base_model: mistralai/Mixtral-8x7B-Instruct-v0.1
model_type: AutoModelForCausalLM
tokenizer_type: LlamaTokenizer
is_mistral_derived_model: true
load_in_8bit: false
load_in_4bit: true
strict: false
chat_template: inst

datasets:
  - path: ./data/raw_format/tool_used_training_small.jsonl
    type: sharegpt
    conversation: mistral
  - path: ./data/raw_format/tool_not_used_training_small.jsonl
    type: sharegpt
    conversation: mistral
  - path: ./data/raw_format/no_tools_training_small.jsonl
    type: sharegpt
    conversation: mistral
  - path: ./data/akoksal_lon_form.jsonl
    type: sharegpt
    conversation: mistral
  - path: ./data/dolly.jsonl
    type: sharegpt
    conversation: mistral

dataset_prepared_path: last_run_prepared
val_set_size: 0.01
output_dir: ./mixtral-lora-2-epochs-r64

adapter: qlora
lora_model_dir:

sequence_len: 4096
sample_packing: true
pad_to_sequence_len: true

lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_fan_in_fan_out:
hub_model_id: liuylhf/mixtral-lora-follow-instruction
hub_strategy: end
# lora_target_linear: true
model_config:
  output_router_logits: true
lora_target_modules:
  - q_proj
  - v_proj
  - k_proj
  - o_proj

wandb_project: function-call
wandb_name: mixtral-instruct-raw-data-v3
wandb_log_model: end

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 0.5
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.001
adam_beta2: 0.95
adam_epsilon: 0.00001
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

# loss_watchdog_threshold: 5.0
# loss_watchdog_patience: 3

warmup_steps: 10
# evals_per_epoch: 20
eval_steps: 0.5
save_steps: 0.5
eval_table_size:
eval_max_new_tokens: 256
# saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0

mixtral-lora-follow-instruction

This model is a fine-tuned version of mistralai/Mixtral-8x7B-Instruct-v0.1 on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.6506

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: 0.001
train_batch_size: 2
eval_batch_size: 2
seed: 42
distributed_type: multi-GPU
num_devices: 2
gradient_accumulation_steps: 4
total_train_batch_size: 16
total_eval_batch_size: 4
optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 10
num_epochs: 0.5

Training results

Training Loss	Epoch	Step	Validation Loss
4.0028	0.01	1	4.1157
0.6411	0.25	39	0.6506

Framework versions

PEFT 0.8.2
Transformers 4.39.0.dev0
Pytorch 2.2.0+cu121
Datasets 2.17.1
Tokenizers 0.15.0