AnanthZeke
commited on
Commit
•
6e213b4
1
Parent(s):
b3e5fbf
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-500-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-500-naamapadam
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [livinNector/tabert-500](https://huggingface.co/livinNector/tabert-500) on the None dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.2821
|
22 |
+
- Precision: 0.7818
|
23 |
+
- Recall: 0.8089
|
24 |
+
- F1: 0.7951
|
25 |
+
- Accuracy: 0.9070
|
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 |
+
| 0.4684 | 0.05 | 400 | 0.3956 | 0.6972 | 0.6926 | 0.6949 | 0.8720 |
|
57 |
+
| 0.3901 | 0.1 | 800 | 0.3706 | 0.7099 | 0.7338 | 0.7216 | 0.8811 |
|
58 |
+
| 0.3658 | 0.15 | 1200 | 0.3551 | 0.7349 | 0.7388 | 0.7369 | 0.8854 |
|
59 |
+
| 0.3535 | 0.21 | 1600 | 0.3445 | 0.7333 | 0.7458 | 0.7395 | 0.8875 |
|
60 |
+
| 0.3512 | 0.26 | 2000 | 0.3353 | 0.7547 | 0.7408 | 0.7477 | 0.8917 |
|
61 |
+
| 0.3377 | 0.31 | 2400 | 0.3302 | 0.7417 | 0.7636 | 0.7525 | 0.8916 |
|
62 |
+
| 0.3297 | 0.36 | 2800 | 0.3279 | 0.7681 | 0.7330 | 0.7501 | 0.8931 |
|
63 |
+
| 0.3331 | 0.41 | 3200 | 0.3252 | 0.7448 | 0.7833 | 0.7636 | 0.8961 |
|
64 |
+
| 0.3247 | 0.46 | 3600 | 0.3210 | 0.7479 | 0.7847 | 0.7659 | 0.8960 |
|
65 |
+
| 0.3175 | 0.51 | 4000 | 0.3155 | 0.7684 | 0.7597 | 0.7640 | 0.8975 |
|
66 |
+
| 0.3142 | 0.57 | 4400 | 0.3113 | 0.7510 | 0.7833 | 0.7668 | 0.8977 |
|
67 |
+
| 0.315 | 0.62 | 4800 | 0.3131 | 0.7574 | 0.7830 | 0.7700 | 0.8969 |
|
68 |
+
| 0.3078 | 0.67 | 5200 | 0.3155 | 0.7569 | 0.7821 | 0.7693 | 0.8980 |
|
69 |
+
| 0.3101 | 0.72 | 5600 | 0.3117 | 0.7708 | 0.7730 | 0.7719 | 0.8990 |
|
70 |
+
| 0.3078 | 0.77 | 6000 | 0.3070 | 0.7665 | 0.7824 | 0.7744 | 0.8992 |
|
71 |
+
| 0.304 | 0.82 | 6400 | 0.3055 | 0.7680 | 0.7875 | 0.7776 | 0.8992 |
|
72 |
+
| 0.2954 | 0.87 | 6800 | 0.3019 | 0.7675 | 0.7929 | 0.7800 | 0.9002 |
|
73 |
+
| 0.2955 | 0.93 | 7200 | 0.3107 | 0.7804 | 0.7755 | 0.7779 | 0.9000 |
|
74 |
+
| 0.2979 | 0.98 | 7600 | 0.2992 | 0.7721 | 0.7931 | 0.7825 | 0.9021 |
|
75 |
+
| 0.2816 | 1.03 | 8000 | 0.3022 | 0.7695 | 0.7971 | 0.7831 | 0.9029 |
|
76 |
+
| 0.2768 | 1.08 | 8400 | 0.3043 | 0.7538 | 0.8045 | 0.7783 | 0.9003 |
|
77 |
+
| 0.2775 | 1.13 | 8800 | 0.2990 | 0.7687 | 0.8003 | 0.7842 | 0.9024 |
|
78 |
+
| 0.2704 | 1.18 | 9200 | 0.2948 | 0.7724 | 0.7987 | 0.7853 | 0.9023 |
|
79 |
+
| 0.2734 | 1.23 | 9600 | 0.2932 | 0.7764 | 0.7993 | 0.7877 | 0.9041 |
|
80 |
+
| 0.2746 | 1.29 | 10000 | 0.2918 | 0.7841 | 0.7949 | 0.7894 | 0.9046 |
|
81 |
+
| 0.2678 | 1.34 | 10400 | 0.2909 | 0.7775 | 0.8039 | 0.7905 | 0.9046 |
|
82 |
+
| 0.272 | 1.39 | 10800 | 0.2909 | 0.7786 | 0.7952 | 0.7868 | 0.9034 |
|
83 |
+
| 0.2636 | 1.44 | 11200 | 0.2900 | 0.7815 | 0.7959 | 0.7886 | 0.9044 |
|
84 |
+
| 0.2663 | 1.49 | 11600 | 0.2863 | 0.7747 | 0.8086 | 0.7913 | 0.9047 |
|
85 |
+
| 0.2617 | 1.54 | 12000 | 0.2876 | 0.7759 | 0.8042 | 0.7898 | 0.9051 |
|
86 |
+
| 0.2634 | 1.59 | 12400 | 0.2896 | 0.7677 | 0.8123 | 0.7894 | 0.9038 |
|
87 |
+
| 0.2651 | 1.65 | 12800 | 0.2871 | 0.7799 | 0.8024 | 0.7910 | 0.9058 |
|
88 |
+
| 0.2676 | 1.7 | 13200 | 0.2870 | 0.7863 | 0.8008 | 0.7935 | 0.9061 |
|
89 |
+
| 0.273 | 1.75 | 13600 | 0.2836 | 0.7804 | 0.8108 | 0.7953 | 0.9064 |
|
90 |
+
| 0.2611 | 1.8 | 14000 | 0.2821 | 0.7821 | 0.8052 | 0.7935 | 0.9064 |
|
91 |
+
| 0.2683 | 1.85 | 14400 | 0.2815 | 0.7791 | 0.8108 | 0.7946 | 0.9064 |
|
92 |
+
| 0.2624 | 1.9 | 14800 | 0.2818 | 0.7819 | 0.8090 | 0.7952 | 0.9071 |
|
93 |
+
| 0.2628 | 1.95 | 15200 | 0.2821 | 0.7818 | 0.8089 | 0.7951 | 0.9070 |
|
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
|