Downloads · 30 days
9
16% of all-time downloads
FineTuning
grrfdghebsz/FineTuning
FineTuning is a text classification model from grrfdghebsz. Use it when you need a label for a piece of text. It is set up for transformers. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
55
Public
Parameters
278M
21.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.1 GB · 98%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- mit
- Model type
- xlm-roberta
- Access
- Public
- Created
- Jan 26, 2024
- Updated
- Jan 26, 2024
- SHA
- c93b4b51
Try a prompt
Base models
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
FineTuning
This model is a fine-tuned version of xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2930
- Jaccard (sample): [0.6076190476190476, 0.4382716049382716, 0.6174636174636174, 0.40869565217391307, 0.25, 0.2815884476534296, 0.20987654320987653, 0.0]
- Jaccard (macro): 0.3517
- Macro-precision: 0.5303
- Macro-recall: 0.4556
- Macro F1: 0.4869
- Micro F1: 0.6352
- Accuracy: 0.3742
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 6
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Jaccard (sample) | Jaccard (macro) | Macro-precision | Macro-recall | Macro F1 | Micro F1 | Accuracy |
|---|---|---|---|---|---|---|---|---|---|---|
| 0.4975 | 1.0 | 339 | 0.3645 | [0.35964912280701755, 0.14566929133858267, 0.014742014742014743, 0.0, 0.0, 0.0, 0.0, 0.0] | 0.0650 | 0.3352 | 0.0688 | 0.1015 | 0.2109 | 0.145 |
| 0.37 | 2.0 | 678 | 0.3212 | [0.5595238095238095, 0.41836734693877553, 0.519916142557652, 0.26013513513513514, 0.15384615384615385, 0.2743055555555556, 0.266304347826087, 0.0] | 0.3065 | 0.5170 | 0.4010 | 0.4403 | 0.5802 | 0.315 |
| 0.3193 | 3.0 | 1017 | 0.3064 | [0.6198198198198198, 0.39100346020761245, 0.5995893223819302, 0.35597826086956524, 0.0, 0.08071748878923767, 0.032520325203252036, 0.0] | 0.2600 | 0.5439 | 0.3302 | 0.3518 | 0.5995 | 0.3592 |
| 0.2894 | 4.0 | 1356 | 0.2954 | [0.5859375, 0.4208955223880597, 0.5944333996023857, 0.3930635838150289, 0.13333333333333333, 0.199203187250996, 0.21084337349397592, 0.0] | 0.3172 | 0.5068 | 0.4093 | 0.4446 | 0.6130 | 0.3667 |
| 0.2679 | 5.0 | 1695 | 0.2927 | [0.5968688845401174, 0.42342342342342343, 0.6072186836518046, 0.39039039039039036, 0.23076923076923078, 0.2847222222222222, 0.20261437908496732, 0.0] | 0.3420 | 0.5541 | 0.4299 | 0.4769 | 0.6247 | 0.3758 |
| 0.2519 | 6.0 | 2034 | 0.2930 | [0.6076190476190476, 0.4382716049382716, 0.6174636174636174, 0.40869565217391307, 0.25, 0.2815884476534296, 0.20987654320987653, 0.0] | 0.3517 | 0.5303 | 0.4556 | 0.4869 | 0.6352 | 0.3742 |
Framework versions
- Transformers 4.36.2
- Pytorch 1.13.0
- Datasets 2.16.1
- Tokenizers 0.15.0
- Task
- Text Classification
- Library
- transformers
- Type
- xlm-roberta
- License
- mit
- Created
- Jan 26, 2024
- Updated
- Jan 26, 2024