TI-GPT-2B
Browse files
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 [google/gemma-2b-it](https://huggingface.co/google/gemma-2b-it) on an unknown dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss:
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -51,14 +51,14 @@ The following hyperparameters were used during training:
|
|
51 |
|
52 |
| Training Loss | Epoch | Step | Validation Loss |
|
53 |
|:-------------:|:-----:|:----:|:---------------:|
|
54 |
-
|
|
55 |
-
|
|
56 |
-
|
|
57 |
-
| 3.
|
58 |
-
| 6.
|
59 |
-
| 6.
|
60 |
-
| 6.
|
61 |
-
| 3.
|
62 |
|
63 |
|
64 |
### Framework versions
|
|
|
16 |
|
17 |
This model is a fine-tuned version of [google/gemma-2b-it](https://huggingface.co/google/gemma-2b-it) on an unknown dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 5.0281
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
51 |
|
52 |
| Training Loss | Epoch | Step | Validation Loss |
|
53 |
|:-------------:|:-----:|:----:|:---------------:|
|
54 |
+
| 7.1896 | 0.8 | 1 | 5.7603 |
|
55 |
+
| 7.1647 | 1.6 | 2 | 5.7035 |
|
56 |
+
| 7.0439 | 2.4 | 3 | 5.5787 |
|
57 |
+
| 3.4231 | 4.0 | 5 | 5.3434 |
|
58 |
+
| 6.6454 | 4.8 | 6 | 5.2429 |
|
59 |
+
| 6.5081 | 5.6 | 7 | 5.1593 |
|
60 |
+
| 6.3933 | 6.4 | 8 | 5.0950 |
|
61 |
+
| 3.1633 | 8.0 | 10 | 5.0281 |
|
62 |
|
63 |
|
64 |
### Framework versions
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2364032
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c6240fada7bf53ad08cb9378ed3a9df22de45e26c869fd85f550a595bfbe30e8
|
3 |
size 2364032
|
runs/Mar31_14-17-18_2b015d01cbf1/events.out.tfevents.1711894638.2b015d01cbf1.14101.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfa90eadca88aa390e76fe4044bf89cdda6ae5e6fdc644a3efacefc6e40e7a2e
|
3 |
+
size 8704
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4856
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fe744618c9c18668d6f5d25a83dfeb03c44842758fbe90b96d38514cf50de1a4
|
3 |
size 4856
|