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
2fa17c2
·
verified ·
1 Parent(s): f7ef50f

Training in progress, step 13500, 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:eecb05c11793262b9cad44b2b9e6cfb08060e09b004b99965dbbd3691972cf98
3
  size 651465828
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74e982a5afc6ad69ded3befd43cf7562bd83852a9d075a0fc62c703476f80bbe
3
  size 651465828
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b42fd14b60987346297b76d85788cfe3cddad143e0eb23b33cf407f22b5cff29
3
  size 1303053067
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4f364e33d30ad2dcdd57fd874bd60fe3dfb8278ec68b0c7b583f0834d0e187e
3
  size 1303053067
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:890f5efe6fe003338da9dc783a32cda0b9b6d764718442f48a74ac2256131dd2
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e80ad0469f215ea5337eb868c59a2aae2f00ac649fc01e5f2dea34d5b7538e7
3
  size 14645
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:12e40c044fc20b06edb62b2decf2bd7a9ba13eb66fc4f9a7e953a32ef0d2f361
3
  size 1383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb93e8820f4ee2418a74fd767141cfc6fe878cd5d24be88a47153cb135054556
3
  size 1383
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:63131499b42362f2fc14145e966c5f313815459678300dde6c5225806b312f8b
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74ecd875ea9852ca54027f00cadd1300f331bc6855eb0507146133323a9a38ff
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "best_global_step": 12500,
3
- "best_metric": 0.9692378378378378,
4
- "best_model_checkpoint": "/kaggle/working/arbert_submeter_training/checkpoints/checkpoint-12500",
5
- "epoch": 2.2483784484995244,
6
  "eval_steps": 500,
7
- "global_step": 13000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -476,6 +476,24 @@
476
  "eval_steps_per_second": 3.452,
477
  "eval_weighted_f1": 0.9634743085321129,
478
  "step": 13000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
479
  }
480
  ],
481
  "logging_steps": 500,
@@ -495,7 +513,7 @@
495
  "attributes": {}
496
  }
497
  },
498
- "total_flos": 5.473201932268877e+16,
499
  "train_batch_size": 128,
500
  "trial_name": null,
501
  "trial_params": null
 
1
  {
2
+ "best_global_step": 13500,
3
+ "best_metric": 0.9696405405405405,
4
+ "best_model_checkpoint": "/kaggle/working/arbert_submeter_training/checkpoints/checkpoint-13500",
5
+ "epoch": 2.3348611951915594,
6
  "eval_steps": 500,
7
+ "global_step": 13500,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
476
  "eval_steps_per_second": 3.452,
477
  "eval_weighted_f1": 0.9634743085321129,
478
  "step": 13000
479
+ },
480
+ {
481
+ "epoch": 2.3348611951915594,
482
+ "grad_norm": 2.883910655975342,
483
+ "learning_rate": 1.1089011875936815e-05,
484
+ "loss": 0.0835,
485
+ "step": 13500
486
+ },
487
+ {
488
+ "epoch": 2.3348611951915594,
489
+ "eval_accuracy": 0.9696405405405405,
490
+ "eval_loss": 0.11618903279304504,
491
+ "eval_macro_f1": 0.5970308633746413,
492
+ "eval_runtime": 418.887,
493
+ "eval_samples_per_second": 883.293,
494
+ "eval_steps_per_second": 3.452,
495
+ "eval_weighted_f1": 0.9638159327084403,
496
+ "step": 13500
497
  }
498
  ],
499
  "logging_steps": 500,
 
513
  "attributes": {}
514
  }
515
  },
516
+ "total_flos": 5.683734244128077e+16,
517
  "train_batch_size": 128,
518
  "trial_name": null,
519
  "trial_params": null