training completed[prod]:pegasus-baseline
Browse files
README.md
CHANGED
|
@@ -1,16 +1,10 @@
|
|
| 1 |
---
|
|
|
|
| 2 |
tags:
|
| 3 |
- generated_from_trainer
|
| 4 |
model-index:
|
| 5 |
- name: pegasus-legalease
|
| 6 |
results: []
|
| 7 |
-
datasets:
|
| 8 |
-
- hheiden/us-congress-117-bills
|
| 9 |
-
language:
|
| 10 |
-
- en
|
| 11 |
-
metrics:
|
| 12 |
-
- rouge
|
| 13 |
-
library_name: transformers
|
| 14 |
---
|
| 15 |
|
| 16 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -18,12 +12,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 18 |
|
| 19 |
# pegasus-legalease
|
| 20 |
|
| 21 |
-
This model
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
-
-
|
| 24 |
-
- Rouge2: 0.3210
|
| 25 |
-
- RougeL: 0.4055
|
| 26 |
-
- Rougelsum: 0.4196
|
| 27 |
|
| 28 |
## Model description
|
| 29 |
|
|
@@ -48,29 +39,40 @@ The following hyperparameters were used during training:
|
|
| 48 |
- seed: 42
|
| 49 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 50 |
- lr_scheduler_type: linear
|
| 51 |
-
- num_epochs:
|
| 52 |
- mixed_precision_training: Native AMP
|
| 53 |
|
| 54 |
### Training results
|
| 55 |
|
| 56 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 57 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 58 |
-
| No log | 0.09 | 250 | 4.
|
| 59 |
-
| 4.
|
| 60 |
-
| 4.
|
| 61 |
-
| 2.
|
| 62 |
-
| 2.
|
| 63 |
-
| 1.
|
| 64 |
-
| 1.
|
| 65 |
-
| 1.
|
| 66 |
-
| 1.
|
| 67 |
-
| 1.
|
| 68 |
-
| 1.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 69 |
|
| 70 |
|
| 71 |
### Framework versions
|
| 72 |
|
| 73 |
- Transformers 4.38.2
|
| 74 |
-
- Pytorch 2.1
|
| 75 |
- Datasets 2.18.0
|
| 76 |
-
- Tokenizers 0.15.2
|
|
|
|
| 1 |
---
|
| 2 |
+
base_model: google/pegasus-xsum
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
| 5 |
model-index:
|
| 6 |
- name: pegasus-legalease
|
| 7 |
results: []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
---
|
| 9 |
|
| 10 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 12 |
|
| 13 |
# pegasus-legalease
|
| 14 |
|
| 15 |
+
This model is a fine-tuned version of [google/pegasus-xsum](https://huggingface.co/google/pegasus-xsum) on an unknown dataset.
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 1.0569
|
|
|
|
|
|
|
|
|
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
|
|
| 39 |
- seed: 42
|
| 40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 41 |
- lr_scheduler_type: linear
|
| 42 |
+
- num_epochs: 2
|
| 43 |
- mixed_precision_training: Native AMP
|
| 44 |
|
| 45 |
### Training results
|
| 46 |
|
| 47 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 48 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 49 |
+
| No log | 0.09 | 250 | 4.5676 |
|
| 50 |
+
| 4.9309 | 0.18 | 500 | 4.1409 |
|
| 51 |
+
| 4.9309 | 0.27 | 750 | 1.9459 |
|
| 52 |
+
| 2.7387 | 0.35 | 1000 | 1.1953 |
|
| 53 |
+
| 2.7387 | 0.44 | 1250 | 1.1557 |
|
| 54 |
+
| 1.3603 | 0.53 | 1500 | 1.1350 |
|
| 55 |
+
| 1.3603 | 0.62 | 1750 | 1.1189 |
|
| 56 |
+
| 1.2237 | 0.71 | 2000 | 1.1092 |
|
| 57 |
+
| 1.2237 | 0.8 | 2250 | 1.0976 |
|
| 58 |
+
| 1.2113 | 0.89 | 2500 | 1.0931 |
|
| 59 |
+
| 1.2113 | 0.98 | 2750 | 1.0854 |
|
| 60 |
+
| 1.2057 | 1.06 | 3000 | 1.0787 |
|
| 61 |
+
| 1.2057 | 1.15 | 3250 | 1.0759 |
|
| 62 |
+
| 1.1613 | 1.24 | 3500 | 1.0714 |
|
| 63 |
+
| 1.1613 | 1.33 | 3750 | 1.0680 |
|
| 64 |
+
| 1.1379 | 1.42 | 4000 | 1.0662 |
|
| 65 |
+
| 1.1379 | 1.51 | 4250 | 1.0634 |
|
| 66 |
+
| 1.163 | 1.6 | 4500 | 1.0622 |
|
| 67 |
+
| 1.163 | 1.68 | 4750 | 1.0600 |
|
| 68 |
+
| 1.1271 | 1.77 | 5000 | 1.0587 |
|
| 69 |
+
| 1.1271 | 1.86 | 5250 | 1.0574 |
|
| 70 |
+
| 1.1358 | 1.95 | 5500 | 1.0569 |
|
| 71 |
|
| 72 |
|
| 73 |
### Framework versions
|
| 74 |
|
| 75 |
- Transformers 4.38.2
|
| 76 |
+
- Pytorch 2.2.1+cu121
|
| 77 |
- Datasets 2.18.0
|
| 78 |
+
- Tokenizers 0.15.2
|
runs/Mar16_21-57-37_a870977f2581/events.out.tfevents.1710626335.a870977f2581.1762.0
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 sha256:904e05b13f72ab61aba55b2ec295309f1ef87b5bb84c8b561448d3df6ba30d2e
|
| 3 |
+
size 14139
|