Files
axolotl/examples/devstral/devstral-small-qlora.yml
VED 258ce8d4fa feat : scaled softmax support (#3338)
* scaled softmax

* comment

* lint

* remove egear

* validation for flash

* lint

* val imporve + neet

* fix correct softmax scale val(learned)

* learned scale val 4 ssm

* lint

* fix model_type rmv

* sdpa_atten

* test fix + lint

* test fix

* sdp_a val rmv

* flex fix

* main flash

* lint

* flex attn

* lint comment

* fix score_mod

* Update src/axolotl/utils/schemas/validation.py

Co-authored-by: NanoCode012 <kevinvong@rocketmail.com>

---------

Co-authored-by: Ved <ved.work2024@gmail.com>
Co-authored-by: NanoCode012 <kevinvong@rocketmail.com>
2026-01-13 14:33:11 +07:00

68 lines
1.2 KiB
YAML

base_model: mistralai/Devstral-Small-2507
# 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
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
scaling_softmax: 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:
# save_first_step: true # uncomment this to validate checkpoint saving works with your config