Can't use chat_template: phi_3 with type: sharegpt

[ccdv-ai]

Please check that this issue hasn't been reported before.

• I searched previous Bug Reports didn't find any similar reports.

Expected Behavior

Should be able to use chat_template: phi_3 and type: sharegpt for the dataset

Current behaviour

  File "/home/user/codes/train/instruct/instruct-v1/axolotl/src/axolotl/utils/data/sft.py", line 403, in load_tokenized_prepared_datasets
    dataset_wrapper, dataset_prompter = get_dataset_wrapper(
                                        ^^^^^^^^^^^^^^^^^^^^
  File "/home/user/codes/train/instruct/instruct-v1/axolotl/src/axolotl/utils/data/sft.py", line 689, in get_dataset_wrapper
    raise ValueError(
ValueError: unhandled prompt tokenization strategy: sharegpt

Steps to reproduce

Similar to phi3-ft.yml

base_model: microsoft/Phi-3-mini-4k-instruct
trust_remote_code: true
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
chat_template: phi_3

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: lightblue/tagengo-gpt4
    type: sharegpt
    conversation: 
    field_messages: conversations
    message_field_role: from
    message_field_content: value

dataset_prepared_path:
val_set_size: 0.01
output_dir: ./out

sequence_len: 4096
sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 64
lora_alpha: 32
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 1
optimizer: adamw_torch
adam_beta2: 0.95
adam_epsilon: 0.00001
max_grad_norm: 1.0
lr_scheduler: cosine
learning_rate: 5.0e-6

train_on_inputs: false
group_by_length: false
bf16: auto

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: True
early_stopping_patience: 3
logging_steps: 1
flash_attention: true

eval_steps: 1000
save_steps: 5000
eval_table_size: 2
eval_batch_size: 2
eval_sample_packing: false
eval_max_new_tokens: 32
eval_causal_lm_metrics: ["perplexity"]
do_causal_lm_eval: true

warmup_ratio: 0.2
debug: true
weight_decay: 0.1
resize_token_embeddings_to_32x: true

Config yaml

No response

Possible solution

No response

Which Operating Systems are you using?

• Linux
• macOS
• Windows

Python Version

3.11

axolotl branch-commit

main/a82a711

Acknowledgements

• My issue title is concise, descriptive, and in title casing.
• I have searched the existing issues to make sure this bug has not been reported yet.
• I am using the latest version of axolotl.
• I have provided enough information for the maintainers to reproduce and diagnose the issue.