See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: unsloth/llama-2-7b
bf16: auto
chat_template: llama3
cosine_min_lr_ratio: 0.1
data_processes: 16
dataset_prepared_path: null
datasets:
- data_files:
  - 995951483a6d6a92_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/995951483a6d6a92_train_data.json
  type:
    field_instruction: en_sentence
    field_output: ja_sentence
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
device_map: '{'''':torch.cuda.current_device()}'
do_eval: true
early_stopping_patience: 1
eval_batch_size: 1
eval_sample_packing: false
eval_steps: 25
evaluation_strategy: steps
flash_attention: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 64
gradient_checkpointing: true
group_by_length: true
hub_model_id: sn56b1/5b953b7c-ad8d-4198-b1dd-e84398e4990e
hub_repo: stevemonite
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0001
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 64
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
lora_target_modules:
- q_proj
- k_proj
- v_proj
- o_proj
- gate_proj
- down_proj
- up_proj
lr_scheduler: cosine
max_grad_norm: 1.0
max_memory:
  0: 70GiB
max_steps: 342
micro_batch_size: 1
mlflow_experiment_name: /tmp/995951483a6d6a92_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
save_strategy: steps
sequence_len: 2056
strict: false
tf32: false
tokenizer_type: AutoTokenizer
torch_compile: false
train_on_inputs: false
trust_remote_code: true
val_set_size: 50
wandb_entity: sn56-miner
wandb_mode: disabled
wandb_name: 5b953b7c-ad8d-4198-b1dd-e84398e4990e
wandb_project: god
wandb_run: vl08
wandb_runid: 5b953b7c-ad8d-4198-b1dd-e84398e4990e
warmup_raio: 0.03
warmup_ratio: 0.04
weight_decay: 0.01
xformers_attention: null

5b953b7c-ad8d-4198-b1dd-e84398e4990e

This model is a fine-tuned version of unsloth/llama-2-7b on the None dataset. It achieves the following results on the evaluation set:

• Loss: nan

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: 0.0001
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 64
• total_train_batch_size: 256
• total_eval_batch_size: 4
• 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: 11
• training_steps: 281

Training results

Training Loss	Epoch	Step	Validation Loss
0.0	0.0107	1	nan
0.0	0.2675	25	nan
0.0	0.5350	50	nan
0.0	0.8025	75	nan

Framework versions

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