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
f380617
·
verified ·
1 Parent(s): ab4d0ee

Training in progress, step 16000, 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 sha256:0b5480293c959a944ef14ff41730b84cfa1d035f101bfa6f16d1d97b1c6c7384
3
  size 651465828
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0ecd62204569d79b09e58105340e64b7bc34255684fa5187dd844dce6e454c1
3
  size 651465828
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c5b3350ed3616186e905b185da2ced89195db507e9bf28662e8548e36429f6a
3
  size 1303053067
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f79d559bb59e72fad60bde06df83ffb275437a9f7f1b4e96977d07d0e615fd66
3
  size 1303053067
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2f6226d983bd11e1009778d42860849834c34de435a756e95c206ed5451e0678
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d96156245456b50da3b75e8b094a79c608e780e3881f20380edf8c41926e0af
3
  size 14645
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a1d086c48bf9ef55507053335c22a801a05683add7c8955ea07815dfc8cac267
3
  size 1383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9e8f14715c120c1b82640d08ff4b50ac8ef3a482a39de36f9dee0ad364309a0
3
  size 1383
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b7e2fc05c77d58e87b922e2178b0c5e30e234cd120c1e72dfacc3051ef58e18
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb8497247ad84cd963d5cf0126b75c1225ed04894043681e3db4ee9b322f14c1
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "best_global_step": 15500,
3
- "best_metric": 0.9702864864864865,
4
- "best_model_checkpoint": "/kaggle/working/arbert_submeter_training/checkpoints/checkpoint-15500",
5
- "epoch": 2.680792181959699,
6
  "eval_steps": 500,
7
- "global_step": 15500,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -566,6 +566,24 @@
566
  "eval_steps_per_second": 3.445,
567
  "eval_weighted_f1": 0.9645615895626319,
568
  "step": 15500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
569
  }
570
  ],
571
  "logging_steps": 500,
@@ -585,7 +603,7 @@
585
  "attributes": {}
586
  }
587
  },
588
- "total_flos": 6.525863491564877e+16,
589
  "train_batch_size": 128,
590
  "trial_name": null,
591
  "trial_params": null
 
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,
 
566
  "eval_steps_per_second": 3.445,
567
  "eval_weighted_f1": 0.9645615895626319,
568
  "step": 15500
569
+ },
570
+ {
571
+ "epoch": 2.7672749286517337,
572
+ "grad_norm": 2.7449326515197754,
573
+ "learning_rate": 3.882739536492564e-06,
574
+ "loss": 0.0792,
575
+ "step": 16000
576
+ },
577
+ {
578
+ "epoch": 2.7672749286517337,
579
+ "eval_accuracy": 0.9706054054054054,
580
+ "eval_loss": 0.1119714081287384,
581
+ "eval_macro_f1": 0.6000477857320852,
582
+ "eval_runtime": 419.5757,
583
+ "eval_samples_per_second": 881.843,
584
+ "eval_steps_per_second": 3.446,
585
+ "eval_weighted_f1": 0.9649497278700637,
586
+ "step": 16000
587
  }
588
  ],
589
  "logging_steps": 500,
 
603
  "attributes": {}
604
  }
605
  },
606
+ "total_flos": 6.736395803424077e+16,
607
  "train_batch_size": 128,
608
  "trial_name": null,
609
  "trial_params": null