See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: JackFram/llama-160m
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 3532d07b974eef52_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/3532d07b974eef52_train_data.json
  type:
    field_input: code
    field_instruction: question
    field_output: solution
    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: 5
eval_batch_size: 8
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: 12
gradient_checkpointing: true
group_by_length: true
hub_model_id: broodmother41/29191c52-e371-4796-9804-1bb5df3abd9c
hub_repo: null
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: 128
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 64
lora_target_linear: true
lr_scheduler: cosine
max_grad_norm: 1.0
max_steps: 1500
micro_batch_size: 12
mlflow_experiment_name: /tmp/3532d07b974eef52_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 1
optim_args:
  adam_beta1: 0.9
  adam_beta2: 0.95
  adam_epsilon: 1e-5
optimizer: adamw_bnb_8bit
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: 1024
special_tokens:
  pad_token: </s>
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: f6c9a3cc-6228-4ee5-86ba-2d74f374f037
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: f6c9a3cc-6228-4ee5-86ba-2d74f374f037
warmup_steps: 20
weight_decay: 0.0
xformers_attention: null

29191c52-e371-4796-9804-1bb5df3abd9c

This model is a fine-tuned version of JackFram/llama-160m on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.3225

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: 12
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 12
• total_train_batch_size: 144
• optimizer: Use OptimizerNames.ADAMW_BNB 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: 20
• training_steps: 1088

Training results

Training Loss	Epoch	Step	Validation Loss
6.0754	0.0009	1	4.4312
1.6275	0.1380	150	1.9198
1.257	0.2759	300	1.6552
1.1749	0.4139	450	1.5186
1.031	0.5519	600	1.4311
0.9195	0.6898	750	1.3665
0.978	0.8278	900	1.3344
0.9236	0.9657	1050	1.3225

Framework versions

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