Commit
•
3f21a40
1
Parent(s):
b48b8c0
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
metrics:
|
| 5 |
+
- precision
|
| 6 |
+
- recall
|
| 7 |
+
- f1
|
| 8 |
+
- accuracy
|
| 9 |
+
model-index:
|
| 10 |
+
- name: tabert-4k-naamapadam
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# tabert-4k-naamapadam
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [livinNector/tabert-4k](https://huggingface.co/livinNector/tabert-4k) on the None dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.2805
|
| 22 |
+
- Precision: 0.7758
|
| 23 |
+
- Recall: 0.8034
|
| 24 |
+
- F1: 0.7894
|
| 25 |
+
- Accuracy: 0.9077
|
| 26 |
+
|
| 27 |
+
## Model description
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Intended uses & limitations
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training and evaluation data
|
| 36 |
+
|
| 37 |
+
More information needed
|
| 38 |
+
|
| 39 |
+
## Training procedure
|
| 40 |
+
|
| 41 |
+
### Training hyperparameters
|
| 42 |
+
|
| 43 |
+
The following hyperparameters were used during training:
|
| 44 |
+
- learning_rate: 5e-05
|
| 45 |
+
- train_batch_size: 64
|
| 46 |
+
- eval_batch_size: 128
|
| 47 |
+
- seed: 42
|
| 48 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 49 |
+
- lr_scheduler_type: linear
|
| 50 |
+
- num_epochs: 2
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
| 55 |
+
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
| 56 |
+
| 0.4467 | 0.05 | 400 | 0.3882 | 0.7144 | 0.6655 | 0.6891 | 0.8755 |
|
| 57 |
+
| 0.3775 | 0.1 | 800 | 0.3540 | 0.7122 | 0.7155 | 0.7138 | 0.8845 |
|
| 58 |
+
| 0.3571 | 0.15 | 1200 | 0.3432 | 0.7329 | 0.7266 | 0.7297 | 0.8872 |
|
| 59 |
+
| 0.3461 | 0.21 | 1600 | 0.3360 | 0.7252 | 0.7368 | 0.7309 | 0.8893 |
|
| 60 |
+
| 0.3456 | 0.26 | 2000 | 0.3359 | 0.7388 | 0.7470 | 0.7428 | 0.8896 |
|
| 61 |
+
| 0.3318 | 0.31 | 2400 | 0.3298 | 0.7460 | 0.7435 | 0.7447 | 0.8908 |
|
| 62 |
+
| 0.326 | 0.36 | 2800 | 0.3255 | 0.7490 | 0.7391 | 0.7440 | 0.8940 |
|
| 63 |
+
| 0.3264 | 0.41 | 3200 | 0.3243 | 0.7493 | 0.7605 | 0.7549 | 0.8953 |
|
| 64 |
+
| 0.3189 | 0.46 | 3600 | 0.3231 | 0.7305 | 0.7715 | 0.7504 | 0.8936 |
|
| 65 |
+
| 0.3119 | 0.51 | 4000 | 0.3125 | 0.7645 | 0.7525 | 0.7584 | 0.8985 |
|
| 66 |
+
| 0.3111 | 0.57 | 4400 | 0.3100 | 0.7479 | 0.7729 | 0.7602 | 0.8970 |
|
| 67 |
+
