training completed[dev]: 512 128
Browse files- README.md +21 -22
- all_results.json +10 -10
- runs/Mar31_00-46-22_93badbe1494c/events.out.tfevents.1711845988.93badbe1494c.1089.4 +2 -2
- test_results.json +10 -10
README.md
CHANGED
@@ -18,13 +18,13 @@ should probably proofread and complete it, then remove this comment. -->
|
|
18 |
|
19 |
This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on an unknown dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
-
- Loss: 1.
|
22 |
-
- Rouge1: 0.
|
23 |
-
- Rouge2: 0.
|
24 |
-
- Rougel: 0.
|
25 |
-
- Rougelsum: 0.
|
26 |
-
- Wer: 0.
|
27 |
-
- Bleurt: 0.
|
28 |
|
29 |
## Model description
|
30 |
|
@@ -56,21 +56,20 @@ The following hyperparameters were used during training:
|
|
56 |
|
57 |
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Wer | Bleurt |
|
58 |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:------:|:------:|
|
59 |
-
| No log | 0.
|
60 |
-
| 1.
|
61 |
-
| 1.
|
62 |
-
| 1.
|
63 |
-
| 1.
|
64 |
-
| 1.
|
65 |
-
| 1.
|
66 |
-
| 1.
|
67 |
-
| 1.
|
68 |
-
| 1.
|
69 |
-
| 1.
|
70 |
-
| 1.
|
71 |
-
| 1.
|
72 |
-
| 1.
|
73 |
-
| 1.2489 | 1.99 | 3750 | 1.1785 | 0.6774 | 0.4106 | 0.6163 | 0.6162 | 0.4869 | 0.3779 |
|
74 |
|
75 |
|
76 |
### Framework versions
|
|
|
18 |
|
19 |
This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on an unknown dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 1.1670
|
22 |
+
- Rouge1: 0.6791
|
23 |
+
- Rouge2: 0.4136
|
24 |
+
- Rougel: 0.6183
|
25 |
+
- Rougelsum: 0.6185
|
26 |
+
- Wer: 0.4846
|
27 |
+
- Bleurt: 0.3314
|
28 |
|
29 |
## Model description
|
30 |
|
|
|
56 |
|
57 |
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Wer | Bleurt |
|
58 |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:------:|:------:|
|
59 |
+
| No log | 0.14 | 250 | 1.3197 | 0.6548 | 0.3804 | 0.5904 | 0.5905 | 0.5188 | 0.3009 |
|
60 |
+
| 1.7026 | 0.27 | 500 | 1.2676 | 0.6613 | 0.3904 | 0.5985 | 0.5987 | 0.5074 | 0.3009 |
|
61 |
+
| 1.7026 | 0.41 | 750 | 1.2385 | 0.6664 | 0.3961 | 0.6043 | 0.6044 | 0.5023 | 0.3009 |
|
62 |
+
| 1.3446 | 0.55 | 1000 | 1.2234 | 0.6691 | 0.4009 | 0.6075 | 0.6076 | 0.4972 | 0.3009 |
|
63 |
+
| 1.3446 | 0.68 | 1250 | 1.2089 | 0.671 | 0.4031 | 0.6099 | 0.6101 | 0.4944 | 0.3009 |
|
64 |
+
| 1.309 | 0.82 | 1500 | 1.1983 | 0.673 | 0.4064 | 0.6121 | 0.6123 | 0.4914 | 0.3009 |
|
65 |
+
| 1.309 | 0.96 | 1750 | 1.1900 | 0.6744 | 0.4075 | 0.6136 | 0.6137 | 0.4897 | 0.3009 |
