8c6a6ea6eb
* fix: do not add training and training_detail block by default * fixed: magistral docs * fix: address pad adding new fields and use built-in from_openai * feat: try enable multiprocessing * fix: check for keys before deleting attn_mask * feat: add mistral pad test * feat: add tool calling test * feat: add devstral tokenizer tests * fix: comma format * chore: remove unused support_preprocessing as tokenizer is pickable now * chore: update magistral doc * feat: add devstral readme and example * chore: refactor error handling
65 lines
1.1 KiB
YAML
65 lines
1.1 KiB
YAML
base_model: mistralai/Devstral-Small-2505
|
|
|
|
# Automatically upload checkpoint and final model to HF
|
|
# hub_model_id: username/custom_model_name
|
|
|
|
# Enable to use mistral-common tokenizer
|
|
tokenizer_use_mistral_common: true
|
|
|
|
load_in_8bit: false
|
|
load_in_4bit: true
|
|
|
|
plugins:
|
|
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
|
|
|
|
datasets:
|
|
- path: fozziethebeat/alpaca_messages_2k_test
|
|
type: chat_template
|
|
|
|
dataset_prepared_path: last_run_prepared
|
|
val_set_size: 0.1
|
|
output_dir: ./outputs/qlora-out
|
|
|
|
adapter: qlora
|
|
lora_model_dir:
|
|
|
|
sequence_len: 2048
|
|
sample_packing: true
|
|
pad_to_sequence_len: true
|
|
|
|
lora_r: 32
|
|
lora_alpha: 16
|
|
lora_dropout: 0
|
|
lora_target_linear: true
|
|
|
|
wandb_project:
|
|
wandb_entity:
|
|
wandb_watch:
|
|
wandb_name:
|
|
wandb_log_model:
|
|
|
|
gradient_accumulation_steps: 4
|
|
micro_batch_size: 2
|
|
num_epochs: 1
|
|
optimizer: adamw_torch
|
|
lr_scheduler: cosine
|
|
learning_rate: 0.0002
|
|
|
|
bf16: auto
|
|
tf32: false
|
|
|
|
gradient_checkpointing: true
|
|
resume_from_checkpoint:
|
|
logging_steps: 1
|
|
flash_attention: true
|
|
|
|
loss_watchdog_threshold: 5.0
|
|
loss_watchdog_patience: 3
|
|
|
|
warmup_ratio: 0.05
|
|
evals_per_epoch: 4
|
|
saves_per_epoch: 1
|
|
|
|
weight_decay: 0.0
|
|
special_tokens:
|