Upload folder using huggingface_hub
Browse files- checkpoint-2724/config.json +40 -0
- checkpoint-2724/model.safetensors +3 -0
- checkpoint-2724/optimizer.pt +3 -0
- checkpoint-2724/preprocessor_config.json +22 -0
- checkpoint-2724/rng_state.pth +3 -0
- checkpoint-2724/scheduler.pt +3 -0
- checkpoint-2724/trainer_state.json +164 -0
- checkpoint-2724/training_args.bin +3 -0
- model.safetensors +1 -1
- training_args.bin +1 -1
checkpoint-2724/config.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "dima806/face_emotions_image_detection",
|
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": "Ahegao",
|
13 |
+
"1": "Angry",
|
14 |
+
"2": "Happy",
|
15 |
+
"3": "Neutral",
|
16 |
+
"4": "Sad",
|
17 |
+
"5": "Surprise"
|
18 |
+
},
|
19 |
+
"image_size": 224,
|
20 |
+
"initializer_range": 0.02,
|
21 |
+
"intermediate_size": 3072,
|
22 |
+
"label2id": {
|
23 |
+
"Ahegao": 0,
|
24 |
+
"Angry": 1,
|
25 |
+
"Happy": 2,
|
26 |
+
"Neutral": 3,
|
27 |
+
"Sad": 4,
|
28 |
+
"Surprise": 5
|
29 |
+
},
|
30 |
+
"layer_norm_eps": 1e-12,
|
31 |
+
"model_type": "vit",
|
32 |
+
"num_attention_heads": 12,
|
33 |
+
"num_channels": 3,
|
34 |
+
"num_hidden_layers": 12,
|
35 |
+
"patch_size": 16,
|
36 |
+
"problem_type": "single_label_classification",
|
37 |
+
"qkv_bias": true,
|
38 |
+
"torch_dtype": "float32",
|
39 |
+
"transformers_version": "4.38.2"
|
40 |
+
}
|
checkpoint-2724/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a650d6fe7034f5cdb38f611d367f591a6927cde3684aa813bd0f1346e9239c64
|
3 |
+
size 343236280
|
checkpoint-2724/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c6bd209bfdaa2d2ff4acb6c3c22a1f93e6014d68789eaaba24dc5a62566aeda
|
3 |
+
size 686593029
|
checkpoint-2724/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 |
+
}
|
checkpoint-2724/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:13d9a9a25571a8bcdfedc8fbe826e977093a10d88d7e3aa1ecd288a693acc7bb
|
3 |
+
size 14575
|
checkpoint-2724/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e9008510da37520a988e9fad2ea2663d3fd1951e432d5ea7494d15925f2a6285
|
3 |
+
size 627
|
checkpoint-2724/trainer_state.json
ADDED
@@ -0,0 +1,164 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.6947017312049866,
|
3 |
+
"best_model_checkpoint": "face_emotions_image_detection/checkpoint-2724",
|
4 |
+
"epoch": 12.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 2724,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"eval_accuracy": 0.7846870150025866,
|
14 |
+
"eval_loss": 0.7017064690589905,
|
15 |
+
"eval_runtime": 138.7488,
|
16 |
+
"eval_samples_per_second": 69.658,
|
17 |
+
"eval_steps_per_second": 2.184,
|
18 |
+
"step": 227
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 2.0,
|
22 |
+
"eval_accuracy": 0.7864459389549923,
|
23 |
+
"eval_loss": 0.7000812888145447,
|
24 |
+
"eval_runtime": 138.1741,
|
25 |
+
"eval_samples_per_second": 69.948,
|
26 |
+
"eval_steps_per_second": 2.193,
|
27 |
+
"step": 454
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 2.2,
|
31 |
+
"grad_norm": 3.1080610752105713,
|
32 |
+
"learning_rate": 8.31712789827973e-08,
|
33 |
+
"loss": 0.6237,
|
34 |
+
"step": 500
|
35 |
+
},
|
36 |
+
{
|
37 |
+
"epoch": 3.0,
|
38 |
+
"eval_accuracy": 0.7862390067252975,
|
39 |
+
"eval_loss": 0.6997734308242798,
|
40 |
+
"eval_runtime": 140.1146,
|
41 |
+
"eval_samples_per_second": 68.979,
|
42 |
+
"eval_steps_per_second": 2.163,
|
43 |
+
"step": 681
|
44 |
+
},
|
45 |
+
{
|
46 |
+
"epoch": 4.0,
|
47 |
+
"eval_accuracy": 0.7867563372995344,
|
48 |
+
"eval_loss": 0.697901725769043,
|
49 |
+
"eval_runtime": 140.0452,
|
50 |
+
"eval_samples_per_second": 69.013,
|
51 |
+
"eval_steps_per_second": 2.164,
|
52 |
+
"step": 908
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"epoch": 4.41,
|
56 |
+
"grad_norm": 3.169142723083496,
|
57 |
+
"learning_rate": 6.447270007479431e-08,
|
