Model save
Browse files- README.md +73 -0
- model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
metrics:
|
| 5 |
+
- accuracy
|
| 6 |
+
- recall
|
| 7 |
+
- precision
|
| 8 |
+
model-index:
|
| 9 |
+
- name: MARBERT-QADI
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# MARBERT-QADI
|
| 17 |
+
|
| 18 |
+
This model was trained from scratch on the None dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 2.0342
|
| 21 |
+
- Macro F1: 0.5099
|
| 22 |
+
- Accuracy: 0.5138
|
| 23 |
+
- Recall: 0.5136
|
| 24 |
+
- Precision: 0.6223
|
| 25 |
+
|
| 26 |
+
## Model description
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Intended uses & limitations
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training and evaluation data
|
| 35 |
+
|
| 36 |
+
More information needed
|
| 37 |
+
|
| 38 |
+
## Training procedure
|
| 39 |
+
|
| 40 |
+
### Training hyperparameters
|
| 41 |
+
|
| 42 |
+
The following hyperparameters were used during training:
|
| 43 |
+
- learning_rate: 4e-06
|
| 44 |
+
- train_batch_size: 128
|
| 45 |
+
- eval_batch_size: 128
|
| 46 |
+
- seed: 42
|
| 47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
+
- lr_scheduler_type: linear
|
| 49 |
+
- num_epochs: 10
|
| 50 |
+
- mixed_precision_training: Native AMP
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss | Macro F1 | Accuracy | Recall | Precision |
|
| 55 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|:------:|:---------:|
|
| 56 |
+
| 0.8588 | 1.0 | 1125 | 0.7883 | 0.7550 | 0.7554 | 0.7552 | 0.7609 |
|
| 57 |
+
| 0.7475 | 2.0 | 2250 | 0.7718 | 0.7632 | 0.7634 | 0.7631 | 0.7653 |
|
| 58 |
+
| 0.6527 | 3.0 | 3375 | 0.7758 | 0.7668 | 0.7673 | 0.7671 | 0.7679 |
|
| 59 |
+
| 0.5654 | 4.0 | 4500 | 0.7845 | 0.7665 | 0.7673 | 0.7671 | 0.7682 |
|
| 60 |
+
| 0.5001 | 5.0 | 5625 | 0.8068 | 0.7650 | 0.7663 | 0.7660 | 0.7657 |
|
| 61 |
+
| 0.4641 | 6.0 | 6750 | 0.8216 | 0.7647 | 0.7658 | 0.7655 | 0.7650 |
|
| 62 |
+
| 0.4049 | 7.0 | 7875 | 0.8393 | 0.7645 | 0.7654 | 0.7649 | 0.7657 |
|
| 63 |
+
| 0.3773 | 8.0 | 9000 | 0.8477 | 0.7651 | 0.7657 | 0.7654 | 0.7659 |
|
| 64 |
+
| 0.3393 | 9.0 | 10125 | 0.8569 | 0.7663 | 0.7669 | 0.7665 | 0.7670 |
|
| 65 |
+
| 0.3383 | 10.0 | 11250 | 0.8589 | 0.7663 | 0.7669 | 0.7666 | 0.7667 |
|
| 66 |
+
|
| 67 |
+
|
| 68 |
+
### Framework versions
|
| 69 |
+
|
| 70 |
+
- Transformers 4.40.1
|
| 71 |
+
- Pytorch 2.2.1+cu121
|
| 72 |
+
- Datasets 2.18.0
|
| 73 |
+
- Tokenizers 0.19.1
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 651444296
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c5fb9ea54f30eec11f32aa44c013b05599c1499dc8029e6dcd2de7a4449824af
|
| 3 |
size 651444296
|