See axolotl config

axolotl version: 0.10.0.dev0

base_model: Dans-DiscountModels/Mistral-Small-3.1-24B-Base-2503-hf-DanChat
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code:

# wandb configuration
wandb_project: 24b-ms-dans-personality-engine
wandb_watch:

wandb_run_id: V1.3.0-1-5 # V{Version}-{Run Number}-{Attempt Number}
wandb_log_model:

# push checkpoints to hub
hub_model_id: Dans-DiscountModels/24b-ms-dans-personality-engine-v1.3.0-TestArticle-1
# how to push checkpoints to hub
# https://huggingface.co/docs/transformers/v4.31.0/en/main_classes/trainer#transformers.TrainingArguments.hub_strategy
hub_strategy: "every_save"
# Whether to use hf `use_auth_token` for loading datasets. Useful for fetching private datasets
# Required to be true when used in combination with `push_dataset_to_hub`
hf_use_auth_token: true

# where to save the finished model to
output_dir: ./24b-ms-dans-personality-engine

save_safetensors: true

datasets:
  - path: Dans-DiscountModels/pretokenization-test-6
    ds_type: parquet
    type:

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

load_in_8bit: false
load_in_4bit: false
strict: false

adapter:
lora_model_dir:

dataset_prepared_path: ./24b-ms-dans-personality-engine
val_set_size: 0.0

sequence_len: 33000

sample_packing: true
eval_sample_packing: true

pad_to_sequence_len: true

gradient_checkpointing: true

gradient_accumulation_steps: 4
micro_batch_size: 1

num_epochs: 2

optimizer: ademamix_8bit
optim_args: "beta1=0.9,beta2=0.999,beta3=0.999,alpha=5"

lr_scheduler: rex
learning_rate: 0.000001
cosine_min_lr_ratio:

max_grad_norm: 0.001

train_on_inputs: false
group_by_length: false

bf16: true
fp16: false
tf32: false

early_stopping_patience:

resume_from_checkpoint:
auto_resume_from_checkpoints: false

local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_ratio: 0.1

evals_per_epoch: 24
eval_table_size:
eval_max_new_tokens:

saves_per_epoch: 4
save_total_limit: 1

debug: false

deepspeed: deepspeed_configs/zero3_bf16.json

fsdp:
fsdp_config:

special_tokens:

24b-ms-dans-personality-engine-v1.3.0-TestArticle-1

This model is a fine-tuned version of Dans-DiscountModels/Mistral-Small-3.1-24B-Base-2503-hf-DanChat on the Dans-DiscountModels/pretokenization-test-6 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: 1e-06
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• total_eval_batch_size: 8
• optimizer: Use ademamix_8bit and the args are: beta1=0.9,beta2=0.999,beta3=0.999,alpha=5
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 338
• num_epochs: 2.0

Training results

Framework versions

• Transformers 4.51.3
• Pytorch 2.4.1+cu121
• Datasets 3.5.1
• Tokenizers 0.21.1