training completed[dev]: 512 128
Browse files- README.md +22 -21
- all_results.json +10 -10
- model.safetensors +1 -1
- runs/Mar31_15-48-53_053f5f175b48/events.out.tfevents.1711900137.053f5f175b48.166.0 +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 |
|
@@ -56,20 +56,21 @@ 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 |
|
74 |
|
75 |
### 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: 1.1785
|
22 |
+
- Rouge1: 0.6772
|
23 |
+
- Rouge2: 0.4105
|
24 |
+
- Rougel: 0.6161
|
25 |
+
- Rougelsum: 0.6161
|
26 |
+
- Wer: 0.4869
|
27 |
+
- Bleurt: 0.3779
|
28 |
|
29 |
## Model description
|
30 |
|
|
|
56 |
|
57 |
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Wer | Bleurt |
|
58 |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:------:|:------:|
|
59 |
+
| No log | 0.13 | 250 | 1.3316 | 0.6509 | 0.3768 | 0.5866 | 0.5865 | 0.5217 | 0.3009 |
|
60 |
+
| 1.7919 | 0.27 | 500 | 1.2776 | 0.6593 | 0.3865 | 0.5962 | 0.5962 | 0.5108 | 0.3009 |
|
61 |
+
| 1.7919 | 0.4 | 750 | 1.2513 | 0.6633 | 0.3931 | 0.6015 | 0.6014 | 0.5039 | 0.3009 |
|
62 |
+
| 1.3552 | 0.53 | 1000 | 1.2326 | 0.6667 | 0.3967 | 0.6048 | 0.6047 | 0.5008 | 0.3009 |
|
63 |
+
| 1.3552 | 0.66 | 1250 | 1.2236 | 0.669 | 0.4 | 0.6072 | 0.6072 | 0.4972 | 0.3314 |
|
64 |
+
| 1.3074 | 0.8 | 1500 | 1.2118 | 0.6711 | 0.4022 | 0.6093 | 0.6093 | 0.4953 | 0.3314 |
|
65 |
+
| 1.3074 | 0.93 | 1750 | 1.2022 | 0.6714 | 0.4034 | 0.6105 | 0.6104 | 0.4932 | 0.2798 |
|
66 |
+
| 1.3037 | 1.06 | 2000 | 1.1972 | 0.673 | 0.4053 | 0.6117 | 0.6116 | 0.4916 | 0.3771 |
|
67 |
+
| 1.3037 | 1.2 | 2250 | 1.1909 | 0.6749 | 0.4068 | 0.6136 | 0.6135 | 0.4905 | 0.3314 |
|
68 |
+
| 1.2676 | 1.33 | 2500 | 1.1889 | 0.676 | 0.4086 | 0.6143 | 0.6143 | 0.4893 | 0.3314 |
|
69 |
+
| 1.2676 | 1.46 | 2750 | 1.1848 | 0.6763 | 0.4091 | 0.615 | 0.6149 | 0.4884 | 0.3314 |
|
70 |
+
| 1.2796 | 1.6 | 3000 | 1.1829 | 0.677 | 0.4095 | 0.6154 | 0.6154 | 0.488 | 0.3123 |
|
71 |
+
| 1.2796 | 1.73 | 3250 | 1.1808 | 0.6767 | 0.41 | 0.6157 | 0.6157 | 0.4876 | 0.3779 |
|
72 |
+
| 1.2489 | 1.86 | 3500 | 1.1787 | 0.6771 | 0.4105 | 0.616 | 0.616 | 0.4869 | 0.3771 |
|
73 |
+
| 1.2489 | 1.99 | 3750 | 1.1785 | 0.6772 | 0.4105 | 0.6161 | 0.6161 | 0.4869 | 0.3779 |
|
74 |
|
75 |
|
76 |
### 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":
|
12 |
}
|
|
|
1 |
{
|
2 |
+
"test_BLEURT": -0.9706,
|
3 |
+
"test_WER": 0.4816,
|
4 |
+
"test_loss": 1.195426344871521,
|
5 |
+
"test_rouge1": 0.6827,
|
6 |
+
"test_rouge2": 0.4184,
|
7 |
+
"test_rougeL": 0.6228,
|
8 |
+
"test_rougeLsum": 0.6222,
|
9 |
+
"test_runtime": 31.0979,
|
10 |
+
"test_samples_per_second": 12.123,
|
11 |
+
"test_steps_per_second": 2.026
|
12 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 891644712
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0b9613afbb9d6a6140659f4336ce375e04d821d1506dcda5db5e31ff0cf1c38a
|
3 |
size 891644712
|
runs/Mar31_15-48-53_053f5f175b48/events.out.tfevents.1711900137.053f5f175b48.166.0
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 sha256:263252bfd89a1284835ab1bc74cb6ee3548261c4494ade5f8a36a236215da838
|
3 |
+
size 15967
|
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":
|
12 |
}
|
|
|
1 |
{
|
2 |
+
"test_BLEURT": -0.9706,
|
3 |
+
"test_WER": 0.4816,
|
4 |
+
"test_loss": 1.195426344871521,
|
5 |
+
"test_rouge1": 0.6827,
|
6 |
+
"test_rouge2": 0.4184,
|
7 |
+
"test_rougeL": 0.6228,
|
8 |
+
"test_rougeLsum": 0.6222,
|
9 |
+
"test_runtime": 31.0979,
|
10 |
+
"test_samples_per_second": 12.123,
|
11 |
+
"test_steps_per_second": 2.026
|
12 |
}
|