See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: tiiuae/falcon-rw-1b
batch_size: 2
bf16: auto
dataset_prepared_path: null
datasets:
- data_files:
  - 4a71a81bf9963904_train_data.json
  ds_type: json
  format: custom
  path: 4a71a81bf9963904_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: 2
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: taopanda-1/9a780296-4d62-4c7f-ba54-ae2ba31ec343
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-1_b7683979-658e-429a-ab3b-266769f33e1a
push_dataset_to_hub: null
resume_from_checkpoint: null
saves_per_epoch: 1
seed: 44816
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-1_b7683979-658e-429a-ab3b-266769f33e1a
wandb_project: subnet56
wandb_runid: taopanda-1_b7683979-658e-429a-ab3b-266769f33e1a
wandb_watch: null
warmup_steps: 40
weight_decay: 0.0
xformers_attention: true

9a780296-4d62-4c7f-ba54-ae2ba31ec343

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: 0.0378

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: 44816
• 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
1.5499	0.0001	1	1.6791
0.1081	0.5000	9320	0.0378

Framework versions

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