Monda/marbert-AraHealthQA-t1s1
Browse files- README.md +64 -0
- eval_metrics.json +7 -7
- model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
base_model: UBC-NLP/MARBERT
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: questions
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# questions
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [UBC-NLP/MARBERT](https://huggingface.co/UBC-NLP/MARBERT) on an unknown dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.3773
|
| 19 |
+
- Micro F1: 0.6604
|
| 20 |
+
- Weighted F1: 0.5871
|
| 21 |
+
- Jaccard: 0.5857
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 2e-05
|
| 41 |
+
- train_batch_size: 16
|
| 42 |
+
- eval_batch_size: 32
|
| 43 |
+
- seed: 42
|
| 44 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 45 |
+
- lr_scheduler_type: linear
|
| 46 |
+
- num_epochs: 5
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss | Micro F1 | Weighted F1 | Jaccard |
|
| 51 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:-----------:|:-------:|
|
| 52 |
+
| 0.5348 | 1.0 | 18 | 0.4242 | 0.6375 | 0.5254 | 0.5017 |
|
| 53 |
+
| 0.4411 | 2.0 | 36 | 0.3905 | 0.6575 | 0.5532 | 0.5821 |
|
| 54 |
+
| 0.4151 | 3.0 | 54 | 0.3773 | 0.6604 | 0.5871 | 0.5857 |
|
| 55 |
+
| 0.3852 | 4.0 | 72 | 0.3773 | 0.6176 | 0.5684 | 0.5476 |
|
| 56 |
+
| 0.3691 | 5.0 | 90 | 0.3732 | 0.6244 | 0.5701 | 0.5524 |
|
| 57 |
+
|
| 58 |
+
|
| 59 |
+
### Framework versions
|
| 60 |
+
|
| 61 |
+
- Transformers 4.52.4
|
| 62 |
+
- Pytorch 2.6.0+cu124
|
| 63 |
+
- Datasets 2.14.4
|
| 64 |
+
- Tokenizers 0.21.1
|
eval_metrics.json
CHANGED
|
@@ -1,10 +1,10 @@
|
|
| 1 |
{
|
| 2 |
-
"eval_loss": 0.
|
| 3 |
-
"eval_micro_f1": 0.
|
| 4 |
-
"eval_weighted_f1": 0.
|
| 5 |
-
"eval_jaccard": 0.
|
| 6 |
-
"eval_runtime": 0.
|
| 7 |
-
"eval_samples_per_second":
|
| 8 |
-
"eval_steps_per_second": 16.
|
| 9 |
"epoch": 5.0
|
| 10 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"eval_loss": 0.3773249089717865,
|
| 3 |
+
"eval_micro_f1": 0.660377358490566,
|
| 4 |
+
"eval_weighted_f1": 0.587091304787934,
|
| 5 |
+
"eval_jaccard": 0.5857142857142856,
|
| 6 |
+
"eval_runtime": 0.1821,
|
| 7 |
+
"eval_samples_per_second": 384.432,
|
| 8 |
+
"eval_steps_per_second": 16.476,
|
| 9 |
"epoch": 5.0
|
| 10 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 651410452
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5d14ed8e19799ee2153c5312a81f785a6aeb5497e7dafb337d5b7101cfba8287
|
| 3 |
size 651410452
|