flintlock_3B_v0.1 / README.md
ambrosfitz's picture
Update README.md
5858480 verified
---
license: apache-2.0
datasets:
- ambrosfitz/ps_data_v2.2
---
### Model
A fine-tuned openllama 3B model, using primary sources from US History to provide a deeper understanding of the historical context.
Run history:
train/epoch β–β–β–‚β–‚β–‚β–ƒβ–ƒβ–„β–„β–„β–…β–…β–…β–†β–†β–‡β–‡β–‡β–ˆβ–ˆβ–ˆ<br>
train/global_step β–β–β–‚β–‚β–‚β–ƒβ–ƒβ–„β–„β–„β–…β–…β–…β–†β–†β–‡β–‡β–‡β–ˆβ–ˆβ–ˆ<br>
train/grad_norm β–ˆβ–ˆβ–„β–…β–„β–…β–ƒβ–‚β–‚β–„β–‚β–‚β–‚β–‚β–β–β–β–β–β–<br>
train/learning_rate β–‚β–‚β–ƒβ–„β–…β–…β–†β–‡β–‡β–ˆβ–‡β–‡β–†β–…β–…β–„β–ƒβ–‚β–‚β–<br>
train/loss β–‡β–ˆβ–‡β–†β–…β–…β–„β–„β–ƒβ–ƒβ–‚β–‚β–‚β–β–‚β–β–β–β–β–<br>
train/total_flos ▁<br>
train/train_loss ▁<br>
train/train_runtime ▁<br>
train/train_samples_per_second ▁<br>
train/train_steps_per_second ▁<br>
Run summary:
train/epoch 2.0<br>
train/global_step 20<br>
train/grad_norm 0.13779<br>
train/learning_rate 0.0<br>
train/loss 1.1365<br>
train/total_flos 4.579249185376512e+16<br>
train/train_loss 1.29891<br>
train/train_runtime 1552.5749<br>
train/train_samples_per_second 1.649<br>
train/train_steps_per_second 0.013<br>