update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,91 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- wmt16
|
7 |
+
metrics:
|
8 |
+
- bleu
|
9 |
+
model-index:
|
10 |
+
- name: t5-small-finetuned-en-to-ro-lr_2e-3-fp_false
|
11 |
+
results:
|
12 |
+
- task:
|
13 |
+
name: Sequence-to-sequence Language Modeling
|
14 |
+
type: text2text-generation
|
15 |
+
dataset:
|
16 |
+
name: wmt16
|
17 |
+
type: wmt16
|
18 |
+
args: ro-en
|
19 |
+
metrics:
|
20 |
+
- name: Bleu
|
21 |
+
type: bleu
|
22 |
+
value: 7.1921
|
23 |
+
---
|
24 |
+
|
25 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
26 |
+
should probably proofread and complete it, then remove this comment. -->
|
27 |
+
|
28 |
+
# t5-small-finetuned-en-to-ro-lr_2e-3-fp_false
|
29 |
+
|
30 |
+
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the wmt16 dataset.
|
31 |
+
It achieves the following results on the evaluation set:
|
32 |
+
- Loss: 1.4239
|
33 |
+
- Bleu: 7.1921
|
34 |
+
- Gen Len: 18.2611
|
35 |
+
|
36 |
+
## Model description
|
37 |
+
|
38 |
+
More information needed
|
39 |
+
|
40 |
+
## Intended uses & limitations
|
41 |
+
|
42 |
+
More information needed
|
43 |
+
|
44 |
+
## Training and evaluation data
|
45 |
+
|
46 |
+
More information needed
|
47 |
+
|
48 |
+
## Training procedure
|
49 |
+
|
50 |
+
### Training hyperparameters
|
51 |
+
|
52 |
+
The following hyperparameters were used during training:
|
53 |
+
- learning_rate: 0.002
|
54 |
+
- train_batch_size: 16
|
55 |
+
- eval_batch_size: 16
|
56 |
+
- seed: 42
|
57 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
58 |
+
- lr_scheduler_type: linear
|
59 |
+
- num_epochs: 1
|
60 |
+
|
61 |
+
### Training results
|
62 |
+
|
63 |
+
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|
64 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|:-------:|
|
65 |
+
| 0.8922 | 0.05 | 2000 | 1.7000 | 6.5274 | 18.2656 |
|
66 |
+
| 0.8621 | 0.1 | 4000 | 1.6409 | 6.6411 | 18.2311 |
|
67 |
+
| 0.8433 | 0.16 | 6000 | 1.6396 | 6.6601 | 18.2596 |
|
68 |
+
| 0.8297 | 0.21 | 8000 | 1.6304 | 6.7129 | 18.2581 |
|
69 |
+
| 0.8006 | 0.26 | 10000 | 1.6022 | 6.6067 | 18.2816 |
|
70 |
+
| 0.793 | 0.31 | 12000 | 1.5999 | 6.551 | 18.2631 |
|
71 |
+
| 0.774 | 0.37 | 14000 | 1.5586 | 6.7105 | 18.2661 |
|
72 |
+
| 0.7618 | 0.42 | 16000 | 1.5769 | 6.7278 | 18.2526 |
|
73 |
+
| 0.7463 | 0.47 | 18000 | 1.5625 | 6.6972 | 18.2201 |
|
74 |
+
| 0.7394 | 0.52 | 20000 | 1.5377 | 6.936 | 18.2491 |
|
75 |
+
| 0.7203 | 0.58 | 22000 | 1.5191 | 7.0205 | 18.2731 |
|
76 |
+
| 0.7158 | 0.63 | 24000 | 1.5055 | 6.835 | 18.2506 |
|
77 |
+
| 0.688 | 0.68 | 26000 | 1.4779 | 7.0534 | 18.2716 |
|
78 |
+
| 0.678 | 0.73 | 28000 | 1.4691 | 6.9735 | 18.2616 |
|
79 |
+
| 0.6677 | 0.79 | 30000 | 1.4702 | 7.0359 | 18.2496 |
|
80 |
+
| 0.6568 | 0.84 | 32000 | 1.4534 | 6.9982 | 18.2556 |
|
81 |
+
| 0.6475 | 0.89 | 34000 | 1.4427 | 7.0443 | 18.2466 |
|
82 |
+
| 0.6395 | 0.94 | 36000 | 1.4265 | 7.1205 | 18.2721 |
|
83 |
+
| 0.6319 | 1.0 | 38000 | 1.4239 | 7.1921 | 18.2611 |
|
84 |
+
|
85 |
+
|
86 |
+
### Framework versions
|
87 |
+
|
88 |
+
- Transformers 4.12.5
|
89 |
+
- Pytorch 1.10.0+cu111
|
90 |
+
- Datasets 1.16.1
|
91 |
+
- Tokenizers 0.10.3
|