Commit
·
6bbc5c6
1
Parent(s):
6916ec0
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,93 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- f1
|
| 7 |
+
model-index:
|
| 8 |
+
- name: newsdiscourse-model
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# newsdiscourse-model
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 1.6987
|
| 20 |
+
- F1: 0.5504
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 3e-05
|
| 40 |
+
- train_batch_size: 1
|
| 41 |
+
- eval_batch_size: 1
|
| 42 |
+
- seed: 42
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- num_epochs: 5.0
|
| 46 |
+
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
| Training Loss | Epoch | Step | Validation Loss | F1 |
|
| 50 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 51 |
+
| No log | 0.14 | 100 | 1.3361 | 0.3723 |
|
| 52 |
+
| No log | 0.28 | 200 | 1.1836 | 0.4345 |
|
| 53 |
+
| No log | 0.43 | 300 | 1.1636 | 0.3997 |
|
| 54 |
+
| No log | 0.57 | 400 | 1.3535 | 0.5028 |
|
| 55 |
+
| 1.2064 | 0.71 | 500 | 1.2941 | 0.4707 |
|
| 56 |
+
| 1.2064 | 0.85 | 600 | 1.2891 | 0.4937 |
|
| 57 |
+
| 1.2064 | 1.0 | 700 | 1.2047 | 0.4774 |
|
| 58 |
+
| 1.2064 | 1.14 | 800 | 1.2191 | 0.4944 |
|
| 59 |
+
| 1.2064 | 1.28 | 900 | 1.1750 | 0.4778 |
|
| 60 |
+
| 0.9207 | 1.42 | 1000 | 1.3087 | 0.4909 |
|
| 61 |
+
| 0.9207 | 1.57 | 1100 | 1.2436 | 0.4976 |
|
| 62 |
+
| 0.9207 | 1.71 | 1200 | 1.1465 | 0.5033 |
|
| 63 |
+
| 0.9207 | 1.85 | 1300 | 1.1134 | 0.5142 |
|
| 64 |
+
| 0.9207 | 1.99 | 1400 | 1.1940 | 0.5383 |
|
| 65 |
+
| 0.8149 | 2.14 | 1500 | 1.2552 | 0.5291 |
|
| 66 |
+
| 0.8149 | 2.28 | 1600 | 1.3747 | 0.5260 |
|
| 67 |
+
| 0.8149 | 2.42 | 1700 | 1.3680 | 0.5329 |
|
| 68 |
+
| 0.8149 | 2.56 | 1800 | 1.2787 | 0.5190 |
|
| 69 |
+
| 0.8149 | 2.71 | 1900 | 1.3889 | 0.5409 |
|
| 70 |
+
| 0.6152 | 2.85 | 2000 | 1.3602 | 0.5435 |
|
| 71 |
+
| 0.6152 | 2.99 | 2100 | 1.3175 | 0.5468 |
|
| 72 |
+
| 0.6152 | 3.13 | 2200 | 1.5887 | 0.5365 |
|
| 73 |
+
| 0.6152 | 3.28 | 2300 | 1.5172 | 0.5563 |
|
| 74 |
+
| 0.6152 | 3.42 | 2400 | 1.5470 | 0.5661 |
|
| 75 |
+
| 0.4719 | 3.56 | 2500 | 1.4928 | 0.5212 |
|
| 76 |
+
| 0.4719 | 3.7 | 2600 | 1.6498 | 0.5356 |
|
| 77 |
+
| 0.4719 | 3.85 | 2700 | 1.4977 | 0.5597 |
|
| 78 |
+
| 0.4719 | 3.99 | 2800 | 1.4720 | 0.5470 |
|
| 79 |
+
| 0.4719 | 4.13 | 2900 | 1.5797 | 0.5493 |
|
| 80 |
+
| 0.372 | 4.27 | 3000 | 1.6874 | 0.5445 |
|
| 81 |
+
| 0.372 | 4.42 | 3100 | 1.6702 | 0.5545 |
|
| 82 |
+
| 0.372 | 4.56 | 3200 | 1.7672 | 0.5469 |
|
| 83 |
+
| 0.372 | 4.7 | 3300 | 1.7351 | 0.5485 |
|
| 84 |
+
| 0.372 | 4.84 | 3400 | 1.7283 | 0.5498 |
|
| 85 |
+
| 0.2944 | 4.99 | 3500 | 1.6987 | 0.5504 |
|
| 86 |
+
|
| 87 |
+
|
| 88 |
+
### Framework versions
|
| 89 |
+
|
| 90 |
+
- Transformers 4.30.2
|
| 91 |
+
- Pytorch 2.0.1+cu117
|
| 92 |
+
- Datasets 2.13.1
|
| 93 |
+
- Tokenizers 0.13.3
|