See axolotl config

axolotl version: 0.9.2

base_model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only
#base_model_ignore_patterns: "consolidated.safetensors"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: NewEden/magnum-v5-sft-prototype-ms3.2-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NewEden/magnum-v5-sft-proto-mistral-v7-tekken-rev1-32k
    ds_type: parquet
    type:
shuffle_merged_datasets: true
dataset_prepared_path: ./magnum-24b-data
val_set_size: 0.0
output_dir: ./magnum-24b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 24b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name: 24b-magnum-lora-mistral-3.2
wandb_log_model:

gradient_accumulation_steps: 16
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 2e-5
max_grad_norm: 1.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:

magnum-v5-sft-prototype-ms3.2-lora

This model is a fine-tuned version of anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only on the NewEden/magnum-v5-sft-proto-mistral-v7-tekken-rev1-32k dataset.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e-05
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 16
• optimizer: Use paged_ademamix_8bit and the args are: No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 40
• num_epochs: 2.0

Training results

Framework versions

• PEFT 0.15.2
• Transformers 4.51.3
• Pytorch 2.7.1+cu128
• Datasets 3.5.1
• Tokenizers 0.21.1