Hugging Face's logo

m-aliabbas1
/
roberta_en_med_merged_classes

Text Classification
Transformers
Safetensors
roberta
Generated from Trainer
Model card Files
xet
 Community
m-aliabbas1 commited on
Commit
0064da1
·
verified ·
1 Parent(s): 741deeb

Training in progress, step 1800, 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 +28 -3
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:84ec469b9a931ceaa48172563637e8990933d25e1be502af4e7ae5611becf20f
3
  size 498637432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d640569f280845850b19876b645b3b11824a1e3a77ded558ed44e9f7a698a39a
3
  size 498637432
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2cc9c3001940abe627d7be7b80893c4009a4964ba4991d59443c18eb73cc1fdc
3
  size 997397434
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efbdf4a6e19f98686ec57ce738ea63ae1c0e0e0f16cb3fdddb9a805437357ce5
3
  size 997397434
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:797f580e891f5abde287b12800586d04473118777fd6947254183148e618fd1b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7051d0434df38410dfdf22db189b4d97ee9a5da62ba7a20c952d0aeb811e0e84
3
  size 14244
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:effa0a4f47489c26c9eb6d82a01e44c96441806dcdd44004dc1934ba079fa6b3
3
  size 988
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15fda9c95e7fb75e97bb18c5dd4254c0b29336dd68bd09b86369dc5a56e92d9d
3
  size 988
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:24314368a361a98a57954473631fda87453de83e38555b1dca4f24bf2f32a584
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e72a739d5c62dd01cfd93f0b641c412bac827fe4cd7d999e555eaaab49a3de3b
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -2,9 +2,9 @@
2
  "best_global_step": 800,
3
  "best_metric": 0.8289822527097279,
4
  "best_model_checkpoint": "roberta_en_med_merged_classes/checkpoint-800",
5
- "epoch": 26.669456066945607,
6
  "eval_steps": 200,
7
- "global_step": 1600,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -208,6 +208,31 @@
208
  "eval_samples_per_second": 905.627,
209
  "eval_steps_per_second": 28.372,
210
  "step": 1600
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
211
  }
212
  ],
213
  "logging_steps": 100,
@@ -227,7 +252,7 @@
227
  "attributes": {}
228
  }
229
  },
230
- "total_flos": 4.29018655215231e+17,
231
  "train_batch_size": 64,
232
  "trial_name": null,
233
  "trial_params": null
 
2
  "best_global_step": 800,
3
  "best_metric": 0.8289822527097279,
4
  "best_model_checkpoint": "roberta_en_med_merged_classes/checkpoint-800",
5
+ "epoch": 30.0,
6
  "eval_steps": 200,
7
+ "global_step": 1800,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
208
  "eval_samples_per_second": 905.627,
209
  "eval_steps_per_second": 28.372,
210
  "step": 1600
211
+ },
212
+ {
213
+ "epoch": 28.334728033472803,
214
+ "grad_norm": 5.792581081390381,
215
+ "learning_rate": 1.1734567901234568e-05,
216
+ "loss": 0.1071,
217
+ "step": 1700
218
+ },
219
+ {
220
+ "epoch": 30.0,
221
+ "grad_norm": 5.362116813659668,
222
+ "learning_rate": 1.1117283950617285e-05,
223
+ "loss": 0.1001,
224
+ "step": 1800
225
+ },
226
+ {
227
+ "epoch": 30.0,
228
+ "eval_accuracy": 0.843358976735564,
229
+ "eval_f1_macro": 0.8274236182829814,
230
+ "eval_f1_weighted": 0.8429144061347414,
231
+ "eval_loss": 0.6331083178520203,
232
+ "eval_runtime": 11.9481,
233
+ "eval_samples_per_second": 902.988,
234
+ "eval_steps_per_second": 28.289,
235
+ "step": 1800
236
  }
237
  ],
238
  "logging_steps": 100,
 
252
  "attributes": {}
253
  }
254
  },
255
+ "total_flos": 4.825855987926221e+17,
256
  "train_batch_size": 64,
257
  "trial_name": null,
258
  "trial_params": null