|
66 |
+
| 1.2783 | 1.09 | 2000 | 1.1840 | 0.6744 | 0.4082 | 0.614 | 0.6141 | 0.4889 | 0.2798 |
|
67 |
+
| 1.2783 | 1.23 | 2250 | 1.1808 | 0.6759 | 0.4102 | 0.6154 | 0.6156 | 0.4875 | 0.2944 |
|
68 |
+
| 1.2683 | 1.36 | 2500 | 1.1763 | 0.6771 | 0.4111 | 0.6163 | 0.6165 | 0.4863 | 0.3153 |
|
69 |
+
| 1.2683 | 1.5 | 2750 | 1.1720 | 0.6772 | 0.4115 | 0.6169 | 0.617 | 0.4859 | 0.4109 |
|
70 |
+
| 1.2469 | 1.64 | 3000 | 1.1701 | 0.6783 | 0.4127 | 0.6176 | 0.6178 | 0.485 | 0.3314 |
|
71 |
+
| 1.2469 | 1.77 | 3250 | 1.1680 | 0.6786 | 0.4131 | 0.6178 | 0.6179 | 0.4849 | 0.3314 |
|
72 |
+
| 1.2171 | 1.91 | 3500 | 1.1670 | 0.6791 | 0.4136 | 0.6183 | 0.6185 | 0.4846 | 0.3314 |
|
|
|
73 |
|
74 |
|
75 |
### Framework versions
|
all_results.json
CHANGED
@@ -1,12 +1,12 @@
|
|
1 |
{
|
2 |
-
"test_BLEURT": -0.
|
3 |
-
"test_WER": 0.
|
4 |
-
"test_loss": 1.
|
5 |
-
"test_rouge1": 0.
|
6 |
-
"test_rouge2": 0.
|
7 |
-
"test_rougeL": 0.
|
8 |
-
"test_rougeLsum": 0.
|
9 |
-
"test_runtime":
|
10 |
-
"test_samples_per_second":
|
11 |
-
"test_steps_per_second": 1.
|
12 |
}
|
|
|
1 |
{
|
2 |
+
"test_BLEURT": -0.2487,
|
3 |
+
"test_WER": 0.4777,
|
4 |
+
"test_loss": 1.1913501024246216,
|
5 |
+
"test_rouge1": 0.6851,
|
6 |
+
"test_rouge2": 0.4239,
|
7 |
+
"test_rougeL": 0.6255,
|
8 |
+
"test_rougeLsum": 0.6251,
|
9 |
+
"test_runtime": 47.9856,
|
10 |
+
"test_samples_per_second": 7.648,
|
11 |
+
"test_steps_per_second": 1.292
|
12 |
}
|
runs/Mar31_00-46-22_93badbe1494c/events.out.tfevents.1711845988.93badbe1494c.1089.4
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:b30a6d758090b185f3db856fb28d44937b8f67936c95a5cf1440a886cddac253
|
3 |
+
size 15396
|
test_results.json
CHANGED
@@ -1,12 +1,12 @@
|
|
1 |
{
|
2 |
-
"test_BLEURT": -0.
|
3 |
-
"test_WER": 0.
|
4 |
-
"test_loss": 1.
|
5 |
-
"test_rouge1": 0.
|
6 |
-
"test_rouge2": 0.
|
7 |
-
"test_rougeL": 0.
|
8 |
-
"test_rougeLsum": 0.
|
9 |
-
"test_runtime":
|
10 |
-
"test_samples_per_second":
|
11 |
-
"test_steps_per_second": 1.
|
12 |
}
|
|
|
1 |
{
|
2 |
+
"test_BLEURT": -0.2487,
|
3 |
+
"test_WER": 0.4777,
|
4 |
+
"test_loss": 1.1913501024246216,
|
5 |
+
"test_rouge1": 0.6851,
|
6 |
+
"test_rouge2": 0.4239,
|
7 |
+
"test_rougeL": 0.6255,
|
8 |
+
"test_rougeLsum": 0.6251,
|
9 |
+
"test_runtime": 47.9856,
|
10 |
+
"test_samples_per_second": 7.648,
|
11 |
+
"test_steps_per_second": 1.292
|
12 |
}
|