See axolotl config

axolotl version: 0.4.1

adapter: lora
auto_resume_from_checkpoints: true
base_model: EleutherAI/pythia-14m
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 39a2a7619b6f1474_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/39a2a7619b6f1474_train_data.json
  type:
    field_instruction: content
    field_output: summary1
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: 4
eval_max_new_tokens: 128
eval_steps: 100
eval_table_size: null
flash_attention: true
dataset_processes: 1
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 2
gradient_checkpointing: false
group_by_length: false
hub_model_id: error577/cab8e368-9316-42bd-b40f-817b565378af
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: 128
lora_dropout: 0.1
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: null
micro_batch_size: 4
mlflow_experiment_name: /tmp/39a2a7619b6f1474_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 10
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: 100
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: 0.0005
wandb_entity: null
wandb_mode: online
wandb_name: d78574b5-6429-4580-9a14-50d625672843
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: d78574b5-6429-4580-9a14-50d625672843
warmup_steps: 30
weight_decay: 0.0
xformers_attention: null

cab8e368-9316-42bd-b40f-817b565378af

This model is a fine-tuned version of EleutherAI/pythia-14m on the None dataset. It achieves the following results on the evaluation set:

• Loss: 8.2058

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: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 2
• 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: 30
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss
11.7044	0.0000	1	5.9029
18.3384	0.0013	100	6.1809
11.3645	0.0026	200	6.3080
21.3634	0.0038	300	6.9268
13.1181	0.0051	400	6.9538
11.6707	0.0064	500	8.2058

Framework versions

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