update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,114 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
datasets:
|
5 |
+
- ccmatrix
|
6 |
+
metrics:
|
7 |
+
- bleu
|
8 |
+
model-index:
|
9 |
+
- name: t5-base_ro-finetuned-en-to-it
|
10 |
+
results:
|
11 |
+
- task:
|
12 |
+
name: Sequence-to-sequence Language Modeling
|
13 |
+
type: text2text-generation
|
14 |
+
dataset:
|
15 |
+
name: ccmatrix
|
16 |
+
type: ccmatrix
|
17 |
+
config: en-it
|
18 |
+
split: train[3000:12000]
|
19 |
+
args: en-it
|
20 |
+
metrics:
|
21 |
+
- name: Bleu
|
22 |
+
type: bleu
|
23 |
+
value: 19.6396
|
24 |
+
---
|
25 |
+
|
26 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
27 |
+
should probably proofread and complete it, then remove this comment. -->
|
28 |
+
|
29 |
+
# t5-base_ro-finetuned-en-to-it
|
30 |
+
|
31 |
+
This model is a fine-tuned version of [j0hngou/t5-base-finetuned-en-to-ro](https://huggingface.co/j0hngou/t5-base-finetuned-en-to-ro) on the ccmatrix dataset.
|
32 |
+
It achieves the following results on the evaluation set:
|
33 |
+
- Loss: 1.4669
|
34 |
+
- Bleu: 19.6396
|
35 |
+
- Gen Len: 52.4247
|
36 |
+
|
37 |
+
## Model description
|
38 |
+
|
39 |
+
More information needed
|
40 |
+
|
41 |
+
## Intended uses & limitations
|
42 |
+
|
43 |
+
More information needed
|
44 |
+
|
45 |
+
## Training and evaluation data
|
46 |
+
|
47 |
+
More information needed
|
48 |
+
|
49 |
+
## Training procedure
|
50 |
+
|
51 |
+
### Training hyperparameters
|
52 |
+
|
53 |
+
The following hyperparameters were used during training:
|
54 |
+
- learning_rate: 2e-05
|
55 |
+
- train_batch_size: 32
|
56 |
+
- eval_batch_size: 32
|
57 |
+
- seed: 42
|
58 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
59 |
+
- lr_scheduler_type: linear
|
60 |
+
- num_epochs: 40
|
61 |
+
- mixed_precision_training: Native AMP
|
62 |
+
|
63 |
+
### Training results
|
64 |
+
|
65 |
+
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|
66 |
+
|:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|
|
67 |
+
| No log | 1.0 | 282 | 2.0942 | 5.6875 | 73.434 |
|
68 |
+
| 2.5108 | 2.0 | 564 | 1.9725 | 6.6631 | 72.6607 |
|
69 |
+
| 2.5108 | 3.0 | 846 | 1.9010 | 7.9227 | 67.01 |
|
70 |
+
| 2.1659 | 4.0 | 1128 | 1.8452 | 8.9935 | 65.1027 |
|
71 |
+
| 2.1659 | 5.0 | 1410 | 1.7979 | 9.4164 | 64.9827 |
|
72 |
+
| 2.0288 | 6.0 | 1692 | 1.7590 | 9.6035 | 66.6933 |
|
73 |
+
| 2.0288 | 7.0 | 1974 | 1.7264 | 10.7658 | 62.068 |
|
74 |
+
| 1.9238 | 8.0 | 2256 | 1.6955 | 11.5779 | 59.472 |
|
75 |
+
| 1.8435 | 9.0 | 2538 | 1.6729 | 12.7588 | 56.584 |
|
76 |
+
| 1.8435 | 10.0 | 2820 | 1.6541 | 13.3086 | 56.1153 |
|
77 |
+
| 1.775 | 11.0 | 3102 | 1.6337 | 13.8543 | 55.3307 |
|
78 |
+
| 1.775 | 12.0 | 3384 | 1.6148 | 14.3566 | 55.2853 |
|
79 |
+
| 1.7204 | 13.0 | 3666 | 1.5994 | 14.693 | 55.6607 |
|
80 |
+
| 1.7204 | 14.0 | 3948 | 1.5838 | 15.1284 | 55.5327 |
|
81 |
+
| 1.6705 | 15.0 | 4230 | 1.5742 | 15.6125 | 55.0087 |
|
82 |
+
| 1.632 | 16.0 | 4512 | 1.5600 | 15.9616 | 54.052 |
|
83 |
+
| 1.632 | 17.0 | 4794 | 1.5526 | 16.495 | 53.562 |
|
84 |
+
| 1.5868 | 18.0 | 5076 | 1.5392 | 16.4252 | 54.4613 |
|
85 |
+
| 1.5868 | 19.0 | 5358 | 1.5311 | 16.753 | 54.1853 |
|
86 |
+
| 1.5656 | 20.0 | 5640 | 1.5262 | 17.0308 | 54.2473 |
|
87 |
+
| 1.5656 | 21.0 | 5922 | 1.5186 | 17.3553 | 53.396 |
|
88 |
+
| 1.529 | 22.0 | 6204 | 1.5121 | 17.6177 | 53.472 |
|
89 |
+
| 1.529 | 23.0 | 6486 | 1.5058 | 17.6409 | 53.6847 |
|
90 |
+
| 1.5071 | 24.0 | 6768 | 1.5038 | 18.2009 | 53.2327 |
|
91 |
+
| 1.4903 | 25.0 | 7050 | 1.4962 | 18.4838 | 52.9587 |
|
92 |
+
| 1.4903 | 26.0 | 7332 | 1.4935 | 18.5545 | 52.688 |
|
93 |
+
| 1.4686 | 27.0 | 7614 | 1.4879 | 18.62 | 53.5 |
|
94 |
+
| 1.4686 | 28.0 | 7896 | 1.4850 | 19.0099 | 52.34 |
|
95 |
+
| 1.4511 | 29.0 | 8178 | 1.4813 | 19.0538 | 52.474 |
|
96 |
+
| 1.4511 | 30.0 | 8460 | 1.4787 | 18.89 | 53.0753 |
|
97 |
+
| 1.4364 | 31.0 | 8742 | 1.4756 | 19.2582 | 52.3587 |
|
98 |
+
| 1.4279 | 32.0 | 9024 | 1.4739 | 19.2973 | 52.69 |
|
99 |
+
| 1.4279 | 33.0 | 9306 | 1.4725 | 19.3624 | 52.694 |
|
100 |
+
| 1.4172 | 34.0 | 9588 | 1.4704 | 19.5421 | 52.1667 |
|
101 |
+
| 1.4172 | 35.0 | 9870 | 1.4689 | 19.4807 | 52.5487 |
|
102 |
+
| 1.4141 | 36.0 | 10152 | 1.4685 | 19.5972 | 52.2733 |
|
103 |
+
| 1.4141 | 37.0 | 10434 | 1.4676 | 19.5835 | 52.374 |
|
104 |
+
| 1.4058 | 38.0 | 10716 | 1.4674 | 19.6374 | 52.3447 |
|
105 |
+
| 1.4058 | 39.0 | 10998 | 1.4671 | 19.6105 | 52.5273 |
|
106 |
+
| 1.4027 | 40.0 | 11280 | 1.4669 | 19.6396 | 52.4247 |
|
107 |
+
|
108 |
+
|
109 |
+
### Framework versions
|
110 |
+
|
111 |
+
- Transformers 4.22.1
|
112 |
+
- Pytorch 1.12.1
|
113 |
+
- Datasets 2.5.1
|
114 |
+
- Tokenizers 0.11.0
|