Training in progress, epoch 0
Browse files- model.safetensors +1 -1
- runs/Feb12_01-50-37_3621747748f3/events.out.tfevents.1707702638.3621747748f3.6471.5 +2 -2
- runs/Feb12_01-59-26_3621747748f3/events.out.tfevents.1707703218.3621747748f3.6471.6 +3 -0
- tmp-checkpoint-171/config.json +71 -0
- tmp-checkpoint-171/model.safetensors +3 -0
- tmp-checkpoint-171/optimizer.pt +3 -0
- tmp-checkpoint-171/preprocessor_config.json +22 -0
- tmp-checkpoint-171/rng_state.pth +3 -0
- tmp-checkpoint-171/scheduler.pt +3 -0
- tmp-checkpoint-171/trainer_state.json +141 -0
- tmp-checkpoint-171/training_args.bin +3 -0
- training_args.bin +1 -1
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 110358212
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:46440987de3f5c8a94e72e022bb7dba5a0c8fe64021871f96e19d3c2e8ccd0fb
|
3 |
size 110358212
|
runs/Feb12_01-50-37_3621747748f3/events.out.tfevents.1707702638.3621747748f3.6471.5
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 sha256:7677d9543b831985a07d0edd43fd681258fa9dec91cd2b0a7c4f2400be0eda92
|
3 |
+
size 8171
|
runs/Feb12_01-59-26_3621747748f3/events.out.tfevents.1707703218.3621747748f3.6471.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f89a05b4b45f7326058ce51e3110cf3e06110d9ba7093161f7b9e1c90136dd82
|
3 |
+
size 6554
|
tmp-checkpoint-171/config.json
ADDED
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/swin-tiny-patch4-window7-224",
|
3 |
+
"architectures": [
|
4 |
+
"SwinForImageClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.0,
|
7 |
+
"depths": [
|
8 |
+
2,
|
9 |
+
2,
|
10 |
+
6,
|
11 |
+
2
|
12 |
+
],
|
13 |
+
"drop_path_rate": 0.1,
|
14 |
+
"embed_dim": 96,
|
15 |
+
"encoder_stride": 32,
|
16 |
+
"hidden_act": "gelu",
|
17 |
+
"hidden_dropout_prob": 0.0,
|
18 |
+
"hidden_size": 768,
|
19 |
+
"id2label": {
|
20 |
+
"0": "0",
|
21 |
+
"1": "1",
|
22 |
+
"2": "2",
|
23 |
+
"3": "3",
|
24 |
+
"4": "4",
|
25 |
+
"5": "5",
|
26 |
+
"6": "6"
|
27 |
+
},
|
28 |
+
"image_size": 224,
|
29 |
+
"initializer_range": 0.02,
|
30 |
+
"label2id": {
|
31 |
+
"0": 0,
|
32 |
+
"1": 1,
|
33 |
+
"2": 2,
|
34 |
+
"3": 3,
|
35 |
+
"4": 4,
|
36 |
+
"5": 5,
|
37 |
+
"6": 6
|
38 |
+
},
|
39 |
+
"layer_norm_eps": 1e-05,
|
40 |
+
"mlp_ratio": 4.0,
|
41 |
+
"model_type": "swin",
|
42 |
+
"num_channels": 3,
|
43 |
+
"num_heads": [
|
44 |
+
3,
|
45 |
+
6,
|
46 |
+
12,
|
47 |
+
24
|
48 |
+
],
|
49 |
+
"num_layers": 4,
|
50 |
+
"out_features": [
|
51 |
+
"stage4"
|
52 |
+
],
|
53 |
+
"out_indices": [
|
54 |
+
4
|
55 |
+
],
|
56 |
+
"patch_size": 4,
|
57 |
+
"path_norm": true,
|
58 |
+
"problem_type": "single_label_classification",
|
59 |
+
"qkv_bias": true,
|
60 |
+
"stage_names": [
|
61 |
+
"stem",
|
62 |
+
"stage1",
|
63 |
+
"stage2",
|
64 |
+
"stage3",
|
65 |
+
"stage4"
|
66 |
+
],
|
67 |
+
"torch_dtype": "float32",
|
68 |
+
"transformers_version": "4.37.2",
|
69 |
+
"use_absolute_embeddings": false,
|
70 |
+
"window_size": 7
|
71 |
+
}
|
tmp-checkpoint-171/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6dedf70c2df2660d690f1a1962dc3af10a0e87b4826ec9d904685207f200ceb2
|
3 |
+
size 110358212
|
tmp-checkpoint-171/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:41b5501351c52709a9dfe0199edf14b5b118b3a049158599e3f095c24e6e0db4
|
3 |
+
size 220381306
|
tmp-checkpoint-171/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 |
+
0.485,
|
7 |
+
0.456,
|
8 |
+
0.406
|
9 |
+
],
|
10 |
+
"image_processor_type": "ViTImageProcessor",
|
11 |
+
"image_std": [
|
12 |
+
0.229,
|
13 |
+
0.224,
|
14 |
+
0.225
|
15 |
+
],
|
16 |
+
"resample": 3,
|
17 |
+
"rescale_factor": 0.00392156862745098,
|
18 |
+
"size": {
|
19 |
+
"height": 224,
|
20 |
+
"width": 224
|
21 |
+
}
|
22 |
+
}
|
tmp-checkpoint-171/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:26d02f9508928bb28f21d5d1b083b1a28985b5bd0ecbe1e5b9c0147bc14a1956
|
3 |
+
size 14244
|
tmp-checkpoint-171/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:79760f282e6b1d3312d9a7d855fc6aba70759deaec819d5a373afcb25264e5e2
|
3 |
+
size 1064
|
tmp-checkpoint-171/trainer_state.json
ADDED
