|
|
--- |
|
|
library_name: peft |
|
|
license: apache-2.0 |
|
|
base_model: Qwen/QwQ-32B-Preview |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
datasets: |
|
|
- phxdev/creed |
|
|
model-index: |
|
|
- name: outputs/heisenberg-crystal |
|
|
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/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl) |
|
|
<details><summary>See axolotl config</summary> |
|
|
|
|
|
axolotl version: `0.8.0.dev0` |
|
|
```yaml |
|
|
adapter: lora |
|
|
base_model: Qwen/QwQ-32B-Preview |
|
|
trust_remote_code: true |
|
|
bf16: true |
|
|
dataset_processes: 64 |
|
|
datasets: |
|
|
- path: phxdev/creed |
|
|
type: completion |
|
|
field: text |
|
|
trust_remote_code: false |
|
|
streaming: true |
|
|
gradient_accumulation_steps: 1 |
|
|
gradient_checkpointing: true |
|
|
gradient_checkpointing_kwargs: |
|
|
use_reentrant: false |
|
|
learning_rate: 0.001 |
|
|
lisa_layers_attribute: model.layers |
|
|
lisa_enabled: true |
|
|
lisa_layers_fraction: 0.25 |
|
|
load_best_model_at_end: true |
|
|
load_in_4bit: false |
|
|
load_in_8bit: true |
|
|
lora_alpha: 128 |
|
|
lora_dropout: 0.15 |
|
|
lora_r: 64 |
|
|
lora_target_modules: |
|
|
- q_proj |
|
|
- v_proj |
|
|
- k_proj |
|
|
- o_proj |
|
|
- gate_proj |
|
|
- down_proj |
|
|
- up_proj |
|
|
lora_fan_in_fan_out: false |
|
|
modules_to_save: |
|
|
- embed_tokens |
|
|
- lm_head |
|
|
loraplus_lr_embedding: 1.0e-06 |
|
|
loraplus_lr_ratio: 16 |
|
|
lr_scheduler: cosine_with_min_lr |
|
|
lr_scheduler_kwargs: |
|
|
min_lr: 0.00001 |
|
|
max_prompt_len: 1024 |
|
|
mean_resizing_embeddings: false |
|
|
micro_batch_size: 1 |
|
|
num_epochs: 3.0 |
|
|
optimizer: adamw_torch |
|
|
# optim_args: |
|
|
# weight_decay: 0.05 |
|
|
# betas: [0.9, 0.95] |
|
|
# eps: 1.0e-8 |
|
|
output_dir: ./outputs/heisenberg-crystal |
|
|
pretrain_multipack_attn: true |
|
|
pretrain_multipack_buffer_size: 20000 |
|
|
qlora_sharded_model_loading: false |
|
|
ray_num_workers: 1 |
|
|
resources_per_worker: |
|
|
GPU: 1 |
|
|
resume_from_checkpoint: null |
|
|
sample_packing: false |
|
|
sample_packing_bin_size: 200 |
|
|
sample_packing_group_size: 100000 |
|
|
sample_packing_seq_len_multiplier: 1.0 |
|
|
save_only_model: true |
|
|
save_safetensors: true |
|
|
save_strategy: steps |
|
|
save_steps: 100 |
|
|
save_total_limit: 3 |
|
|
eval_strategy: steps |
|
|
eval_steps: 100 |
|
|
metric_for_best_model: loss |
|
|
greater_is_better: false |
|
|
sequence_len: 512 |
|
|
shuffle_merged_datasets: true |
|
|
skip_prepare_dataset: false |
|
|
strict: false |
|
|
train_on_inputs: false |
|
|
neftune_noise_alpha: 5.0 |
|
|
model_config: |
|
|
rope_scaling: |
|
|
type: linear |
|
|
factor: 1.5 |
|
|
dataloader_prefetch_factor: 4 |
|
|
dataloader_num_workers: 8 |
|
|
dataloader_pin_memory: true |
|
|
dataloader_persistent_workers: true |
|
|
max_grad_norm: 1.0 |
|
|
adam_beta2_schedule: cosine |
|
|
torch_compile: true |
|
|
torch_compile_backend: inductor |
|
|
trl: |
|
|
log_completions: true |
|
|
ref_model_mixup_alpha: 0.9 |
|
|
