Update README.md
Browse files
README.md
CHANGED
|
@@ -15,6 +15,15 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 15 |
- bnb_4bit_quant_type: nf4
|
| 16 |
- bnb_4bit_use_double_quant: True
|
| 17 |
- bnb_4bit_compute_dtype: bfloat16
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
### Framework versions
|
| 19 |
|
| 20 |
|
|
|
|
| 15 |
- bnb_4bit_quant_type: nf4
|
| 16 |
- bnb_4bit_use_double_quant: True
|
| 17 |
- bnb_4bit_compute_dtype: bfloat16
|
| 18 |
+
|
| 19 |
+
## Model Summary
|
| 20 |
+
|
| 21 |
+
train/loss : 0.4354
|
| 22 |
+
train/learning_rate: 0.00017567567567567568
|
| 23 |
+
train/epoch : 5.0
|
| 24 |
+
train/global_step : 10
|
| 25 |
+
|
| 26 |
+
|
| 27 |
### Framework versions
|
| 28 |
|
| 29 |
|