81 lines
2.8 KiB
Markdown
81 lines
2.8 KiB
Markdown
---
|
|
license: cc-by-nc-4.0
|
|
language:
|
|
- en
|
|
---
|
|
|
|
Trained with compute from [Backyard.ai](https://backyard.ai/) | Thanks to them and @dynafire for helping me out.
|
|
|
|
---
|
|
|
|
Training Details:
|
|
<br>Trained at 8K Context -> Expanded to 32K Context with PoSE training.
|
|
|
|
Dataset Modifications:
|
|
<br>\- Further Cleaned up Roleplaying Samples -> Quality Check
|
|
<br>\- Removed Low Quality Samples from Manual Check -> Increased Baseline Quality Floor
|
|
<br>\- More Creative Writing Samples -> 2x Samples
|
|
<br>\- Remade and Refined Detailed Instruct Data
|
|
|
|
Notes:
|
|
<br>\- Training run is much less aggressive than previous Stheno versions.
|
|
<br>\- This model works when tested in bf16 with the same configs as within the file.
|
|
<br>\- I do not know the effects quantisation has on it.
|
|
<br>\- Roleplays pretty well. Feels nice in my opinion.
|
|
<br>\- It has some issues on long context understanding and reasoning. Much better vs rope scaling normally though, so that is a plus.
|
|
<br>\- Reminder, this isn't a native 32K model. It has it's issues, but it's coherent and working well.
|
|
|
|
Sanity Check // Needle in a Haystack Results:
|
|
<br>\- This is not as complex as RULER or NIAN, but it's a basic evaluator. Some improper train examples had Haystack scores ranging from Red to Orange for most of the extended contexts.
|
|
|
|
|
|
Wandb Run:
|
|
|
|
|
|
---
|
|
|
|
Relevant Axolotl Configurations:
|
|
<br>-> Taken from [winglian/Llama-3-8b-64k-PoSE](https://huggingface.co/winglian/Llama-3-8b-64k-PoSE)
|
|
<br>\- I tried to find my own configs, hours of tinkering but the one he used worked best, so I stuck to it.
|
|
<br>\- 2M Rope Theta had the best loss results during training compared to other values.
|
|
<br>\- Leaving it at 500K rope wasn't that much worse, but 4M and 8M Theta made the grad_norm values worsen even if loss drops fast.
|
|
<br>\- Mixing in Pretraining Data was a PITA. Made it a lot worse with formatting.
|
|
<br>\- Pretraining / Noise made it worse at Haystack too? It wasn't all Green, Mainly Oranges.
|
|
<br>\- Improper / Bad Rope Theta shows in Grad_Norm exploding to thousands. It'll drop to low values alright, but it's a scary fast drop even with gradient clipping.
|
|
|
|
```
|
|
sequence_len: 8192
|
|
use_pose: true
|
|
pose_max_context_len: 32768
|
|
|
|
overrides_of_model_config:
|
|
rope_theta: 2000000.0
|
|
max_position_embeddings: 32768
|
|
|
|
# peft_use_dora: true
|
|
adapter: lora
|
|
peft_use_rslora: true
|
|
lora_model_dir:
|
|
lora_r: 256
|
|
lora_alpha: 256
|
|
lora_dropout: 0.1
|
|
lora_target_linear: true
|
|
lora_target_modules:
|
|
- gate_proj
|
|
- down_proj
|
|
- up_proj
|
|
- q_proj
|
|
- v_proj
|
|
- k_proj
|
|
- o_proj
|
|
|
|
warmup_steps: 80
|
|
gradient_accumulation_steps: 6
|
|
micro_batch_size: 1
|
|
num_epochs: 2
|
|
optimizer: adamw_bnb_8bit
|
|
lr_scheduler: cosine_with_min_lr
|
|
learning_rate: 0.00004
|
|
lr_scheduler_kwargs:
|
|
min_lr: 0.000004
|
|
``` |