gemma2b-summarize-claude3sonnet
Collection
9 items
•
Updated
This model is a fine-tuned version of google/gemma-2b on the llama-duo/synth_summarize_dataset_dedup 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 |
---|---|---|---|
2.777 | 0.9231 | 6 | 2.9954 |
2.4096 | 2.0 | 13 | 2.7120 |
2.0954 | 2.9231 | 19 | 2.6309 |
1.7235 | 4.0 | 26 | 2.5914 |
1.5996 | 4.9231 | 32 | 2.5729 |
1.5071 | 6.0 | 39 | 2.5704 |
1.4254 | 6.9231 | 45 | 2.5704 |
1.3939 | 8.0 | 52 | 2.5644 |
1.3833 | 8.9231 | 58 | 2.5642 |
1.3864 | 9.2308 | 60 | 2.5640 |
Base model
google/gemma-2b