Instructions to use bilkultheek/ColdLLamaLite with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use bilkultheek/ColdLLamaLite with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("ahxt/LiteLlama-460M-1T") model = PeftModel.from_pretrained(base_model, "bilkultheek/ColdLLamaLite") - Notebooks
- Google Colab
- Kaggle
End of training
Browse files
README.md
CHANGED
|
@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [ahxt/LiteLlama-460M-1T](https://huggingface.co/ahxt/LiteLlama-460M-1T) on the None dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
-
- Loss: 2.
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
@@ -46,18 +46,24 @@ The following hyperparameters were used during training:
|
|
| 46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
- lr_scheduler_type: cosine
|
| 48 |
- lr_scheduler_warmup_ratio: 0.03
|
| 49 |
-
- num_epochs:
|
| 50 |
|
| 51 |
### Training results
|
| 52 |
|
| 53 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 54 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 55 |
-
| 4.
|
| 56 |
-
| 3.
|
| 57 |
-
| 2.
|
| 58 |
-
| 2.
|
| 59 |
-
| 2.
|
| 60 |
-
| 2.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 61 |
|
| 62 |
|
| 63 |
### Framework versions
|
|
|
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [ahxt/LiteLlama-460M-1T](https://huggingface.co/ahxt/LiteLlama-460M-1T) on the None dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 2.0471
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
- lr_scheduler_type: cosine
|
| 48 |
- lr_scheduler_warmup_ratio: 0.03
|
| 49 |
+
- num_epochs: 10
|
| 50 |
|
| 51 |
### Training results
|
| 52 |
|
| 53 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 54 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 55 |
+
| 4.1747 | 0.8 | 25 | 3.9257 |
|
| 56 |
+
| 3.626 | 1.6 | 50 | 3.2474 |
|
| 57 |
+
| 2.8441 | 2.4 | 75 | 2.4490 |
|
| 58 |
+
| 2.3365 | 3.2 | 100 | 2.2482 |
|
| 59 |
+
| 2.2153 | 4.0 | 125 | 2.1758 |
|
| 60 |
+
| 2.1591 | 4.8 | 150 | 2.1316 |
|
| 61 |
+
| 2.1214 | 5.6 | 175 | 2.1011 |
|
| 62 |
+
| 2.0946 | 6.4 | 200 | 2.0781 |
|
| 63 |
+
| 2.0818 | 7.2 | 225 | 2.0622 |
|
| 64 |
+
| 2.0614 | 8.0 | 250 | 2.0528 |
|
| 65 |
+
| 2.0571 | 8.8 | 275 | 2.0485 |
|
| 66 |
+
| 2.0522 | 9.6 | 300 | 2.0471 |
|
| 67 |
|
| 68 |
|
| 69 |
### Framework versions
|
runs/Aug03_09-18-38_fastgpuserv/events.out.tfevents.1722690531.fastgpuserv.2914688.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:01f6462e33b14e20a451c94459665f31bb87ad7d037deac0f025e8b117299d64
|
| 3 |
+
size 359
|