Upload folder using huggingface_hub
Browse files- checkpoint-825/config.json +38 -0
- checkpoint-825/model.safetensors +3 -0
- checkpoint-825/optimizer.pt +3 -0
- checkpoint-825/preprocessor_config.json +36 -0
- checkpoint-825/rng_state.pth +3 -0
- checkpoint-825/scheduler.pt +3 -0
- checkpoint-825/trainer_state.json +55 -0
- checkpoint-825/training_args.bin +3 -0
- config.json +2 -2
- model.safetensors +3 -0
- preprocessor_config.json +14 -0
- training_args.bin +2 -2
checkpoint-825/config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "dima806/shoe_types_image_detection",
|
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": "Clog",
|
13 |
+
"1": "Brogue",
|
14 |
+
"2": "Sneaker",
|
15 |
+
"3": "Boat",
|
16 |
+
"4": "Ballet Flat"
|
17 |
+
},
|
18 |
+
"image_size": 224,
|
19 |
+
"initializer_range": 0.02,
|
20 |
+
"intermediate_size": 3072,
|
21 |
+
"label2id": {
|
22 |
+
"Ballet Flat": 4,
|
23 |
+
"Boat": 3,
|
24 |
+
"Brogue": 1,
|
25 |
+
"Clog": 0,
|
26 |
+
"Sneaker": 2
|
27 |
+
},
|
28 |
+
"layer_norm_eps": 1e-12,
|
29 |
+
"model_type": "vit",
|
30 |
+
"num_attention_heads": 12,
|
31 |
+
"num_channels": 3,
|
32 |
+
"num_hidden_layers": 12,
|
33 |
+
"patch_size": 16,
|
34 |
+
"problem_type": "single_label_classification",
|
35 |
+
"qkv_bias": true,
|
36 |
+
"torch_dtype": "float32",
|
37 |
+
"transformers_version": "4.39.2"
|
38 |
+
}
|
checkpoint-825/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:66b3fbaa2f117ecc951b8f4feb09d6368677734fea7e953178f78c64b91ce80e
|
3 |
+
size 343233204
|
checkpoint-825/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:269c30064d83c9eb44f7581f3a4056f5af02905b6fc90097e581ac810d9e2d5c
|
3 |
+
size 686586885
|
checkpoint-825/preprocessor_config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_valid_processor_keys": [
|
3 |
+
"images",
|
4 |
+
"do_resize",
|
5 |
+
"size",
|
6 |
+
"resample",
|
7 |
+
"do_rescale",
|
8 |
+
"rescale_factor",
|
9 |
+
"do_normalize",
|
10 |
+
"image_mean",
|
11 |
+
"image_std",
|
12 |
+
"return_tensors",
|
13 |
+
"data_format",
|
14 |
+
"input_data_format"
|
15 |
+
],
|
16 |
+
"do_normalize": true,
|
17 |
+
"do_rescale": true,
|
18 |
+
"do_resize": true,
|
19 |
+
"image_mean": [
|
20 |
+
0.5,
|
21 |
+
0.5,
|
22 |
+
0.5
|
23 |
+
],
|
24 |
+
"image_processor_type": "ViTImageProcessor",
|
25 |
+
"image_std": [
|
26 |
+
0.5,
|
27 |
+
0.5,
|
28 |
+
0.5
|
29 |
+
],
|
30 |
+
"resample": 2,
|
31 |
+
"rescale_factor": 0.00392156862745098,
|
32 |
+
"size": {
|
33 |
+
"height": 224,
|
34 |
+
"width": 224
|
35 |
+
}
|
36 |
+
}
|
checkpoint-825/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:598a147207a775aa56d721e83dcab0044c3d8d282dbcb649c00bd2c70dd64a80
|
3 |
+
size 14575
|
checkpoint-825/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a4bd4c2fdc30fcff2b4851d0d3dbb6f1a76c7d297c5a9da96d7cfac8ba7f921b
|
3 |
+
size 627
|
checkpoint-825/trainer_state.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.11397659778594971,
|
3 |
+
