Files
veyra2-15m-base-1b-tokens/veyra2_15m_1b_eval_summary.json

17 lines
500 B
JSON
Raw Normal View History

{
"model_name": "veyra2-15m-base-1b-tokens",
"source_folder": "/content/drive/MyDrive/veyra_runs/veyra2_15m_base_pretrain_1b/checkpoints/final_hf",
"params": 14685888,
"train_tokens": 2000158720,
"quick_eval_loss": 2.8223165422677994,
"quick_eval_ppl": 16.815760006000545,
"vocab_size": 8192,
"context_length": 1024,
"architecture": {
"hidden_size": 448,
"intermediate_size": 1024,
"num_hidden_layers": 6,
"num_attention_heads": 7,
"num_key_value_heads": 1
}
}