Moreno La Quatra
commited on
Commit
•
ef2e4e4
1
Parent(s):
d0b5b30
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- accuracy
|
| 7 |
+
- f1
|
| 8 |
+
- precision
|
| 9 |
+
- recall
|
| 10 |
+
model-index:
|
| 11 |
+
- name: distilbert-base-cased-emotion
|
| 12 |
+
results: []
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 16 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 17 |
+
|
| 18 |
+
# distilbert-base-cased-emotion
|
| 19 |
+
|
| 20 |
+
This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on an unknown dataset.
|
| 21 |
+
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 0.1771
|
| 23 |
+
- Accuracy: 0.9265
|
| 24 |
+
- F1: 0.9263
|
| 25 |
+
- Precision: 0.9276
|
| 26 |
+
- Recall: 0.9265
|
| 27 |
+
|
| 28 |
+
## Model description
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Intended uses & limitations
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training and evaluation data
|
| 37 |
+
|
| 38 |
+
More information needed
|
| 39 |
+
|
| 40 |
+
## Training procedure
|
| 41 |
+
|
| 42 |
+
### Training hyperparameters
|
| 43 |
+
|
| 44 |
+
The following hyperparameters were used during training:
|
| 45 |
+
- learning_rate: 5e-05
|
| 46 |
+
- train_batch_size: 32
|
| 47 |
+
- eval_batch_size: 32
|
| 48 |
+
- seed: 42
|
| 49 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 50 |
+
- lr_scheduler_type: linear
|
| 51 |
+
- lr_scheduler_warmup_steps: 500
|
| 52 |
+
- num_epochs: 10
|
| 53 |
+
- mixed_precision_training: Native AMP
|
| 54 |
+
|
| 55 |
+
### Training results
|
| 56 |
+
|
| 57 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|
| 58 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
|
| 59 |
+
| 0.2633 | 1.0 | 500 | 0.2505 | 0.917 | 0.9174 | 0.9183 | 0.917 |
|
| 60 |
+
| 0.1815 | 2.0 | 1000 | 0.1921 | 0.9305 | 0.9304 | 0.9329 | 0.9305 |
|
| 61 |
+
| 0.1224 | 3.0 | 1500 | 0.1721 | 0.9355 | 0.9361 | 0.9388 | 0.9355 |
|
| 62 |
+
| 0.093 | 4.0 | 2000 | 0.1712 | 0.9365 | 0.9359 | 0.9367 | 0.9365 |
|
| 63 |
+
| 0.0782 | 5.0 | 2500 | 0.2116 | 0.9275 | 0.9271 | 0.9272 | 0.9275 |
|
| 64 |
+
| 0.0548 | 6.0 | 3000 | 0.2353 | 0.936 | 0.9348 | 0.9362 | 0.936 |
|
| 65 |
+
| 0.0358 | 7.0 | 3500 | 0.2729 | 0.9325 | 0.9331 | 0.9345 | 0.9325 |
|
| 66 |
+
| 0.0185 | 8.0 | 4000 | 0.3059 | 0.9325 | 0.9323 | 0.9322 | 0.9325 |
|
| 67 |
+
| 0.0124 | 9.0 | 4500 | 0.3103 | 0.9325 | 0.9325 | 0.9325 | 0.9325 |
|
| 68 |
+
| 0.0137 | 10.0 | 5000 | 0.3161 | 0.9305 | 0.9303 | 0.9303 | 0.9305 |
|
| 69 |
+
|
| 70 |
+
|
| 71 |
+
### Framework versions
|
| 72 |
+
|
| 73 |
+
- Transformers 4.22.1
|
| 74 |
+
- Pytorch 1.11.0+cu113
|
| 75 |
+
- Datasets 2.0.0
|
| 76 |
+
- Tokenizers 0.11.6
|