data-use-unsloth-phi-3.5-simpleschema-thinking-tccml-iclr-prwp-train-10epochs-1738646702-lora
/
tokenizer_config.json

{"epoch": 0, "global_step": 0, "max_steps": 5650, "logging_steps": 100, "eval_steps": 100, "save_steps": 100, "train_batch_size": 4, "num_train_epochs": 10, "num_input_tokens_seen": 0, "total_flos": 0, "log_history": [], "best_metric": null, "best_model_checkpoint": null, "is_local_process_zero": true, "is_world_process_zero": true, "is_hyper_param_search": false, "trial_name": null, "trial_params": null, "stateful_callbacks": {"TrainerControl": {"args": {"should_training_stop": false, "should_epoch_stop": false, "should_save": false, "should_evaluate": false, "should_log": false}, "attributes": {}}}} (Trained with Unsloth)
4efa13d
verified
{ | |
"add_bos_token": false, | |
"add_eos_token": false, | |
"add_prefix_space": null, | |
"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": true, | |
"single_word": false, | |
"special": false | |
}, | |
"32000": { | |
"content": "<|endoftext|>", | |
"lstrip": false, | |
"normalized": false, | |
"rstrip": false, | |
"single_word": false, | |
"special": true | |
}, | |
"32001": { | |
"content": "<|assistant|>", | |
"lstrip": false, | |
"normalized": false, | |
"rstrip": true, | |
"single_word": false, | |
"special": true | |
}, | |
"32002": { | |
"content": "<|placeholder1|>", | |
"lstrip": false, | |
"normalized": false, | |
"rstrip": true, | |
"single_word": false, | |
"special": true | |
}, | |
"32003": { | |
"content": "<|placeholder2|>", | |
"lstrip": false, | |
"normalized": false, | |
"rstrip": true, | |
"single_word": false, | |
"special": true | |
}, | |
"32004": { | |
"content": "<|placeholder3|>", | |
"lstrip": false, | |
"normalized": false, | |
"rstrip": true, | |
"single_word": false, | |
"special": true | |
}, | |
"32005": { | |
"content": "<|placeholder4|>", | |
"lstrip": false, | |
"normalized": false, | |
"rstrip": true, | |
"single_word": false, | |
"special": true | |
}, | |
"32006": { | |
"content": "<|system|>", | |
"lstrip": false, | |
"normalized": false, | |
"rstrip": true, | |
"single_word": false, | |
"special": true | |
}, | |
"32007": { | |
"content": "<|end|>", | |
"lstrip": false, | |
"normalized": false, | |
"rstrip": true, | |
"single_word": false, | |
"special": true | |
}, | |
"32008": { | |
"content": "<|placeholder5|>", | |
"lstrip": false, | |
"normalized": false, | |
"rstrip": true, | |
"single_word": false, | |
"special": true | |
}, | |
"32009": { | |
"content": "<|placeholder6|>", | |
"lstrip": false, | |
"normalized": false, | |
"rstrip": true, | |
"single_word": false, | |
"special": true | |
}, | |
"32010": { | |
"content": "<|user|>", | |
"lstrip": false, | |
"normalized": false, | |
"rstrip": true, | |
"single_word": false, | |
"special": true | |
} | |
}, | |
"bos_token": "<s>", | |
"chat_template": "{% if 'role' in messages[0] %}{% for message in messages %}{% if message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% else %}{{'<|' + message['role'] + '|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% endif %}{% else %}{% for message in messages %}{% if message['from'] == 'human' %}{{'<|user|>\n' + message['value'] + '<|end|>\n'}}{% elif message['from'] == 'gpt' %}{{'<|assistant|>\n' + message['value'] + '<|end|>\n'}}{% else %}{{'<|' + message['from'] + '|>\n' + message['value'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% endif %}{% endif %}", | |
"clean_up_tokenization_spaces": false, | |
"eos_token": "<|endoftext|>", | |
"extra_special_tokens": {}, | |
"legacy": false, | |
"model_max_length": 131072, | |
"pad_token": "<|placeholder6|>", | |
"padding_side": "left", | |
"sp_model_kwargs": {}, | |
"tokenizer_class": "LlamaTokenizer", | |
"unk_token": "<unk>", | |
"use_default_system_prompt": false | |
} | |