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
3f1bd1c
·
verified ·
1 Parent(s): de82822

Training in progress, step 15500, 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 sha256:651e61b153b3149ac3ce33e0b97e23286c0e65e20692fed53116376210dd5643
3
  size 651465828
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b5480293c959a944ef14ff41730b84cfa1d035f101bfa6f16d1d97b1c6c7384
3
  size 651465828
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:27eb5818412e7e7894f3b462191e554716ea91c7b47f4f1e6535412a46d70fca
3
  size 1303053067
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c5b3350ed3616186e905b185da2ced89195db507e9bf28662e8548e36429f6a
3
  size 1303053067
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:60d4026715a17089972b4da95d68c0225e81b22cd1f40015bcd89ebaf1c3e7e3
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f6226d983bd11e1009778d42860849834c34de435a756e95c206ed5451e0678
3
  size 14645
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b0415cc902581048eff49426d3b5977e3d3a9842950529c62d3aba0c1eceb6cc
3
  size 1383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1d086c48bf9ef55507053335c22a801a05683add7c8955ea07815dfc8cac267
3
  size 1383
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f8433be9bc1fc438fbebc88878b9cb26c559fbfad46d0cd7ce1cc34e345d21d7
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b7e2fc05c77d58e87b922e2178b0c5e30e234cd120c1e72dfacc3051ef58e18
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "best_global_step": 15000,
3
- "best_metric": 0.9698027027027027,
4
- "best_model_checkpoint": "/kaggle/working/arbert_submeter_training/checkpoints/checkpoint-15000",
5
- "epoch": 2.594309435267664,
6
  "eval_steps": 500,
7
- "global_step": 15000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -548,6 +548,24 @@
548
  "eval_steps_per_second": 3.45,
549
  "eval_weighted_f1": 0.9643335590541979,
550
  "step": 15000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
551
  }
552
  ],
553
  "logging_steps": 500,
@@ -567,7 +585,7 @@
567
  "attributes": {}
568
  }
569
  },
570
- "total_flos": 6.315331179705677e+16,
571
  "train_batch_size": 128,
572
  "trial_name": null,
573
  "trial_params": null
 
1
  {
2
+ "best_global_step": 15500,
3
+ "best_metric": 0.9702864864864865,
4
+ "best_model_checkpoint": "/kaggle/working/arbert_submeter_training/checkpoints/checkpoint-15500",
5
+ "epoch": 2.680792181959699,
6
  "eval_steps": 500,
7
+ "global_step": 15500,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
548
  "eval_steps_per_second": 3.45,
549
  "eval_weighted_f1": 0.9643335590541979,
550
  "step": 15000
551
+ },
552
+ {
553
+ "epoch": 2.680792181959699,
554
+ "grad_norm": 2.286464214324951,
555
+ "learning_rate": 5.323994004381414e-06,
556
+ "loss": 0.0813,
557
+ "step": 15500
558
+ },
559
+ {
560
+ "epoch": 2.680792181959699,
561
+ "eval_accuracy": 0.9702864864864865,
562
+ "eval_loss": 0.1135055348277092,
563
+ "eval_macro_f1": 0.5963674935323597,
564
+ "eval_runtime": 419.7981,
565
+ "eval_samples_per_second": 881.376,
566
+ "eval_steps_per_second": 3.445,
567
+ "eval_weighted_f1": 0.9645615895626319,
568
+ "step": 15500
569
  }
570
  ],
571
  "logging_steps": 500,
 
585
  "attributes": {}
586
  }
587
  },
588
+ "total_flos": 6.525863491564877e+16,
589
  "train_batch_size": 128,
590
  "trial_name": null,
591
  "trial_params": null