|
--- |
|
license: other |
|
library_name: peft |
|
tags: |
|
- axolotl |
|
- generated_from_trainer |
|
base_model: deepseek-ai/deepseek-coder-1.3b-instruct |
|
model-index: |
|
- name: deepseek-code-1.3b-inst-NLQ2Cypher |
|
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: `0.4.1` |
|
```yaml |
|
base_model: deepseek-ai/deepseek-coder-1.3b-instruct |
|
# base_model: Qwen/CodeQwen1.5-7B-Chat |
|
model_type: AutoModelForCausalLM |
|
tokenizer_type: AutoTokenizer |
|
is_mistral_derived_model: false |
|
|
|
load_in_8bit: false |
|
load_in_4bit: true |
|
strict: false |
|
|
|
lora_fan_in_fan_out: false |
|
data_seed: 49 |
|
seed: 49 |
|
|
|
datasets: |
|
- path: sample_data/alpaca_synth_cypher.jsonl |
|
type: sharegpt |
|
conversation: alpaca |
|
dataset_prepared_path: last_run_prepared |
|
val_set_size: 0.1 |
|
output_dir: ./qlora-alpaca-deepseek-1.3b-inst |
|
# output_dir: ./qlora-alpaca-out |
|
|
|
# hub_model_id: jermyn/CodeQwen1.5-7B-Chat-NLQ2Cypher |
|
hub_model_id: jermyn/deepseek-code-1.3b-inst-NLQ2Cypher |
|
|
|
adapter: qlora |
|
lora_model_dir: |
|
|
|
sequence_len: 896 |
|
sample_packing: false |
|
pad_to_sequence_len: true |
|
|
|
lora_r: 16 |
|
lora_alpha: 16 |
|
lora_dropout: 0.05 |
|
lora_target_linear: true |
|
lora_fan_in_fan_out: |
|
lora_target_modules: |
|
- gate_proj |
|
- down_proj |
|
- up_proj |
|
- q_proj |
|
- v_proj |
|
- k_proj |
|
- o_proj |
|
|
|
# If you added new tokens to the tokenizer, you may need to save some LoRA modules because they need to know the new tokens. |
|
# For LLaMA and Mistral, you need to save `embed_tokens` and `lm_head`. It may vary for other models. |
|
# `embed_tokens` converts tokens to embeddings, and `lm_head` converts embeddings to token probabilities. |
|
# https://github.com/huggingface/peft/issues/334#issuecomment-1561727994 |
|
# lora_modules_to_save: |
|
# - embed_tokens |
|
# - lm_head |
|
|
|
wandb_project: fine-tune-axolotl |
|
wandb_entity: jermyn |
|
|
|
gradient_accumulation_steps: 1 |
|
micro_batch_size: 16 |
|
eval_batch_size: 16 |
|
num_epochs: 6 |
|
optimizer: adamw_bnb_8bit |
|
lr_scheduler: cosine |
|
learning_rate: 0.0005 |
|
max_grad_norm: 1.0 |
|
adam_beta2: 0.95 |
|
adam_epsilon: 0.00001 |
|
|
|
train_on_inputs: false |
|
group_by_length: false |
|
bf16: true |
|
fp16: false |
|
tf32: false |
|
|
|
gradient_checkpointing: true |
|
early_stopping_patience: |
|
resume_from_checkpoint: |
|
local_rank: |
|
logging_steps: 1 |
|
xformers_attention: |
|
flash_attention: true |
|
|
|
loss_watchdog_threshold: 5.0 |
|
loss_watchdog_patience: 3 |
|
|
|
warmup_steps: 10 |
|
evals_per_epoch: 4 |
|
eval_table_size: |
|
eval_table_max_new_tokens: 128 |
|
# saves_per_epoch: 6 |
|
save_steps: 10 |
|
save_total_limit: 3 |
|
debug: |
|
weight_decay: 0.0 |
|
fsdp: |
|
fsdp_config: |
|
# special_tokens: |
|
# bos_token: "<s>" |
|
# eos_token: "</s>" |
|
# unk_token: "<unk>" |
|
save_safetensors: true |
|
|
|
``` |
|
|
|
</details><br> |
|
|
|
# deepseek-code-1.3b-inst-NLQ2Cypher |
|
|
|
This model is a fine-tuned version of [deepseek-ai/deepseek-coder-1.3b-instruct](https://huggingface.co/deepseek-ai/deepseek-coder-1.3b-instruct) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3839 |
|
|
|
## 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: 0.0005 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 16 |
|
- seed: 49 |
|
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_steps: 10 |
|
- num_epochs: 6 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 1.8723 | 0.1429 | 1 | 1.6354 | |
|
| 1.9222 | 0.2857 | 2 | 1.6215 | |
|
| 1.6971 | 0.5714 | 4 | 1.4205 | |
|
| 1.2458 | 0.8571 | 6 | 0.9204 | |
|
| 0.6179 | 1.1429 | 8 | 0.6923 | |
|
| 0.366 | 1.4286 | 10 | 0.5647 | |
|
| 0.2752 | 1.7143 | 12 | 0.5225 | |
|
| 0.2931 | 2.0 | 14 | 0.5167 | |
|
| 0.1812 | 2.2857 | 16 | 0.4564 | |
|
| 0.1258 | 2.5714 | 18 | 0.4038 | |
|
| 0.0885 | 2.8571 | 20 | 0.3689 | |
|
| 0.0886 | 3.1429 | 22 | 0.3647 | |
|
| 0.1281 | 3.4286 | 24 | 0.3503 | |
|
| 0.0606 | 3.7143 | 26 | 0.3458 | |
|
| 0.0603 | 4.0 | 28 | 0.3635 | |
|
| 0.0479 | 4.2857 | 30 | 0.3724 | |
|
| 0.0963 | 4.5714 | 32 | 0.3827 | |
|
| 0.0725 | 4.8571 | 34 | 0.3868 | |
|
| 0.049 | 5.1429 | 36 | 0.3873 | |
|
| 0.0572 | 5.4286 | 38 | 0.3860 | |
|
| 0.061 | 5.7143 | 40 | 0.3890 | |
|
| 0.0702 | 6.0 | 42 | 0.3839 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.11.1 |
|
- Transformers 4.41.1 |
|
- Pytorch 2.1.2+cu118 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
