Upload folder using huggingface_hub
Browse files- checkpoint-4688/config.json +46 -0
- checkpoint-4688/model.safetensors +3 -0
- checkpoint-4688/optimizer.pt +3 -0
- checkpoint-4688/preprocessor_config.json +23 -0
- checkpoint-4688/rng_state.pth +3 -0
- checkpoint-4688/scheduler.pt +3 -0
- checkpoint-4688/trainer_state.json +116 -0
- checkpoint-4688/training_args.bin +3 -0
- model.safetensors +1 -1
checkpoint-4688/config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "0-2",
|
13 |
+
"1": "3-9",
|
14 |
+
"2": "10-19",
|
15 |
+
"3": "20-29",
|
16 |
+
"4": "30-39",
|
17 |
+
"5": "40-49",
|
18 |
+
"6": "50-59",
|
19 |
+
"7": "60-69",
|
20 |
+
"8": "more than 70"
|
21 |
+
},
|
22 |
+
"image_size": 224,
|
23 |
+
"initializer_range": 0.02,
|
24 |
+
"intermediate_size": 3072,
|
25 |
+
"label2id": {
|
26 |
+
"0-2": 0,
|
27 |
+
"10-19": 2,
|
28 |
+
"20-29": 3,
|
29 |
+
"3-9": 1,
|
30 |
+
"30-39": 4,
|
31 |
+
"40-49": 5,
|
32 |
+
"50-59": 6,
|
33 |
+
"60-69": 7,
|
34 |
+
"more than 70": 8
|
35 |
+
},
|
36 |
+
"layer_norm_eps": 1e-12,
|
37 |
+
"model_type": "vit",
|
38 |
+
"num_attention_heads": 12,
|
39 |
+
"num_channels": 3,
|
40 |
+
"num_hidden_layers": 12,
|
41 |
+
"patch_size": 16,
|
42 |
+
"problem_type": "single_label_classification",
|
43 |
+
"qkv_bias": true,
|
44 |
+
"torch_dtype": "float32",
|
45 |
+
"transformers_version": "4.47.0"
|
46 |
+
}
|
checkpoint-4688/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f6f3b28c3de06bcedbae8b985363f2df21de98524d8165e2c6cc7f998d98c57
|
3 |
+
size 343245508
|
checkpoint-4688/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8791320f4d583baaa89f9cc262a7a6bbf539b9f9a9e4914e6837a32bd47a7d98
|
3 |
+
size 686611898
|
checkpoint-4688/preprocessor_config.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_convert_rgb": null,
|
3 |
+
"do_normalize": true,
|
4 |
+
"do_rescale": true,
|
5 |
+
"do_resize": true,
|
6 |
+
"image_mean": [
|
7 |
+
0.5,
|
8 |
+
0.5,
|
9 |
+
0.5
|
10 |
+
],
|
11 |
+
"image_processor_type": "ViTImageProcessor",
|
12 |
+
"image_std": [
|
13 |
+
0.5,
|
14 |
+
0.5,
|
15 |
+
0.5
|
16 |
+
],
|
17 |
+
"resample": 2,
|
18 |
+
"rescale_factor": 0.00392156862745098,
|
19 |
+
"size": {
|
20 |
+
"height": 224,
|
21 |
+
"width": 224
|
22 |
+
}
|
23 |
+
}
|
checkpoint-4688/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b3ee827a7a00012c0a116546df467feee35e70376d81a7a85b1a70eb90414d3
|
3 |
+
size 14244
|
checkpoint-4688/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b93e187257ca6fe0f5b0bc88b5e29ad4936be1b98b0acb5f887bb184be713f3d
|
3 |
+
size 1064
|
checkpoint-4688/trainer_state.json
ADDED
@@ -0,0 +1,116 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 1.233594298362732,
|
3 |
+
"best_model_checkpoint": "fairface_age_image_detection/checkpoint-4688",
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 4688,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.21331058020477817,
|
13 |
+
"grad_norm": 1.7164175510406494,
|
14 |
+
"learning_rate": 2.2574385510996123e-06,
|
15 |
+
"loss": 1.945,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.42662116040955633,
|
20 |
+
"grad_norm": 1.979918360710144,
|
21 |
+
"learning_rate": 1.9879258300991807e-06,
