Nexspear commited on
Commit
976bccb
·
verified ·
1 Parent(s): a8fc5ea

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 sha256:77983f5a540752d9581591f97062db6deefd810d2da45f5a335607319d8d5cd4
3
  size 201892112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:541da51ef915f07af108b4a4b260e49fcbe64fa2e2c70f21f4c6c7a7b609c8f8
3
  size 201892112
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ef2586f79bba9931ca167018e3215609b6552b5bc39a44edfb79ad1d2f123fc
3
  size 102864548
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eda9e734113895a3351a222bad111140e755eec121d7e0ea4d75cad382ed93d9
3
  size 102864548
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c9860c11c537813edac1dabfc5de8450c647a71a83d9008b84e93eeede466520
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:623574dc33bf754135f8d5f515849ae4680b1797668721ae490e0317b52e5ef3
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": 0.008461032245934004,
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": 49.623,
193
  "eval_steps_per_second": 6.204,
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": 9599165336125440.0,
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": 0.00940114693992667,
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": 49.623,
193
  "eval_steps_per_second": 6.204,
194
  "step": 45
195
+ },
196
+ {
197
+ "epoch": 0.009025101062329604,
198
+ "grad_norm": 0.5945635437965393,
199
+ "learning_rate": 6.15582970243117e-07,
200
+ "loss": 0.4824,
201
+ "step": 48
202
+ },
203
+ {
204
+ "epoch": 0.00940114693992667,
205
+ "eval_loss": 0.4674220681190491,
206
+ "eval_runtime": 180.3649,
207
+ "eval_samples_per_second": 49.666,
208
+ "eval_steps_per_second": 6.21,
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": 1.06657392623616e+16,
230
  "train_batch_size": 8,
231
  "trial_name": null,
232
  "trial_params": null