See axolotl config

axolotl version: 0.4.1

adapter: qlora
auto_resume_from_checkpoints: true
base_model: lmsys/vicuna-13b-v1.5
bf16: auto
chat_template: llama3
dataset_prepared_path: null
dataset_processes: 6
datasets:
- data_files:
  - e31d885c5dae4699_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/e31d885c5dae4699_train_data.json
  type:
    field_input: entities
    field_instruction: document_description
    field_output: text
    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: 4
gradient_checkpointing: true
group_by_length: false
hub_model_id: error577/3d16a411-282e-45f0-abe4-44b56d1e3741
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: 1
mlflow_experiment_name: /tmp/e31d885c5dae4699_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: 0.002
wandb_entity: null
wandb_mode: online
wandb_name: 4cf97627-012d-4f22-94cb-2d59103f1d0e
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 4cf97627-012d-4f22-94cb-2d59103f1d0e
warmup_steps: 30
weight_decay: 0.0
xformers_attention: null

3d16a411-282e-45f0-abe4-44b56d1e3741

This model is a fine-tuned version of lmsys/vicuna-13b-v1.5 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.3448

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: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 4
• 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
0.8394	0.0001	1	0.7449
0.4248	0.0134	200	0.3568
0.3586	0.0269	400	0.3421
0.6092	0.0403	600	0.3346
0.344	0.0537	800	0.3333
0.3573	0.0671	1000	0.3325
0.3846	0.0806	1200	0.3288
0.44	0.0940	1400	0.3374
0.3613	0.1074	1600	0.3264
0.4886	0.1208	1800	0.3282
0.4304	0.1343	2000	0.3370
0.4358	0.1477	2200	0.3448

Framework versions

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