|
22 |
+
"loss": 1.5803,
|
23 |
+
"step": 1000
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.6399317406143344,
|
27 |
+
"grad_norm": 2.0418295860290527,
|
28 |
+
"learning_rate": 1.7184131090987496e-06,
|
29 |
+
"loss": 1.4368,
|
30 |
+
"step": 1500
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.8532423208191127,
|
34 |
+
"grad_norm": 2.872443199157715,
|
35 |
+
"learning_rate": 1.4489003880983182e-06,
|
36 |
+
"loss": 1.3531,
|
37 |
+
"step": 2000
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 1.0,
|
41 |
+
"eval_accuracy": 0.5275,
|
42 |
+
"eval_loss": 1.3043227195739746,
|
43 |
+
"eval_model_preparation_time": 0.0035,
|
44 |
+
"eval_runtime": 894.9363,
|
45 |
+
"eval_samples_per_second": 11.174,
|
46 |
+
"eval_steps_per_second": 1.397,
|
47 |
+
"step": 2344
|
48 |
+
},
|
49 |
+
{
|
50 |
+
"epoch": 1.0665529010238908,
|
51 |
+
"grad_norm": 4.807504177093506,
|
52 |
+
"learning_rate": 1.179387667097887e-06,
|
53 |
+
"loss": 1.3097,
|
54 |
+
"step": 2500
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 1.2798634812286689,
|
58 |
+
"grad_norm": 6.204404830932617,
|
59 |
+
"learning_rate": 9.098749460974558e-07,
|
60 |
+
"loss": 1.2671,
|
61 |
+
"step": 3000
|
62 |
+
},
|
63 |
+
{
|
64 |
+
"epoch": 1.493174061433447,
|
65 |
+
"grad_norm": 6.795459270477295,
|
66 |
+
"learning_rate": 6.403622250970247e-07,
|
67 |
+
"loss": 1.2428,
|
68 |
+
"step": 3500
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 1.7064846416382253,
|
72 |
+
"grad_norm": 3.4942402839660645,
|
73 |
+
"learning_rate": 3.708495040965934e-07,
|
74 |
+
"loss": 1.2307,
|
75 |
+
"step": 4000
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 1.9197952218430034,
|
79 |
+
"grad_norm": 3.384183406829834,
|
80 |
+
"learning_rate": 1.0133678309616215e-07,
|
81 |
+
"loss": 1.2214,
|
82 |
+
"step": 4500
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"epoch": 2.0,
|
86 |
+
"eval_accuracy": 0.5385,
|
87 |
+
"eval_loss": 1.233594298362732,
|
88 |
+
"eval_model_preparation_time": 0.0035,
|
89 |
+
"eval_runtime": 903.6391,
|
90 |
+
"eval_samples_per_second": 11.066,
|
91 |
+
"eval_steps_per_second": 1.383,
|
92 |
+
"step": 4688
|
93 |
+
}
|
94 |
+
],
|
95 |
+
"logging_steps": 500,
|
96 |
+
"max_steps": 4688,
|
97 |
+
"num_input_tokens_seen": 0,
|
98 |
+
"num_train_epochs": 2,
|
99 |
+
"save_steps": 500,
|
100 |
+
"stateful_callbacks": {
|
101 |
+
"TrainerControl": {
|
102 |
+
"args": {
|
103 |
+
"should_epoch_stop": false,
|
104 |
+
"should_evaluate": false,
|
105 |
+
"should_log": false,
|
106 |
+
"should_save": true,
|
107 |
+
"should_training_stop": true
|
108 |
+
},
|
109 |
+
"attributes": {}
|
110 |
+
}
|
111 |
+
},
|
112 |
+
"total_flos": 1.16245277051904e+19,
|
113 |
+
"train_batch_size": 32,
|
114 |
+
"trial_name": null,
|
115 |
+
"trial_params": null
|
116 |
+
}
|
checkpoint-4688/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:28ebf2b6dbb08045128c07625eb89924fd949f0c3794edd35784a5c320305df8
|
3 |
+
size 5304
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 343245508
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f6f3b28c3de06bcedbae8b985363f2df21de98524d8165e2c6cc7f998d98c57
|
3 |
size 343245508
|