See axolotl config

axolotl version: 0.4.1

adapter: lora
auto_find_batch_size: true
base_model: NousResearch/CodeLlama-7b-hf
bf16: auto
chat_template: llama3
dataloader_num_workers: 12
dataset_prepared_path: null
datasets:
- data_files:
  - b64954fcc6e77b0d_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/b64954fcc6e77b0d_train_data.json
  type:
    field_input: input
    field_instruction: instruction
    field_output: output
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: 3
early_stopping_threshold: 0.0001
eval_max_new_tokens: 128
eval_steps: 96
eval_strategy: null
flash_attention: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 2
gradient_checkpointing: false
group_by_length: false
hub_model_id: mrferr3t/4463fa2d-bcef-4d53-8443-d3c7f10564d8
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0004
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 96
lora_alpha: 16
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 8
lora_target_linear: true
lr_scheduler: cosine
max_steps: 
micro_batch_size: 32
mlflow_experiment_name: /tmp/b64954fcc6e77b0d_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 100
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: 
s2_attention: null
sample_packing: false
save_steps: 96
saves_per_epoch: 0
sequence_len: 512
special_tokens:
  pad_token: </s>
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: 
wandb_name: bbdc12a3-1333-4e46-9918-0d4631f90551
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: bbdc12a3-1333-4e46-9918-0d4631f90551
warmup_steps: 100
weight_decay: 0.0
xformers_attention: true

4463fa2d-bcef-4d53-8443-d3c7f10564d8

This model is a fine-tuned version of NousResearch/CodeLlama-7b-hf on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.9914

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: 0.0004
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 64
• optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 100
• num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0054	1	2.6265
2.8198	0.5161	96	1.0719
1.8322	1.0323	192	0.9115
1.4055	1.5484	288	0.8627
1.2677	2.0645	384	0.8888
0.9139	2.5806	480	0.8767
0.9038	3.0968	576	0.9914

Framework versions

• PEFT 0.13.2
• Transformers 4.46.0
• Pytorch 2.5.0+cu124
• Datasets 3.0.1
• Tokenizers 0.20.1