sayanmandal
commited on
Commit
•
1cbcac0
1
Parent(s):
1ee42a5
update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,112 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- translation
|
4 |
+
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- bleu
|
7 |
+
model-index:
|
8 |
+
- name: t5-small_6_3-en-hi_en_bt
|
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 |
+
# t5-small_6_3-en-hi_en_bt
|
16 |
+
|
17 |
+
This model was trained from scratch on the None dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 1.9293
|
20 |
+
- Bleu: 8.9676
|
21 |
+
- Gen Len: 33.391
|
22 |
+
|
23 |
+
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training and evaluation data
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training procedure
|
36 |
+
|
37 |
+
### Training hyperparameters
|
38 |
+
|
39 |
+
The following hyperparameters were used during training:
|
40 |
+
- learning_rate: 0.0001
|
41 |
+
- train_batch_size: 8
|
42 |
+
- eval_batch_size: 8
|
43 |
+
- seed: 42
|
44 |
+
- gradient_accumulation_steps: 8
|
45 |
+
- total_train_batch_size: 64
|
46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
+
- lr_scheduler_type: linear
|
48 |
+
- num_epochs: 50
|
49 |
+
- mixed_precision_training: Native AMP
|
50 |
+
|
51 |
+
### Training results
|
52 |
+
|
53 |
+
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|
54 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|:-------:|
|
55 |
+
| 3.7929 | 1.0 | 526 | 2.6759 | 1.5672 | 16.749 |
|
56 |
+
| 3.1151 | 2.0 | 1052 | 2.3843 | 2.2962 | 16.5287 |
|
57 |
+
| 2.8701 | 3.0 | 1578 | 2.2287 | 2.8811 | 16.4953 |
|
58 |
+
| 2.7121 | 4.0 | 2104 | 2.1302 | 3.3949 | 16.5247 |
|
59 |
+
| 2.5844 | 5.0 | 2630 | 2.0593 | 3.8161 | 16.4513 |
|
60 |
+
| 2.4917 | 6.0 | 3156 | 2.0063 | 3.9831 | 16.4272 |
|
61 |
+
| 2.4067 | 7.0 | 3682 | 1.9733 | 4.0511 | 16.3378 |
|
62 |
+
| 2.3395 | 8.0 | 4208 | 1.9399 | 4.3067 | 16.4112 |
|
63 |
+
| 2.2713 | 9.0 | 4734 | 1.9148 | 4.3195 | 16.3618 |
|
64 |
+
| 2.2217 | 10.0 | 5260 | 1.8961 | 4.3905 | 16.4112 |
|
65 |
+
| 2.1659 | 11.0 | 5786 | 1.8787 | 4.4548 | 16.3298 |
|
66 |
+
| 2.1267 | 12.0 | 6312 | 1.8651 | 4.5779 | 16.3618 |
|
67 |
+
| 2.0793 | 13.0 | 6838 | 1.8540 | 4.4863 | 16.2603 |
|
68 |
+
| 2.0473 | 14.0 | 7364 | 1.8444 | 4.556 | 16.3044 |
|
69 |
+
| 2.0082 | 15.0 | 7890 | 1.8353 | 4.5957 | 16.3124 |
|
70 |
+
