130ef7c51a
* fix to not use batch feature indexing * more vlm fixes * use AutoModelForImageTextToText * add example yaml and need num2words for chat template * improve handling of adding image tokens to conversation * add lfm2-vl support * update the lfm readme * fix markdown and add rtol for loss checks * feat: add smolvlm2 processing strat * fix: check for causal-conv1d in lfm models * feat: add docs for lfm2 * feat: add new models and tips to docs * feat: add smolvlm2 docs and remove extra dep * chore: update docs * feat: add video instructions * chore: cleanup * chore: comments * fix: typo * feat: add usage stats * chore: refactor --------- Co-authored-by: NanoCode012 <nano@axolotl.ai>
50 lines
901 B
YAML
50 lines
901 B
YAML
base_model: LiquidAI/LFM2-350M
|
|
|
|
chunked_cross_entropy: true
|
|
|
|
eot_tokens:
|
|
- "<|im_end|>"
|
|
datasets:
|
|
- path: mlabonne/FineTome-100k
|
|
type: chat_template
|
|
split: train[:20%]
|
|
field_messages: conversations
|
|
message_field_role: from
|
|
message_field_content: value
|
|
dataset_prepared_path: last_run_prepared
|
|
val_set_size: 0.05
|
|
output_dir: ./outputs/out
|
|
|
|
sequence_len: 4096
|
|
sample_packing: true
|
|
|
|
|
|
wandb_project:
|
|
wandb_entity:
|
|
wandb_watch:
|
|
wandb_name:
|
|
wandb_log_model:
|
|
|
|
gradient_accumulation_steps: 2
|
|
micro_batch_size: 4
|
|
num_epochs: 1
|
|
optimizer: adamw_torch_fused
|
|
lr_scheduler: cosine
|
|
learning_rate: 5e-5
|
|
|
|
bf16: true
|
|
tf32: true
|
|
|
|
gradient_checkpointing: false
|
|
resume_from_checkpoint:
|
|
logging_steps: 1
|
|
flash_attention: true
|
|
|
|
warmup_ratio: 0.1
|
|
evals_per_epoch: 2
|
|
saves_per_epoch: 1
|
|
|
|
weight_decay: 0.0
|
|
|
|
# save_first_step: true # uncomment this to validate checkpoint saving works with your config
|