Michael-Vptn
commited on
Commit
•
19cfdeb
1
Parent(s):
cf58176
Upload TFT5ForConditionalGeneration
Browse files- README.md +53 -13
- tf_model.h5 +1 -1
README.md
CHANGED
@@ -15,9 +15,9 @@ probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Train Loss: 0.
|
19 |
-
- Validation Loss: 0.
|
20 |
-
- Epoch:
|
21 |
|
22 |
## Model description
|
23 |
|
@@ -43,16 +43,56 @@ The following hyperparameters were used during training:
|
|
43 |
|
44 |
| Train Loss | Validation Loss | Epoch |
|
45 |
|:----------:|:---------------:|:-----:|
|
46 |
-
| 1.
|
47 |
-
| 1.
|
48 |
-
| 1.
|
49 |
-
| 1.
|
50 |
-
| 1.
|
51 |
-
| 1.
|
52 |
-
| 1.
|
53 |
-
| 1.
|
54 |
-
| 1.
|
55 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
56 |
|
57 |
|
58 |
### Framework versions
|
|
|
15 |
|
16 |
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Train Loss: 0.3202
|
19 |
+
- Validation Loss: 0.0689
|
20 |
+
- Epoch: 49
|
21 |
|
22 |
## Model description
|
23 |
|
|
|
43 |
|
44 |
| Train Loss | Validation Loss | Epoch |
|
45 |
|:----------:|:---------------:|:-----:|
|
46 |
+
| 1.6155 | 1.3909 | 0 |
|
47 |
+
| 1.4232 | 1.2592 | 1 |
|
48 |
+
| 1.3301 | 1.1768 | 2 |
|
49 |
+
| 1.2562 | 1.0908 | 3 |
|
50 |
+
| 1.1925 | 1.0136 | 4 |
|
51 |
+
| 1.1417 | 0.9589 | 5 |
|
52 |
+
| 1.0953 | 0.9173 | 6 |
|
53 |
+
| 1.0502 | 0.8531 | 7 |
|
54 |
+
| 1.0103 | 0.8009 | 8 |
|
55 |
+
| 0.9761 | 0.7488 | 9 |
|
56 |
+
| 0.9404 | 0.7100 | 10 |
|
57 |
+
| 0.9095 | 0.6793 | 11 |
|
58 |
+
| 0.8743 | 0.6319 | 12 |
|
59 |
+
| 0.8480 | 0.6139 | 13 |
|
60 |
+
| 0.8233 | 0.5741 | 14 |
|
61 |
+
| 0.7942 | 0.5479 | 15 |
|
62 |
+
| 0.7697 | 0.5176 | 16 |
|
63 |
+
| 0.7456 | 0.4847 | 17 |
|
64 |
+
| 0.7250 | 0.4650 | 18 |
|
65 |
+
| 0.6996 | 0.4370 | 19 |
|
66 |
+
| 0.6790 | 0.4141 | 20 |
|
67 |
+
| 0.6607 | 0.3959 | 21 |
|
68 |
+
| 0.6428 | 0.3666 | 22 |
|
69 |
+
| 0.6249 | 0.3511 | 23 |
|
70 |
+
| 0.6060 | 0.3344 | 24 |
|
71 |
+
| 0.5944 | 0.3178 | 25 |
|
72 |
+
| 0.5750 | 0.2942 | 26 |
|
73 |
+
| 0.5607 | 0.2787 | 27 |
|
74 |
+
| 0.5453 | 0.2608 | 28 |
|
75 |
+
| 0.5317 | 0.2472 | 29 |
|
76 |
+
| 0.5146 | 0.2365 | 30 |
|
77 |
+
| 0.5017 | 0.2146 | 31 |
|
78 |
+
| 0.4909 | 0.2078 | 32 |
|
79 |
+
| 0.4764 | 0.1945 | 33 |
|
80 |
+
| 0.4664 | 0.1831 | 34 |
|
81 |
+
| 0.4517 | 0.1703 | 35 |
|
82 |
+
| 0.4397 | 0.1643 | 36 |
|
83 |
+
| 0.4316 | 0.1588 | 37 |
|
84 |
+
| 0.4196 | 0.1428 | 38 |
|
85 |
+
| 0.4073 | 0.1311 | 39 |
|
86 |
+
| 0.3949 | 0.1232 | 40 |
|
87 |
+
| 0.3871 | 0.1175 | 41 |
|
88 |
+
| 0.3776 | 0.1105 | 42 |
|
89 |
+
| 0.3705 | 0.1025 | 43 |
|
90 |
+
| 0.3623 | 0.0959 | 44 |
|
91 |
+
| 0.3514 | 0.0928 | 45 |
|
92 |
+
| 0.3427 | 0.0828 | 46 |
|
93 |
+
| 0.3346 | 0.0799 | 47 |
|
94 |
+
| 0.3268 | 0.0736 | 48 |
|
95 |
+
| 0.3202 | 0.0689 | 49 |
|
96 |
|
97 |
|
98 |
### Framework versions
|
tf_model.h5
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 373902664
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a80b6152ada69ce7c7f642b4973439ae2a31ce3744c97fdd3d1af0f6db6f6af
|
3 |
size 373902664
|