See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: HuggingFaceM4/tiny-random-LlamaForCausalLM
bf16: auto
chat_template: llama3
data_processes: 16
dataset_prepared_path: null
datasets:
- data_files:
  - e5a3ce2c4d0b4f05_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/e5a3ce2c4d0b4f05_train_data.json
  type:
    field_input: idiom
    field_instruction: sentence
    field_output: usage
    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: 1
eval_batch_size: 8
eval_max_new_tokens: 128
eval_steps: 25
eval_table_size: null
evals_per_epoch: null
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: true
hub_model_id: sn56b2/f7b5075a-a5de-43b4-9f70-e95544a8dfb6
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: 8
mlflow_experiment_name: /tmp/e5a3ce2c4d0b4f05_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 2
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
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 50
wandb_entity: sn56-miner
wandb_mode: disabled
wandb_name: f7b5075a-a5de-43b4-9f70-e95544a8dfb6
wandb_project: god
wandb_run: 8b9l
wandb_runid: f7b5075a-a5de-43b4-9f70-e95544a8dfb6
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

f7b5075a-a5de-43b4-9f70-e95544a8dfb6

This model is a fine-tuned version of HuggingFaceM4/tiny-random-LlamaForCausalLM on the None dataset. It achieves the following results on the evaluation set:

• Loss: 10.0675

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: 8
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 4
• total_train_batch_size: 128
• total_eval_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
10.3427	0.0029	1	10.3341
10.2747	0.0722	25	10.2657
10.1545	0.1444	50	10.1410
10.121	0.2166	75	10.0970
10.0897	0.2888	100	10.0820
10.0795	0.3610	125	10.0737
10.0766	0.4332	150	10.0690
10.0732	0.5054	175	10.0684
10.0696	0.5776	200	10.0675

Framework versions

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