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
4a236ad
·
verified ·
1 Parent(s): 190c7f9

Training in progress, step 11000, 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 sha256:67863636fa0549bd8b1d92955423f0eff097a6d4456d05b8586e80aa5568a2a5
3
  size 651465828
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01cac7c918901d6947e45f61570115c2973993c8f46091c07a139aa2b8e2f7ae
3
  size 651465828
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a43425247f221fb9cbcd9dec338ac204503301bbe41c737f544084da95d5134c
3
  size 1303053067
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cd4ae2a9172e52440e8dcd2adfd4920bd076ce5091bc8e4db8900ffd422d9fa
3
  size 1303053067
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:841e0445f7a47cdc73fd32ae7c7f244d44f36f8c061ab0df905d5adda4ae66f9
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03edea280c419a52aac0484396ae487bf545a7eba6c00a74a5cf6e1ee5fca946
3
  size 14645
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e04d2b4683c173960a4dbb276081df3ab8cca990f45024155f8dd48eb6216523
3
  size 1383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01903b6f628f65f68918eac51237e59dd0d0b2affabd2cd100779d9eb7ee7430
3
  size 1383
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:70ac65d02ceaeadaa54a452ac798461fa992abdeea570ca18b955a035d6ec47c
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:581a4ae4b3d43e1731ebcde9408603a981417da09a0e43c4a0ddd15ffc47bccd
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "best_global_step": 10500,
3
- "best_metric": 0.9673864864864865,
4
- "best_model_checkpoint": "/kaggle/working/arbert_submeter_training/checkpoints/checkpoint-10500",
5
- "epoch": 1.8160511977860416,
6
  "eval_steps": 500,
7
- "global_step": 10500,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -386,6 +386,24 @@
386
  "eval_steps_per_second": 3.453,
387
  "eval_weighted_f1": 0.9612394940368674,
388
  "step": 10500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
389
  }
390
  ],
391
  "logging_steps": 500,
@@ -405,7 +423,7 @@
405
  "attributes": {}
406
  }
407
  },
408
- "total_flos": 4.420859461008038e+16,
409
  "train_batch_size": 128,
410
  "trial_name": null,
411
  "trial_params": null
 
1
  {
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,
 
386
  "eval_steps_per_second": 3.453,
387
  "eval_weighted_f1": 0.9612394940368674,
388
  "step": 10500
389
+ },
390
+ {
391
+ "epoch": 1.9025339444780767,
392
+ "grad_norm": 2.6713507175445557,
393
+ "learning_rate": 1.8295284215381068e-05,
394
+ "loss": 0.1103,
395
+ "step": 11000
396
+ },
397
+ {
398
+ "epoch": 1.9025339444780767,
399
+ "eval_accuracy": 0.9684972972972973,
400
+ "eval_loss": 0.11646272242069244,
401
+ "eval_macro_f1": 0.5835802563966344,
402
+ "eval_runtime": 418.3811,
403
+ "eval_samples_per_second": 884.361,
404
+ "eval_steps_per_second": 3.456,
405
+ "eval_weighted_f1": 0.9622871010076606,
406
+ "step": 11000
407
  }
408
  ],
409
  "logging_steps": 500,
 
423
  "attributes": {}
424
  }
425
  },
426
+ "total_flos": 4.631391772867238e+16,
427
  "train_batch_size": 128,
428
  "trial_name": null,
429
  "trial_params": null