|
--- |
|
license: cc-by-sa-4.0 |
|
base_model: stabilityai/stablelm-3b-4e1t |
|
tags: |
|
- axolotl |
|
- generated_from_trainer |
|
model-index: |
|
- name: stablelm-4e1t-2b-v0.1 |
|
results: [] |
|
language: |
|
- en |
|
--- |
|
|
|
# stablelm-4e1t-2b-v0.1 |
|
|
|
|
|
This is a layer pruning experiment based off of [stablelm-3b-4e1t](https://hf.co/stabilityai/stablelm-3b-4e1t): |
|
|
|
- 10 layers pruned with [PruneMe](https://github.com/pszemraj/PruneMe/tree/upgrades)/MergeKit |
|
- layers selected using [BEE-spoke-data/fineweb-100k_en-med](https://hf.co/datasets/BEE-spoke-data/fineweb-100k_en-med) |
|
- brief subsequent continued pretraining @ ctx 4096 |
|
- data: 10k rows of FineWeb (different than pruning data) + some curated data |
|
- wandb [here](https://wandb.ai/pszemraj/llama3-pruning) |
|
|
|
|
|
## details |
|
|
|
[<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> |
|
|
|
### config |
|
|
|
|
|
axolotl version: `0.4.0` |
|
```yaml |
|
base_model: pszemraj/stablelm-3b-4e1t-prune10 |
|
model_type: AutoModelForCausalLM |
|
tokenizer_type: AutoTokenizer |
|
|
|
strict: false |
|
seed: 80085 |
|
|
|
# dataset |
|
datasets: |
|
- path: BEE-spoke-data/KI-smorgasbord_fw-small |
|
type: completion # format from earlier |
|
field: text # Optional[str] default: text, field to use for completion data |
|
val_set_size: 0.015 |
|
|
|
sequence_len: 4096 |
|
sample_packing: true |
|
pad_to_sequence_len: false |
|
train_on_inputs: false |
|
group_by_length: false |
|
|
|
# WANDB |
|
wandb_project: llama3-pruning |
|
wandb_entity: pszemraj |
|
wandb_watch: gradients |
|
wandb_name: stablelm-4e1t-2b-v0.1 |
|
hub_model_id: pszemraj/stablelm-4e1t-2b-v0.1 |
|
hub_strategy: every_save |
|
|
|
gradient_accumulation_steps: 16 |
|
micro_batch_size: 1 |
|
num_epochs: 2 |
|
optimizer: adamw_torch_fused # paged_adamw_32bit |
|
weight_decay: 0.05 |
|
lr_scheduler: cosine |
|
learning_rate: 5e-5 |
|
warmup_ratio: 0.1 |
|
|
|
load_in_8bit: false |
|
load_in_4bit: false |
|
bf16: true |
|
tf32: true |
|
|
|
flash_attention: true |
|
torch_compile: true # requires >= torch 2.0, may sometimes cause problems |
|
torch_compile_backend: inductor # Optional[str] |
|
gradient_checkpointing: true |
|
gradient_checkpointing_kwargs: |
|
use_reentrant: false |
|
|
|
# hyperparams for freq of evals, saving, etc |
|
evals_per_epoch: 5 |
|
saves_per_epoch: 3 |
|
save_safetensors: true |
|
save_total_limit: 1 |
|
output_dir: ./output-axolotl/output-model-2b |
|
logging_steps: 8 |
|
|
|
deepspeed: |
|
|
|
special_tokens: |
|
pad_token: <|end_of_text|> |
|
|
|
``` |
|
|
|
</details><br> |
|
|
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| No log | 0.0006 | 1 | 4.4344 | |
|
| 2.6558 | 0.2004 | 332 | 2.7150 | |
|
| 2.6548 | 0.4007 | 664 | 2.6196 | |
|
| 2.5435 | 0.6011 | 996 | 2.5981 | |
|
| 2.5133 | 0.8014 | 1328 | 2.5502 | |
|
| 2.489 | 1.0018 | 1660 | 2.5106 | |
|
| 2.2671 | 1.1898 | 1992 | 2.4944 | |
|
| 2.2038 | 1.3902 | 2324 | 2.4843 | |
|
| 2.2513 | 1.5905 | 2656 | 2.4761 | |
|
| 2.1654 | 1.7909 | 2988 | 2.4769 | |
|
|
|
--- |
|
|