Files
axolotl/examples/mistral/mps/lora-mps.yml
NanoCode012 09959fac70 Feat: add Magistral Small 2509 and native mistral3 tokenizer support (#3165)
* feat: update mistral common

* feat: add mistral3processor

* fix: loading

* fix: cast pixel_values to fp32

* fix: image tensor conversion

* feat: add FA2 support for pixtral based models

* fix: update mistral small 3.1 to use native tokenizer

* fix: install tips

* fix: improve info on sample dataset files

* chore: move mistral configs into subfolders

* fix: remove unneeded patch

* fix: indent

* feat: add integration tests

* chore: move

* feat: add magistral 2509 docs and example

* fix: convert tensor to bool

* feat: expand tests

* chore: move tests
2025-09-18 15:42:20 +07:00

69 lines
1.3 KiB
YAML

base_model: mistralai/Mistral-7B-v0.1
# optionally might have model_type or tokenizer_type
model_type: MistralForCausalLM
tokenizer_type: LlamaTokenizer
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name
datasets:
- path: mhenrichsen/alpaca_2k_test
type: alpaca
dataset_prepared_path: last_run_prepared
val_set_size: 0
output_dir: ./outputs/lora-out
eval_sample_packing: false
adapter: lora
lora_model_dir:
sequence_len: 4096
sample_packing: true
lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_target_modules:
- gate_proj
- down_proj
- up_proj
- q_proj
- v_proj
- k_proj
- o_proj
wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 8
micro_batch_size: 1
num_epochs: 2
optimizer: adamw_torch_fused
lr_scheduler: cosine
learning_rate: 0.0002
bf16: auto
fp16: false
tf32: true
gradient_checkpointing: true
resume_from_checkpoint:
logging_steps: 1
flash_attention: false
sdp_attention: true
loss_watchdog_threshold: 5.0
loss_watchdog_patience: 3
warmup_ratio: 0.1
evals_per_epoch: 4
saves_per_epoch: 1
weight_decay: 0.0
special_tokens:
# save_first_step: true # uncomment this to validate checkpoint saving works with your config