See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: unsloth/Meta-Llama-3.1-8B-Instruct
bf16: auto
chat_template: llama3
dataloader_num_workers: 12
dataset_prepared_path: null
datasets:
- data_files:
  - 8f43695c624b17f7_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/8f43695c624b17f7_train_data.json
  type:
    field_input: ''
    field_instruction: en_US
    field_output: de_DE
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
device_map: auto
do_eval: true
early_stopping_patience: 2
eval_batch_size: 4
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: 4
gradient_checkpointing: true
group_by_length: true
hub_model_id: nttx/0b4b1071-701f-43fa-9a69-c3194ac561dd
hub_repo: null
hub_strategy: end
hub_token: null
learning_rate: 5.0e-05
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 10
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: 75GB
max_steps: 1200
micro_batch_size: 4
mlflow_experiment_name: /tmp/8f43695c624b17f7_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 10
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: 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: 31aa5a8b-15d8-4603-ac95-354afbca7bac
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 31aa5a8b-15d8-4603-ac95-354afbca7bac
warmup_steps: 50
weight_decay: 0.0
xformers_attention: null

0b4b1071-701f-43fa-9a69-c3194ac561dd

This model is a fine-tuned version of unsloth/Meta-Llama-3.1-8B-Instruct on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.7028

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: 5e-05
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• 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: 50
• training_steps: 1200

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0010	1	5.7027
1.0139	0.1538	150	0.9292
0.9205	0.3077	300	0.8236
0.7007	0.4615	450	0.7849
0.7204	0.6154	600	0.7462
0.7861	0.7692	750	0.7289
0.7518	0.9231	900	0.7094
0.6121	1.0769	1050	0.7037
0.5586	1.2308	1200	0.7028

Framework versions

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