See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: llamafactory/tiny-random-Llama-3
bf16: auto
chat_template: llama3
data_processes: 16
dataset_prepared_path: null
datasets:
- data_files:
  - f3da94acd2c26ae7_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/f3da94acd2c26ae7_train_data.json
  type:
    field_instruction: question
    field_output: answers
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
device_map: auto
do_eval: true
early_stopping_patience: 1
eval_batch_size: 8
eval_max_new_tokens: 128
eval_steps: 25
eval_table_size: null
evals_per_epoch: null
flash_attention: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 32
gradient_checkpointing: true
group_by_length: true
hub_model_id: nttx/d8f5457e-ab43-4e9e-89f2-06e312608b90
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0003
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 32
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 16
lora_target_linear: true
lr_scheduler: cosine
max_grad_norm: 1.0
max_memory:
  0: 70GB
max_steps: 200
micro_batch_size: 1
mlflow_experiment_name: /tmp/f3da94acd2c26ae7_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optim_args:
  adam_beta1: 0.9
  adam_beta2: 0.95
  adam_epsilon: 1e-5
optimizer: adamw_torch
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 50
saves_per_epoch: null
sequence_len: 1028
special_tokens:
  pad_token: <|eot_id|>
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 50
wandb_entity: null
wandb_mode: online
wandb_name: d8f5457e-ab43-4e9e-89f2-06e312608b90
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: d8f5457e-ab43-4e9e-89f2-06e312608b90
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

d8f5457e-ab43-4e9e-89f2-06e312608b90

This model is a fine-tuned version of llamafactory/tiny-random-Llama-3 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 11.6238

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: 0.0003
• train_batch_size: 1
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 32
• total_train_batch_size: 32
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.95,adam_epsilon=1e-5
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 10
• training_steps: 200

Training results

Training Loss	Epoch	Step	Validation Loss
11.7564	0.0001	1	11.7570
11.7136	0.0029	25	11.7204
11.6284	0.0058	50	11.6545
11.6323	0.0086	75	11.6352
11.6151	0.0115	100	11.6292
11.6265	0.0144	125	11.6254
11.602	0.0173	150	11.6237
11.6244	0.0201	175	11.6238

Framework versions

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