
Commit
13bfd1c
·
verified ·
1 Parent(s): fb77c87

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 sha256:6137c48656511a4041b41fe82b23b2fd9080ce734a6db5e0143dd900d0d71296
3
  size 42487072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18bd789dfc0cc749d317a47f37b44d2c16d9ab37cf734a25f18418e159b523ae
3
  size 42487072
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:20de964ab454e0c1409bd1b6e2dae9d382a7c63a5c41f718b0b07a805fb1d952
3
  size 21735354
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bf1c438ecc80903d74925ad19b75746451f832b77e6bbafe9eb3eb4385edf26
3
  size 21735354
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0923d445f321df35110251ce013719390c03945935abe7a84cbff340b8eba72c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:833de54fa67bebfc6153fd7640b89dcb3fd1a249d48973ef2a90aab23406282a
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": 0.4411764705882353,
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": 120.413,
193
  "eval_steps_per_second": 15.402,
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": 1589448731000832.0,
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": 0.49019607843137253,
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": 120.413,
193
  "eval_steps_per_second": 15.402,
194
  "step": 45
195
+ },
196
+ {
197
+ "epoch": 0.47058823529411764,
198
+ "grad_norm": 10.30472183227539,
199
+ "learning_rate": 6.15582970243117e-07,
200
+ "loss": 8.2143,
201
+ "step": 48
202
+ },
203
+ {
204
+ "epoch": 0.49019607843137253,
205
+ "eval_loss": 1.8856240510940552,
206
+ "eval_runtime": 1.4439,
207
+ "eval_samples_per_second": 119.12,
208
+ "eval_steps_per_second": 15.236,
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": 1758739128385536.0,
230
  "train_batch_size": 8,
231
  "trial_name": null,
232
  "trial_params": null