Upload folder using huggingface_hub
Browse files- checkpoint-8752/config.json +46 -0
- checkpoint-8752/model.safetensors +3 -0
- checkpoint-8752/optimizer.pt +3 -0
- checkpoint-8752/preprocessor_config.json +23 -0
- checkpoint-8752/rng_state.pth +3 -0
- checkpoint-8752/scheduler.pt +3 -0
- checkpoint-8752/trainer_state.json +192 -0
- checkpoint-8752/training_args.bin +3 -0
- model.safetensors +1 -1
- training_args.bin +1 -1
checkpoint-8752/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-8752/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cd3a725b1119d48b89118403515c77428316605407f871bbc7bba7fb50b32305
|
3 |
+
size 343245508
|
checkpoint-8752/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:087e51816b138512d362a1022cf69ae38505cd21144fa8057f954593880b9011
|
3 |
+
size 686611898
|
checkpoint-8752/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-8752/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:48ee9b73399c28d7e668360bf1d5a4d11095c4738bf96c13f7bb6fbff59f8ccb
|
3 |
+
size 14244
|
checkpoint-8752/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:197fc8dcfe2b6e4805b14a2ff8529c35795cc2f0491c4b5a6bd2783753725f19
|
3 |
+
size 1064
|
checkpoint-8752/trainer_state.json
ADDED
@@ -0,0 +1,192 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 1.0447938442230225,
|
3 |
+
"best_model_checkpoint": "fairface_age_image_detection/checkpoint-8752",
|
4 |
+
"epoch": 4.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 8752,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.22851919561243145,
|
13 |
+
"grad_norm": 2.228593587875366,
|
14 |
+
"learning_rate": 3.7931509997701674e-06,
|
15 |
+
"loss": 1.8122,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.4570383912248629,
|
20 |
+
"grad_norm": 3.4612433910369873,
|
21 |
+
"learning_rate": 3.5633187772925763e-06,
|
22 |
+
"loss": 1.4177,
|
23 |
+
"step": 1000
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.6855575868372943,
|
27 |
+
"grad_norm": 5.7468061447143555,
|
28 |
+
"learning_rate": 3.333486554814985e-06,
|
29 |
+
"loss": 1.3017,
|
30 |
+
"step": 1500
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.9140767824497258,
|
34 |
+
"grad_norm": 4.807565212249756,
|
35 |
+
"learning_rate": 3.1036543323373935e-06,
|
36 |
+
"loss": 1.2187,
|
37 |
+
"step": 2000
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 1.0,
|
41 |
+
"eval_accuracy": 0.5457,
|
42 |
+
"eval_loss": 1.1929566860198975,
|
43 |
+
"eval_model_preparation_time": 0.0035,
|
44 |
+
"eval_runtime": 876.5594,
|
45 |
+
"eval_samples_per_second": 11.408,
|
46 |
+
"eval_steps_per_second": 1.426,
|
47 |
+
"step": 2188
|
48 |
+
},
|
49 |
+
{
|
50 |
+
"epoch": 1.1425959780621573,
|
51 |
+
"grad_norm": 3.004606246948242,
|
52 |
+
"learning_rate": 2.873822109859802e-06,
|
53 |
+
"loss": 1.1713,
|
54 |
+
"step": 2500
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 1.3711151736745886,
|
58 |
+
"grad_norm": 4.531455039978027,
|
59 |
+
"learning_rate": 2.643989887382211e-06,
|
60 |
+
"loss": 1.1284,
|
61 |
+
"step": 3000
|
62 |
+
},
|
63 |
+
{
|
64 |
+
"epoch": 1.59963436928702,
|
65 |
+
"grad_norm": 3.8209729194641113,
|
66 |
+
"learning_rate": 2.4141576649046196e-06,
|
67 |
+
"loss": 1.105,
|
68 |
+
"step": 3500
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 1.8281535648994516,
|
72 |
+
"grad_norm": 3.4607913494110107,
|
73 |
+
"learning_rate": 2.184325442427028e-06,
|
74 |
+
"loss": 1.0773,
|
75 |
+
"step": 4000
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 2.0,
|
79 |
+
"eval_accuracy": 0.5754,
|
80 |
+
"eval_loss": 1.085502028465271,
|
81 |
+
"eval_model_preparation_time": 0.0035,
|
82 |
+
"eval_runtime": 892.4566,
|
83 |
+
"eval_samples_per_second": 11.205,
|
84 |
+
