Update README.md
Browse files
README.md
CHANGED
|
@@ -21,7 +21,7 @@ This model has been finetuned on roughly 80k samples so far.
|
|
| 21 |
# Training
|
| 22 |
|
| 23 |
+ Time to complete: ~20 hours
|
| 24 |
-
+ Datasets: Thermostatic/flowers, Intel/orca_dpo_pairs, jondurbin/truthy-dpo-v0.1
|
| 25 |
+ Cost: ~$20 in H100 hours
|
| 26 |
+ Evaluation loss: 0.69
|
| 27 |
+ Method: LoRa
|
|
|
|
| 21 |
# Training
|
| 22 |
|
| 23 |
+ Time to complete: ~20 hours
|
| 24 |
+
+ Datasets: Thermostatic/flowers, Intel/orca_dpo_pairs, jondurbin/truthy-dpo-v0.1, glaiveai/glaive_function_calling_v2
|
| 25 |
+ Cost: ~$20 in H100 hours
|
| 26 |
+ Evaluation loss: 0.69
|
| 27 |
+ Method: LoRa
|