See axolotl config

axolotl version: 0.4.1

adapter: qlora
base_model: EleutherAI/gpt-neo-1.3B
bf16: auto
chat_template: llama3
dataloader_num_workers: 6
dataset_prepared_path: null
datasets:
- data_files:
  - 32cf61f12c8b4c22_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/32cf61f12c8b4c22_train_data.json
  type:
    field_input: input
    field_instruction: instruction
    field_output: output
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping:
  metric: eval_loss
  mode: min
  patience: 3
eval_max_new_tokens: 128
eval_steps: 20
eval_table_size: null
evals_per_epoch: null
flash_attention: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 16
gradient_checkpointing: true
group_by_length: true
hub_model_id: error577/d812ccbf-2b40-4bb7-a951-21c412b54967
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0003
load_in_4bit: true
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 64
lora_dropout: 0.3
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
lr_scheduler: cosine
max_grad_norm: 1.0
max_steps: 300
micro_batch_size: 1
mlflow_experiment_name: /tmp/32cf61f12c8b4c22_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 50
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: 20
sequence_len: 512
special_tokens:
  pad_token: <|endoftext|>
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.02
wandb_entity: null
wandb_mode: online
wandb_name: 2e6bda4a-e88c-4677-a36d-3d29f849c380
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 2e6bda4a-e88c-4677-a36d-3d29f849c380
warmup_steps: 10
weight_decay: 0.01
xformers_attention: null

d812ccbf-2b40-4bb7-a951-21c412b54967

This model is a fine-tuned version of EleutherAI/gpt-neo-1.3B on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.0239

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: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 16
• optimizer: Use OptimizerNames.ADAMW_BNB 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: 300

Training results

Training Loss	Epoch	Step	Validation Loss
31.8352	0.0017	1	2.3466
24.0002	0.0335	20	1.4193
18.1259	0.0670	40	1.3105
20.3449	0.1005	60	1.2982
18.4843	0.1340	80	1.1776
15.1067	0.1675	100	1.2319
16.9593	0.2010	120	1.1272
15.7509	0.2345	140	1.1026
17.9105	0.2680	160	1.1434
16.1038	0.3015	180	1.0748
16.3666	0.3350	200	1.0887
16.7504	0.3685	220	1.0800
14.2973	0.4021	240	1.0353
18.3425	0.4356	260	1.0315
15.6136	0.4691	280	1.0244
14.6577	0.5026	300	1.0239

Framework versions

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