update model card README.md
Browse files
README.md
CHANGED
@@ -2,8 +2,6 @@
|
|
2 |
license: apache-2.0
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
-
metrics:
|
6 |
-
- accuracy
|
7 |
model-index:
|
8 |
- name: distilbert-base-uncased-finetuned-sst2
|
9 |
results: []
|
@@ -14,10 +12,15 @@ should probably proofread and complete it, then remove this comment. -->
|
|
14 |
|
15 |
# distilbert-base-uncased-finetuned-sst2
|
16 |
|
17 |
-
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
-
|
20 |
-
-
|
|
|
|
|
|
|
|
|
|
|
21 |
|
22 |
## Model description
|
23 |
|
@@ -36,22 +39,13 @@ More information needed
|
|
36 |
### Training hyperparameters
|
37 |
|
38 |
The following hyperparameters were used during training:
|
39 |
-
- learning_rate:
|
40 |
-
- train_batch_size:
|
41 |
- eval_batch_size: 16
|
42 |
-
- seed:
|
43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
- lr_scheduler_type: linear
|
45 |
-
- num_epochs:
|
46 |
-
|
47 |
-
### Training results
|
48 |
-
|
49 |
-
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
50 |
-
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
51 |
-
| No log | 1.0 | 25 | 0.6027 | 0.6541 |
|
52 |
-
| No log | 2.0 | 50 | 0.5744 | 0.6541 |
|
53 |
-
| No log | 3.0 | 75 | 0.5620 | 0.6541 |
|
54 |
-
|
55 |
|
56 |
### Framework versions
|
57 |
|
|
|
2 |
license: apache-2.0
|
3 |
tags:
|
4 |
- generated_from_trainer
|
|
|
|
|
5 |
model-index:
|
6 |
- name: distilbert-base-uncased-finetuned-sst2
|
7 |
results: []
|
|
|
12 |
|
13 |
# distilbert-base-uncased-finetuned-sst2
|
14 |
|
15 |
+
This model is a fine-tuned version of [Telstema/distilbert-base-uncased-finetuned-sst2](https://huggingface.co/Telstema/distilbert-base-uncased-finetuned-sst2) on the None dataset.
|
16 |
It achieves the following results on the evaluation set:
|
17 |
+
- eval_loss: 2.7080
|
18 |
+
- eval_accuracy: 0.7218
|
19 |
+
- eval_runtime: 13.1083
|
20 |
+
- eval_samples_per_second: 10.146
|
21 |
+
- eval_steps_per_second: 0.687
|
22 |
+
- epoch: 2.0
|
23 |
+
- step: 100
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
39 |
### Training hyperparameters
|
40 |
|
41 |
The following hyperparameters were used during training:
|
42 |
+
- learning_rate: 3.909275911638729e-06
|
43 |
+
- train_batch_size: 8
|
44 |
- eval_batch_size: 16
|
45 |
+
- seed: 23
|
46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
- lr_scheduler_type: linear
|
48 |
+
- num_epochs: 2
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
49 |
|
50 |
### Framework versions
|
51 |
|