jmmr-8282 commited on
Commit
6eed503
·
verified ·
1 Parent(s): a5d20ca

Training in progress, epoch 19, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b1151d48ca26da998da8f35ed6a9a4e4e2f85606582f7d78af0dd56865e83f9
3
  size 437961700
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2ced86c9801e4026be1866776c08ce5492085a1175dafe22ada264e86f7429d
3
  size 437961700
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c3ee46ee1b54baa8173b876a66e1f120a7f18badab15292bad4f99556ae0d8f
3
  size 4748067
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3dcddf7bb6f2e8c0e8f3643f658d18e7a5b96ecb3471c2d3a9d09d724bad43b
3
  size 4748067
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:722c7a3ce0a5935d68a61cf21171e07f55d762fc7fa330765d1b718d707750ad
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb9e414eff58722d667823de371e35357986a30e64b45bc494d4828098d21f8a
3
  size 14645
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bcab6042103a2fd0e8743c8a9400dce12c7ba68761a2938ae1a0e95e40c788f4
3
  size 1383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b37f55e0b7fd54d79a33d1831f931fecb2307d10ee17c884fd456e2c04818e63
3
  size 1383
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fbeba2a26b533fa268eae33390ad4db87f2ced5c93b7068df15ec865fdb10ee3
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5326aad5a305cb353756fdbafb0841ec9b31231063515dd7ba118b57c91e3aac
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": 18.0,
6
  "eval_steps": 500,
7
- "global_step": 3528,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -201,6 +201,14 @@
201
  "eval_samples_per_second": 58.515,
202
  "eval_steps_per_second": 1.83,
203
  "step": 3528
 
 
 
 
 
 
 
 
204
  }
205
  ],
206
  "logging_steps": 500,
@@ -220,7 +228,7 @@
220
  "attributes": {}
221
  }
222
  },
223
- "total_flos": 2.9557635120728064e+16,
224
  "train_batch_size": 32,
225
  "trial_name": null,
226
  "trial_params": null
 
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,
 
201
  "eval_samples_per_second": 58.515,
202
  "eval_steps_per_second": 1.83,
203
  "step": 3528
204
+ },
205
+ {
206
+ "epoch": 19.0,
207
+ "eval_loss": 2.079270362854004,
208
+ "eval_runtime": 30.0587,
209
+ "eval_samples_per_second": 58.519,
210
+ "eval_steps_per_second": 1.83,
211
+ "step": 3724
212
  }
213
  ],
214
  "logging_steps": 500,
 
228
  "attributes": {}
229
  }
230
  },
231
+ "total_flos": 3.119972596076851e+16,
232
  "train_batch_size": 32,
233
  "trial_name": null,
234
  "trial_params": null