See axolotl config

axolotl version: 0.6.0

adapter: lora
base_model: EleutherAI/gpt-neo-125m
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 7b998b3798810931_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/7b998b3798810931_train_data.json
  type:
    field_input: context
    field_instruction: prompt_serial
    field_output: hypothesis
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: null
eval_max_new_tokens: 128
eval_table_size: null
evals_per_epoch: 4
flash_attention: false
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 16
gradient_checkpointing: false
group_by_length: true
hub_model_id: jssky/6d7768e6-b1a4-4dd3-a233-a99d685456f6
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0002
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 16
lora_dropout: 0.05
lora_fan_in_fan_out: false
lora_inference_mode: true
lora_model_dir: null
lora_modules_to_save:
- lm_head
lora_r: 8
lora_target_linear: true
lr_scheduler: cosine
max_grad_norm: 1.0
max_steps: 1500
micro_batch_size: 2
mlflow_experiment_name: /tmp/7b998b3798810931_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 1
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
peft_use_rslora: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
saves_per_epoch: 4
sequence_len: 1024
special_tokens:
  pad_token: <|endoftext|>
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: c08c1e63-7861-46f7-8cb3-d4b374cdfd7b
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: c08c1e63-7861-46f7-8cb3-d4b374cdfd7b
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

6d7768e6-b1a4-4dd3-a233-a99d685456f6

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: 0.0002

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: 16
• total_train_batch_size: 32
• optimizer: Use adamw_bnb_8bit 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: 10
• training_steps: 1182

Training results

Training Loss	Epoch	Step	Validation Loss
0.0005	0.2505	296	0.0017
0.0002	0.5010	592	0.0002
0.0001	0.7515	888	0.0002

Framework versions

• PEFT 0.14.0
• Transformers 4.46.3
• Pytorch 2.5.1+cu124
• Datasets 3.1.0
• Tokenizers 0.20.3