58 |
+
"loss": 0.6196,
|
59 |
+
"step": 1000
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 5.0,
|
63 |
+
"eval_accuracy": 0.7861355406104501,
|
64 |
+
"eval_loss": 0.6978036761283875,
|
65 |
+
"eval_runtime": 138.4527,
|
66 |
+
"eval_samples_per_second": 69.807,
|
67 |
+
"eval_steps_per_second": 2.188,
|
68 |
+
"step": 1135
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 6.0,
|
72 |
+
"eval_accuracy": 0.7867563372995344,
|
73 |
+
"eval_loss": 0.6966344714164734,
|
74 |
+
"eval_runtime": 138.1448,
|
75 |
+
"eval_samples_per_second": 69.963,
|
76 |
+
"eval_steps_per_second": 2.193,
|
77 |
+
"step": 1362
|
78 |
+
},
|
79 |
+
{
|
80 |
+
"epoch": 6.61,
|
81 |
+
"grad_norm": 2.5825114250183105,
|
82 |
+
"learning_rate": 4.577412116679132e-08,
|
83 |
+
"loss": 0.6197,
|
84 |
+
"step": 1500
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 7.0,
|
88 |
+
"eval_accuracy": 0.7861355406104501,
|
89 |
+
"eval_loss": 0.6963701248168945,
|
90 |
+
"eval_runtime": 138.8184,
|
91 |
+
"eval_samples_per_second": 69.623,
|
92 |
+
"eval_steps_per_second": 2.183,
|
93 |
+
"step": 1589
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 8.0,
|
97 |
+
"eval_accuracy": 0.7867563372995344,
|
98 |
+
"eval_loss": 0.6955450177192688,
|
99 |
+
"eval_runtime": 138.7578,
|
100 |
+
"eval_samples_per_second": 69.654,
|
101 |
+
"eval_steps_per_second": 2.184,
|
102 |
+
"step": 1816
|
103 |
+
},
|
104 |
+
{
|
105 |
+
"epoch": 8.81,
|
106 |
+
"grad_norm": 1.9823120832443237,
|
107 |
+
"learning_rate": 2.7075542258788332e-08,
|
108 |
+
"loss": 0.6181,
|
109 |
+
"step": 2000
|
110 |
+
},
|
111 |
+
{
|
112 |
+
"epoch": 9.0,
|
113 |
+
"eval_accuracy": 0.7873771339886187,
|
114 |
+
"eval_loss": 0.694798469543457,
|
115 |
+
"eval_runtime": 139.1363,
|
116 |
+
"eval_samples_per_second": 69.464,
|
117 |
+
"eval_steps_per_second": 2.178,
|
118 |
+
"step": 2043
|
119 |
+
},
|
120 |
+
{
|
121 |
+
"epoch": 10.0,
|
122 |
+
"eval_accuracy": 0.7877909984480083,
|
123 |
+
"eval_loss": 0.6949805021286011,
|
124 |
+
"eval_runtime": 139.7823,
|
125 |
+
"eval_samples_per_second": 69.143,
|
126 |
+
"eval_steps_per_second": 2.168,
|
127 |
+
"step": 2270
|
128 |
+
},
|
129 |
+
{
|
130 |
+
"epoch": 11.0,
|
131 |
+
"eval_accuracy": 0.7868598034143818,
|
132 |
+
"eval_loss": 0.6948076486587524,
|
133 |
+
"eval_runtime": 139.4215,
|
134 |
+
"eval_samples_per_second": 69.322,
|
135 |
+
"eval_steps_per_second": 2.173,
|
136 |
+
"step": 2497
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 11.01,
|
140 |
+
"grad_norm": 3.7631289958953857,
|
141 |
+
"learning_rate": 8.37696335078534e-09,
|
142 |
+
"loss": 0.6174,
|
143 |
+
"step": 2500
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 12.0,
|
147 |
+
"eval_accuracy": 0.7877909984480083,
|
148 |
+
"eval_loss": 0.6947017312049866,
|
149 |
+
"eval_runtime": 140.3799,
|
150 |
+
"eval_samples_per_second": 68.849,
|
151 |
+
"eval_steps_per_second": 2.158,
|
152 |
+
"step": 2724
|
153 |
+
}
|
154 |
+
],
|
155 |
+
"logging_steps": 500,
|
156 |
+
"max_steps": 2724,
|
157 |
+
"num_input_tokens_seen": 0,
|
158 |
+
"num_train_epochs": 12,
|
159 |
+
"save_steps": 500,
|
160 |
+
"total_flos": 1.3481299778489303e+19,
|
161 |
+
"train_batch_size": 64,
|
162 |
+
"trial_name": null,
|
163 |
+
"trial_params": null
|
164 |
+
}
|
checkpoint-2724/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9dc0e4c6109cd1f16e9f3a30871e8df4e0d93ecb02bd9018029433b1a0b0b004
|
3 |
+
size 4411
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 343236280
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a650d6fe7034f5cdb38f611d367f591a6927cde3684aa813bd0f1346e9239c64
|
3 |
size 343236280
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4411
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9dc0e4c6109cd1f16e9f3a30871e8df4e0d93ecb02bd9018029433b1a0b0b004
|
3 |
size 4411
|