Downloads · 30 days
120
4% of all-time downloads
RichardErkhov/PolyAgent_-_gemma-7b-ua-ckpt-h100-lower-lr-gguf
PolyAgent_-_gemma-7b-ua-ckpt-h100-lower-lr-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Downloads · 30 days
120
4% of all-time downloads
All-time downloads
3.1K
Public
Repo size
99.8 GB
Likes
0
Public
Click a slice to open those files.
.gguf116 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
gemma-7b-ua-ckpt-h100-lower-lr - GGUF
license: gemma base_model: PolyAgent/gemma-7b-custom-tokenizer-base tags:
This model is a fine-tuned version of PolyAgent/gemma-7b-custom-tokenizer-base on the PolyAgent/ukrainian-en-wiki 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 |
|---|---|---|---|
| 2.7554 | 0.0360 | 500 | 2.7084 |
| 2.4122 | 0.0719 | 1000 | 2.1895 |
| 2.2982 | 0.1079 | 1500 | 2.0190 |
| 2.2796 | 0.1438 | 2000 | 1.9706 |
| 2.2194 | 0.1798 | 2500 | 1.9128 |
| 2.2064 | 0.2157 | 3000 | 1.8791 |
| 2.2237 | 0.2517 | 3500 | 1.8555 |
| 2.1941 | 0.2876 | 4000 | 1.8229 |
| 2.1708 | 0.3236 | 4500 | 1.8023 |
| 2.1601 | 0.3595 | 5000 | 1.7858 |
| 2.1733 | 0.3955 | 5500 | 1.7697 |
| 2.0827 | 0.4314 | 6000 | 1.7508 |
| 2.1464 | 0.4674 | 6500 | 1.7283 |
| 2.0892 | 0.5033 | 7000 | 1.7179 |
| 2.0425 | 0.5393 | 7500 | 1.7039 |
| 2.0573 | 0.5752 | 8000 | 1.7075 |
| 2.0132 | 0.6112 | 8500 | 1.6547 |
| 2.0225 | 0.6471 | 9000 | 1.6366 |
| 1.9904 | 0.6831 | 9500 | 1.6261 |
| 1.9827 | 0.7190 | 10000 | 1.6251 |
| 1.963 | 0.7550 | 10500 | 1.6125 |
| 1.9516 | 0.7910 | 11000 | 1.5945 |
| 1.9856 | 0.8269 | 11500 | 1.5833 |
| 1.9592 | 0.8629 | 12000 | 1.5725 |
| 1.9568 | 0.8988 | 12500 | 1.5663 |
| 1.9301 | 0.9348 | 13000 | 1.5634 |
| 1.975 | 0.9707 | 13500 | 1.5611 |
| 1.8125 | 1.0067 | 14000 | 1.5891 |
| 1.7976 | 1.0426 | 14500 | 1.5754 |
| 1.788 | 1.0786 | 15000 | 1.5760 |
| 1.7762 | 1.1145 | 15500 | 1.5763 |
| 1.7862 | 1.1505 | 16000 | 1.5772 |
| 1.7839 | 1.1864 | 16500 | 1.5839 |
| 1.7988 | 1.2224 | 17000 | 1.5814 |
| 1.8897 | 1.2584 | 17500 | 1.6072 |
| 1.7994 | 1.2943 | 18000 | 1.5962 |
| 1.8445 | 1.3303 | 18500 | 1.6049 |
| 1.8438 | 1.3662 | 19000 | 1.5822 |
| 1.8079 | 1.4022 | 19500 | 1.5860 |
| 1.8321 | 1.4381 | 20000 | 1.5767 |
| 1.8225 | 1.4741 | 20500 | 1.5648 |
| 1.8169 | 1.5100 | 21000 | 1.5604 |
| 1.7938 | 1.5460 | 21500 | 1.5556 |
| 1.8176 | 1.5819 | 22000 | 1.5479 |
| 1.7996 | 1.6179 | 22500 | 1.5429 |
| 1.7495 | 1.6538 | 23000 | 1.5375 |
| 1.7889 | 1.6898 | 23500 | 1.5329 |
| 1.7676 | 1.7257 | 24000 | 1.5292 |
| 1.7942 | 1.7617 | 24500 | 1.5258 |
| 1.7707 | 1.7976 | 25000 | 1.5234 |
| 1.7779 | 1.8336 | 25500 | 1.5212 |
| 1.7767 | 1.8695 | 26000 | 1.5198 |
| 1.7548 | 1.9055 | 26500 | 1.5192 |
| 1.7274 | 1.9415 | 27000 | 1.5180 |
| 1.7433 | 1.9774 | 27500 | 1.5180 |