End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: google/muril-base-cased
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: nepali_complaints_classification_muril2
|
| 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 |
+
# nepali_complaints_classification_muril2
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [google/muril-base-cased](https://huggingface.co/google/muril-base-cased) on an unknown dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 2.6391
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 0.0003
|
| 38 |
+
- train_batch_size: 16
|
| 39 |
+
- eval_batch_size: 16
|
| 40 |
+
- seed: 42
|
| 41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
+
- lr_scheduler_type: linear
|
| 43 |
+
- lr_scheduler_warmup_steps: 50
|
| 44 |
+
- num_epochs: 5
|
| 45 |
+
|
| 46 |
+
### Training results
|
| 47 |
+
|
| 48 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 49 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
| 50 |
+
| 2.641 | 0.22 | 500 | 2.6403 |
|
| 51 |
+
| 2.6415 | 0.45 | 1000 | 2.6393 |
|
| 52 |
+
| 2.6399 | 0.67 | 1500 | 2.6393 |
|
| 53 |
+
| 2.64 | 0.89 | 2000 | 2.6395 |
|
| 54 |
+
| 2.6398 | 1.11 | 2500 | 2.6395 |
|
| 55 |
+
| 2.64 | 1.34 | 3000 | 2.6392 |
|
| 56 |
+
| 2.64 | 1.56 | 3500 | 2.6392 |
|
| 57 |
+
| 2.6387 | 1.78 | 4000 | 2.6402 |
|
| 58 |
+
| 2.64 | 2.01 | 4500 | 2.6391 |
|
| 59 |
+
| 2.6396 | 2.23 | 5000 | 2.6392 |
|
| 60 |
+
| 2.6394 | 2.45 | 5500 | 2.6391 |
|
| 61 |
+
| 2.64 | 2.67 | 6000 | 2.6392 |
|
| 62 |
+
| 2.6398 | 2.9 | 6500 | 2.6391 |
|
| 63 |
+
| 2.6395 | 3.12 | 7000 | 2.6391 |
|
| 64 |
+
| 2.6392 | 3.34 | 7500 | 2.6391 |
|
| 65 |
+
| 2.6384 | 3.57 | 8000 | 2.6394 |
|
| 66 |
+
| 2.6392 | 3.79 | 8500 | 2.6391 |
|
| 67 |
+
| 2.6392 | 4.01 | 9000 | 2.6391 |
|
| 68 |
+
| 2.639 | 4.23 | 9500 | 2.6391 |
|
| 69 |
+
| 2.6391 | 4.46 | 10000 | 2.6391 |
|
| 70 |
+
| 2.6391 | 4.68 | 10500 | 2.6391 |
|
| 71 |
+
| 2.6391 | 4.9 | 11000 | 2.6391 |
|
| 72 |
+
|
| 73 |
+
|
| 74 |
+
### Framework versions
|
| 75 |
+
|
| 76 |
+
- Transformers 4.38.2
|
| 77 |
+
- Pytorch 2.1.0+cu121
|
| 78 |
+
- Datasets 2.18.0
|
| 79 |
+
- Tokenizers 0.15.2
|