Update README.md
Browse files
README.md
CHANGED
|
@@ -25,7 +25,6 @@ It classifies prompts into **3 difficulty tiers** with a single classification h
|
|
| 25 |
|
| 26 |
- **Model type:** Text Classification (3‑tier, single head)
|
| 27 |
- **Language:** English
|
| 28 |
-
- **Backbone:** microsoft/deberta-v3-xsmall
|
| 29 |
- **License:** Apache‑2.0
|
| 30 |
- **Finetuned from model:** microsoft/deberta-v3-xsmall
|
| 31 |
- **Training data:** `RowRed/prompts-24000-en` (L0 downsampled to 2,000, L1/L2/L3 kept fully)
|
|
@@ -88,7 +87,7 @@ This model is a research prototype.
|
|
| 88 |
- **Max sequence length:** 256 tokens
|
| 89 |
- **Epochs:** 12 max (Early stopping patience = 4 on F1-macro; stopped at epoch 7, best checkpoint at epoch 3)
|
| 90 |
- **Class balancing:** WeightedRandomSampler only; class weights in loss removed to avoid double-counting
|
| 91 |
-
- **Head:** 256-dim, dropout=0.1
|
| 92 |
- **Precision:** FP16 mixed precision
|
| 93 |
|
| 94 |
## Evaluation Results
|
|
|
|
| 25 |
|
| 26 |
- **Model type:** Text Classification (3‑tier, single head)
|
| 27 |
- **Language:** English
|
|
|
|
| 28 |
- **License:** Apache‑2.0
|
| 29 |
- **Finetuned from model:** microsoft/deberta-v3-xsmall
|
| 30 |
- **Training data:** `RowRed/prompts-24000-en` (L0 downsampled to 2,000, L1/L2/L3 kept fully)
|
|
|
|
| 87 |
- **Max sequence length:** 256 tokens
|
| 88 |
- **Epochs:** 12 max (Early stopping patience = 4 on F1-macro; stopped at epoch 7, best checkpoint at epoch 3)
|
| 89 |
- **Class balancing:** WeightedRandomSampler only; class weights in loss removed to avoid double-counting
|
| 90 |
+
- **Head:** 256-dim, dropout=0.1
|
| 91 |
- **Precision:** FP16 mixed precision
|
| 92 |
|
| 93 |
## Evaluation Results
|