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
d101707
·
verified ·
1 Parent(s): 43bc8b7

Training in progress, step 15000, 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 sha256:0c72ee8409ec885a543e3bed573bad94dc29a61bd88c2517b82203d51751b870
3
  size 651465828
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:651e61b153b3149ac3ce33e0b97e23286c0e65e20692fed53116376210dd5643
3
  size 651465828
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e23e81689734717df9d16c9b0411afa23f841438bbe2ce605c4f6dc1fbf3406
3
  size 1303053067
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27eb5818412e7e7894f3b462191e554716ea91c7b47f4f1e6535412a46d70fca
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:a34c4d8dac7e78ad518019a9e11aabf33a43371c666e9ab103ffa83fac85d2cc
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60d4026715a17089972b4da95d68c0225e81b22cd1f40015bcd89ebaf1c3e7e3
3
  size 14645
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:99d64c09115fa692aa58836dc85da0fb5a3140a6dc206691a319d8c97325517a
3
  size 1383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0415cc902581048eff49426d3b5977e3d3a9842950529c62d3aba0c1eceb6cc
3
  size 1383
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f1eeda66520cb16f999c65f76e144d75cf7de088e4557dd2d28794ee9c8eb5e3
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8433be9bc1fc438fbebc88878b9cb26c559fbfad46d0cd7ce1cc34e345d21d7
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "best_global_step": 14500,
3
- "best_metric": 0.9697621621621622,
4
- "best_model_checkpoint": "/kaggle/working/arbert_submeter_training/checkpoints/checkpoint-14500",
5
- "epoch": 2.507826688575629,
6
  "eval_steps": 500,
7
- "global_step": 14500,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -530,6 +530,24 @@
530
  "eval_steps_per_second": 3.437,
531
  "eval_weighted_f1": 0.964013311849684,
532
  "step": 14500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
533
  }
534
  ],
535
  "logging_steps": 500,
@@ -549,7 +567,7 @@
549
  "attributes": {}
550
  }
551
  },
552
- "total_flos": 6.104798867846477e+16,
553
  "train_batch_size": 128,
554
  "trial_name": null,
555
  "trial_params": null
 
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,
 
530
  "eval_steps_per_second": 3.437,
531
  "eval_weighted_f1": 0.964013311849684,
532
  "step": 14500
533
+ },
534
+ {
535
+ "epoch": 2.594309435267664,
536
+ "grad_norm": 4.085644245147705,
537
+ "learning_rate": 6.765248472270265e-06,
538
+ "loss": 0.0819,
539
+ "step": 15000
540
+ },
541
+ {
542
+ "epoch": 2.594309435267664,
543
+ "eval_accuracy": 0.9698027027027027,
544
+ "eval_loss": 0.1152041032910347,
545
+ "eval_macro_f1": 0.6003991642644262,
546
+ "eval_runtime": 419.1122,
547
+ "eval_samples_per_second": 882.818,
548
+ "eval_steps_per_second": 3.45,
549
+ "eval_weighted_f1": 0.9643335590541979,
550
+ "step": 15000
551
  }
552
  ],
553
  "logging_steps": 500,
 
567
  "attributes": {}
568
  }
569
  },
570
+ "total_flos": 6.315331179705677e+16,
571
  "train_batch_size": 128,
572
  "trial_name": null,
573
  "trial_params": null