
2 Epoch ~ Eval Loss on Organic Created Dataset is is roughly 0.4 which is good enough for now, might go another epoch or 2 to see if it goes up or down, Im being impatient.
3fce18f
verified
{ | |
"add_bos_token": true, | |
"add_eos_token": false, | |
"added_tokens_decoder": { | |
"0": { | |
"content": "<unk>", | |
"lstrip": false, | |
"normalized": false, | |
"rstrip": false, | |
"single_word": false, | |
"special": true | |
}, | |
"1": { | |
"content": "<s>", | |
"lstrip": false, | |
"normalized": false, | |
"rstrip": false, | |
"single_word": false, | |
"special": true | |
}, | |
"2": { | |
"content": "</s>", | |
"lstrip": false, | |
"normalized": false, | |
"rstrip": false, | |
"single_word": false, | |
"special": true | |
} | |
}, | |
"additional_special_tokens": [], | |
"bos_token": "<s>", | |
"clean_up_tokenization_spaces": false, | |
"eos_token": "</s>", | |
"legacy": true, | |
"model_max_length": 1000000000000000019884624838656, | |
"pad_token": null, | |
"sp_model_kwargs": {}, | |
"spaces_between_special_tokens": false, | |
"tokenizer_class": "LlamaTokenizer", | |
"unk_token": "<unk>", | |
"use_default_system_prompt": true | |
} | |