See axolotl config

axolotl version: 0.4.1

adapter: lora
auto_find_batch_size: true
base_model: EleutherAI/gpt-neo-1.3B
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - e5625f7766855655_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/e5625f7766855655_train_data.json
  type:
    field_instruction: chat
    field_output: text
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
do_eval: true
eval_max_new_tokens: 128
eval_steps: 50
evals_per_epoch: null
flash_attention: false
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
gradient_clipping: 1.0
group_by_length: false
hub_model_id: lesso18/8bb2f01b-f878-43ed-a4da-9e613e1cc717
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 5.0e-05
load_in_4bit: true
load_in_8bit: true
local_rank: null
logging_steps: 10
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_steps: 500
micro_batch_size: 2
mlflow_experiment_name: /tmp/e5625f7766855655_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 1
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: 50
saves_per_epoch: null
seed: 180
sequence_len: 512
special_tokens:
  pad_token: <|endoftext|>
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
use_cache: false
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: 6bb1ae2c-eec7-426b-8297-d030ba828c03
wandb_project: 18a
wandb_run: your_name
wandb_runid: 6bb1ae2c-eec7-426b-8297-d030ba828c03
warmup_steps: 50
weight_decay: 0.01
xformers_attention: true

8bb2f01b-f878-43ed-a4da-9e613e1cc717

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: 0.0228

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: 5e-05
• train_batch_size: 2
• eval_batch_size: 2
• seed: 180
• gradient_accumulation_steps: 4
• total_train_batch_size: 8
• 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: 50
• training_steps: 500

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0001	1	0.7158
1.473	0.0037	50	0.2752
0.2149	0.0075	100	0.0498
0.1639	0.0112	150	0.0372
0.117	0.0149	200	0.0313
0.1046	0.0187	250	0.0275
0.131	0.0224	300	0.0252
0.0879	0.0262	350	0.0240
0.1083	0.0299	400	0.0232
0.0834	0.0336	450	0.0228
0.0909	0.0374	500	0.0228

Framework versions

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