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
a85822f
·
verified ·
1 Parent(s): f8a18be

Training in progress, step 14000, 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 +21 -3
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:74e982a5afc6ad69ded3befd43cf7562bd83852a9d075a0fc62c703476f80bbe
3
  size 651465828
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9183095513c09e7caf88b2691d0e0099681c70636a95c09d4a5d7cd2778edc7a
3
  size 651465828
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f4f364e33d30ad2dcdd57fd874bd60fe3dfb8278ec68b0c7b583f0834d0e187e
3
  size 1303053067
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6aa7dea0462ca59f960c2d83fb6a59715b2fd51cd440f52bd26e2595f8010870
3
  size 1303053067
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e80ad0469f215ea5337eb868c59a2aae2f00ac649fc01e5f2dea34d5b7538e7
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae17e5a80bec2df456d8c3e6817d0fa1e463ac5cadef8358a703dbcf135df0a8
3
  size 14645
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fb93e8820f4ee2418a74fd767141cfc6fe878cd5d24be88a47153cb135054556
3
  size 1383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23c844bc341ec75b5cad5ad0be21d7c0eeee0623194498c334d6946af672123e
3
  size 1383
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:74ecd875ea9852ca54027f00cadd1300f331bc6855eb0507146133323a9a38ff
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4125dc0cbe081a7ce5c5ed6d876fd0fd32566582d40b6c2f790fd54edbc901b3
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -2,9 +2,9 @@
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,
@@ -494,6 +494,24 @@
494
  "eval_steps_per_second": 3.452,
495
  "eval_weighted_f1": 0.9638159327084403,
496
  "step": 13500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
497
  }
498
  ],
499
  "logging_steps": 500,
@@ -513,7 +531,7 @@
513
  "attributes": {}
514
  }
515
  },
516
- "total_flos": 5.683734244128077e+16,
517
  "train_batch_size": 128,
518
  "trial_name": null,
519
  "trial_params": null
 
2
  "best_global_step": 13500,
3
  "best_metric": 0.9696405405405405,
4
  "best_model_checkpoint": "/kaggle/working/arbert_submeter_training/checkpoints/checkpoint-13500",
5
+ "epoch": 2.421343941883594,
6
  "eval_steps": 500,
7
+ "global_step": 14000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
494
  "eval_steps_per_second": 3.452,
495
  "eval_weighted_f1": 0.9638159327084403,
496
  "step": 13500
497
+ },
498
+ {
499
+ "epoch": 2.421343941883594,
500
+ "grad_norm": 0.7860650420188904,
501
+ "learning_rate": 9.647757408047965e-06,
502
+ "loss": 0.0854,
503
+ "step": 14000
504
+ },
505
+ {
506
+ "epoch": 2.421343941883594,
507
+ "eval_accuracy": 0.9694459459459459,
508
+ "eval_loss": 0.1158711388707161,
509
+ "eval_macro_f1": 0.592536606494846,
510
+ "eval_runtime": 419.3296,
511
+ "eval_samples_per_second": 882.361,
512
+ "eval_steps_per_second": 3.448,
513
+ "eval_weighted_f1": 0.9638996969783739,
514
+ "step": 14000
515
  }
516
  ],
517
  "logging_steps": 500,
 
531
  "attributes": {}
532
  }
533
  },
534
+ "total_flos": 5.894266555987277e+16,
535
  "train_batch_size": 128,
536
  "trial_name": null,
537
  "trial_params": null