Model save
Browse files
README.md
CHANGED
@@ -3,6 +3,8 @@ license: apache-2.0
|
|
3 |
base_model: tigeryi/imagenet1k
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
|
|
6 |
model-index:
|
7 |
- name: imagenet-tiger
|
8 |
results: []
|
@@ -15,12 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
This model is a fine-tuned version of [tigeryi/imagenet1k](https://huggingface.co/tigeryi/imagenet1k) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
-
|
19 |
-
-
|
20 |
-
- eval_runtime: 189.3787
|
21 |
-
- eval_samples_per_second: 52.804
|
22 |
-
- eval_steps_per_second: 1.653
|
23 |
-
- step: 0
|
24 |
|
25 |
## Model description
|
26 |
|
@@ -39,13 +37,22 @@ More information needed
|
|
39 |
### Training hyperparameters
|
40 |
|
41 |
The following hyperparameters were used during training:
|
42 |
-
- learning_rate:
|
43 |
- train_batch_size: 32
|
44 |
- eval_batch_size: 32
|
45 |
-
- seed:
|
46 |
-
- optimizer: Adam with betas=(0.9,0.
|
47 |
-
- lr_scheduler_type:
|
48 |
-
- num_epochs:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
49 |
|
50 |
### Framework versions
|
51 |
|
|
|
3 |
base_model: tigeryi/imagenet1k
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
model-index:
|
9 |
- name: imagenet-tiger
|
10 |
results: []
|
|
|
17 |
|
18 |
This model is a fine-tuned version of [tigeryi/imagenet1k](https://huggingface.co/tigeryi/imagenet1k) on an unknown dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.6595
|
21 |
+
- Accuracy: 0.8254
|
|
|
|
|
|
|
|
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
37 |
### Training hyperparameters
|
38 |
|
39 |
The following hyperparameters were used during training:
|
40 |
+
- learning_rate: 0.0001
|
41 |
- train_batch_size: 32
|
42 |
- eval_batch_size: 32
|
43 |
+
- seed: 42
|
44 |
+
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
|
45 |
+
- lr_scheduler_type: cosine
|
46 |
+
- num_epochs: 3
|
47 |
+
|
48 |
+
### Training results
|
49 |
+
|
50 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
51 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
52 |
+
| 1.0771 | 1.0 | 1250 | 0.7663 | 0.7971 |
|
53 |
+
| 0.8206 | 2.0 | 2500 | 0.6772 | 0.8207 |
|
54 |
+
| 0.7212 | 3.0 | 3750 | 0.6595 | 0.8254 |
|
55 |
+
|
56 |
|
57 |
### Framework versions
|
58 |
|