Commit
·
9cd94dc
1
Parent(s):
a05273e
Update README.md
Browse files
README.md
CHANGED
|
@@ -41,6 +41,10 @@ A dataset containing 6,003 GPT-generated human instruction and Solidity source c
|
|
| 41 |
- Learning rate scheduler type: cosine
|
| 42 |
- Warmup ratio: 0.03
|
| 43 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 44 |
# Training Loss
|
| 45 |
```
|
| 46 |
Step Training Loss
|
|
@@ -135,6 +139,7 @@ model = AutoModelForCausalLM.from_pretrained("AlfredPros/CodeLlama-7b-Instruct-S
|
|
| 135 |
# Make input
|
| 136 |
input='Make a smart contract to create a whitelist of approved wallets. The purpose of this contract is to allow the DAO (Decentralized Autonomous Organization) to approve or revoke certain wallets, and also set a checker address for additional validation if needed. The current owner address can be changed by the current owner.'
|
| 137 |
|
|
|
|
| 138 |
prompt = f"""### Instruction:
|
| 139 |
Use the Task below and the Input given to write the Response, which is a programming code that can solve the following Task:
|
| 140 |
|
|
|
|
| 41 |
- Learning rate scheduler type: cosine
|
| 42 |
- Warmup ratio: 0.03
|
| 43 |
|
| 44 |
+
# Training Details
|
| 45 |
+
- GPU used: 1x NVIDIA GeForce GTX 1080Ti
|
| 46 |
+
- Training time: 21 hours and 5 minutes
|
| 47 |
+
|
| 48 |
# Training Loss
|
| 49 |
```
|
| 50 |
Step Training Loss
|
|
|
|
| 139 |
# Make input
|
| 140 |
input='Make a smart contract to create a whitelist of approved wallets. The purpose of this contract is to allow the DAO (Decentralized Autonomous Organization) to approve or revoke certain wallets, and also set a checker address for additional validation if needed. The current owner address can be changed by the current owner.'
|
| 141 |
|
| 142 |
+
# Make prompt template
|
| 143 |
prompt = f"""### Instruction:
|
| 144 |
Use the Task below and the Input given to write the Response, which is a programming code that can solve the following Task:
|
| 145 |
|