End of training
Browse files
README.md
CHANGED
@@ -14,9 +14,9 @@ probably proofread and complete it, then remove this comment. -->
|
|
14 |
|
15 |
This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset.
|
16 |
It achieves the following results on the evaluation set:
|
17 |
-
- Train Loss:
|
18 |
-
- Validation Loss: 3.
|
19 |
-
- Epoch:
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -43,6 +43,25 @@ The following hyperparameters were used during training:
|
|
43 |
| Train Loss | Validation Loss | Epoch |
|
44 |
|:----------:|:---------------:|:-----:|
|
45 |
| 4.2136 | 3.8303 | 0 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
46 |
|
47 |
|
48 |
### Framework versions
|
|
|
14 |
|
15 |
This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset.
|
16 |
It achieves the following results on the evaluation set:
|
17 |
+
- Train Loss: 3.1769
|
18 |
+
- Validation Loss: 3.5116
|
19 |
+
- Epoch: 19
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
43 |
| Train Loss | Validation Loss | Epoch |
|
44 |
|:----------:|:---------------:|:-----:|
|
45 |
| 4.2136 | 3.8303 | 0 |
|
46 |
+
| 3.8997 | 3.6993 | 1 |
|
47 |
+
| 3.7790 | 3.6344 | 2 |
|
48 |
+
| 3.7061 | 3.5923 | 3 |
|
49 |
+
| 3.6476 | 3.5653 | 4 |
|
50 |
+
| 3.6003 | 3.5513 | 5 |
|
51 |
+
| 3.5578 | 3.5360 | 6 |
|
52 |
+
| 3.5204 | 3.5277 | 7 |
|
53 |
+
| 3.4843 | 3.5171 | 8 |
|
54 |
+
| 3.4514 | 3.5117 | 9 |
|
55 |
+
| 3.4194 | 3.5048 | 10 |
|
56 |
+
| 3.3903 | 3.5040 | 11 |
|
57 |
+
| 3.3627 | 3.5006 | 12 |
|
58 |
+
| 3.3332 | 3.5006 | 13 |
|
59 |
+
| 3.3052 | 3.5019 | 14 |
|
60 |
+
| 3.2772 | 3.5051 | 15 |
|
61 |
+
| 3.2514 | 3.5043 | 16 |
|
62 |
+
| 3.2249 | 3.5026 | 17 |
|
63 |
+
| 3.2019 | 3.5129 | 18 |
|
64 |
+
| 3.1769 | 3.5116 | 19 |
|
65 |
|
66 |
|
67 |
### Framework versions
|
logs/train/events.out.tfevents.1665047898.c89fd8197338.67.0.v2
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:daff8c23e5df5104b0afa67b855436c5954968c308e628e99b3b9b9686bdc4f2
|
3 |
+
size 892456
|
logs/validation/events.out.tfevents.1665047974.c89fd8197338.67.1.v2
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0bf28eccc465bdc27774c74b65b7b28164a3846116405fcf45d3ceff4f80d5bf
|
3 |
+
size 3158
|
tf_model.h5
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 327745496
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:22856a8850f45b86bfeceae8b3c8597a6ab3792254c3f1ce83465b09dd1add04
|
3 |
size 327745496
|