Jakub
67061cf373
Document six completed LR runs as preparation for full Aya training on Perun. Record selection of LR 0.00010 by lowest final validation loss, selected-model lm-eval and partial SK-bench results, reproducible provenance, and dataset-access/context-truncation limitations. Preserve existing 30k and Titan material.
20 lines
521 B
JSON
20 lines
521 B
JSON
{
|
|
"add_prefix_space": true,
|
|
"backend": "tokenizers",
|
|
"bos_token": "<s>",
|
|
"clean_up_tokenization_spaces": false,
|
|
"eos_token": "</s>",
|
|
"extra_special_tokens": [],
|
|
"is_local": false,
|
|
"legacy": true,
|
|
"model_max_length": 1000000000000000019884624838656,
|
|
"pad_token": "</s>",
|
|
"padding_side": "left",
|
|
"sp_model_kwargs": {},
|
|
"spaces_between_special_tokens": false,
|
|
"split_special_tokens": false,
|
|
"tokenizer_class": "TokenizersBackend",
|
|
"unk_token": "<unk>",
|
|
"use_default_system_prompt": false
|
|
}
|