53 lines
1.0 KiB
Markdown
53 lines
1.0 KiB
Markdown
|
# Training Log Summary
|
||
|
|
|
||
|
|
## Final Training Run (train_v2_fast.py)
|
||
|
|
|
||
|
|
**Start:** February 18, 2026, ~17:30
|
||
|
|
**End:** February 19, 2026, ~20:00
|
||
|
|
**Duration:** 26.5 hours
|
||
|
|
|
||
|
|
### Loss Progression
|
||
|
|
|
||
|
|
| Epoch | Loss |
|
||
|
|
|-------|------|
|
||
|
|
| 0.95 | 0.28 |
|
||
|
|
| 1.90 | 0.24 |
|
||
|
|
| 3.00 | 0.27 |
|
||
|
|
|
||
|
|
**Final training loss:** 0.27
|
||
|
|
|
||
|
|
### Configuration Used
|
||
|
|
```python
|
||
|
|
num_train_epochs = 3
|
||
|
|
per_device_train_batch_size = 8
|
||
|
|
gradient_accumulation_steps = 4 # Effective batch = 32
|
||
|
|
learning_rate = 2e-5
|
||
|
|
max_length = 384 # tokens
|
||
|
|
warmup_steps = 200
|
||
|
|
weight_decay = 0.01
|
||
|
|
|
||
|
|
# LoRA Config
|
||
|
|
lora_r = 64
|
||
|
|
lora_alpha = 128
|
||
|
|
lora_target_modules = [
|
||
|
|
"q_proj", "k_proj", "v_proj",
|
||
|
|
"o_proj", "gate_proj", "up_proj"
|
||
|
|
]
|
||
|
|
lora_dropout = 0.05
|
||
|
|
```
|
||
|
|
|
||
|
|
### Hardware
|
||
|
|
|
||
|
|
- GPU: NVIDIA A100 SXM 80GB
|
||
|
|
- Training framework: Transformers + PEFT
|
||
|
|
- Mixed precision: FP16
|
||
|
|
|
||
|
|
### Dataset
|
||
|
|
|
||
|
|
- Source: Chamaka8/Serendip-sft-sinhala
|
||
|
|
- File: serendipllm_sft_final_train_v2.json
|
||
|
|
- Examples: 309,328
|
||
|
|
- News classification: 45,080 examples
|
||
|
|
- General Sinhala: 205,403 examples
|
||
|
|
- QA pairs: 29,390 examples
|