Commit
•
6b09551
1
Parent(s):
1332bd2
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- bleu
|
| 7 |
+
model-index:
|
| 8 |
+
- name: Xegho.30.2
|
| 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.30.2
|
| 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: 0.1632
|
| 20 |
+
- Bleu: 91.1608
|
| 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: 2
|
| 41 |
+
- eval_batch_size: 2
|
| 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 | 0.6 | 100 | 1.4767 | 23.2970 |
|
| 52 |
+
| No log | 1.19 | 200 | 1.0102 | 34.8884 |
|
| 53 |
+
| No log | 1.79 | 300 | 0.7680 | 39.9415 |
|
| 54 |
+
| No log | 2.38 | 400 | 0.6129 | 42.4210 |
|
| 55 |
+
| 1.2252 | 2.98 | 500 | 0.4962 | 46.5901 |
|
| 56 |
+
| 1.2252 | 3.57 | 600 | 0.4293 | 48.9165 |
|
| 57 |
+
| 1.2252 | 4.17 | 700 | 0.3698 | 50.4146 |
|
| 58 |
+
| 1.2252 | 4.76 | 800 | 0.3194 | 52.4519 |
|
| 59 |
+
| 1.2252 | 5.36 | 900 | 0.2836 | 53.0005 |
|
| 60 |
+
| 0.463 | 5.95 | 1000 | 0.2635 | 55.5264 |
|
| 61 |
+
| 0.463 | 6.55 | 1100 | 0.2444 | 57.7553 |
|
| 62 |
+
| 0.463 | 7.14 | 1200 | 0.2262 | 60.8152 |
|
| 63 |
+
| 0.463 | 7.74 | 1300 | 0.2205 | 60.3349 |
|
| 64 |
+
| 0.463 | 8.33 | 1400 | 0.2082 | 62.5781 |
|
| 65 |
+
| 0.297 | 8.93 | 1500 | 0.2045 | 62.9341 |
|
| 66 |
+
| 0.297 | 9.52 | 1600 | 0.1969 | 63.9225 |
|
| 67 |
+
| 0.297 | 10.12 | 1700 | 0.1939 | 63.9559 |
|
| 68 |
+
| 0.297 | 10.71 | 1800 | 0.1842 | 66.0123 |
|
| 69 |
+
| 0.297 | 11.31 | 1900 | 0.1836 | 65.7767 |
|
| 70 |
+
| 0.2403 | 11.9 | 2000 | 0.1807 | 65.1204 |
|
| 71 |
+
| 0.2403 | 12.5 | 2100 | 0.1778 | 65.5556 |
|
| 72 |
+
| 0.2403 | 13.1 | 2200 | 0.1753 | 66.2715 |
|
| 73 |
+
| 0.2403 | 13.69 | 2300 | 0.1728 | 67.0917 |
|
| 74 |
+
| 0.2403 | 14.29 | 2400 | 0.1716 | 67.2965 |
|
| 75 |
+
| 0.1976 | 14.88 | 2500 | 0.1719 | 66.5856 |
|
| 76 |
+
| 0.1976 | 15.48 | 2600 | 0.1706 | 66.7707 |
|
| 77 |
+
| 0.1976 | 16.07 | 2700 | 0.1698 | 66.8323 |
|
| 78 |
+
| 0.1976 | 16.67 | 2800 | 0.1705 | 66.8579 |
|
| 79 |
+
| 0.1976 | 17.26 | 2900 | 0.1663 | 67.3175 |
|
| 80 |
+
| 0.1747 | 17.86 | 3000 | 0.1671 | 68.2097 |
|
| 81 |
+
| 0.1747 | 18.45 | 3100 | 0.1681 | 68.1515 |
|
| 82 |
+
| 0.1747 | 19.05 | 3200 | 0.1650 | 68.6221 |
|
| 83 |
+
| 0.1747 | 19.64 | 3300 | 0.1643 | 68.6828 |
|
| 84 |
+
| 0.1747 | 20.24 | 3400 | 0.1662 | 68.9329 |
|
| 85 |
+
| 0.1626 | 20.83 | 3500 | 0.1644 | 68.9651 |
|
| 86 |
+
| 0.1626 | 21.43 | 3600 | 0.1660 | 68.6685 |
|
| 87 |
+
| 0.1626 | 22.02 | 3700 | 0.1640 | 68.7471 |
|
| 88 |
+
| 0.1626 | 22.62 | 3800 | 0.1630 | 68.6685 |
|
| 89 |
+
| 0.1626 | 23.21 | 3900 | 0.1637 | 68.6835 |
|
| 90 |
+
| 0.1437 | 23.81 | 4000 | 0.1632 | 68.5208 |
|
| 91 |
+
| 0.1437 | 24.4 | 4100 | 0.1640 | 68.5059 |
|
| 92 |
+
| 0.1437 | 25.0 | 4200 | 0.1645 | 68.5059 |
|
| 93 |
+
| 0.1437 | 25.6 | 4300 | 0.1639 | 68.5059 |
|
| 94 |
+
|
| 95 |
+
|
| 96 |
+
### Framework versions
|
| 97 |
+
|
| 98 |
+
- Transformers 4.18.0
|
| 99 |
+
- Pytorch 1.11.0a0+17540c5
|
| 100 |
+
- Datasets 2.1.0
|
| 101 |
+
- Tokenizers 0.12.1
|