Commit
·
f83c306
1
Parent(s):
d67c2dd
Update README.md
Browse files
README.md
CHANGED
|
@@ -6,13 +6,13 @@ tags:
|
|
| 6 |
- llama2
|
| 7 |
datasets:
|
| 8 |
- Zangs3011/no_robots_FalconChatFormated
|
| 9 |
-
base_model: llama/Llama-2-7b-hf
|
| 10 |
license: apache-2.0
|
| 11 |
---
|
| 12 |
|
| 13 |
### Finetuning Overview:
|
| 14 |
|
| 15 |
-
**Model Used:** llama/Llama-2-7b-hf
|
| 16 |
**Dataset:** HuggingFaceH4/no_robots
|
| 17 |
|
| 18 |
#### Dataset Insights:
|
|
@@ -32,7 +32,7 @@ With the utilization of [MonsterAPI](https://monsterapi.ai)'s [LLM finetuner](ht
|
|
| 32 |
- **Epochs:** 1
|
| 33 |
- **Cost Per Epoch:** $1.313
|
| 34 |
- **Total Finetuning Cost:** $1.313
|
| 35 |
-
- **Model Path:** llama/Llama-2-7b-hf
|
| 36 |
- **Learning Rate:** 0.0002
|
| 37 |
- **Data Split:** 99% train 1% validation
|
| 38 |
- **Gradient Accumulation Steps:** 4
|
|
|
|
| 6 |
- llama2
|
| 7 |
datasets:
|
| 8 |
- Zangs3011/no_robots_FalconChatFormated
|
| 9 |
+
base_model: meta-llama/Llama-2-7b-hf
|
| 10 |
license: apache-2.0
|
| 11 |
---
|
| 12 |
|
| 13 |
### Finetuning Overview:
|
| 14 |
|
| 15 |
+
**Model Used:** meta-llama/Llama-2-7b-hf
|
| 16 |
**Dataset:** HuggingFaceH4/no_robots
|
| 17 |
|
| 18 |
#### Dataset Insights:
|
|
|
|
| 32 |
- **Epochs:** 1
|
| 33 |
- **Cost Per Epoch:** $1.313
|
| 34 |
- **Total Finetuning Cost:** $1.313
|
| 35 |
+
- **Model Path:** meta-llama/Llama-2-7b-hf
|
| 36 |
- **Learning Rate:** 0.0002
|
| 37 |
- **Data Split:** 99% train 1% validation
|
| 38 |
- **Gradient Accumulation Steps:** 4
|