Instructions to use engindemir/bart_tr_dependencyparsing with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use engindemir/bart_tr_dependencyparsing with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("engindemir/bart_tr_dependencyparsing") model = AutoModelForSeq2SeqLM.from_pretrained("engindemir/bart_tr_dependencyparsing") - Notebooks
- Google Colab
- Kaggle
End of training
Browse files
README.md
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
---
|
| 2 |
-
base_model: facebook/bart-base
|
| 3 |
library_name: transformers
|
| 4 |
license: apache-2.0
|
|
|
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
model-index:
|
|
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the None dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
-
- Loss: 0.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
@@ -45,10 +45,21 @@ The following hyperparameters were used during training:
|
|
| 45 |
|
| 46 |
### Training results
|
| 47 |
|
| 48 |
-
| Training Loss | Epoch | Step
|
| 49 |
-
|:-------------:|:------:|:----:|:---------------:|
|
| 50 |
-
| 0.
|
| 51 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 52 |
|
| 53 |
|
| 54 |
### Framework versions
|
|
|
|
| 1 |
---
|
|
|
|
| 2 |
library_name: transformers
|
| 3 |
license: apache-2.0
|
| 4 |
+
base_model: facebook/bart-base
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
model-index:
|
|
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the None dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.0136
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
|
|
| 45 |
|
| 46 |
### Training results
|
| 47 |
|
| 48 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 49 |
+
|:-------------:|:------:|:-----:|:---------------:|
|
| 50 |
+
| 0.3664 | 0.2187 | 1000 | 0.0402 |
|
| 51 |
+
| 0.0437 | 0.4374 | 2000 | 0.0287 |
|
| 52 |
+
| 0.0358 | 0.6562 | 3000 | 0.0250 |
|
| 53 |
+
| 0.0304 | 0.8749 | 4000 | 0.0223 |
|
| 54 |
+
| 0.0276 | 1.0936 | 5000 | 0.0203 |
|
| 55 |
+
| 0.0246 | 1.3123 | 6000 | 0.0195 |
|
| 56 |
+
| 0.0234 | 1.5311 | 7000 | 0.0181 |
|
| 57 |
+
| 0.0227 | 1.7498 | 8000 | 0.0167 |
|
| 58 |
+
| 0.0213 | 1.9685 | 9000 | 0.0157 |
|
| 59 |
+
| 0.0193 | 2.1872 | 10000 | 0.0149 |
|
| 60 |
+
| 0.0184 | 2.4059 | 11000 | 0.0144 |
|
| 61 |
+
| 0.0177 | 2.6247 | 12000 | 0.0140 |
|
| 62 |
+
| 0.017 | 2.8434 | 13000 | 0.0136 |
|
| 63 |
|
| 64 |
|
| 65 |
### Framework versions
|