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
d973079
·
verified ·
1 Parent(s): 2d01dc3

Training in progress, step 11500, 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 +21 -3
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:01cac7c918901d6947e45f61570115c2973993c8f46091c07a139aa2b8e2f7ae
3
  size 651465828
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:900d2d30d885969255af7871e504937a3fdf43367bf4c8fb400a078803308015
3
  size 651465828
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9cd4ae2a9172e52440e8dcd2adfd4920bd076ce5091bc8e4db8900ffd422d9fa
3
  size 1303053067
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d95a7a63237d7406f7439f9538d7cc49d27d150f93d5f55e8c596ffbda73c8fd
3
  size 1303053067
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:03edea280c419a52aac0484396ae487bf545a7eba6c00a74a5cf6e1ee5fca946
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f38e426d00f289ba3da271df8237ec0033c45bbcd3372361acf01221c52a67e1
3
  size 14645
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:01903b6f628f65f68918eac51237e59dd0d0b2affabd2cd100779d9eb7ee7430
3
  size 1383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:103f922acd71a775c101e48b559b3373155a7a0c1f836849133cbaf72bb3b718
3
  size 1383
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:581a4ae4b3d43e1731ebcde9408603a981417da09a0e43c4a0ddd15ffc47bccd
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fe67c4e3d00e74e6424528563a7ae51e4f6d9a51c8fdf7ce02cb1280db7a7e8
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -2,9 +2,9 @@
2
  "best_global_step": 11000,
3
  "best_metric": 0.9684972972972973,
4
  "best_model_checkpoint": "/kaggle/working/arbert_submeter_training/checkpoints/checkpoint-11000",
5
- "epoch": 1.9025339444780767,
6
  "eval_steps": 500,
7
- "global_step": 11000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -404,6 +404,24 @@
404
  "eval_steps_per_second": 3.456,
405
  "eval_weighted_f1": 0.9622871010076606,
406
  "step": 11000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
407
  }
408
  ],
409
  "logging_steps": 500,
@@ -423,7 +441,7 @@
423
  "attributes": {}
424
  }
425
  },
426
- "total_flos": 4.631391772867238e+16,
427
  "train_batch_size": 128,
428
  "trial_name": null,
429
  "trial_params": null
 
2
  "best_global_step": 11000,
3
  "best_metric": 0.9684972972972973,
4
  "best_model_checkpoint": "/kaggle/working/arbert_submeter_training/checkpoints/checkpoint-11000",
5
+ "epoch": 1.9890166911701117,
6
  "eval_steps": 500,
7
+ "global_step": 11500,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
404
  "eval_steps_per_second": 3.456,
405
  "eval_weighted_f1": 0.9622871010076606,
406
  "step": 11000
407
+ },
408
+ {
409
+ "epoch": 1.9890166911701117,
410
+ "grad_norm": 2.58137845993042,
411
+ "learning_rate": 1.6854029747492218e-05,
412
+ "loss": 0.1093,
413
+ "step": 11500
414
+ },
415
+ {
416
+ "epoch": 1.9890166911701117,
417
+ "eval_accuracy": 0.9683432432432433,
418
+ "eval_loss": 0.11723459511995316,
419
+ "eval_macro_f1": 0.5835321485745915,
420
+ "eval_runtime": 419.3158,
421
+ "eval_samples_per_second": 882.39,
422
+ "eval_steps_per_second": 3.448,
423
+ "eval_weighted_f1": 0.9623140045622489,
424
+ "step": 11500
425
  }
426
  ],
427
  "logging_steps": 500,
 
441
  "attributes": {}
442
  }
443
  },
444
+ "total_flos": 4.841924084726438e+16,
445
  "train_batch_size": 128,
446
  "trial_name": null,
447
  "trial_params": null