Commit
•
2bb4a9f
1
Parent(s):
4b0703f
ChrisGuarino/cats
Browse files- README.md +52 -0
- all_results.json +7 -0
- config.json +32 -0
- model.safetensors +3 -0
- preprocessor_config.json +22 -0
- train_results.json +7 -0
- trainer_state.json +66 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: google/vit-base-patch16-224-in21k
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: cat_ds
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# cat_ds
|
15 |
+
|
16 |
+
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.
|
17 |
+
|
18 |
+
## Model description
|
19 |
+
|
20 |
+
More information needed
|
21 |
+
|
22 |
+
## Intended uses & limitations
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Training and evaluation data
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training procedure
|
31 |
+
|
32 |
+
### Training hyperparameters
|
33 |
+
|
34 |
+
The following hyperparameters were used during training:
|
35 |
+
- learning_rate: 0.0002
|
36 |
+
- train_batch_size: 16
|
37 |
+
- eval_batch_size: 8
|
38 |
+
- seed: 42
|
39 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
40 |
+
- lr_scheduler_type: linear
|
41 |
+
- num_epochs: 4
|
42 |
+
|
43 |
+
### Training results
|
44 |
+
|
45 |
+
|
46 |
+
|
47 |
+
### Framework versions
|
48 |
+
|
49 |
+
- Transformers 4.36.2
|
50 |
+
- Pytorch 2.1.2
|
51 |
+
- Datasets 2.16.0
|
52 |
+
- Tokenizers 0.15.0
|
all_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 4.0,
|
3 |
+
"train_loss": 0.12354437162478765,
|
4 |
+
"train_runtime": 816.8581,
|
5 |
+
"train_samples_per_second": 1.131,
|
6 |
+
"train_steps_per_second": 0.073
|
7 |
+
}
|
config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/vit-base-patch16-224-in21k",
|
3 |
+
"architectures": [
|
4 |
+
"ViTForImageClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.0,
|
7 |
+
"encoder_stride": 16,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.0,
|
10 |
+
"hidden_size": 768,
|
11 |
+
"id2label": {
|
12 |
+
"0": "prim",
|
13 |
+
"1": "rupe"
|
14 |
+
},
|
15 |
+
"image_size": 224,
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"intermediate_size": 3072,
|
18 |
+
"label2id": {
|
19 |
+
"prim": "0",
|
20 |
+
"rupe": "1"
|
21 |
+
},
|
22 |
+
"layer_norm_eps": 1e-12,
|
23 |
+
"model_type": "vit",
|
24 |
+
"num_attention_heads": 12,
|
25 |
+
"num_channels": 3,
|
26 |
+
"num_hidden_layers": 12,
|
27 |
+
"patch_size": 16,
|
28 |
+
"problem_type": "single_label_classification",
|
29 |
+
"qkv_bias": true,
|
30 |
+
"torch_dtype": "float32",
|
31 |
+
"transformers_version": "4.36.2"
|
32 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5472cbd618ef0d3c3b04e83047187bc72de0f548d053a6148232410589ba0f33
|
3 |
+
size 343223968
|
preprocessor_config.json
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": true,
|
3 |
+
"do_rescale": true,
|
4 |
+
"do_resize": true,
|
5 |
+
"image_mean": [
|
6 |
+
0.5,
|
7 |
+
0.5,
|
8 |
+
0.5
|
9 |
+
],
|
10 |
+
"image_processor_type": "ViTImageProcessor",
|
11 |
+
"image_std": [
|
12 |
+
0.5,
|
13 |
+
0.5,
|
14 |
+
0.5
|
15 |
+
],
|
16 |
+
"resample": 2,
|
17 |
+
"rescale_factor": 0.00392156862745098,
|
18 |
+
"size": {
|
19 |
+
"height": 224,
|
20 |
+
"width": 224
|
21 |
+
}
|
22 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 4.0,
|
3 |
+
"train_loss": 0.12354437162478765,
|
4 |
+
"train_runtime": 816.8581,
|
5 |
+
"train_samples_per_second": 1.131,
|
6 |
+
"train_steps_per_second": 0.073
|
7 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.0,
|
5 |
+
"eval_steps": 100,
|
6 |
+
"global_step": 60,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.67,
|
13 |
+
"learning_rate": 0.0001666666666666667,
|
14 |
+
"loss": 0.5123,
|
15 |
+
"step": 10
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 1.33,
|
19 |
+
"learning_rate": 0.00013333333333333334,
|
20 |
+
"loss": 0.1132,
|
21 |
+
"step": 20
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 2.0,
|
25 |
+
"learning_rate": 0.0001,
|
26 |
+
"loss": 0.0663,
|
27 |
+
"step": 30
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 2.67,
|
31 |
+
"learning_rate": 6.666666666666667e-05,
|
32 |
+
"loss": 0.024,
|
33 |
+
"step": 40
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 3.33,
|
37 |
+
"learning_rate": 3.3333333333333335e-05,
|
38 |
+
"loss": 0.0122,
|
39 |
+
"step": 50
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 4.0,
|
43 |
+
"learning_rate": 0.0,
|
44 |
+
"loss": 0.0131,
|
45 |
+
"step": 60
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 4.0,
|
49 |
+
"step": 60,
|
50 |
+
"total_flos": 7.160259840388301e+16,
|
51 |
+
"train_loss": 0.12354437162478765,
|
52 |
+
"train_runtime": 816.8581,
|
53 |
+
"train_samples_per_second": 1.131,
|
54 |
+
"train_steps_per_second": 0.073
|
55 |
+
}
|
56 |
+
],
|
57 |
+
"logging_steps": 10,
|
58 |
+
"max_steps": 60,
|
59 |
+
"num_input_tokens_seen": 0,
|
60 |
+
"num_train_epochs": 4,
|
61 |
+
"save_steps": 100,
|
62 |
+
"total_flos": 7.160259840388301e+16,
|
63 |
+
"train_batch_size": 16,
|
64 |
+
"trial_name": null,
|
65 |
+
"trial_params": null
|
66 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61371cd75b4f638b15ec45c535d3fe4ceb885a5adcccc6832a649781076427f3
|
3 |
+
size 4664
|