Hugging Face's logo

jco1
/
results_bert_full

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Model card Files
xet
Metrics Community
jco1 commited on
Commit
6996bd8
·
verified ·
1 Parent(s): b4e1888

jco1/causality_bert_v2

Browse files
Files changed (7) hide show
  1. README.md +23 -19
  2. config.json +1 -1
  3. model.safetensors +1 -1
  4. runs/Feb17_15-34-28_1daf70cbb8e0/events.out.tfevents.1739806471.1daf70cbb8e0.4204.0 +3 -0
  5. runs/Feb17_15-39-09_1daf70cbb8e0/events.out.tfevents.1739806750.1daf70cbb8e0.8469.0 +3 -0
  6. runs/Feb17_15-44-06_1daf70cbb8e0/events.out.tfevents.1739807046.1daf70cbb8e0.8469.1 +3 -0
  7. training_args.bin +2 -2
README.md CHANGED
@@ -7,6 +7,8 @@ tags:
7
  metrics:
8
  - accuracy
9
  - f1
 
 
10
  model-index:
11
  - name: results_bert_full
12
  results: []
@@ -19,9 +21,11 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.4327
23
- - Accuracy: 0.8533
24
- - F1: 0.8517
 
 
25
 
26
  ## Model description
27
 
@@ -44,29 +48,29 @@ The following hyperparameters were used during training:
44
  - train_batch_size: 8
45
  - eval_batch_size: 8
46
  - seed: 42
47
- - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
  - lr_scheduler_type: linear
49
  - num_epochs: 10
50
 
51
  ### Training results
52
 
53
- | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
54
- |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
55
- | No log | 1.0 | 450 | 0.4571 | 0.8367 | 0.7623 |
56
- | 0.4531 | 2.0 | 900 | 0.4590 | 0.8367 | 0.7623 |
57
- | 0.4643 | 3.0 | 1350 | 0.4480 | 0.8367 | 0.7623 |
58
- | 0.4537 | 4.0 | 1800 | 0.4498 | 0.8367 | 0.7623 |
59
- | 0.4508 | 5.0 | 2250 | 0.4466 | 0.8367 | 0.7623 |
60
- | 0.4531 | 6.0 | 2700 | 0.4467 | 0.8367 | 0.7623 |
61
- | 0.4553 | 7.0 | 3150 | 0.4498 | 0.8367 | 0.7623 |
62
- | 0.4388 | 8.0 | 3600 | 0.4473 | 0.8367 | 0.7623 |
63
- | 0.3981 | 9.0 | 4050 | 0.3563 | 0.8722 | 0.8472 |
64
- | 0.2981 | 10.0 | 4500 | 0.4327 | 0.8533 | 0.8517 |
65
 
66
 
67
  ### Framework versions
68
 
69
- - Transformers 4.47.1
70
- - Pytorch 2.5.1+cu121
71
- - Datasets 3.2.0
72
  - Tokenizers 0.21.0
 
7
  metrics:
8
  - accuracy
9
  - f1
10
+ - recall
11
+ - precision
12
  model-index:
13
  - name: results_bert_full
14
  results: []
 
21
 
22
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
23
  It achieves the following results on the evaluation set:
24
+ - Loss: 0.9742
25
+ - Accuracy: 0.878
26
+ - F1: 0.8729
27
+ - Recall: 0.878
28
+ - Precision: 0.8709
29
 
30
  ## Model description
31
 
 
48
  - train_batch_size: 8
49
  - eval_batch_size: 8
50
  - seed: 42
51
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
52
  - lr_scheduler_type: linear
53
  - num_epochs: 10
54
 
55
  ### Training results
56
 
57
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Recall | Precision |
58
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:---------:|
59
+ | 0.3524 | 1.0 | 500 | 0.6161 | 0.867 | 0.8508 | 0.867 | 0.8553 |
60
+ | 0.2878 | 2.0 | 1000 | 0.5404 | 0.882 | 0.8706 | 0.882 | 0.8739 |
61
+ | 0.1682 | 3.0 | 1500 | 0.7048 | 0.879 | 0.8684 | 0.879 | 0.8699 |
62
+ | 0.1006 | 4.0 | 2000 | 0.7590 | 0.877 | 0.8610 | 0.877 | 0.8698 |
63
+ | 0.0421 | 5.0 | 2500 | 0.7716 | 0.878 | 0.8742 | 0.878 | 0.8722 |
64
+ | 0.0205 | 6.0 | 3000 | 0.8432 | 0.887 | 0.8804 | 0.887 | 0.8798 |
65
+ | 0.0294 | 7.0 | 3500 | 0.8998 | 0.884 | 0.8661 | 0.884 | 0.8837 |
66
+ | 0.0099 | 8.0 | 4000 | 0.9366 | 0.882 | 0.8746 | 0.882 | 0.8739 |
67
+ | 0.0046 | 9.0 | 4500 | 0.9346 | 0.882 | 0.8789 | 0.882 | 0.8771 |
68
+ | 0.0028 | 10.0 | 5000 | 0.9742 | 0.878 | 0.8729 | 0.878 | 0.8709 |
69
 
70
 
71
  ### Framework versions
72
 
73
+ - Transformers 4.48.3
74
+ - Pytorch 2.5.1+cu124
75
+ - Datasets 3.3.1
76
  - Tokenizers 0.21.0
config.json CHANGED
@@ -20,7 +20,7 @@
20
  "position_embedding_type": "absolute",
21
  "problem_type": "single_label_classification",
22
  "torch_dtype": "float32",
23
- "transformers_version": "4.47.1",
24
  "type_vocab_size": 2,
25
  "use_cache": true,
26
  "vocab_size": 30522
 
20
  "position_embedding_type": "absolute",
21
  "problem_type": "single_label_classification",
22
  "torch_dtype": "float32",
23
+ "transformers_version": "4.48.3",
24
  "type_vocab_size": 2,
25
  "use_cache": true,
26
  "vocab_size": 30522
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:50b3c5b94a60f7c98a59fc61b820d234992a4b9c9c9e08a56d949190ba00b5f8
3
  size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f8b287c392cf15dacba35b41d80a25d10397759257ab730afe403d32b288dc6
3
  size 437958648
runs/Feb17_15-34-28_1daf70cbb8e0/events.out.tfevents.1739806471.1daf70cbb8e0.4204.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d714f8dccd1c565d70da957ea7f7986d3808e97a08ec47bbdd6b804021d7e17
3
+ size 5060
runs/Feb17_15-39-09_1daf70cbb8e0/events.out.tfevents.1739806750.1daf70cbb8e0.8469.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bb8b04ea973b9b2ee0dbbc16c732c4708ab5be53a3f809aa5cd62b492144a01
3
+ size 5258
runs/Feb17_15-44-06_1daf70cbb8e0/events.out.tfevents.1739807046.1daf70cbb8e0.8469.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80f30e28d7e3e4bfd302b232d0d16e797c084f14eb0793c3ddbee69f56ab10e6
3
+ size 12280
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:acfb2302e2e100bf2f7c16b5a2c813c5404129f4f937e540ebe7ad5639f4b712
3
- size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afe9d02667adefaee2cd1173ca24b23311e3adb738b7e361a9019b9df7059528
3
+ size 5304