See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: NousResearch/CodeLlama-7b-hf
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 3eeea2777a8212e7_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/3eeea2777a8212e7_train_data.json
  type:
    field_instruction: instruction
    field_output: response
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: 4
eval_max_new_tokens: 128
eval_steps: 150
eval_table_size: null
flash_attention: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: false
hub_model_id: Romain-XV/d2394e99-7964-494b-bf3d-eb804e99d43a
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0002
load_best_model_at_end: true
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 128
lora_dropout: 0.3
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 64
lora_target_linear: true
lora_target_modules:
- q_proj
- k_proj
- v_proj
lr_scheduler: cosine
max_grad_norm: 1.0
max_steps: 1344
micro_batch_size: 2
mlflow_experiment_name: /tmp/3eeea2777a8212e7_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 150
sequence_len: 2048
special_tokens:
  pad_token: </s>
strict: false
tf32: true
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.02503755633450175
wandb_entity: null
wandb_mode: online
wandb_name: 1cf249aa-30aa-4b8c-84ee-a1b5a0ed3381
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 1cf249aa-30aa-4b8c-84ee-a1b5a0ed3381
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

d2394e99-7964-494b-bf3d-eb804e99d43a

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: 0.7901

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: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 8
• 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: 10
• training_steps: 1344

Training results

Training Loss	Epoch	Step	Validation Loss
5.2724	0.0000	1	1.2237
3.3999	0.0062	150	0.9080
3.1661	0.0123	300	0.8736
3.3116	0.0185	450	0.8484
3.1214	0.0247	600	0.8300
2.8888	0.0308	750	0.8146
3.5464	0.0370	900	0.8026
2.854	0.0431	1050	0.7941
3.7346	0.0493	1200	0.7901

Framework versions

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