Commit
•
49f3c45
1
Parent(s):
57af322
Update README.md
Browse files
README.md
CHANGED
|
@@ -6,6 +6,8 @@ tags:
|
|
| 6 |
model-index:
|
| 7 |
- name: zephyr-220m-sft-full
|
| 8 |
results: []
|
|
|
|
|
|
|
| 9 |
---
|
| 10 |
|
| 11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -13,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 13 |
|
| 14 |
# zephyr-220m-sft-full
|
| 15 |
|
| 16 |
-
This model is a fine-tuned version of [BEE-spoke-data/smol_llama-220M-openhermes](https://huggingface.co/BEE-spoke-data/smol_llama-220M-openhermes) on the
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
- Loss: 1.6579
|
| 19 |
|
|
@@ -61,4 +63,4 @@ The following hyperparameters were used during training:
|
|
| 61 |
- Datasets 2.15.0
|
| 62 |
- Tokenizers 0.15.0
|
| 63 |
|
| 64 |
-
https://wandb.ai/amazingvince/huggingface/runs/5rffzk3x/workspace?workspace=user-amazingvince
|
|
|
|
| 6 |
model-index:
|
| 7 |
- name: zephyr-220m-sft-full
|
| 8 |
results: []
|
| 9 |
+
datasets:
|
| 10 |
+
- HuggingFaceH4/ultrachat_200k
|
| 11 |
---
|
| 12 |
|
| 13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 15 |
|
| 16 |
# zephyr-220m-sft-full
|
| 17 |
|
| 18 |
+
This model is a fine-tuned version of [BEE-spoke-data/smol_llama-220M-openhermes](https://huggingface.co/BEE-spoke-data/smol_llama-220M-openhermes) on the Ultrachat_200k dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
- Loss: 1.6579
|
| 21 |
|
|
|
|
| 63 |
- Datasets 2.15.0
|
| 64 |
- Tokenizers 0.15.0
|
| 65 |
|
| 66 |
+
https://wandb.ai/amazingvince/huggingface/runs/5rffzk3x/workspace?workspace=user-amazingvince
|