File size: 1,106 Bytes
0cf0388 1aad7aa 0cf0388 1aad7aa 0cf0388 1aad7aa 0cf0388 1aad7aa 0cf0388 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 |
Training Details:
Trained at 8K Context -> Expanded to 32K Context due to context extension with PoSE training.
Dataset Modifications:
- Further Cleaned up Roleplaying Samples -> Quality Check
- Removed Low Quality Samples from Manual Check
- More Creative Writing Samples -> 2x
- Remade and Refined Detailed Instruct Data
Needle in a Haystack Results:
Coherent at 32K Context. Not as good as a natively trained 32K model, but much better than regular rope scaling.
```
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
``` |