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
2d0ef35
·
verified ·
1 Parent(s): c50df30

Training in progress, step 7000, 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:cd8eb51586015b96114ad3bed48811e3850551bc992d6d49d45c89b103988465
3
  size 651465828
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:816f94dc7b94d274001859bde263e04f4a896a53ade67e2995123aff402a7dba
3
  size 651465828
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d589184aeb5f2363d6ace789239adcdf45f4f20cc33c3a408f232bfc21d169bf
3
  size 1303053067
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:910bf906db23867b28de9ff3400e9d96bd6229d7648305bd0e8f7eec43737b1d
3
  size 1303053067
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8304aef9c8e25daa597b118c0cc771e2d04b30d8876daf7c6ea3f6587df11e04
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a9f9a5b995960bd6f60a802e206be9213a2e7efe51466b4832018c81181c9d4
3
  size 14645
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:72ec040f7dbfafb8a0d9c346b901cc53a9760e25574232230ec90bf3c4a5f84d
3
  size 1383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be40a03f70bb2a35bb567114fb5ceb05ce1222c8df24b1e1100746c617c5be10
3
  size 1383
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:968db3e7ebf342cf531002d612ad1567d0cdb68cf93b976366564e3b71aa041c
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b92a571b8baa5cd2064db834c0b66314226372027955024045490e8e27e64eb
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "best_global_step": 6500,
3
- "best_metric": 0.9628189189189189,
4
- "best_model_checkpoint": "/kaggle/working/arbert_submeter_training/checkpoints/checkpoint-6500",
5
- "epoch": 1.1241892242497622,
6
  "eval_steps": 500,
7
- "global_step": 6500,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -242,6 +242,24 @@
242
  "eval_steps_per_second": 3.443,
243
  "eval_weighted_f1": 0.9568010100001315,
244
  "step": 6500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
245
  }
246
  ],
247
  "logging_steps": 500,
@@ -261,7 +279,7 @@
261
  "attributes": {}
262
  }
263
  },
264
- "total_flos": 2.7366009661344384e+16,
265
  "train_batch_size": 128,
266
  "trial_name": null,
267
  "trial_params": null
 
1
  {
2
+ "best_global_step": 7000,
3
+ "best_metric": 0.9632054054054054,
4
+ "best_model_checkpoint": "/kaggle/working/arbert_submeter_training/checkpoints/checkpoint-7000",
5
+ "epoch": 1.210671970941797,
6
  "eval_steps": 500,
7
+ "global_step": 7000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
242
  "eval_steps_per_second": 3.443,
243
  "eval_weighted_f1": 0.9568010100001315,
244
  "step": 6500
245
+ },
246
+ {
247
+ "epoch": 1.210671970941797,
248
+ "grad_norm": 2.2167930603027344,
249
+ "learning_rate": 2.982531995849187e-05,
250
+ "loss": 0.123,
251
+ "step": 7000
252
+ },
253
+ {
254
+ "epoch": 1.210671970941797,
255
+ "eval_accuracy": 0.9632054054054054,
256
+ "eval_loss": 0.1349489837884903,
257
+ "eval_macro_f1": 0.5686206184279916,
258
+ "eval_runtime": 419.1921,
259
+ "eval_samples_per_second": 882.65,
260
+ "eval_steps_per_second": 3.449,
261
+ "eval_weighted_f1": 0.9570982563798056,
262
+ "step": 7000
263
  }
264
  ],
265
  "logging_steps": 500,
 
279
  "attributes": {}
280
  }
281
  },
282
+ "total_flos": 2.9471332779936384e+16,
283
  "train_batch_size": 128,
284
  "trial_name": null,
285
  "trial_params": null