Update README.md
Browse files
README.md
CHANGED
|
@@ -14,10 +14,21 @@ language:
|
|
| 14 |
|
| 15 |
# Uploaded model
|
| 16 |
|
|
|
|
| 17 |
- **Developed by:** ThatsGroes
|
| 18 |
- **License:** apache-2.0
|
| 19 |
- **Finetuned from model :** AI-Sweden-Models/Llama-3-8B-instruct
|
| 20 |
|
| 21 |
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
| 22 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
|
|
|
| 14 |
|
| 15 |
# Uploaded model
|
| 16 |
|
| 17 |
+
- **Computed sponsored by:** Arroc ECS Denmark and Nvidia through Danish Data Science Community
|
| 18 |
- **Developed by:** ThatsGroes
|
| 19 |
- **License:** apache-2.0
|
| 20 |
- **Finetuned from model :** AI-Sweden-Models/Llama-3-8B-instruct
|
| 21 |
|
| 22 |
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
| 23 |
|
| 24 |
+
{'train_runtime': 215438.6486, 'train_samples_per_second': 3.141, 'train_steps_per_second': 0.393, 'train_loss': 1.035243785800245, 'epoch': 4.0}
|
| 25 |
+
|
| 26 |
+
[codecarbon INFO @ 07:52:43] Energy consumed for RAM : 11.292402 kWh. RAM Power : 188.78840446472168 W
|
| 27 |
+
[codecarbon INFO @ 07:52:43] Energy consumed for all GPUs : 17.520012 kWh. Total GPU Power : 245.77458591976836 W
|
| 28 |
+
[codecarbon INFO @ 07:52:43] Energy consumed for all CPUs : 2.543341 kWh. Total CPU Power : 42.5 W
|
| 29 |
+
[codecarbon INFO @ 07:52:43] 31.355754 kWh of electricity used since the beginning.
|
| 30 |
+
|
| 31 |
+
|
| 32 |
+
We ended up using 65.56 GB GPU memory (82.84%), of which 49.83 GB (62.97%) was used for LoRa.
|
| 33 |
+
|
| 34 |
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|