adapter: qlora
base_model: tiiuae/falcon-7b
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 8f073387c42aa48e_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/8f073387c42aa48e_train_data.json
  type:
    field_instruction: topic
    field_output: argument
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: 5
eval_max_new_tokens: 128
eval_steps: 20
eval_table_size: null
flash_attention: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 32
gradient_checkpointing: true
group_by_length: true
hub_model_id: error577/3cc5effd-0d44-4f37-9b8e-2bd72b6ca137
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0005
load_in_4bit: true
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 128
lora_dropout: 0.15
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 64
lora_target_linear: true
lr_scheduler: cosine
micro_batch_size: 1
mlflow_experiment_name: /tmp/8f073387c42aa48e_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optimizer: adamw_torch_fused
output_dir: miner_id_24
pad_to_sequence_len: true
restore_best_weights: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 20
sequence_len: 1024
special_tokens:
  pad_token: <|endoftext|>
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.005
wandb_entity: null
wandb_mode: online
wandb_name: 8d0ff302-a900-427b-ad5c-528836b2745e
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 8d0ff302-a900-427b-ad5c-528836b2745e
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

3cc5effd-0d44-4f37-9b8e-2bd72b6ca137

This model is a fine-tuned version of tiiuae/falcon-7b on the None dataset. It achieves the following results on the evaluation set:

Loss: 2.4173

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: 0.0005
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 32
total_train_batch_size: 32
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
94.8878	0.0011	1	3.5758
67.6042	0.0218	20	2.3959
70.3715	0.0436	40	2.5071
74.3671	0.0654	60	2.3972
74.6497	0.0872	80	2.4058
76.5784	0.1090	100	3.6613
70.9215	0.1308	120	2.4173

Framework versions

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