convergence_random / checkpoint-14000 /tokenizer_config.json
fpadovani's picture
Training in progress epoch 0
eb86bcf verified
raw
history blame
1.25 kB
{
"added_tokens_decoder": {
"0": {
"content": "[UNK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "[CLS]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "[SEP]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "[PAD]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"4": {
"content": "[EOS]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"5": {
"content": "[BOS]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "[BOS]",
"clean_up_tokenization_spaces": true,
"eos_token": "[EOS]",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "[PAD]",
"tokenizer_class": "PreTrainedTokenizerFast"
}