See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: NousResearch/CodeLlama-7b-hf-flash
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 1e0e167bddc4af81_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/1e0e167bddc4af81_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
device: cuda
early_stopping_patience: null
eval_max_new_tokens: 128
eval_table_size: null
evals_per_epoch: 4
flash_attention: false
fp16: null
gradient_accumulation_steps: 4
gradient_checkpointing: false
group_by_length: false
hub_model_id: kokovova/0ca74a48-513c-4cfe-9867-47e7787f9ddc
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0001
load_in_4bit: false
load_in_8bit: false
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: 8
lora_target_linear: true
lr_scheduler: cosine
max_memory:
  0: 75GiB
max_steps: 15
micro_batch_size: 2
mlflow_experiment_name: /tmp/1e0e167bddc4af81_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optimizer: adamw_torch
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 5
sequence_len: 1024
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: online
wandb_name: 0ca74a48-513c-4cfe-9867-47e7787f9ddc
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 0ca74a48-513c-4cfe-9867-47e7787f9ddc
warmup_steps: 5
weight_decay: 0.1
xformers_attention: true

0ca74a48-513c-4cfe-9867-47e7787f9ddc

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

• Loss: 1.4605

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: 0.0001
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 8
• optimizer: Use OptimizerNames.ADAMW_TORCH 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: 5
• training_steps: 15

Training results

Training Loss	Epoch	Step	Validation Loss
6.1151	0.0020	1	1.5243
6.2336	0.0040	2	1.5242
6.2151	0.0080	4	1.5223
6.2224	0.0120	6	1.5145
5.6233	0.0161	8	1.4976
5.4797	0.0201	10	1.4783
5.7392	0.0241	12	1.4654
5.9203	0.0281	14	1.4605

Framework versions

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