adapter: lora
base_model: tiiuae/falcon-rw-1b
batch_size: 2
bf16: auto
dataset_prepared_path: null
datasets:
- data_files:
  - 4216a06bafbd436d_train_data.json
  ds_type: json
  format: custom
  path: 4216a06bafbd436d_train_data.json
  type:
    field: null
    field_input: Context
    field_instruction: Question
    field_output: Answer
    field_system: null
    format: null
    no_input_format: null
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: null
evals_per_epoch: 4
flash_attention: null
fp16: null
fsdp: null
fsdp_config: null
gptq: false
gptq_groupsize: null
gptq_model_v1: null
gradient_checkpointing: true
group_by_length: false
hub_model_id: FatCat87/taopanda-2_b3db347c-a6bb-4682-9904-41bfd73f101a
learning_rate: 3.0e-05
load_in_4bit: false
load_in_8bit: true
local_rank: null
logging_steps: 1
lora_alpha: 32
lora_dropout: 0.0
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 16
lora_target_linear: true
lora_target_modules: null
lr_scheduler: cosine
max_packed_sequence_len: null
micro_batch_size: 1
model_type: AutoModelForCausalLM
num_epochs: 1
optimizer: adamw_bnb_8bit
output_dir: ./outputs/falcon-7b/taopanda-2_b3db347c-a6bb-4682-9904-41bfd73f101a
push_dataset_to_hub: null
resume_from_checkpoint: null
saves_per_epoch: 1
seed: 58124
sequence_len: 2048
special_tokens:
  pad_token: <|endoftext|>
strict: false
tf32: true
tokenizer_type: AutoTokenizer
torchdistx_path: null
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: fatcat87-taopanda
wandb_log_model: null
wandb_mode: online
wandb_name: taopanda-2_b3db347c-a6bb-4682-9904-41bfd73f101a
wandb_project: subnet56
wandb_runid: taopanda-2_b3db347c-a6bb-4682-9904-41bfd73f101a
wandb_watch: null
warmup_steps: 40
weight_decay: 0.0
xformers_attention: true

Visualize in Weights & Biases

taopanda-2_b3db347c-a6bb-4682-9904-41bfd73f101a

This model is a fine-tuned version of tiiuae/falcon-rw-1b on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.4245

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: 3e-05
train_batch_size: 1
eval_batch_size: 1
seed: 58124
distributed_type: multi-GPU
num_devices: 4
total_train_batch_size: 4
total_eval_batch_size: 4
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 40
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
5.5975	0.0003	1	4.1179
0.27	0.2501	957	0.5492
0.3738	0.5001	1914	0.4590
0.1297	0.7502	2871	0.4245

Framework versions

PEFT 0.11.1
Transformers 4.42.3
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.19.1