Update README.md
Browse files
README.md
CHANGED
@@ -32,47 +32,30 @@ A model that can detect 101 variety of food.
|
|
32 |
## Training Details
|
33 |
|
34 |
### Training Data
|
35 |
-
|
36 |
-
|
37 |
-
|
38 |
-
|
39 |
-
|
40 |
-
|
41 |
-
|
42 |
-
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
43 |
-
|
44 |
-
[More Information Needed]
|
45 |
-
|
46 |
-
### Training Procedure
|
47 |
-
|
48 |
-
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
49 |
-
|
50 |
-
#### Preprocessing [optional]
|
51 |
-
|
52 |
-
[More Information Needed]
|
53 |
-
|
54 |
|
55 |
#### Training Hyperparameters
|
56 |
|
57 |
The following hyperparameters were used during training:
|
58 |
|
59 |
-
|
60 |
-
|
61 |
-
|
62 |
-
|
63 |
-
|
64 |
-
|
65 |
-
-**num_epochs:** 1
|
66 |
-
|
67 |
-
[More Information Needed]
|
68 |
|
69 |
## Evaluation
|
70 |
|
71 |
<!-- This section describes the evaluation protocols and provides the results. -->
|
72 |
-
|
73 |
-
|
74 |
-
|
75 |
-
|
76 |
-
|
77 |
-
-**epoch:** 1.0
|
78 |
-
|
|
|
32 |
## Training Details
|
33 |
|
34 |
### Training Data
|
35 |
+
<ul>-**training_loss:**</ul>
|
36 |
+
<ul>-**train_runtime:** 3538</ul>
|
37 |
+
<ul>-**train_samples_per_second:** 21.409</ul>
|
38 |
+
<ul>-**train_steps_per_second:** 1.338</ul>
|
39 |
+
<ul>-**total_flos:** 5.8752267138432e+18</ul>
|
40 |
+
<ul>-**train_loss:** 1.7299224627936907</ul>
|
41 |
+
<ul>-**epoch:** 1.0</ul>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
42 |
|
43 |
#### Training Hyperparameters
|
44 |
|
45 |
The following hyperparameters were used during training:
|
46 |
|
47 |
+
<ul>-**learning_rate:** 5e-05</ul>
|
48 |
+
<ul>-**train_batch_size**: 16</ul>
|
49 |
+
<ul>-**seed:** 42</ul>
|
50 |
+
<ul>-**optimizer:** Adam with betas=(0.9,0.999) and epsilon=1e-08</ul>
|
51 |
+
<ul>-**lr_scheduler_type:** linear</ul>
|
52 |
+
<ul>-**num_epochs:** 1</ul>
|
|
|
|
|
|
|
53 |
|
54 |
## Evaluation
|
55 |
|
56 |
<!-- This section describes the evaluation protocols and provides the results. -->
|
57 |
+
<ul>-**eval_loss:** 0.7166455984115601</ul>
|
58 |
+
<ul>-**eval_accuracy:** 0.8753663366336634 </ul>
|
59 |
+
<ul>-**eval_runtime:** 446.9362</ul>
|
60 |
+
<ul>-**eval_steps_per_second:** 3.533</ul>
|
61 |
+
<ul>-**epoch:** 1.0</ul>
|
|
|
|