@@ -0,0 +1,141 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.7170383055043567,
|
3 |
+
"best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-art/checkpoint-171",
|
4 |
+
"epoch": 1.9941690962099126,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 171,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.12,
|
13 |
+
"learning_rate": 1.96078431372549e-06,
|
14 |
+
"loss": 2.0347,
|
15 |
+
"step": 10
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.23,
|
19 |
+
"learning_rate": 3.92156862745098e-06,
|
20 |
+
"loss": 1.9855,
|
21 |
+
"step": 20
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.35,
|
25 |
+
"learning_rate": 5.882352941176471e-06,
|
26 |
+
"loss": 1.8774,
|
27 |
+
"step": 30
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.47,
|
31 |
+
"learning_rate": 7.84313725490196e-06,
|
32 |
+
"loss": 1.7658,
|
33 |
+
"step": 40
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.58,
|
37 |
+
"learning_rate": 9.803921568627451e-06,
|
38 |
+
"loss": 1.6138,
|
39 |
+
"step": 50
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.7,
|
43 |
+
"learning_rate": 1.1764705882352942e-05,
|
44 |
+
"loss": 1.422,
|
45 |
+
"step": 60
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.82,
|
49 |
+
"learning_rate": 1.3725490196078432e-05,
|
50 |
+
"loss": 1.3298,
|
51 |
+
"step": 70
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.93,
|
55 |
+
"learning_rate": 1.568627450980392e-05,
|
56 |
+
"loss": 1.262,
|
57 |
+
"step": 80
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.99,
|
61 |
+
"eval_f1": 0.5746968921742681,
|
62 |
+
"eval_loss": 1.1490696668624878,
|
63 |
+
"eval_runtime": 23.7551,
|
64 |
+
"eval_samples_per_second": 115.302,
|
65 |
+
"eval_steps_per_second": 3.62,
|
66 |
+
"step": 85
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 1.05,
|
70 |
+
"learning_rate": 1.7647058823529414e-05,
|
71 |
+
"loss": 1.1287,
|
72 |
+
"step": 90
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 1.17,
|
76 |
+
"learning_rate": 1.9607843137254903e-05,
|
77 |
+
"loss": 1.0018,
|
78 |
+
"step": 100
|
79 |
+
},
|
80 |
+
{
|
81 |
+
"epoch": 1.28,
|
82 |
+
"learning_rate": 2.1568627450980395e-05,
|
83 |
+
"loss": 1.01,
|
84 |
+
"step": 110
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 1.4,
|
88 |
+
"learning_rate": 2.3529411764705884e-05,
|
89 |
+
"loss": 1.032,
|
90 |
+
"step": 120
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 1.52,
|
94 |
+
"learning_rate": 2.5490196078431373e-05,
|
95 |
+
"loss": 0.9039,
|
96 |
+
"step": 130
|
97 |
+
},
|
98 |
+
{
|
99 |
+
"epoch": 1.63,
|
100 |
+
"learning_rate": 2.7450980392156865e-05,
|
101 |
+
"loss": 0.8492,
|
102 |
+
"step": 140
|
103 |
+
},
|
104 |
+
{
|
105 |
+
"epoch": 1.75,
|
106 |
+
"learning_rate": 2.9411764705882354e-05,
|
107 |
+
"loss": 0.8667,
|
108 |
+
"step": 150
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 1.87,
|
112 |
+
"learning_rate": 3.137254901960784e-05,
|
113 |
+
"loss": 0.7881,
|
114 |
+
"step": 160
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 1.98,
|
118 |
+
"learning_rate": 3.3333333333333335e-05,
|
119 |
+
"loss": 0.7538,
|
120 |
+
"step": 170
|
121 |
+
},
|
122 |
+
{
|
123 |
+
"epoch": 1.99,
|
124 |
+
"eval_f1": 0.7170383055043567,
|
125 |
+
"eval_loss": 0.7177160978317261,
|
126 |
+
"eval_runtime": 27.6306,
|
127 |
+
"eval_samples_per_second": 99.129,
|
128 |
+
"eval_steps_per_second": 3.112,
|
129 |
+
"step": 171
|
130 |
+
}
|
131 |
+
],
|
132 |
+
"logging_steps": 10,
|
133 |
+
"max_steps": 2550,
|
134 |
+
"num_input_tokens_seen": 0,
|
135 |
+
"num_train_epochs": 30,
|
136 |
+
"save_steps": 500,
|
137 |
+
"total_flos": 5.4452164834993766e+17,
|
138 |
+
"train_batch_size": 32,
|
139 |
+
"trial_name": null,
|
140 |
+
"trial_params": null
|
141 |
+
}
|
tmp-checkpoint-171/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ef751f4bf4face5cd82ee28830aff995ffc43704fce6b432389be6b8cd94afb
|
3 |
+
size 4728
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4728
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:95231cafff335d8674e0be344939852dfd20eede2ea3fa613ed8afe557eddffc
|
3 |
size 4728
|