See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: lmsys/vicuna-7b-v1.5
bf16: true
chat_template: llama3
dataloader_num_workers: 24
dataset_prepared_path: null
datasets:
- data_files:
  - df7f1ea13237a221_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/df7f1ea13237a221_train_data.json
  type:
    field_input: document_title
    field_instruction: question
    field_output: answer
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
device_map: auto
do_eval: true
early_stopping_patience: 3
eval_batch_size: 2
eval_max_new_tokens: 128
eval_steps: 150
eval_table_size: null
evals_per_epoch: null
flash_attention: true
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 8
gradient_checkpointing: false
group_by_length: true
hub_model_id: alchemist69/ac2f02cd-67a9-4af1-8c46-09bec0ff0128
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0002
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 50
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: 3000
micro_batch_size: 2
mlflow_experiment_name: /tmp/df7f1ea13237a221_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 10
optim_args:
  adam_beta1: 0.9
  adam_beta2: 0.999
  adam_epsilon: 1e-8
optimizer: adamw_torch_fused
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 150
saves_per_epoch: null
sequence_len: 512
strict: false
tf32: true
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: c7d658ca-3069-4d72-9644-63c38a2389b8
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: c7d658ca-3069-4d72-9644-63c38a2389b8
warmup_steps: 50
weight_decay: 0.0
xformers_attention: null

ac2f02cd-67a9-4af1-8c46-09bec0ff0128

This model is a fine-tuned version of lmsys/vicuna-7b-v1.5 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.4639

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: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 16
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.999,adam_epsilon=1e-8
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 50
• training_steps: 3000

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0006	1	2.5583
1.6067	0.0868	150	1.6457
1.5446	0.1736	300	1.6045
1.5953	0.2604	450	1.5722
1.4934	0.3472	600	1.5525
1.5136	0.4340	750	1.5347
1.534	0.5208	900	1.5193
1.5247	0.6076	1050	1.5018
1.474	0.6943	1200	1.4797
1.4343	0.7811	1350	1.4673
1.4209	0.8679	1500	1.4514
1.4348	0.9547	1650	1.4322
0.9143	1.0415	1800	1.4642
0.8897	1.1283	1950	1.4691
0.8882	1.2151	2100	1.4639

Framework versions

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