See axolotl config

axolotl version: 0.4.1

adapter: lora
auto_find_batch_size: false
base_model: NousResearch/CodeLlama-13b-hf
bf16: auto
chat_template: llama3
dataloader_num_workers: 12
dataset_prepared_path: null
datasets:
- data_files:
  - df148ae60e6052ad_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/df148ae60e6052ad_train_data.json
  type:
    field_instruction: text
    field_output: title
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: 3
early_stopping_threshold: 1.0e-05
eval_max_new_tokens: 128
eval_steps: 216
eval_strategy: null
flash_attention: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 1
gradient_checkpointing: false
group_by_length: false
hub_model_id: mrferr3t/c7b21dba-ac3a-4cd0-ae10-2363fe936b78
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: 216
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: 2
mlflow_experiment_name: /tmp/df148ae60e6052ad_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: null
s2_attention: null
sample_packing: false
save_steps: 216
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: .05000000
wandb_entity: null
wandb_mode: 
wandb_name: e766b42c-1b28-479c-8415-87cc714ac2f5
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: e766b42c-1b28-479c-8415-87cc714ac2f5
warmup_steps: 100
weight_decay: 0.0
xformers_attention: null

c7b21dba-ac3a-4cd0-ae10-2363fe936b78

This model is a fine-tuned version of NousResearch/CodeLlama-13b-hf on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.8765

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: 2
• eval_batch_size: 2
• seed: 42
• 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	0.0009	1	3.3609
1.4672	0.1930	216	0.8772
0.8823	0.3861	432	0.8260
0.8829	0.5791	648	0.7717
0.8202	0.7721	864	0.6872
0.7515	0.9651	1080	0.6267
0.576	1.1582	1296	0.7200
0.4868	1.3512	1512	0.7308
0.5231	1.5442	1728	0.8765

Framework versions

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