See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: EleutherAI/gpt-neo-125m
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 77cc533a1da87fc9_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/77cc533a1da87fc9_train_data.json
  type:
    field_input: system
    field_instruction: instruction
    field_output: response
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
device: cuda
early_stopping_patience: 1
eval_max_new_tokens: 128
eval_steps: 5
eval_table_size: null
evals_per_epoch: null
flash_attention: false
fp16: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: true
hub_model_id: cvoffer/9660fe11-625c-4748-85b1-7c2f3b2be139
hub_repo: null
hub_strategy: end
hub_token: null
learning_rate: 0.0002
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 3
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_memory:
  0: 78GiB
max_steps: 30
micro_batch_size: 2
mlflow_experiment_name: /tmp/77cc533a1da87fc9_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 1
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: 10
sequence_len: 1024
special_tokens:
  pad_token: <|endoftext|>
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: true
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: 684c3805-5bf2-48df-8676-fbdd3195ced8
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 684c3805-5bf2-48df-8676-fbdd3195ced8
warmup_steps: 5
weight_decay: 0.001
xformers_attention: true

9660fe11-625c-4748-85b1-7c2f3b2be139

This model is a fine-tuned version of EleutherAI/gpt-neo-125m on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.7260

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: 0.0002
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 8
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 5
• training_steps: 30

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0004	1	2.8323
10.411	0.0020	5	2.8291
10.6035	0.0040	10	2.7993
11.7116	0.0060	15	2.7610
11.2081	0.0080	20	2.7376
11.0049	0.0100	25	2.7283
10.8303	0.0119	30	2.7260

Framework versions

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