ref_model_sync_steps: 64 |
|
|
sync_ref_model: false |
|
|
use_vllm: false |
|
|
vllm_device: auto |
|
|
vllm_dtype: auto |
|
|
vllm_gpu_memory_utilization: 0.9 |
|
|
use_ray: false |
|
|
val_set_size: 0.05 |
|
|
warmup_steps: 100 |
|
|
warmup_ratio: 0.0 |
|
|
weight_decay: 0.05 |
|
|
flash_attention: true |
|
|
flash_attn_cross_entropy: true |
|
|
flash_attn_rms_norm: true |
|
|
flash_attn_fuse_qkv: false |
|
|
flash_attn_fuse_mlp: false |
|
|
ddp_backend: nccl |
|
|
ddp_broadcast_buffers: false |
|
|
ddp_find_unused_parameters: false |
|
|
tf32: true |
|
|
bf16_full_eval: false |
|
|
fp16: false |
|
|
# unfrozen_parameters: |
|
|
# - lm_head.* |
|
|
# - embed_tokens.* |
|
|
# - norm.* |
|
|
xformers_attention: false |
|
|
s2_attention: false |
|
|
sdp_attention: false |
|
|
pad_to_sequence_len: true |
|
|
peft_use_dora: false |
|
|
peft_lora_modules_to_save: null |
|
|
special_tokens: |
|
|
pad_token: <|endoftext|> |
|
|
deepspeed: null |
|
|
fsdp: null |
|
|
fsdp_config: null |
|
|
# wandb_project: heisenberg-qwen |
|
|
# wandb_entity: null |
|
|
# wandb_name: blue-crystal-run |
|
|
# wandb_log_model: checkpoint |
|
|
hub_model_id: null |
|
|
hub_strategy: null |
|
|
report_to: [] |
|
|
logging_strategy: steps |
|
|
logging_steps: 10 |
|
|
logging_first_step: true |
|
|
``` |
|
|
|
|
|
</details><br> |
|
|
|
|
|
# outputs/heisenberg-crystal |
|
|
|
|
|
This model is a fine-tuned version of [Qwen/QwQ-32B-Preview](https://huggingface.co/Qwen/QwQ-32B-Preview) on the phxdev/creed dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: nan |
|
|
|
|
|
## 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: 0.001 |
|
|
- train_batch_size: 1 |
|
|
- eval_batch_size: 1 |
|
|
- seed: 42 |
|
|
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
|
- lr_scheduler_type: cosine_with_min_lr |
|
|
- lr_scheduler_warmup_steps: 100 |
|
|
- num_epochs: 3.0 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:------:|:----:|:---------------:| |
|
|
| No log | 0.0013 | 1 | nan | |
|
|
| 7.8286 | 0.1259 | 100 | nan | |
|
|
| 7.2486 | 0.2519 | 200 | nan | |
|
|
| 7.2601 | 0.3778 | 300 | nan | |
|
|
| 8.2142 | 0.5038 | 400 | nan | |
|
|
| 7.1902 | 0.6297 | 500 | nan | |
|
|
| 6.3799 | 0.7557 | 600 | nan | |
|
|
| 6.7115 | 0.8816 | 700 | nan | |
|
|
| 6.0414 | 1.0076 | 800 | nan | |
|
|
| 6.428 | 1.1335 | 900 | nan | |
|
|
| 6.3167 | 1.2594 | 1000 | nan | |
|
|
| 6.0359 | 1.3854 | 1100 | nan | |
|
|
| 6.3701 | 1.5113 | 1200 | nan | |
|
|
| 6.9225 | 1.6373 | 1300 | nan | |
|
|
| 6.5807 | 1.7632 | 1400 | nan | |
|
|
| 6.8649 | 1.8892 | 1500 | nan | |
|
|
| 6.1397 | 2.0151 | 1600 | nan | |
|
|
| 5.7675 | 2.1411 | 1700 | nan | |
|
|
| 6.2605 | 2.2670 | 1800 | nan | |
|
|
| 5.8788 | 2.3929 | 1900 | nan | |
|
|
| 6.0279 | 2.5189 | 2000 | nan | |
|
|
| 6.3911 | 2.6448 | 2100 | nan | |
|
|
| 6.0412 | 2.7708 | 2200 | nan | |
|
|
| 6.0862 | 2.8967 | 2300 | nan | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.14.0 |
|
|
- Transformers 4.49.0 |
|
|
- Pytorch 2.5.1+cu124 |
|
|
- Datasets 3.2.0 |
|
|
- Tokenizers 0.21.0 |
