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
afd9a24
·
verified ·
1 Parent(s): cf827d1

Training in progress, step 12000, 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 sha256:900d2d30d885969255af7871e504937a3fdf43367bf4c8fb400a078803308015
3
  size 651465828
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1480d9f4a630f6362b6c9b9468cf771d2a85b6a789312d734a4392acf6401523
3
  size 651465828
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d95a7a63237d7406f7439f9538d7cc49d27d150f93d5f55e8c596ffbda73c8fd
3
  size 1303053067
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2281b994c226e57b66b8d419588cdcb42cbd3535018df591d44d76344dea3b7
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:f38e426d00f289ba3da271df8237ec0033c45bbcd3372361acf01221c52a67e1
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3e8edef986f4bbf76f2de5f38080bedbaeda32f953eac6bedda8cf73cae1fd6
3
  size 14645
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:103f922acd71a775c101e48b559b3373155a7a0c1f836849133cbaf72bb3b718
3
  size 1383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae029a8e6af9f014c9ef8b713fcd28cef1f184648ddde977ce75efc89ca9a242
3
  size 1383
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4fe67c4e3d00e74e6424528563a7ae51e4f6d9a51c8fdf7ce02cb1280db7a7e8
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d447d717c68fd522f6372d2b3ebbc9666da3ac61bf609597ba0f72b0cdaf7a6
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "best_global_step": 11000,
3
- "best_metric": 0.9684972972972973,
4
- "best_model_checkpoint": "/kaggle/working/arbert_submeter_training/checkpoints/checkpoint-11000",
5
- "epoch": 1.9890166911701117,
6
  "eval_steps": 500,
7
- "global_step": 11500,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -422,6 +422,24 @@
422
  "eval_steps_per_second": 3.448,
423
  "eval_weighted_f1": 0.9623140045622489,
424
  "step": 11500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
425
  }
426
  ],
427
  "logging_steps": 500,
@@ -441,7 +459,7 @@
441
  "attributes": {}
442
  }
443
  },
444
- "total_flos": 4.841924084726438e+16,
445
  "train_batch_size": 128,
446
  "trial_name": null,
447
  "trial_params": null
 
1
  {
2
+ "best_global_step": 12000,
3
+ "best_metric": 0.9689324324324324,
4
+ "best_model_checkpoint": "/kaggle/working/arbert_submeter_training/checkpoints/checkpoint-12000",
5
+ "epoch": 2.0754129551154543,
6
  "eval_steps": 500,
7
+ "global_step": 12000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
422
  "eval_steps_per_second": 3.448,
423
  "eval_weighted_f1": 0.9623140045622489,
424
  "step": 11500
425
+ },
426
+ {
427
+ "epoch": 2.0754129551154543,
428
+ "grad_norm": 3.1163055896759033,
429
+ "learning_rate": 1.5412775279603368e-05,
430
+ "loss": 0.0899,
431
+ "step": 12000
432
+ },
433
+ {
434
+ "epoch": 2.0754129551154543,
435
+ "eval_accuracy": 0.9689324324324324,
436
+ "eval_loss": 0.11741844564676285,
437
+ "eval_macro_f1": 0.5972224837605217,
438
+ "eval_runtime": 419.245,
439
+ "eval_samples_per_second": 882.539,
440
+ "eval_steps_per_second": 3.449,
441
+ "eval_weighted_f1": 0.9632448268921581,
442
+ "step": 12000
443
  }
444
  ],
445
  "logging_steps": 500,
 
459
  "attributes": {}
460
  }
461
  },
462
+ "total_flos": 5.052137308550477e+16,
463
  "train_batch_size": 128,
464
  "trial_name": null,
465
  "trial_params": null