| 0.3088 | 0.62 | 4800 | 0.3148 | 0.7510 | 0.7749 | 0.7628 | 0.8966 |
|
| 68 |
+
| 0.3047 | 0.67 | 5200 | 0.3089 | 0.7581 | 0.7728 | 0.7654 | 0.8981 |
|
| 69 |
+
| 0.3054 | 0.72 | 5600 | 0.3073 | 0.7615 | 0.7709 | 0.7662 | 0.8990 |
|
| 70 |
+
| 0.3028 | 0.77 | 6000 | 0.3066 | 0.7466 | 0.7835 | 0.7646 | 0.8984 |
|
| 71 |
+
| 0.3007 | 0.82 | 6400 | 0.3035 | 0.7555 | 0.7791 | 0.7671 | 0.8995 |
|
| 72 |
+
| 0.2923 | 0.87 | 6800 | 0.3004 | 0.7647 | 0.7829 | 0.7737 | 0.9008 |
|
| 73 |
+
| 0.2927 | 0.93 | 7200 | 0.3050 | 0.7700 | 0.7646 | 0.7673 | 0.9002 |
|
| 74 |
+
| 0.2949 | 0.98 | 7600 | 0.2979 | 0.7686 | 0.7723 | 0.7704 | 0.9014 |
|
| 75 |
+
| 0.2758 | 1.03 | 8000 | 0.3013 | 0.7713 | 0.7783 | 0.7748 | 0.9030 |
|
| 76 |
+
| 0.2699 | 1.08 | 8400 | 0.3019 | 0.7503 | 0.7997 | 0.7742 | 0.9017 |
|
| 77 |
+
| 0.2688 | 1.13 | 8800 | 0.3002 | 0.7593 | 0.7940 | 0.7762 | 0.9017 |
|
| 78 |
+
| 0.2625 | 1.18 | 9200 | 0.2926 | 0.7590 | 0.7941 | 0.7762 | 0.9033 |
|
| 79 |
+
| 0.2671 | 1.23 | 9600 | 0.2922 | 0.7640 | 0.8019 | 0.7825 | 0.9043 |
|
| 80 |
+
| 0.267 | 1.29 | 10000 | 0.2895 | 0.7719 | 0.7877 | 0.7797 | 0.9044 |
|
| 81 |
+
| 0.2611 | 1.34 | 10400 | 0.2897 | 0.7704 | 0.7978 | 0.7839 | 0.9053 |
|
| 82 |
+
| 0.2666 | 1.39 | 10800 | 0.2896 | 0.7688 | 0.7887 | 0.7786 | 0.9042 |
|
| 83 |
+
| 0.2563 | 1.44 | 11200 | 0.2894 | 0.7672 | 0.7981 | 0.7823 | 0.9045 |
|
| 84 |
+
| 0.2598 | 1.49 | 11600 | 0.2841 | 0.7705 | 0.7960 | 0.7831 | 0.9058 |
|
| 85 |
+
| 0.2549 | 1.54 | 12000 | 0.2854 | 0.7695 | 0.7975 | 0.7832 | 0.9065 |
|
| 86 |
+
| 0.2558 | 1.59 | 12400 | 0.2873 | 0.7619 | 0.8108 | 0.7856 | 0.9045 |
|
| 87 |
+
| 0.2564 | 1.65 | 12800 | 0.2863 | 0.7757 | 0.7897 | 0.7826 | 0.9062 |
|
| 88 |
+
| 0.2618 | 1.7 | 13200 | 0.2860 | 0.7778 | 0.7899 | 0.7838 | 0.9066 |
|
| 89 |
+
| 0.2659 | 1.75 | 13600 | 0.2831 | 0.7748 | 0.8013 | 0.7879 | 0.9073 |
|
| 90 |
+
| 0.254 | 1.8 | 14000 | 0.2811 | 0.7761 | 0.7978 | 0.7868 | 0.9079 |
|
| 91 |
+
| 0.2628 | 1.85 | 14400 | 0.2807 | 0.7713 | 0.8028 | 0.7868 | 0.9069 |
|
| 92 |
+
| 0.2552 | 1.9 | 14800 | 0.2806 | 0.7756 | 0.7990 | 0.7872 | 0.9077 |
|
| 93 |
+
| 0.2568 | 1.95 | 15200 | 0.2805 | 0.7758 | 0.8034 | 0.7894 | 0.9077 |
|
| 94 |
+
|
| 95 |
+
|
| 96 |
+
### Framework versions
|
| 97 |
+
|
| 98 |
+
- Transformers 4.29.2
|
| 99 |
+
- Pytorch 2.0.0
|
| 100 |
+
- Datasets 2.12.0
|
| 101 |
+
- Tokenizers 0.13.3
|