adityay1221
commited on
Commit
•
a17a5a0
1
Parent(s):
235f95d
update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- bleu
|
7 |
+
model-index:
|
8 |
+
- name: Xegho.30.4
|
9 |
+
results: []
|
10 |
+
---
|
11 |
+
|
12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
+
should probably proofread and complete it, then remove this comment. -->
|
14 |
+
|
15 |
+
# Xegho.30.4
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the None dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.1814
|
20 |
+
- Bleu: 87.4768
|
21 |
+
|
22 |
+
## Model description
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Intended uses & limitations
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training and evaluation data
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training procedure
|
35 |
+
|
36 |
+
### Training hyperparameters
|
37 |
+
|
38 |
+
The following hyperparameters were used during training:
|
39 |
+
- learning_rate: 1e-05
|
40 |
+
- train_batch_size: 4
|
41 |
+
- eval_batch_size: 4
|
42 |
+
- seed: 121
|
43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
+
- lr_scheduler_type: linear
|
45 |
+
- num_epochs: 30
|
46 |
+
|
47 |
+
### Training results
|
48 |
+
|
49 |
+
| Training Loss | Epoch | Step | Validation Loss | Bleu |
|
50 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
51 |
+
| No log | 1.19 | 100 | 1.2331 | 23.9598 |
|
52 |
+
| No log | 2.38 | 200 | 0.7943 | 39.0191 |
|
53 |
+
| No log | 3.57 | 300 | 0.5889 | 42.0816 |
|
54 |
+
| No log | 4.76 | 400 | 0.4595 | 47.6986 |
|
55 |
+
| 1.0058 | 5.95 | 500 | 0.3801 | 49.9630 |
|
56 |
+
| 1.0058 | 7.14 | 600 | 0.3209 | 50.4290 |
|
57 |
+
| 1.0058 | 8.33 | 700 | 0.2848 | 51.1531 |
|
58 |
+
| 1.0058 | 9.52 | 800 | 0.2544 | 54.0631 |
|
59 |
+
| 1.0058 | 10.71 | 900 | 0.2338 | 56.3553 |
|
60 |
+
| 0.3559 | 11.9 | 1000 | 0.2224 | 59.7317 |
|
61 |
+
| 0.3559 | 13.1 | 1100 | 0.2110 | 62.2114 |
|
62 |
+
| 0.3559 | 14.29 | 1200 | 0.2060 | 63.4936 |
|
63 |
+
| 0.3559 | 15.48 | 1300 | 0.1994 | 63.7621 |
|
64 |
+
| 0.3559 | 16.67 | 1400 | 0.1959 | 63.3415 |
|
65 |
+
| 0.2423 | 17.86 | 1500 | 0.1932 | 63.7683 |
|
66 |
+
| 0.2423 | 19.05 | 1600 | 0.1898 | 64.2757 |
|
67 |
+
| 0.2423 | 20.24 | 1700 | 0.1901 | 64.2757 |
|
68 |
+
| 0.2423 | 21.43 | 1800 | 0.1875 | 64.1890 |
|
69 |
+
| 0.2423 | 22.62 | 1900 | 0.1852 | 63.8513 |
|
70 |
+
| 0.2051 | 23.81 | 2000 | 0.1837 | 64.4531 |
|
71 |
+
| 0.2051 | 25.0 | 2100 | 0.1829 | 64.4531 |
|
72 |
+
| 0.2051 | 26.19 | 2200 | 0.1818 | 64.6303 |
|
73 |
+
| 0.2051 | 27.38 | 2300 | 0.1817 | 64.6303 |
|
74 |
+
| 0.2051 | 28.57 | 2400 | 0.1816 | 65.0213 |
|
75 |
+
| 0.186 | 29.76 | 2500 | 0.1814 | 65.0213 |
|
76 |
+
|
77 |
+
|
78 |
+
### Framework versions
|
79 |
+
|
80 |
+
- Transformers 4.18.0
|
81 |
+
- Pytorch 1.11.0a0+17540c5
|
82 |
+
- Datasets 2.1.0
|
83 |
+
- Tokenizers 0.12.1
|