upload new model checkpoint
Browse files- config.json +42 -0
- optimizer.pt +3 -0
- preprocessor_config.json +22 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +79 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "Apparel",
|
13 |
+
"1": "Sporting Goods",
|
14 |
+
"2": "Home",
|
15 |
+
"3": "Free Items",
|
16 |
+
"4": "Personal Care",
|
17 |
+
"5": "Accessories",
|
18 |
+
"6": "Footwear"
|
19 |
+
},
|
20 |
+
"image_size": 224,
|
21 |
+
"initializer_range": 0.02,
|
22 |
+
"intermediate_size": 3072,
|
23 |
+
"label2id": {
|
24 |
+
"Accessories": 5,
|
25 |
+
"Apparel": 0,
|
26 |
+
"Footwear": 6,
|
27 |
+
"Free Items": 3,
|
28 |
+
"Home": 2,
|
29 |
+
"Personal Care": 4,
|
30 |
+
"Sporting Goods": 1
|
31 |
+
},
|
32 |
+
"layer_norm_eps": 1e-12,
|
33 |
+
"model_type": "vit",
|
34 |
+
"num_attention_heads": 12,
|
35 |
+
"num_channels": 3,
|
36 |
+
"num_hidden_layers": 12,
|
37 |
+
"patch_size": 16,
|
38 |
+
"problem_type": "single_label_classification",
|
39 |
+
"qkv_bias": true,
|
40 |
+
"torch_dtype": "float32",
|
41 |
+
"transformers_version": "4.28.1"
|
42 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:97cc3dcc2c9c673ce88499adfd630921a9a2f4767c3f66d76a6f616590c048f4
|
3 |
+
size 686549637
|
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 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf0dbaf8fcf0f6c476ffa48f57d18fe20712ada3d5648fd5133d52f0828f16b6
|
3 |
+
size 343284077
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:43babfc04eb37728491e763ea3da2387a71720ed39253f7834f4a7b70160caf3
|
3 |
+
size 14575
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5d9ff003eb9eb44b690cad87eb468397a5b1ae91ff019f6aced32c8273a40a73
|
3 |
+
size 627
|
trainer_state.json
ADDED
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.9954722872755659,
|
3 |
+
"best_model_checkpoint": "Fashion-Product-Images/checkpoint-3405",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"global_step": 3405,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.44,
|
12 |
+
"learning_rate": 1.7063142437591777e-05,
|
13 |
+
"loss": 0.3201,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.88,
|
18 |
+
"learning_rate": 1.4126284875183555e-05,
|
19 |
+
"loss": 0.0822,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 1.0,
|
24 |
+
"eval_accuracy": 0.9925058548009368,
|
25 |
+
"eval_loss": 0.05954417213797569,
|
26 |
+
"eval_runtime": 104.2766,
|
27 |
+
"eval_samples_per_second": 61.423,
|
28 |
+
"eval_steps_per_second": 15.363,
|
29 |
+
"step": 1135
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 1.32,
|
33 |
+
"learning_rate": 1.1189427312775332e-05,
|
34 |
+
"loss": 0.0579,
|
35 |
+
"step": 1500
|
36 |
+
},
|
37 |
+
{
|
38 |
+
"epoch": 1.76,
|
39 |
+
"learning_rate": 8.252569750367108e-06,
|
40 |
+
"loss": 0.0428,
|
41 |
+
"step": 2000
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 2.0,
|
45 |
+
"eval_accuracy": 0.9953161592505855,
|
46 |
+
"eval_loss": 0.035637322813272476,
|
47 |
+
"eval_runtime": 105.6472,
|
48 |
+
"eval_samples_per_second": 60.626,
|
49 |
+
"eval_steps_per_second": 15.164,
|
50 |
+
"step": 2270
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 2.2,
|
54 |
+
"learning_rate": 5.3157121879588845e-06,
|
55 |
+
"loss": 0.0346,
|
56 |
+
"step": 2500
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 2.64,
|
60 |
+
"learning_rate": 2.378854625550661e-06,
|
61 |
+
"loss": 0.0333,
|
62 |
+
"step": 3000
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 3.0,
|
66 |
+
"eval_accuracy": 0.9954722872755659,
|
67 |
+
"eval_loss": 0.03034268133342266,
|
68 |
+
"eval_runtime": 103.3556,
|
69 |
+
"eval_samples_per_second": 61.97,
|
70 |
+
"eval_steps_per_second": 15.5,
|
71 |
+
"step": 3405
|
72 |
+
}
|
73 |
+
],
|
74 |
+
"max_steps": 3405,
|
75 |
+
"num_train_epochs": 3,
|
76 |
+
"total_flos": 8.43809341205118e+18,
|
77 |
+
"trial_name": null,
|
78 |
+
"trial_params": null
|
79 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:669f0a99796ef19ecf6f8cc22b49a160d59cbe82f7b9ad1e81db41435958db56
|
3 |
+
size 3579
|