|
--- |
|
license: bigcode-openrail-m |
|
base_model: WizardLM/WizardCoder-1B-V1.0 |
|
tags: |
|
- axolotl |
|
- dpo |
|
- trl |
|
- dpo |
|
- generated_from_trainer |
|
model-index: |
|
- name: WizardCoder-1B-V1.0-dpo-beta-0.01 |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl) |
|
<details><summary>See axolotl config</summary> |
|
|
|
axolotl version: `0.4.0` |
|
```yaml |
|
base_model: WizardLM/WizardCoder-1B-V1.0 |
|
model_type: AutoModelForCausalLM |
|
tokenizer_type: AutoTokenizer |
|
trust_remote_code: true |
|
|
|
hub_model_id: AlekseyKorshuk/WizardCoder-1B-V1.0-dpo-beta-0.01 |
|
hub_strategy: every_save |
|
|
|
load_in_8bit: false |
|
load_in_4bit: false |
|
strict: false |
|
|
|
rl: dpo |
|
datasets: |
|
- path: AlekseyKorshuk/evol-codealpaca-v1-dpo |
|
split: train |
|
type: wizardcoder.intel |
|
|
|
|
|
dataset_prepared_path: |
|
#val_set_size: 0.001 |
|
output_dir: ./output |
|
|
|
sequence_len: 2048 |
|
#sample_packing: false # currently unsupported |
|
pad_to_sequence_len: |
|
|
|
lora_r: |
|
lora_alpha: |
|
lora_dropout: |
|
lora_target_modules: |
|
lora_target_linear: |
|
lora_fan_in_fan_out: |
|
|
|
wandb_project: ui-thesis |
|
wandb_entity: |
|
wandb_watch: |
|
wandb_name: ultrachat-stable-code-3b-dpo-chatml-beta-0.01 |
|
wandb_log_model: |
|
|
|
gradient_accumulation_steps: 8 |
|
micro_batch_size: 4 |
|
num_epochs: 1 |
|
optimizer: paged_adamw_8bit |
|
adam_beta1: 0.9 |
|
adam_beta2: 0.95 |
|
max_grad_norm: 1.0 |
|
adam_epsilon: 0.00001 |
|
lr_scheduler: cosine |
|
cosine_min_lr_ratio: 0.1 |
|
learning_rate: 8.0e-7 |
|
warmup_steps: 32 |
|
#warmup_ratio: 0.1 |
|
weight_decay: 0.01 |
|
dpo_beta: 0.01 |
|
|
|
train_on_inputs: false |
|
group_by_length: false |
|
bf16: true |
|
fp16: false |
|
tf32: true |
|
#float16: true |
|
|
|
gradient_checkpointing: true |
|
early_stopping_patience: |
|
resume_from_checkpoint: |
|
local_rank: |
|
logging_steps: 1 |
|
xformers_attention: |
|
flash_attention: false |
|
|
|
|
|
#evals_per_epoch: 5 |
|
#eval_table_size: 8 # Approximate number of predictions sent to wandb depending on batch size. Enabled above 0. Default is 0 |
|
#eval_table_max_new_tokens: 768 # Total number of tokens generated for predictions sent to wandb. Default is 128 |
|
|
|
#chat_template: chatml |
|
#saves_per_epoch: 1 |
|
save_steps: 500 |
|
save_total_limit: 1 |
|
seed: 42 |
|
debug: |
|
deepspeed: |
|
|
|
|
|
fsdp: |
|
fsdp_config: |
|
resize_token_embeddings_to_32x: true |
|
|
|
``` |
|
|
|
</details><br> |
|
|
|
# WizardCoder-1B-V1.0-dpo-beta-0.01 |
|
|
|
This model is a fine-tuned version of [WizardLM/WizardCoder-1B-V1.0](https://huggingface.co/WizardLM/WizardCoder-1B-V1.0) on the None dataset. |
|
|
|
## 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: 8e-07 |
|
- train_batch_size: 4 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- distributed_type: multi-GPU |
|
- num_devices: 4 |
|
- gradient_accumulation_steps: 8 |
|
- total_train_batch_size: 128 |
|
- total_eval_batch_size: 32 |
|
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_steps: 32 |
|
- training_steps: 312 |
|
|
|
### Training results |
|
|
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.0.dev0 |
|
- Pytorch 2.1.2+cu118 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.0 |
|
|
