![finnstrom3693's picture](https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/R15ksyXv72eZttRtsgMvA.png)
training using pytorch native 3 epoch, batch size 14, block size 512,lr 1e-4 cosine
8d45360
verified
{ | |
"_from_model_config": true, | |
"bos_token_id": 50256, | |
"eos_token_id": 50256, | |
"transformers_version": "4.40.1" | |
} | |
{ | |
"_from_model_config": true, | |
"bos_token_id": 50256, | |
"eos_token_id": 50256, | |
"transformers_version": "4.40.1" | |
} | |