You can deploy this model and start earning money today!

taopanda-4/
468ca133-4214-4539-a14f-1b1ee5704fe0

Name: 468ca133-4214-4539-a14f-1b1ee5704fe0
Availability: InStock

generated_from_trainer

Qwen/Qwen1.5-0.5B

adapter

other

Views

No views yet

See axolotl config

axolotl version: 0.4.1

yaml

adapter: lora
base_model: Qwen/Qwen1.5-0.5B
bf16: auto
dataset_prepared_path: null
datasets:
- data_files:
  - 223a29e970e70cf2_train_data.json
  ds_type: json
  format: custom
  path: 223a29e970e70cf2_train_data.json
  type:
    field: null
    field_input: null
    field_instruction: Question
    field_output: A
    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: 1
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
group_by_length: false
hub_model_id: taopanda-4/468ca133-4214-4539-a14f-1b1ee5704fe0
learning_rate: 0.0002
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 16
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
lr_scheduler: cosine
micro_batch_size: 1
num_epochs: 2
optimizer: paged_adamw_8bit
output_dir: ./outputs/out/taopanda-4_8cc33ac9-f924-455b-8b96-1103a51c90b5
pad_to_sequence_len: false
resume_from_checkpoint: null
sample_packing: false
saves_per_epoch: 1
seed: 61157
sequence_len: 1024
special_tokens: null
strict: false
tf32: true
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-4_8cc33ac9-f924-455b-8b96-1103a51c90b5
wandb_project: subnet56
wandb_runid: taopanda-4_8cc33ac9-f924-455b-8b96-1103a51c90b5
wandb_watch: null
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

Visualize in Weights & Biases

468ca133-4214-4539-a14f-1b1ee5704fe0

This model is a fine-tuned version of Qwen/Qwen1.5-0.5B on the None dataset. It achieves the following results on the evaluation set:

Loss: 2.0038

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: 1
eval_batch_size: 1
seed: 61157
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 4
total_train_batch_size: 16
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: 10
num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
2.768	0.0011	1	2.7560
1.8555	1.0	949	2.0047
1.6581	2.0	1898	2.0038

Framework versions

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