Commit
•
e86e10c
1
Parent(s):
3e626ad
Training complete
Browse files
README.md
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
metrics:
|
| 5 |
+
- accuracy
|
| 6 |
+
model-index:
|
| 7 |
+
- name: mamba_text_classification
|
| 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 |
+
# mamba_text_classification
|
| 15 |
+
|
| 16 |
+
This model was trained from scratch on an unknown dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.2144
|
| 19 |
+
- Accuracy: 0.944
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 5e-05
|
| 39 |
+
- train_batch_size: 4
|
| 40 |
+
- eval_batch_size: 16
|
| 41 |
+
- seed: 42
|
| 42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
+
- lr_scheduler_type: cosine
|
| 44 |
+
- lr_scheduler_warmup_ratio: 0.01
|
| 45 |
+
- num_epochs: 1
|
| 46 |
+
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 50 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 51 |
+
| 0.0088 | 0.1 | 625 | 0.2663 | 0.9216 |
|
| 52 |
+
| 3.5723 | 0.2 | 1250 | 0.3047 | 0.8962 |
|
| 53 |
+
| 1.4067 | 0.3 | 1875 | 0.2881 | 0.919 |
|
| 54 |
+
| 0.278 | 0.4 | 2500 | 0.2252 | 0.9322 |
|
| 55 |
+
| 0.0034 | 0.5 | 3125 | 0.2200 | 0.9382 |
|
| 56 |
+
| 2.526 | 0.6 | 3750 | 0.2670 | 0.9354 |
|
| 57 |
+
| 0.5528 | 0.7 | 4375 | 0.2209 | 0.9386 |
|
| 58 |
+
| 0.0006 | 0.8 | 5000 | 0.2294 | 0.9432 |
|
| 59 |
+
| 0.0358 | 0.9 | 5625 | 0.2167 | 0.9438 |
|
| 60 |
+
| 0.5311 | 1.0 | 6250 | 0.2144 | 0.944 |
|
| 61 |
+
|
| 62 |
+
|
| 63 |
+
### Framework versions
|
| 64 |
+
|
| 65 |
+
- Transformers 4.40.0
|
| 66 |
+
- Pytorch 2.2.1+cu121
|
| 67 |
+
- Datasets 2.19.0
|
| 68 |
+
- Tokenizers 0.19.1
|