| 1.9748 | 16.0 | 8416 | 1.8313 | 4.5593 | 16.3204 |
|
71 |
+
| 1.9456 | 17.0 | 8942 | 1.8259 | 4.4522 | 16.2764 |
|
72 |
+
| 1.9177 | 18.0 | 9468 | 1.8231 | 4.3345 | 16.3084 |
|
73 |
+
| 1.8871 | 19.0 | 9994 | 1.8177 | 4.48 | 16.3458 |
|
74 |
+
| 1.8422 | 20.0 | 10520 | 1.8123 | 4.5078 | 16.287 |
|
75 |
+
| 1.8161 | 21.0 | 11046 | 1.8106 | 4.3289 | 16.3405 |
|
76 |
+
| 1.7972 | 22.0 | 11572 | 1.8106 | 4.5204 | 16.3244 |
|
77 |
+
| 1.7785 | 23.0 | 12098 | 1.8117 | 4.4651 | 16.3605 |
|
78 |
+
| 1.7563 | 24.0 | 12624 | 1.8125 | 4.3938 | 16.3538 |
|
79 |
+
| 1.7444 | 25.0 | 13150 | 1.8089 | 4.5367 | 16.3792 |
|
80 |
+
| 1.7256 | 26.0 | 13676 | 1.8075 | 4.4212 | 16.3925 |
|
81 |
+
| 1.7021 | 27.0 | 14202 | 1.8080 | 4.5491 | 16.3992 |
|
82 |
+
| 1.6969 | 28.0 | 14728 | 1.8061 | 4.6568 | 16.3645 |
|
83 |
+
| 1.6766 | 29.0 | 15254 | 1.8063 | 4.6297 | 16.3738 |
|
84 |
+
| 1.6653 | 30.0 | 15780 | 1.8095 | 4.6167 | 16.2977 |
|
85 |
+
| 1.6543 | 31.0 | 16306 | 1.8085 | 4.5452 | 16.3538 |
|
86 |
+
| 1.6413 | 32.0 | 16832 | 1.8112 | 4.6667 | 16.3351 |
|
87 |
+
| 1.6293 | 33.0 | 17358 | 1.8126 | 4.6127 | 16.3351 |
|
88 |
+
| 1.6204 | 34.0 | 17884 | 1.8115 | 4.7196 | 16.3111 |
|
89 |
+
| 1.6082 | 35.0 | 18410 | 1.8134 | 4.7011 | 16.3324 |
|
90 |
+
| 1.6048 | 36.0 | 18936 | 1.8122 | 4.6429 | 16.2964 |
|
91 |
+
| 1.5911 | 37.0 | 19462 | 1.8143 | 4.6424 | 16.3124 |
|
92 |
+
| 1.5834 | 38.0 | 19988 | 1.8131 | 4.6254 | 16.3164 |
|
93 |
+
| 1.5742 | 39.0 | 20514 | 1.8154 | 4.6998 | 16.287 |
|
94 |
+
| 1.5623 | 40.0 | 21040 | 1.8147 | 4.6469 | 16.3471 |
|
95 |
+
| 1.5599 | 41.0 | 21566 | 1.8185 | 4.6654 | 16.3231 |
|
96 |
+
| 1.5516 | 42.0 | 22092 | 1.8173 | 4.6961 | 16.3471 |
|
97 |
+
| 1.5441 | 43.0 | 22618 | 1.8180 | 4.7176 | 16.3084 |
|
98 |
+
| 1.545 | 44.0 | 23144 | 1.8177 | 4.5571 | 16.275 |
|
99 |
+
| 1.5418 | 45.0 | 23670 | 1.8195 | 4.5927 | 16.3097 |
|
100 |
+
| 1.5329 | 46.0 | 24196 | 1.8187 | 4.7025 | 16.2724 |
|
101 |
+
| 1.5348 | 47.0 | 24722 | 1.8198 | 4.6575 | 16.3057 |
|
102 |
+
| 1.5362 | 48.0 | 25248 | 1.8197 | 4.6912 | 16.2991 |
|
103 |
+
| 1.5231 | 49.0 | 25774 | 1.8202 | 4.6752 | 16.2951 |
|
104 |
+
| 1.5314 | 50.0 | 26300 | 1.8208 | 4.6114 | 16.2937 |
|
105 |
+
|
106 |
+
|
107 |
+
### Framework versions
|
108 |
+
|
109 |
+
- Transformers 4.20.0.dev0
|
110 |
+
- Pytorch 1.8.0
|
111 |
+
- Datasets 2.1.0
|
112 |
+
- Tokenizers 0.12.1
|