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
0a9986b
·
verified ·
1 Parent(s): 35048e9

Training in progress, step 17000, 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 sha256:7d433179785838dfc4b23eb0dacfb59e4e4f4c51da5360354ca8fbb95b3108c0
3
  size 651465828
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a50330db4c30408b0d667e66275ea8ddd76919ff801ccbdb36b76b7033c822f
3
  size 651465828
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ebdcb1c91825f260b51a8914eabbc2a036534b7b269f83ec61be38764a1b1545
3
  size 1303053067
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0377cb9439a2c4fa7ab3da1e65f4a9334577b67e8348530a9aa4ac53b34ccc3c
3
  size 1303053067
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b9804c67883689ef3b7b7fa0419bc7f88f097913b2e306b9aac9ec7dd98183f
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61e291d680fcef9565923cfdb6bcc681c7ae1e2a5dfdcf83d690c053218bbf75
3
  size 14645
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d161e1a1c9710b775cdfd4d3f7418d2f5d0704984b12753a82383fc09cd4a45a
3
  size 1383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c792eca26ddd2cafb935aabba9dbf816b7c25feaa4b191867652327a92bef5c
3
  size 1383
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8008cf85ed9b6d28ee7bd11771668b0a8beeac520bec0ee5a418b3cd82dfcab7
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9949b8e01fb3dfd15b9a46fe77b60d978d1d99cd0b006a7fd2c8fa82e3677a82
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "best_global_step": 16500,
3
- "best_metric": 0.9707135135135135,
4
- "best_model_checkpoint": "/kaggle/working/arbert_submeter_training/checkpoints/checkpoint-16500",
5
- "epoch": 2.853757675343769,
6
  "eval_steps": 500,
7
- "global_step": 16500,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -602,6 +602,24 @@
602
  "eval_steps_per_second": 3.452,
603
  "eval_weighted_f1": 0.9653056586898462,
604
  "step": 16500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
605
  }
606
  ],
607
  "logging_steps": 500,
@@ -621,7 +639,7 @@
621
  "attributes": {}
622
  }
623
  },
624
- "total_flos": 6.946928115283277e+16,
625
  "train_batch_size": 128,
626
  "trial_name": null,
627
  "trial_params": null
 
1
  {
2
+ "best_global_step": 17000,
3
+ "best_metric": 0.9708837837837838,
4
+ "best_model_checkpoint": "/kaggle/working/arbert_submeter_training/checkpoints/checkpoint-17000",
5
+ "epoch": 2.940240422035804,
6
  "eval_steps": 500,
7
+ "global_step": 17000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
602
  "eval_steps_per_second": 3.452,
603
  "eval_weighted_f1": 0.9653056586898462,
604
  "step": 16500
605
+ },
606
+ {
607
+ "epoch": 2.940240422035804,
608
+ "grad_norm": 0.9345380663871765,
609
+ "learning_rate": 1.0002306007148624e-06,
610
+ "loss": 0.0789,
611
+ "step": 17000
612
+ },
613
+ {
614
+ "epoch": 2.940240422035804,
615
+ "eval_accuracy": 0.9708837837837838,
616
+ "eval_loss": 0.11126039922237396,
617
+ "eval_macro_f1": 0.6020869942813024,
618
+ "eval_runtime": 419.4331,
619
+ "eval_samples_per_second": 882.143,
620
+ "eval_steps_per_second": 3.448,
621
+ "eval_weighted_f1": 0.9654166847298334,
622
+ "step": 17000
623
  }
624
  ],
625
  "logging_steps": 500,
 
639
  "attributes": {}
640
  }
641
  },
642
+ "total_flos": 7.157460427142477e+16,
643
  "train_batch_size": 128,
644
  "trial_name": null,
645
  "trial_params": null