adapter: lora
base_model: unsloth/SmolLM-360M
bf16: true
chat_template: llama3
dataloader_num_workers: 6
dataset_prepared_path: null
datasets:
- data_files:
  - 3c93a9b743c88ef1_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/3c93a9b743c88ef1_train_data.json
  type:
    field_instruction: instruction
    field_output: response
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: 3
eval_max_new_tokens: 128
eval_steps: 20
eval_table_size: null
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 8
gradient_checkpointing: false
group_by_length: false
hub_model_id: error577/3879cab7-641e-4b47-b66d-acf1b3e1ba35
hub_repo: null
hub_strategy: end
hub_token: null
learning_rate: 0.0002
load_in_4bit: false
load_in_8bit: true
local_rank: null
logging_steps: 1
lora_alpha: 16
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_steps: 100
micro_batch_size: 2
mlflow_experiment_name: /tmp/3c93a9b743c88ef1_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 4
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: 1024
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: f859b220-fbed-4154-88a3-f8364e11434f
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: f859b220-fbed-4154-88a3-f8364e11434f
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

3879cab7-641e-4b47-b66d-acf1b3e1ba35

This model is a fine-tuned version of unsloth/SmolLM-360M on the None dataset. It achieves the following results on the evaluation set:

Loss: 1.4144

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: 8
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: 100

Training results

Training Loss	Epoch	Step	Validation Loss
1.8984	0.0006	1	1.9493
1.8595	0.0122	20	1.7981
1.5078	0.0245	40	1.5574
1.4617	0.0367	60	1.4578
1.3566	0.0490	80	1.4209
1.3537	0.0612	100	1.4144

Framework versions

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