"eval_steps_per_second": 1.401,
|
85 |
+
"step": 4376
|
86 |
+
},
|
87 |
+
{
|
88 |
+
"epoch": 2.056672760511883,
|
89 |
+
"grad_norm": 4.261874675750732,
|
90 |
+
"learning_rate": 1.954493219949437e-06,
|
91 |
+
"loss": 1.0657,
|
92 |
+
"step": 4500
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 2.2851919561243146,
|
96 |
+
"grad_norm": 3.815229654312134,
|
97 |
+
"learning_rate": 1.7246609974718455e-06,
|
98 |
+
"loss": 1.036,
|
99 |
+
"step": 5000
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 2.5137111517367456,
|
103 |
+
"grad_norm": 4.119363307952881,
|
104 |
+
"learning_rate": 1.494828774994254e-06,
|
105 |
+
"loss": 1.0255,
|
106 |
+
"step": 5500
|
107 |
+
},
|
108 |
+
{
|
109 |
+
"epoch": 2.742230347349177,
|
110 |
+
"grad_norm": 4.172023296356201,
|
111 |
+
"learning_rate": 1.2649965525166627e-06,
|
112 |
+
"loss": 1.0126,
|
113 |
+
"step": 6000
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 2.9707495429616086,
|
117 |
+
"grad_norm": 3.792961597442627,
|
118 |
+
"learning_rate": 1.0351643300390714e-06,
|
119 |
+
"loss": 1.008,
|
120 |
+
"step": 6500
|
121 |
+
},
|
122 |
+
{
|
123 |
+
"epoch": 3.0,
|
124 |
+
"eval_accuracy": 0.5792,
|
125 |
+
"eval_loss": 1.0549699068069458,
|
126 |
+
"eval_model_preparation_time": 0.0035,
|
127 |
+
"eval_runtime": 902.9283,
|
128 |
+
"eval_samples_per_second": 11.075,
|
129 |
+
"eval_steps_per_second": 1.384,
|
130 |
+
"step": 6564
|
131 |
+
},
|
132 |
+
{
|
133 |
+
"epoch": 3.19926873857404,
|
134 |
+
"grad_norm": 6.58300256729126,
|
135 |
+
"learning_rate": 8.053321075614801e-07,
|
136 |
+
"loss": 0.9923,
|
137 |
+
"step": 7000
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 3.4277879341864717,
|
141 |
+
"grad_norm": 7.9831223487854,
|
142 |
+
"learning_rate": 5.754998850838887e-07,
|
143 |
+
"loss": 0.9792,
|
144 |
+
"step": 7500
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 3.656307129798903,
|
148 |
+
"grad_norm": 6.074549198150635,
|
149 |
+
"learning_rate": 3.456676626062974e-07,
|
150 |
+
"loss": 0.9826,
|
151 |
+
"step": 8000
|
152 |
+
},
|
153 |
+
{
|
154 |
+
"epoch": 3.8848263254113347,
|
155 |
+
"grad_norm": 6.298589706420898,
|
156 |
+
"learning_rate": 1.1583544012870603e-07,
|
157 |
+
"loss": 0.9858,
|
158 |
+
"step": 8500
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 4.0,
|
162 |
+
"eval_accuracy": 0.5809,
|
163 |
+
"eval_loss": 1.0447938442230225,
|
164 |
+
"eval_model_preparation_time": 0.0035,
|
165 |
+
"eval_runtime": 893.1973,
|
166 |
+
"eval_samples_per_second": 11.196,
|
167 |
+
"eval_steps_per_second": 1.399,
|
168 |
+
"step": 8752
|
169 |
+
}
|
170 |
+
],
|
171 |
+
"logging_steps": 500,
|
172 |
+
"max_steps": 8752,
|
173 |
+
"num_input_tokens_seen": 0,
|
174 |
+
"num_train_epochs": 4,
|
175 |
+
"save_steps": 500,
|
176 |
+
"stateful_callbacks": {
|
177 |
+
"TrainerControl": {
|
178 |
+
"args": {
|
179 |
+
"should_epoch_stop": false,
|
180 |
+
"should_evaluate": false,
|
181 |
+
"should_log": false,
|
182 |
+
"should_save": true,
|
183 |
+
"should_training_stop": true
|
184 |
+
},
|
185 |
+
"attributes": {}
|
186 |
+
}
|
187 |
+
},
|
188 |
+
"total_flos": 2.169911838302208e+19,
|
189 |
+
"train_batch_size": 32,
|
190 |
+
"trial_name": null,
|
191 |
+
"trial_params": null
|
192 |
+
}
|
checkpoint-8752/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e97ef976af56a6fd0395073925187744ad7c56829cffa99ff2332a90f94307b2
|
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:cd3a725b1119d48b89118403515c77428316605407f871bbc7bba7fb50b32305
|
3 |
size 343245508
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5304
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e97ef976af56a6fd0395073925187744ad7c56829cffa99ff2332a90f94307b2
|
3 |
size 5304
|