Downloads · 30 days
262
12% of all-time downloads
ffsouza/t5-tiny-random-length-96-learning_rate-0.0002-weight_decay-0.01-finetuned-en-to-ro
t5-tiny-random-length-96-learning_rate-0.0002-weight_decay-0.01-finetuned-en-to-ro is a machine learning model from ffsouza. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
262
12% of all-time downloads
All-time downloads
2.2K
Public
Repo size
5.7 GB
Likes
0
Public
Click a slice to open those files.
.bin8.9 MB · 79%
From the Hugging Face model README
This model is a fine-tuned version of patrickvonplaten/t5-tiny-random on the wmt16_en_ro_pre_processed dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 4.5828 | 1.0 | 76290 | 5.5397 | 0.0089 | 8.981 |
| 4.187 | 2.0 | 152580 | 5.2241 | 0.0172 | 8.989 |
| 3.9612 | 3.0 | 228870 | 5.0092 | 0.034 | 8.988 |
| 3.8151 | 4.0 | 305160 | 4.8688 | 0.0365 | 8.9865 |
| 3.7162 | 5.0 | 381450 | 4.7656 | 0.0469 | 8.9865 |
| 3.6498 | 6.0 | 457740 | 4.6874 | 0.0531 | 8.9885 |
| 3.6147 | 7.0 | 534030 | 4.6612 | 0.0585 | 8.9875 |
| 3.5972 | 8.0 | 610320 | 4.6426 | 0.0617 | 8.9895 |