metadata
library_name: peft
license: apache-2.0
base_model: Qwen/Qwen2-0.5B
tags:
- axolotl
- generated_from_trainer
model-index:
- name: test_hf
results: []
See axolotl config
axolotl version: 0.4.1
base_model: "Qwen/Qwen2-0.5B"
model_type: "AutoModelForCausalLM"
tokenizer_type: "AutoTokenizer"
load_in_8bit: false
load_in_4bit: true
strict: false
chat_template: "llama3"
datasets:
- path: "/workspace/input_data/train_data.json"
format: "custom"
type:
system_prompt: ""
system_format: "{system}"
field_instruction: "prompt"
field_output: "question"
no_input_format: "{instruction}"
format: "{instruction}"
ds_type: "json"
data_files:
- "train_data.json"
dataset_prepared_path: null
val_set_size: 0.04
output_dir: "miner_id_24"
sequence_len: 1024
sample_packing: false
pad_to_sequence_len: true
trust_remote_code: true
adapter: "lora"
lora_model_dir: null
lora_r: 64
lora_alpha: 128
lora_dropout: 0.3
lora_target_linear: true
lora_fan_in_fan_out: null
gradient_accumulation_steps: 6
micro_batch_size: 4
optimizer: "adamw_bnb_8bit"
lr_scheduler: "cosine"
learning_rate: 0.0002
num_epochs: 3
max_steps: 2
train_on_inputs: false
group_by_length: false
bf16: true
fp16: null
tf32: true
max_grad_norm: 1.0
gradient_checkpointing: true
early_stopping_patience: 4
save_steps: 100
eval_steps: 100
resume_from_checkpoint: null
local_rank: null
logging_steps: 1
xformers_attention: null
flash_attention: true
s2_attention: null
load_best_model_at_end: true
wandb_project: "Gradients-On-Demand"
wandb_entity: null
wandb_mode: "online"
wandb_run: "your_name"
wandb_runid: "c29f8be0-1d6a-40dd-83f1-f1d58697725a"
hub_model_id: "Alphatao/test_hf"
hub_repo: null
hub_strategy: "end"
hub_token: null
warmup_steps: 10
eval_table_size: null
eval_max_new_tokens: 128
debug: null
deepspeed: null
weight_decay: 0.0
fsdp: null
fsdp_config: null
wandb_name: "c29f8be0-1d6a-40dd-83f1-f1d58697725a"
lora_target_modules: ["q_proj", "k_proj", "v_proj"]
mlflow_experiment_name: "/tmp/train_data.json"
test_hf
This model is a fine-tuned version of Qwen/Qwen2-0.5B on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4452
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 6
- total_train_batch_size: 24
- 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: 2
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.26 | 0.0006 | 1 | 0.4452 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1