"best_model_checkpoint": "shoe_types_image_detection/checkpoint-825",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 825,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"eval_accuracy": 0.9733242134062927,
|
14 |
+
"eval_loss": 0.1169578805565834,
|
15 |
+
"eval_runtime": 56.7835,
|
16 |
+
"eval_samples_per_second": 102.988,
|
17 |
+
"eval_steps_per_second": 12.873,
|
18 |
+
"step": 275
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 1.82,
|
22 |
+
"grad_norm": 0.18791599571704865,
|
23 |
+
"learning_rate": 6.60377358490566e-07,
|
24 |
+
"loss": 0.1145,
|
25 |
+
"step": 500
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 2.0,
|
29 |
+
"eval_accuracy": 0.9726402188782489,
|
30 |
+
"eval_loss": 0.11590158939361572,
|
31 |
+
"eval_runtime": 55.7676,
|
32 |
+
"eval_samples_per_second": 104.864,
|
33 |
+
"eval_steps_per_second": 13.108,
|
34 |
+
"step": 550
|
35 |
+
},
|
36 |
+
{
|
37 |
+
"epoch": 3.0,
|
38 |
+
"eval_accuracy": 0.9728112175102599,
|
39 |
+
"eval_loss": 0.11397659778594971,
|
40 |
+
"eval_runtime": 58.6195,
|
41 |
+
"eval_samples_per_second": 99.762,
|
42 |
+
"eval_steps_per_second": 12.47,
|
43 |
+
"step": 825
|
44 |
+
}
|
45 |
+
],
|
46 |
+
"logging_steps": 500,
|
47 |
+
"max_steps": 1375,
|
48 |
+
"num_input_tokens_seen": 0,
|
49 |
+
"num_train_epochs": 5,
|
50 |
+
"save_steps": 500,
|
51 |
+
"total_flos": 2.039334030940889e+18,
|
52 |
+
"train_batch_size": 32,
|
53 |
+
"trial_name": null,
|
54 |
+
"trial_params": null
|
55 |
+
}
|
checkpoint-825/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:55d5158de814356169cb68bf14bd11d8e53e1dc7ba8f76430b973ff8a16bdec5
|
3 |
+
size 4411
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"ViTForImageClassification"
|
5 |
],
|
@@ -34,5 +34,5 @@
|
|
34 |
"problem_type": "single_label_classification",
|
35 |
"qkv_bias": true,
|
36 |
"torch_dtype": "float32",
|
37 |
-
"transformers_version": "4.
|
38 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "dima806/shoe_types_image_detection",
|
3 |
"architectures": [
|
4 |
"ViTForImageClassification"
|
5 |
],
|
|
|
34 |
"problem_type": "single_label_classification",
|
35 |
"qkv_bias": true,
|
36 |
"torch_dtype": "float32",
|
37 |
+
"transformers_version": "4.39.2"
|
38 |
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:66b3fbaa2f117ecc951b8f4feb09d6368677734fea7e953178f78c64b91ce80e
|
3 |
+
size 343233204
|
preprocessor_config.json
CHANGED
@@ -1,4 +1,18 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"do_normalize": true,
|
3 |
"do_rescale": true,
|
4 |
"do_resize": true,
|
|
|
1 |
{
|
2 |
+
"_valid_processor_keys": [
|
3 |
+
"images",
|
4 |
+
"do_resize",
|
5 |
+
"size",
|
6 |
+
"resample",
|
7 |
+
"do_rescale",
|
8 |
+
"rescale_factor",
|
9 |
+
"do_normalize",
|
10 |
+
"image_mean",
|
11 |
+
"image_std",
|
12 |
+
"return_tensors",
|
13 |
+
"data_format",
|
14 |
+
"input_data_format"
|
15 |
+
],
|
16 |
"do_normalize": true,
|
17 |
"do_rescale": true,
|
18 |
"do_resize": true,
|
training_args.bin
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 sha256:55d5158de814356169cb68bf14bd11d8e53e1dc7ba8f76430b973ff8a16bdec5
|
3 |
+
size 4411
|