Hugging Face's logo

jmmr-8282
/
email

Text Classification
Transformers
Safetensors
bert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Community
jmmr-8282 commited on
Commit
51d1b13
·
verified ·
1 Parent(s): 7a5ca36

Training in progress, epoch 18, checkpoint

Browse files
Files changed (6) hide show
  1. last-checkpoint/model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scaler.pt +1 -1
  5. last-checkpoint/scheduler.pt +1 -1
  6. last-checkpoint/trainer_state.json +18 -3
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a5aca013f636e2217131f4a7766259db7295ca86fb1445203771da2c76157ab0
3
  size 437961700
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b1151d48ca26da998da8f35ed6a9a4e4e2f85606582f7d78af0dd56865e83f9
3
  size 437961700
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fd7a805625a4650e18784f6973092b0c1dd89f8a7d20488d159672bd0ecb3606
3
  size 4748067
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c3ee46ee1b54baa8173b876a66e1f120a7f18badab15292bad4f99556ae0d8f
3
  size 4748067
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e14d99073472e5fac9c9b54d5364f7405db8d7e8f9b468d5259ff782448daec
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:722c7a3ce0a5935d68a61cf21171e07f55d762fc7fa330765d1b718d707750ad
3
  size 14645
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:155d0458e802a09af1803acd5ca09397dfd2a0c2a3f47062dbdd5c0e90f235c5
3
  size 1383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcab6042103a2fd0e8743c8a9400dce12c7ba68761a2938ae1a0e95e40c788f4
3
  size 1383
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eb74e84cce811dee064e6d98b21b052b1fb8034b631f09a89b9c60cf36467639
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbeba2a26b533fa268eae33390ad4db87f2ced5c93b7068df15ec865fdb10ee3
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": 17.0,
6
  "eval_steps": 500,
7
- "global_step": 3332,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -186,6 +186,21 @@
186
  "eval_samples_per_second": 58.443,
187
  "eval_steps_per_second": 1.827,
188
  "step": 3332
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
189
  }
190
  ],
191
  "logging_steps": 500,
@@ -205,7 +220,7 @@
205
  "attributes": {}
206
  }
207
  },
208
- "total_flos": 2.7915544280687616e+16,
209
  "train_batch_size": 32,
210
  "trial_name": null,
211
  "trial_params": null
 
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,
 
186
  "eval_samples_per_second": 58.443,
187
  "eval_steps_per_second": 1.827,
188
  "step": 3332
189
+ },
190
+ {
191
+ "epoch": 17.857142857142858,
192
+ "grad_norm": 4.039883136749268,
193
+ "learning_rate": 1.0739795918367347e-06,
194
+ "loss": 1.9600203857421874,
195
+ "step": 3500
196
+ },
197
+ {
198
+ "epoch": 18.0,
199
+ "eval_loss": 2.080489158630371,
200
+ "eval_runtime": 30.0606,
201
+ "eval_samples_per_second": 58.515,
202
+ "eval_steps_per_second": 1.83,
203
+ "step": 3528
204
  }
205
  ],
206
  "logging_steps": 500,
 
220
  "attributes": {}
221
  }
222
  },
223
+ "total_flos": 2.9557635120728064e+16,
224
  "train_batch_size": 32,
225
  "trial_name": null,
226
  "trial_params": null