Model save
Browse files- README.md +15 -2
- adapter_model.safetensors +1 -1
README.md
CHANGED
|
@@ -3,6 +3,8 @@ license: apache-2.0
|
|
| 3 |
library_name: peft
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
|
|
|
|
|
|
| 6 |
base_model: google-t5/t5-small
|
| 7 |
model-index:
|
| 8 |
- name: t5-small-v2
|
|
@@ -15,6 +17,12 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
# t5-small-v2
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [google-t5/t5-small](https://huggingface.co/google-t5/t5-small) on an unknown dataset.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
@@ -34,8 +42,8 @@ More information needed
|
|
| 34 |
|
| 35 |
The following hyperparameters were used during training:
|
| 36 |
- learning_rate: 4e-05
|
| 37 |
-
- train_batch_size:
|
| 38 |
-
- eval_batch_size:
|
| 39 |
- seed: 7
|
| 40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 41 |
- lr_scheduler_type: linear
|
|
@@ -43,6 +51,11 @@ The following hyperparameters were used during training:
|
|
| 43 |
|
| 44 |
### Training results
|
| 45 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
|
| 47 |
|
| 48 |
### Framework versions
|
|
|
|
| 3 |
library_name: peft
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- rouge
|
| 8 |
base_model: google-t5/t5-small
|
| 9 |
model-index:
|
| 10 |
- name: t5-small-v2
|
|
|
|
| 17 |
# t5-small-v2
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [google-t5/t5-small](https://huggingface.co/google-t5/t5-small) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 2.2734
|
| 22 |
+
- Rouge1: 25.8039
|
| 23 |
+
- Rouge2: 7.8029
|
| 24 |
+
- Rougel: 17.9541
|
| 25 |
+
- Rougelsum: 17.9584
|
| 26 |
|
| 27 |
## Model description
|
| 28 |
|
|
|
|
| 42 |
|
| 43 |
The following hyperparameters were used during training:
|
| 44 |
- learning_rate: 4e-05
|
| 45 |
+
- train_batch_size: 128
|
| 46 |
+
- eval_batch_size: 128
|
| 47 |
- seed: 7
|
| 48 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 49 |
- lr_scheduler_type: linear
|
|
|
|
| 51 |
|
| 52 |
### Training results
|
| 53 |
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|
| 55 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|
|
| 56 |
+
| 2.577 | 1.49 | 250 | 2.2480 | 26.1891 | 7.8964 | 17.9400 | 17.9370 |
|
| 57 |
+
| 2.5599 | 2.98 | 500 | 2.2617 | 26.2088 | 7.9532 | 18.3182 | 18.3326 |
|
| 58 |
+
| 2.5877 | 4.46 | 750 | 2.2734 | 25.8039 | 7.8029 | 17.9541 | 17.9584 |
|
| 59 |
|
| 60 |
|
| 61 |
### Framework versions
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2369320
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e9f66598df1993cbad707e9a1acaeb5f6b2e47b544faa8f14932964cde0f56d2
|
| 3 |
size 2369320
|