See axolotl config

axolotl version: 0.4.1

adapter: lora
auto_find_batch_size: true
base_model: NousResearch/CodeLlama-7b-hf-flash
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 68126dc6c922929d_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/68126dc6c922929d_train_data.json
  type:
    field_input: metadata
    field_instruction: topic
    field_output: prompt
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: 3
eval_max_new_tokens: 128
eval_steps: 50
eval_table_size: null
flash_attention: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 8
gradient_checkpointing: false
group_by_length: true
hub_model_id: tuantmdev/4605e6f7-f791-43c8-afcd-f380768bbcf0
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 1e-4
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 40
lora_alpha: 64
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_grad_norm: 1.0
max_steps: 400
micro_batch_size: 2
mlflow_experiment_name: /tmp/68126dc6c922929d_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 1
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: 50
save_strategy: steps
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: online
wandb_name: d6e52fb4-2684-483d-9de0-7fc8ced2855c
wandb_project: Gradients-On-Demand
wandb_run: unknown
wandb_runid: d6e52fb4-2684-483d-9de0-7fc8ced2855c
warmup_steps: 80
weight_decay: 0.0
xformers_attention: null

4605e6f7-f791-43c8-afcd-f380768bbcf0

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: 2.2648

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: 8
• total_train_batch_size: 16
• 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: 80
• training_steps: 400

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0017	1	3.1104
19.6782	0.0839	50	2.5086
18.273	0.1679	100	2.4641
18.2049	0.2518	150	2.4177
20.0164	0.3358	200	2.3485
17.856	0.4197	250	2.3001
17.2507	0.5037	300	2.2563
17.8261	0.5876	350	2.2642
19.4166	0.6716	400	2.2648

Framework versions

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