Update README.md
Browse files
README.md
CHANGED
|
@@ -6,6 +6,8 @@ tags:
|
|
| 6 |
model-index:
|
| 7 |
- name: zephyr-7b-spin-iter1-v0
|
| 8 |
results: []
|
|
|
|
|
|
|
| 9 |
---
|
| 10 |
|
| 11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -13,7 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 13 |
|
| 14 |
# zephyr-7b-spin-iter1-v0
|
| 15 |
|
| 16 |
-
This model is a fine-tuned version of [
|
|
|
|
|
|
|
|
|
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
- Loss: 0.0831
|
| 19 |
- Rewards/real: 1.3037
|
|
@@ -71,4 +76,4 @@ The following hyperparameters were used during training:
|
|
| 71 |
- Transformers 4.37.0
|
| 72 |
- Pytorch 2.1.2+cu121
|
| 73 |
- Datasets 2.14.6
|
| 74 |
-
- Tokenizers 0.15.2
|
|
|
|
| 6 |
model-index:
|
| 7 |
- name: zephyr-7b-spin-iter1-v0
|
| 8 |
results: []
|
| 9 |
+
datasets:
|
| 10 |
+
- argilla/10k_prompts_SPIN_iter1_zephyr_top
|
| 11 |
---
|
| 12 |
|
| 13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 15 |
|
| 16 |
# zephyr-7b-spin-iter1-v0
|
| 17 |
|
| 18 |
+
This model is a fine-tuned version of [argilla/zephyr-7b-spin-iter0-v0](https://huggingface.co/argilla/zephyr-7b-spin-iter0-v0) on the
|
| 19 |
+
[argilla/10k_prompts_SPIN_iter1_zephyr_top](https://huggingface.co/datasets/argilla/10k_prompts_SPIN_iter1_zephyr_top) and
|
| 20 |
+
[argilla/10k_prompts_SPIN_iter0_zephyr_top](https://huggingface.co/datasets/argilla/10k_prompts_SPIN_iter0_zephyr_top) dataset.
|
| 21 |
+
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
- Loss: 0.0831
|
| 24 |
- Rewards/real: 1.3037
|
|
|
|
| 76 |
- Transformers 4.37.0
|
| 77 |
- Pytorch 2.1.2+cu121
|
| 78 |
- Datasets 2.14.6
|
| 79 |
+
- Tokenizers 0.15.2
|