adapter: lora
base_model: unsloth/codellama-7b
bf16: auto
dataset_prepared_path: null
datasets:
- data_files:
  - d9dc2847fe55f9a2_train_data.json
  ds_type: json
  format: custom
  path: d9dc2847fe55f9a2_train_data.json
  type:
    field: null
    field_input: Link
    field_instruction: Question
    field_output: Answer
    field_system: null
    format: null
    no_input_format: null
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: null
eval_strategy: 'no'
evals_per_epoch: 4
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: false
hub_model_id: taopanda-1/63306c59-da97-4a22-91ac-779ae0bf5e34
learning_rate: 0.0002
load_in_4bit: false
load_in_8bit: true
local_rank: null
logging_steps: 1
lora_alpha: 16
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
lr_scheduler: cosine
max_steps: '2000'
micro_batch_size: 2
model_type: LlamaForCausalLM
num_epochs: 2
optimizer: adamw_bnb_8bit
output_dir: ./outputs/lora-out/taopanda-1_60b86504-c610-4208-96aa-22995728c587
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: true
save_steps: '500'
seed: 23069
sequence_len: 4096
special_tokens:
  bos_token: <s>
  eos_token: </s>
  unk_token: <unk>
strict: false
tf32: false
tokenizer_type: CodeLlamaTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.0
wandb_entity: fatcat87-taopanda
wandb_log_model: null
wandb_mode: online
wandb_name: taopanda-1_60b86504-c610-4208-96aa-22995728c587
wandb_project: subnet56
wandb_runid: taopanda-1_60b86504-c610-4208-96aa-22995728c587
wandb_watch: null
warmup_steps: 5
weight_decay: 0.0
xformers_attention: null

Visualize in Weights & Biases

63306c59-da97-4a22-91ac-779ae0bf5e34

This model is a fine-tuned version of unsloth/codellama-7b on the None 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: 0.0002
train_batch_size: 2
eval_batch_size: 2
seed: 23069
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 4
total_train_batch_size: 32
total_eval_batch_size: 8
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 5
training_steps: 30

Training results

Framework versions

PEFT 0.11.1
Transformers 4.42.3
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.19.1