Hugging Face's logo

Shaer-AI
/
ARBERT-base-submeter-classifier

Text Classification
Transformers
Safetensors
bert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Community
NourFakih commited on
Commit
4e51388
·
verified ·
1 Parent(s): 561965a

Training in progress, step 5000, 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 +24 -6
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:759c7c3dc8b8a977f96c54dc6091e6b8d76952d45a68af63bfd9cc20855a2cc8
3
  size 651465828
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b23f011ce2362c571abb2427f9987a6c4706a2a7a0ebdb43d939b6409cc811a2
3
  size 651465828
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d96dfc714953d1a8ff52a7a455f377370390dc1a138c1e24bdce92adaea47d2e
3
  size 1303053067
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d8a4d430a10c49af040178394250ee3c0e1f64a287e5330b6ebc9951d47466f
3
  size 1303053067
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dbe3959441c1e1942eefadc50f29de4fc080c3ca8c311c2ebeeda1537571efdc
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed6a6b2b9edacd2ae73ddb3992b05a5ae24954ddfb334654fbbc9febd06408d1
3
  size 14645
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b62db0ba9861d9ab63380744e79a287faa461a1bf55700140a411fe1e976f1cd
3
  size 1383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82ad8990572ad11a824b7db276c8af49c179ca7e7724b4e6906cd0ae480a80a8
3
  size 1383
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:414e55f58b5266553da3c3fe877f96c896218d59ea6b776dd34481a4e5d7964e
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebcec4f03a21fe981e8dfe7c171b1a853d27e1cc2c6e7b6ca31853e54775121a
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "best_global_step": 4500,
3
- "best_metric": 0.9571459459459459,
4
- "best_model_checkpoint": "/kaggle/working/arbert_submeter_training/checkpoints/checkpoint-4500",
5
- "epoch": 0.7783447202283145,
6
  "eval_steps": 500,
7
- "global_step": 4500,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -170,6 +170,24 @@
170
  "eval_steps_per_second": 3.459,
171
  "eval_weighted_f1": 0.9507761247869798,
172
  "step": 4500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
173
  }
174
  ],
175
  "logging_steps": 500,
@@ -189,7 +207,7 @@
189
  "attributes": {}
190
  }
191
  },
192
- "total_flos": 1.8947908067328e+16,
193
  "train_batch_size": 128,
194
  "trial_name": null,
195
  "trial_params": null
 
1
  {
2
+ "best_global_step": 5000,
3
+ "best_metric": 0.9585405405405405,
4
+ "best_model_checkpoint": "/kaggle/working/arbert_submeter_training/checkpoints/checkpoint-5000",
5
+ "epoch": 0.8648274669203494,
6
  "eval_steps": 500,
7
+ "global_step": 5000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
170
  "eval_steps_per_second": 3.459,
171
  "eval_weighted_f1": 0.9507761247869798,
172
  "step": 4500
173
+ },
174
+ {
175
+ "epoch": 0.8648274669203494,
176
+ "grad_norm": 5.704383850097656,
177
+ "learning_rate": 3.559033783004728e-05,
178
+ "loss": 0.1622,
179
+ "step": 5000
180
+ },
181
+ {
182
+ "epoch": 0.8648274669203494,
183
+ "eval_accuracy": 0.9585405405405405,
184
+ "eval_loss": 0.1496480107307434,
185
+ "eval_macro_f1": 0.5578920159472586,
186
+ "eval_runtime": 418.0713,
187
+ "eval_samples_per_second": 885.017,
188
+ "eval_steps_per_second": 3.459,
189
+ "eval_weighted_f1": 0.9523043519198916,
190
+ "step": 5000
191
  }
192
  ],
193
  "logging_steps": 500,
 
207
  "attributes": {}
208
  }
209
  },
210
+ "total_flos": 2.105323118592e+16,
211
  "train_batch_size": 128,
212
  "trial_name": null,
213
  "trial_params": null