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
95291ff
·
verified ·
1 Parent(s): 33c1c5e

Training in progress, step 5500, 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:b23f011ce2362c571abb2427f9987a6c4706a2a7a0ebdb43d939b6409cc811a2
3
  size 651465828
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c063be5646bdd548ecf3b4ab7f9c2b91e45c71b9c9604cc7739ae2ce57156601
3
  size 651465828
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5d8a4d430a10c49af040178394250ee3c0e1f64a287e5330b6ebc9951d47466f
3
  size 1303053067
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc51b9293489ca30d6dbff10b4294572048e3eb175e5855b611474ffe8eaa441
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:ed6a6b2b9edacd2ae73ddb3992b05a5ae24954ddfb334654fbbc9febd06408d1
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b983edfe88b8213df49573de3b0a2e9dd491e6543bf5f5bd102232be36fc39e
3
  size 14645
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:82ad8990572ad11a824b7db276c8af49c179ca7e7724b4e6906cd0ae480a80a8
3
  size 1383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bb8c4f79563cb7c9027a7d8be443142caa0e3f4a88491ec812af28bc90af134
3
  size 1383
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ebcec4f03a21fe981e8dfe7c171b1a853d27e1cc2c6e7b6ca31853e54775121a
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78c40077907b8f0920b0693d5918e0226f1b7b772e68b0f126acf47e6adc0ab9
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -1,10 +1,10 @@
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,
@@ -188,6 +188,24 @@
188
  "eval_steps_per_second": 3.459,
189
  "eval_weighted_f1": 0.9523043519198916,
190
  "step": 5000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
191
  }
192
  ],
193
  "logging_steps": 500,
@@ -207,7 +225,7 @@
207
  "attributes": {}
208
  }
209
  },
210
- "total_flos": 2.105323118592e+16,
211
  "train_batch_size": 128,
212
  "trial_name": null,
213
  "trial_params": null
 
1
  {
2
+ "best_global_step": 5500,
3
+ "best_metric": 0.9602459459459459,
4
+ "best_model_checkpoint": "/kaggle/working/arbert_submeter_training/checkpoints/checkpoint-5500",
5
+ "epoch": 0.9513102136123843,
6
  "eval_steps": 500,
7
+ "global_step": 5500,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
188
  "eval_steps_per_second": 3.459,
189
  "eval_weighted_f1": 0.9523043519198916,
190
  "step": 5000
191
+ },
192
+ {
193
+ "epoch": 0.9513102136123843,
194
+ "grad_norm": 3.2097666263580322,
195
+ "learning_rate": 3.4149083362158425e-05,
196
+ "loss": 0.1569,
197
+ "step": 5500
198
+ },
199
+ {
200
+ "epoch": 0.9513102136123843,
201
+ "eval_accuracy": 0.9602459459459459,
202
+ "eval_loss": 0.14497891068458557,
203
+ "eval_macro_f1": 0.5471822620722766,
204
+ "eval_runtime": 418.9758,
205
+ "eval_samples_per_second": 883.106,
206
+ "eval_steps_per_second": 3.451,
207
+ "eval_weighted_f1": 0.9536733224654437,
208
+ "step": 5500
209
  }
210
  ],
211
  "logging_steps": 500,
 
225
  "attributes": {}
226
  }
227
  },
228
+ "total_flos": 2.3158554304512e+16,
229
  "train_batch_size": 128,
230
  "trial_name": null,
231
  "trial_params": null