Chatbot-009
Collection
En ésta colección se encuentran los modelos afinados del acuerdo 009
•
7 items
•
Updated
•
1
This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on the None 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 |
---|---|---|---|
0.5521 | 0.9927 | 102 | 0.5792 |
0.4385 | 1.9927 | 204 | 0.4978 |
0.464 | 2.9927 | 306 | 0.4432 |
0.4133 | 3.9927 | 408 | 0.3984 |
0.3496 | 4.9927 | 510 | 0.3579 |
0.3212 | 5.9927 | 612 | 0.3265 |
0.2927 | 6.9927 | 714 | 0.3045 |
0.2645 | 7.9927 | 816 | 0.2904 |
0.2538 | 8.9927 | 918 | 0.2817 |
0.2347 | 9.9927 | 1020 | 0.2788 |
Base model
meta-llama/Meta-Llama-3-8B-Instruct