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
7e03419
·
verified ·
1 Parent(s): 1feed08

Training in progress, step 16500, 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:e0ecd62204569d79b09e58105340e64b7bc34255684fa5187dd844dce6e454c1
3
  size 651465828
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d433179785838dfc4b23eb0dacfb59e4e4f4c51da5360354ca8fbb95b3108c0
3
  size 651465828
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f79d559bb59e72fad60bde06df83ffb275437a9f7f1b4e96977d07d0e615fd66
3
  size 1303053067
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebdcb1c91825f260b51a8914eabbc2a036534b7b269f83ec61be38764a1b1545
3
  size 1303053067
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0d96156245456b50da3b75e8b094a79c608e780e3881f20380edf8c41926e0af
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b9804c67883689ef3b7b7fa0419bc7f88f097913b2e306b9aac9ec7dd98183f
3
  size 14645
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d9e8f14715c120c1b82640d08ff4b50ac8ef3a482a39de36f9dee0ad364309a0
3
  size 1383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d161e1a1c9710b775cdfd4d3f7418d2f5d0704984b12753a82383fc09cd4a45a
3
  size 1383
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eb8497247ad84cd963d5cf0126b75c1225ed04894043681e3db4ee9b322f14c1
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8008cf85ed9b6d28ee7bd11771668b0a8beeac520bec0ee5a418b3cd82dfcab7
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "best_global_step": 16000,
3
- "best_metric": 0.9706054054054054,
4
- "best_model_checkpoint": "/kaggle/working/arbert_submeter_training/checkpoints/checkpoint-16000",
5
- "epoch": 2.7672749286517337,
6
  "eval_steps": 500,
7
- "global_step": 16000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -584,6 +584,24 @@
584
  "eval_steps_per_second": 3.446,
585
  "eval_weighted_f1": 0.9649497278700637,
586
  "step": 16000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
587
  }
588
  ],
589
  "logging_steps": 500,
@@ -603,7 +621,7 @@
603
  "attributes": {}
604
  }
605
  },
606
- "total_flos": 6.736395803424077e+16,
607
  "train_batch_size": 128,
608
  "trial_name": null,
609
  "trial_params": null
 
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,
 
584
  "eval_steps_per_second": 3.446,
585
  "eval_weighted_f1": 0.9649497278700637,
586
  "step": 16000
587
+ },
588
+ {
589
+ "epoch": 2.853757675343769,
590
+ "grad_norm": 1.0509530305862427,
591
+ "learning_rate": 2.441485068603713e-06,
592
+ "loss": 0.0786,
593
+ "step": 16500
594
+ },
595
+ {
596
+ "epoch": 2.853757675343769,
597
+ "eval_accuracy": 0.9707135135135135,
598
+ "eval_loss": 0.11158089339733124,
599
+ "eval_macro_f1": 0.6009545374695694,
600
+ "eval_runtime": 418.9418,
601
+ "eval_samples_per_second": 883.178,
602
+ "eval_steps_per_second": 3.452,
603
+ "eval_weighted_f1": 0.9653056586898462,
604
+ "step": 16500
605
  }
606
  ],
607
  "logging_steps": 500,
 
621
  "attributes": {}
622
  }
623
  },
624
+ "total_flos": 6.946928115283277e+16,
625
  "train_batch_size": 128,
626
  "trial_name": null,
627
  "trial_params": null