See axolotl config

axolotl version: 0.4.1

adapter: qlora
auto_resume_from_checkpoints: true
base_model: berkeley-nest/Starling-LM-7B-alpha
bf16: auto
chat_template: llama3
dataset_prepared_path: null
dataset_processes: 6
datasets:
- data_files:
  - 2249b20683fd84f7_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/2249b20683fd84f7_train_data.json
  type:
    field_input: all_generated_responses
    field_instruction: prompt
    field_output: prompt_id
    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: 200
eval_table_size: null
evals_per_epoch: null
flash_attention: true
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 1
gradient_checkpointing: true
group_by_length: false
hub_model_id: error577/18544a08-dcda-4e0d-bbdd-6d81ab527732
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0002
load_in_4bit: true
load_in_8bit: false
local_rank: null
logging_steps: 1
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_grad_norm: 1.0
max_steps: null
micro_batch_size: 4
mlflow_experiment_name: /tmp/2249b20683fd84f7_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optimizer: adamw_torch_4bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 200
sequence_len: 512
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.003
wandb_entity: null
wandb_mode: online
wandb_name: 0424100c-66c0-4847-a695-88d796c16444
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 0424100c-66c0-4847-a695-88d796c16444
warmup_steps: 30
weight_decay: 0.0
xformers_attention: null

18544a08-dcda-4e0d-bbdd-6d81ab527732

This model is a fine-tuned version of berkeley-nest/Starling-LM-7B-alpha on the None dataset. It achieves the following results on the evaluation set:

• Loss: 3.0428

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: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_4BIT 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: 30
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
4.0919	0.0001	1	4.0121
3.0783	0.0132	200	3.0437
3.0679	0.0264	400	3.0835
3.1476	0.0397	600	3.0390
3.0362	0.0529	800	3.0649
3.029	0.0661	1000	3.0664
2.9824	0.0793	1200	3.0428

Framework versions

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