Commit ·
0107ebf
1
Parent(s): 9557ec9
Training complete
Browse files- README.md +22 -13
- pytorch_model.bin +1 -1
README.md
CHANGED
|
@@ -4,8 +4,8 @@ base_model: google/mt5-small
|
|
| 4 |
tags:
|
| 5 |
- summarization
|
| 6 |
- generated_from_trainer
|
| 7 |
-
|
| 8 |
-
-
|
| 9 |
model-index:
|
| 10 |
- name: mT5
|
| 11 |
results: []
|
|
@@ -16,18 +16,13 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
# mT5
|
| 18 |
|
| 19 |
-
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
-
-
|
| 22 |
-
-
|
| 23 |
-
-
|
| 24 |
-
-
|
| 25 |
-
-
|
| 26 |
-
- eval_runtime: 80.7804
|
| 27 |
-
- eval_samples_per_second: 0.619
|
| 28 |
-
- eval_steps_per_second: 0.087
|
| 29 |
-
- epoch: 3.0
|
| 30 |
-
- step: 939
|
| 31 |
|
| 32 |
## Model description
|
| 33 |
|
|
@@ -54,6 +49,20 @@ The following hyperparameters were used during training:
|
|
| 54 |
- lr_scheduler_type: linear
|
| 55 |
- num_epochs: 8
|
| 56 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 57 |
### Framework versions
|
| 58 |
|
| 59 |
- Transformers 4.32.1
|
|
|
|
| 4 |
tags:
|
| 5 |
- summarization
|
| 6 |
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- rouge
|
| 9 |
model-index:
|
| 10 |
- name: mT5
|
| 11 |
results: []
|
|
|
|
| 16 |
|
| 17 |
# mT5
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the None dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 2.7797
|
| 22 |
+
- Rouge1: 17.5958
|
| 23 |
+
- Rouge2: 5.5502
|
| 24 |
+
- Rougel: 14.89
|
| 25 |
+
- Rougelsum: 15.8861
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
|
| 27 |
## Model description
|
| 28 |
|
|
|
|
| 49 |
- lr_scheduler_type: linear
|
| 50 |
- num_epochs: 8
|
| 51 |
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|
| 55 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|
|
| 56 |
+
| 6.7587 | 1.0 | 313 | 3.0537 | 15.5845 | 4.426 | 12.7262 | 13.9385 |
|
| 57 |
+
| 3.6224 | 2.0 | 626 | 2.8799 | 16.4339 | 4.8534 | 13.3138 | 14.9449 |
|
| 58 |
+
| 3.3322 | 3.0 | 939 | 2.8378 | 18.1043 | 6.2202 | 15.376 | 16.5012 |
|
| 59 |
+
| 3.1974 | 4.0 | 1252 | 2.8008 | 17.8905 | 5.7529 | 15.0379 | 16.3205 |
|
| 60 |
+
| 3.1183 | 5.0 | 1565 | 2.7936 | 17.7318 | 5.4565 | 14.8508 | 15.9979 |
|
| 61 |
+
| 3.0522 | 6.0 | 1878 | 2.7824 | 17.6328 | 5.5352 | 14.7803 | 15.8202 |
|
| 62 |
+
| 3.019 | 7.0 | 2191 | 2.7846 | 17.7348 | 5.4391 | 14.7499 | 15.8859 |
|
| 63 |
+
| 2.9889 | 8.0 | 2504 | 2.7797 | 17.5958 | 5.5502 | 14.89 | 15.8861 |
|
| 64 |
+
|
| 65 |
+
|
| 66 |
### Framework versions
|
| 67 |
|
| 68 |
- Transformers 4.32.1
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1200769925
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3faf35e22d606c93f54a0c93543d9df15c99ca10c1485234b779d6e5911ddde7
|
| 3 |
size 1200769925
|