jmmr-8282 commited on
Commit
c783a04
·
verified ·
1 Parent(s): 8846a35

Training in progress, epoch 20, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b2ced86c9801e4026be1866776c08ce5492085a1175dafe22ada264e86f7429d
3
  size 437961700
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69b8a1fbb0b2ebabc7c5f8e8d5ec25388cfef2747f737797e282dcd01b2a50bc
3
  size 437961700
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e3dcddf7bb6f2e8c0e8f3643f658d18e7a5b96ecb3471c2d3a9d09d724bad43b
3
  size 4748067
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:548e94dc2685e005b0d7e57dbcabd457777d3eaaa84ead92f32763cc36dfa36d
3
  size 4748067
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fb9e414eff58722d667823de371e35357986a30e64b45bc494d4828098d21f8a
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74236b95568a925beb79e7faf7870231eb1e38b3bfebea880411163d4b5261b1
3
  size 14645
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b37f55e0b7fd54d79a33d1831f931fecb2307d10ee17c884fd456e2c04818e63
3
  size 1383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0f37305dcafcb7d1b99695ee592b933dde91868bc75eb3897eb1e1cbce31146
3
  size 1383
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5326aad5a305cb353756fdbafb0841ec9b31231063515dd7ba118b57c91e3aac
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93868e507dd0a2ffbdee1d3242238179b3c04f412293c025930b9b63d57cd536
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -2,9 +2,9 @@
2
  "best_global_step": 2548,
3
  "best_metric": 2.07909893989563,
4
  "best_model_checkpoint": "./bert-resume/checkpoint-2548",
5
- "epoch": 19.0,
6
  "eval_steps": 500,
7
- "global_step": 3724,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -209,6 +209,14 @@
209
  "eval_samples_per_second": 58.519,
210
  "eval_steps_per_second": 1.83,
211
  "step": 3724
 
 
 
 
 
 
 
 
212
  }
213
  ],
214
  "logging_steps": 500,
@@ -223,12 +231,12 @@
223
  "should_evaluate": false,
224
  "should_log": false,
225
  "should_save": true,
226
- "should_training_stop": false
227
  },
228
  "attributes": {}
229
  }
230
  },
231
- "total_flos": 3.119972596076851e+16,
232
  "train_batch_size": 32,
233
  "trial_name": null,
234
  "trial_params": null
 
2
  "best_global_step": 2548,
3
  "best_metric": 2.07909893989563,
4
  "best_model_checkpoint": "./bert-resume/checkpoint-2548",
5
+ "epoch": 20.0,
6
  "eval_steps": 500,
7
+ "global_step": 3920,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
209
  "eval_samples_per_second": 58.519,
210
  "eval_steps_per_second": 1.83,
211
  "step": 3724
212
+ },
213
+ {
214
+ "epoch": 20.0,
215
+ "eval_loss": 2.0794472694396973,
216
+ "eval_runtime": 30.0698,
217
+ "eval_samples_per_second": 58.497,
218
+ "eval_steps_per_second": 1.829,
219
+ "step": 3920
220
  }
221
  ],
222
  "logging_steps": 500,
 
231
  "should_evaluate": false,
232
  "should_log": false,
233
  "should_save": true,
234
+ "should_training_stop": true
235
  },
236
  "attributes": {}
237
  }
238
  },
239
+ "total_flos": 3.284181680080896e+16,
240
  "train_batch_size": 32,
241
  "trial_name": null,
242
  "trial_params": null