End of training
Browse files
README.md
CHANGED
@@ -4,8 +4,6 @@ license: apache-2.0
|
|
4 |
base_model: google/vit-base-patch16-224-in21k
|
5 |
tags:
|
6 |
- generated_from_trainer
|
7 |
-
metrics:
|
8 |
-
- accuracy
|
9 |
model-index:
|
10 |
- name: asl_classification
|
11 |
results: []
|
@@ -18,8 +16,13 @@ should probably proofread and complete it, then remove this comment. -->
|
|
18 |
|
19 |
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
-
-
|
22 |
-
-
|
|
|
|
|
|
|
|
|
|
|
23 |
|
24 |
## Model description
|
25 |
|
@@ -38,32 +41,16 @@ More information needed
|
|
38 |
### Training hyperparameters
|
39 |
|
40 |
The following hyperparameters were used during training:
|
41 |
-
- learning_rate:
|
42 |
-
- train_batch_size:
|
43 |
-
- eval_batch_size:
|
44 |
- seed: 42
|
45 |
-
- gradient_accumulation_steps:
|
46 |
-
- total_train_batch_size:
|
47 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
48 |
-
- lr_scheduler_type:
|
49 |
- lr_scheduler_warmup_ratio: 0.1
|
50 |
-
- num_epochs:
|
51 |
-
|
52 |
-
### Training results
|
53 |
-
|
54 |
-
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
55 |
-
|:-------------:|:------:|:----:|:---------------:|:--------:|
|
56 |
-
| No log | 0.9231 | 6 | 3.1928 | 0.1058 |
|
57 |
-
| 2.9337 | 2.0 | 13 | 3.2067 | 0.0865 |
|
58 |
-
| 2.9337 | 2.9231 | 19 | 3.1925 | 0.1154 |
|
59 |
-
| 2.9273 | 4.0 | 26 | 3.1791 | 0.0769 |
|
60 |
-
| 2.9166 | 4.9231 | 32 | 3.1959 | 0.0962 |
|
61 |
-
| 2.9166 | 6.0 | 39 | 3.1797 | 0.0962 |
|
62 |
-
| 2.9078 | 6.9231 | 45 | 3.1835 | 0.1058 |
|
63 |
-
| 2.9157 | 8.0 | 52 | 3.1814 | 0.1154 |
|
64 |
-
| 2.9157 | 8.9231 | 58 | 3.1744 | 0.1058 |
|
65 |
-
| 2.9313 | 9.2308 | 60 | 3.1843 | 0.0962 |
|
66 |
-
|
67 |
|
68 |
### Framework versions
|
69 |
|
|
|
4 |
base_model: google/vit-base-patch16-224-in21k
|
5 |
tags:
|
6 |
- generated_from_trainer
|
|
|
|
|
7 |
model-index:
|
8 |
- name: asl_classification
|
9 |
results: []
|
|
|
16 |
|
17 |
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- eval_loss: 3.0043
|
20 |
+
- eval_accuracy: 0.2019
|
21 |
+
- eval_runtime: 1.4504
|
22 |
+
- eval_samples_per_second: 71.703
|
23 |
+
- eval_steps_per_second: 2.758
|
24 |
+
- epoch: 21.5385
|
25 |
+
- step: 35
|
26 |
|
27 |
## Model description
|
28 |
|
|
|
41 |
### Training hyperparameters
|
42 |
|
43 |
The following hyperparameters were used during training:
|
44 |
+
- learning_rate: 3e-05
|
45 |
+
- train_batch_size: 32
|
46 |
+
- eval_batch_size: 32
|
47 |
- seed: 42
|
48 |
+
- gradient_accumulation_steps: 8
|
49 |
+
- total_train_batch_size: 256
|
50 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
+
- lr_scheduler_type: cosine
|
52 |
- lr_scheduler_warmup_ratio: 0.1
|
53 |
+
- num_epochs: 100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
54 |
|
55 |
### Framework versions
|
56 |
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 343297800
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cd7b1f219566d255e5df5509f04e3ff4d7c93d17fad9472421f53a36aa2ff84e
|
3 |
size 343297800
|
runs/Sep22_05-51-58_a5fe0263c8a0/events.out.tfevents.1726984319.a5fe0263c8a0.1647.1
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3ba8901722369f2ff6c7c7d62f22ca2ff9edfd3b74aa803599b93ba07c2a2b33
|
3 |
+
size 13346
|