End of training
Browse files- README.md +11 -11
- adapter_model.safetensors +1 -1
README.md
CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
This model is a fine-tuned version of [ericzzz/falcon-rw-1b-instruct-openorca](https://huggingface.co/ericzzz/falcon-rw-1b-instruct-openorca) on an unknown dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss:
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -51,16 +51,16 @@ The following hyperparameters were used during training:
|
|
51 |
|
52 |
| Training Loss | Epoch | Step | Validation Loss |
|
53 |
|:-------------:|:-----:|:----:|:---------------:|
|
54 |
-
| 2.
|
55 |
-
| 2.
|
56 |
-
| 1.
|
57 |
-
| 1.
|
58 |
-
| 0.
|
59 |
-
| 0.
|
60 |
-
| 0.
|
61 |
-
| 0.
|
62 |
-
| 0.
|
63 |
-
| 0.
|
64 |
|
65 |
|
66 |
### Framework versions
|
|
|
16 |
|
17 |
This model is a fine-tuned version of [ericzzz/falcon-rw-1b-instruct-openorca](https://huggingface.co/ericzzz/falcon-rw-1b-instruct-openorca) on an unknown dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 3.6185
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
51 |
|
52 |
| Training Loss | Epoch | Step | Validation Loss |
|
53 |
|:-------------:|:-----:|:----:|:---------------:|
|
54 |
+
| 2.6649 | 1.0 | 28 | 2.5872 |
|
55 |
+
| 2.0983 | 2.0 | 56 | 2.5236 |
|
56 |
+
| 1.6296 | 3.0 | 84 | 2.5791 |
|
57 |
+
| 1.2573 | 4.0 | 112 | 2.6976 |
|
58 |
+
| 0.9665 | 5.0 | 140 | 2.8468 |
|
59 |
+
| 0.7261 | 6.0 | 168 | 2.9899 |
|
60 |
+
| 0.5295 | 7.0 | 196 | 3.1940 |
|
61 |
+
| 0.38 | 8.0 | 224 | 3.3579 |
|
62 |
+
| 0.2729 | 9.0 | 252 | 3.5245 |
|
63 |
+
| 0.208 | 10.0 | 280 | 3.6185 |
|
64 |
|
65 |
|
66 |
### Framework versions
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 100690288
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:99f320cbe65cf5c4fb4e94a75129bc0f9f1e49e265255114f690828a6503c280
|
3 |
size 100690288
|