Download training_summary.json from FlyinGodzilla/AMOR-Mamba2-440M: direct link, hf CLI and curl.
- Browser
- Download file 551 Bytes
-
https://huggingface.co/FlyinGodzilla/AMOR-Mamba2-440M/resolve/main/training_summary.json
- Command line
-
hf download hf://FlyinGodzilla/AMOR-Mamba2-440M/training_summary.json
-
curl -L -o training_summary.json https://huggingface.co/FlyinGodzilla/AMOR-Mamba2-440M/resolve/main/training_summary.json
551 Bytes
| { | |
| "model": "amor", | |
| "scale": "440m", | |
| "final_val_loss": 2.9757252883911134, | |
| "final_val_ppl": 19.60383652966566, | |
| "best_val_loss": 2.9758635330200196, | |
| "best_val_ppl": 19.606546842110593, | |
| "total_steps": 18255, | |
| "tokens_trained": 8973017088, | |
| "training_hours": 14.797530925538805, | |
| "n_params": 448650496, | |
| "flops_per_token": 1634942976.0, | |
| "world_size": 1, | |
| "linear_flops": 778505772072960, | |
| "attention_flops": 18916646584320, | |
| "ssm_flops": 6184752906240, | |
| "final_fire_rate": 0.4057179203764526, | |
| "final_alpha": 0.7287433220977273 | |
| } | |