See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: codellama/CodeLlama-7b-Instruct-hf
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 63c42ba40d1682d1_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/63c42ba40d1682d1_train_data.json
  type:
    field_instruction: summary
    field_output: infobox
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: null
eval_max_new_tokens: 128
eval_table_size: null
evals_per_epoch: 4
flash_attention: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: false
hub_model_id: ardaspear/9f1775bb-fcf2-4d2e-8561-d663935d6039
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0001
load_in_4bit: false
load_in_8bit: false
local_rank: 0
logging_steps: 3
lora_alpha: 64
lora_dropout: 0.1
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
lr_scheduler: cosine
max_memory:
  0: 72GB
max_steps: 50
micro_batch_size: 4
mlflow_experiment_name: /tmp/63c42ba40d1682d1_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: false
sample_packing: false
saves_per_epoch: 4
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: leixa-personal
wandb_mode: online
wandb_name: 9f1775bb-fcf2-4d2e-8561-d663935d6039
wandb_project: Gradients-On-Five
wandb_run: your_name
wandb_runid: 9f1775bb-fcf2-4d2e-8561-d663935d6039
warmup_steps: 10
weight_decay: 0.01
xformers_attention: null

9f1775bb-fcf2-4d2e-8561-d663935d6039

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

• Loss: nan

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: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 4
• 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: 10
• training_steps: 50

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0090	1	nan
0.0	0.0449	5	nan
0.0	0.0899	10	nan
0.0	0.1348	15	nan
0.0	0.1798	20	nan
0.0	0.2247	25	nan
0.0	0.2697	30	nan
0.0	0.3146	35	nan
0.0	0.3596	40	nan
0.0	0.4045	45	nan
0.0	0.4494	50	nan

Framework versions

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