base_model: Maykeye/TinyLLama-v0
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
load_in_8bit: true
load_in_4bit: false
strict: false
chat_template: chatml
datasets:
- path: /workspace/input_data/3f3fa868c0c784c4_train_data.json
  format: custom
  type:
    system_prompt: ''
    system_format: '{system}'
    field_instruction: query
    field_input: equation
    field_output: response
    no_input_format: '{instruction}'
    format: '{instruction} {input}'
  ds_type: json
  data_files:
  - 3f3fa868c0c784c4_train_data.json
dataset_prepared_path: null
val_set_size: 0.05
output_dir: miner_id_e0428bac-e71b-40ed-b453-d7547b91824d
sequence_len: 4056
sample_packing: false
pad_to_sequence_len: true
trust_remote_code: true
adapter: lora
lora_model_dir: null
lora_r: 16
lora_alpha: 32
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out: null
gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 1
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0002
train_on_inputs: false
group_by_length: false
bf16: auto
fp16: null
tf32: false
gradient_checkpointing: false
early_stopping_patience: null
resume_from_checkpoint: null
local_rank: null
logging_steps: 1
xformers_attention: null
flash_attention: true
s2_attention: null
wandb_project: Gradients-On-Demand
wandb_entity: prongsie
wandb_mode: online
wandb_run: your_name
wandb_runid: default
hub_model_id: tensor24/miner_id_e0428bac-e71b-40ed-b453-d7547b91824d
hub_repo: tensor24/miner_id_e0428bac-e71b-40ed-b453-d7547b91824d
hub_strategy: checkpoint
hub_token: null
saves_per_epoch: 4
warmup_steps: 10
evals_per_epoch: 4
eval_table_size: null
eval_max_new_tokens: 128
max_steps: 10
debug: null
deepspeed: null
weight_decay: 0.0
fsdp: null
fsdp_config: null
tokenizer_config: Maykeye/TinyLLama-v0
mlflow_experiment_name: /tmp/3f3fa868c0c784c4_train_data.json

miner_id_e0428bac-e71b-40ed-b453-d7547b91824d

This model is a fine-tuned version of Maykeye/TinyLLama-v0 on the None dataset. It achieves the following results on the evaluation set:

Loss: 6.9799

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: 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: 10
training_steps: 10

Training results

Training Loss	Epoch	Step	Validation Loss
7.7466	0.0093	1	7.7405
7.5346	0.0280	3	7.7041
6.9106	0.0561	6	7.3868
7.3138	0.0841	9	6.9799

Framework versions

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