Upload . with huggingface_hub (#1)
Browse files- Upload . with huggingface_hub (e562b6a3df626e9b2a9c8a9b7fd6c42864b8b5ef)
- config.json +80 -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 +115 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "A",
|
13 |
+
"1": "B",
|
14 |
+
"10": "K",
|
15 |
+
"11": "L",
|
16 |
+
"12": "M",
|
17 |
+
"13": "N",
|
18 |
+
"14": "O",
|
19 |
+
"15": "P",
|
20 |
+
"16": "Q",
|
21 |
+
"17": "R",
|
22 |
+
"18": "S",
|
23 |
+
"19": "T",
|
24 |
+
"2": "C",
|
25 |
+
"20": "U",
|
26 |
+
"21": "V",
|
27 |
+
"22": "W",
|
28 |
+
"23": "X",
|
29 |
+
"24": "Y",
|
30 |
+
"25": "Z",
|
31 |
+
"3": "D",
|
32 |
+
"4": "E",
|
33 |
+
"5": "F",
|
34 |
+
"6": "G",
|
35 |
+
"7": "H",
|
36 |
+
"8": "I",
|
37 |
+
"9": "J"
|
38 |
+
},
|
39 |
+
"image_size": 224,
|
40 |
+
"initializer_range": 0.02,
|
41 |
+
"intermediate_size": 3072,
|
42 |
+
"label2id": {
|
43 |
+
"A": "0",
|
44 |
+
"B": "1",
|
45 |
+
"C": "2",
|
46 |
+
"D": "3",
|
47 |
+
"E": "4",
|
48 |
+
"F": "5",
|
49 |
+
"G": "6",
|
50 |
+
"H": "7",
|
51 |
+
"I": "8",
|
52 |
+
"J": "9",
|
53 |
+
"K": "10",
|
54 |
+
"L": "11",
|
55 |
+
"M": "12",
|
56 |
+
"N": "13",
|
57 |
+
"O": "14",
|
58 |
+
"P": "15",
|
59 |
+
"Q": "16",
|
60 |
+
"R": "17",
|
61 |
+
"S": "18",
|
62 |
+
"T": "19",
|
63 |
+
"U": "20",
|
64 |
+
"V": "21",
|
65 |
+
"W": "22",
|
66 |
+
"X": "23",
|
67 |
+
"Y": "24",
|
68 |
+
"Z": "25"
|
69 |
+
},
|
70 |
+
"layer_norm_eps": 1e-12,
|
71 |
+
"model_type": "vit",
|
72 |
+
"num_attention_heads": 12,
|
73 |
+
"num_channels": 3,
|
74 |
+
"num_hidden_layers": 12,
|
75 |
+
"patch_size": 16,
|
76 |
+
"problem_type": "single_label_classification",
|
77 |
+
"qkv_bias": true,
|
78 |
+
"torch_dtype": "float32",
|
79 |
+
"transformers_version": "4.27.1"
|
80 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4707f9afea1247ccf057df046d4da0f2dd3bf03e769079dcc2b91d002a4c58e3
|
3 |
+
size 686660677
|
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": "ViTFeatureExtractor",
|
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 sha256:83928cef548c01069d7ccdac9276a369ba934e364667133ddb531589b1d85417
|
3 |
+
size 343339757
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3bba1190063f9fd0c4fc38a73ada17cafcc64fcc8718ee377386996547e80d9f
|
3 |
+
size 13553
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a5e04b1e94948353a19f8926f6b8f153ec481673b668cfaf76d635ec0f994fd9
|
3 |
+
size 627
|
trainer_state.json
ADDED
@@ -0,0 +1,115 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.6364051699638367,
|
3 |
+
"best_model_checkpoint": "./vit-base-beans/checkpoint-120",
|
4 |
+
"epoch": 3.5294117647058822,
|
5 |
+
"global_step": 120,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.29,
|
12 |
+
"learning_rate": 0.00018529411764705883,
|
13 |
+
"loss": 3.1752,
|
14 |
+
"step": 10
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.59,
|
18 |
+
"learning_rate": 0.00017058823529411766,
|
19 |
+
"loss": 2.7524,
|
20 |
+
"step": 20
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.88,
|
24 |
+
"learning_rate": 0.00015588235294117648,
|
25 |
+
"loss": 2.3486,
|
26 |
+
"step": 30
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 1.18,
|
30 |
+
"learning_rate": 0.0001411764705882353,
|
31 |
+
"loss": 1.8512,
|
32 |
+
"step": 40
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 1.18,
|
36 |
+
"eval_accuracy": 0.7372881355932204,
|
37 |
+
"eval_loss": 1.7551679611206055,
|
38 |
+
"eval_runtime": 80.0325,
|
39 |
+
"eval_samples_per_second": 1.474,
|
40 |
+
"eval_steps_per_second": 0.187,
|
41 |
+
"step": 40
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 1.47,
|
45 |
+
"learning_rate": 0.0001264705882352941,
|
46 |
+
"loss": 1.5475,
|
47 |
+
"step": 50
|
48 |
+
},
|
49 |
+
{
|
50 |
+
"epoch": 1.76,
|
51 |
+
"learning_rate": 0.00011176470588235294,
|
52 |
+
"loss": 1.2493,
|
53 |
+
"step": 60
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 2.06,
|
57 |
+
"learning_rate": 9.705882352941177e-05,
|
58 |
+
"loss": 1.0852,
|
59 |
+
"step": 70
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 2.35,
|
63 |
+
"learning_rate": 8.23529411764706e-05,
|
64 |
+
"loss": 0.8329,
|
65 |
+
"step": 80
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 2.35,
|
69 |
+
"eval_accuracy": 0.9915254237288136,
|
70 |
+
"eval_loss": 0.9235942363739014,
|
71 |
+
"eval_runtime": 79.6393,
|
72 |
+
"eval_samples_per_second": 1.482,
|
73 |
+
"eval_steps_per_second": 0.188,
|
74 |
+
"step": 80
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 2.65,
|
78 |
+
"learning_rate": 6.764705882352942e-05,
|
79 |
+
"loss": 0.7635,
|
80 |
+
"step": 90
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 2.94,
|
84 |
+
"learning_rate": 5.294117647058824e-05,
|
85 |
+
"loss": 0.6581,
|
86 |
+
"step": 100
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 3.24,
|
90 |
+
"learning_rate": 3.8235294117647055e-05,
|
91 |
+
"loss": 0.5925,
|
92 |
+
"step": 110
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 3.53,
|
96 |
+
"learning_rate": 2.3529411764705884e-05,
|
97 |
+
"loss": 0.5486,
|
98 |
+
"step": 120
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 3.53,
|
102 |
+
"eval_accuracy": 0.9915254237288136,
|
103 |
+
"eval_loss": 0.6364051699638367,
|
104 |
+
"eval_runtime": 80.6234,
|
105 |
+
"eval_samples_per_second": 1.464,
|
106 |
+
"eval_steps_per_second": 0.186,
|
107 |
+
"step": 120
|
108 |
+
}
|
109 |
+
],
|
110 |
+
"max_steps": 136,
|
111 |
+
"num_train_epochs": 4,
|
112 |
+
"total_flos": 1.467238905086976e+17,
|
113 |
+
"trial_name": null,
|
114 |
+
"trial_params": null
|
115 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:64a424eaf6c6eced35203e0c2568f3bd00124f92f235a25aead1cd39bfbb90ec
|
3 |
+
size 3515
|