dima806 commited on
Commit
663d621
·
verified ·
1 Parent(s): 43a549f

Upload folder using huggingface_hub

Browse files
checkpoint-2720/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-2720/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eee9038c9276c6d6e40ff864346d278bf4129b3050408403208e88d2a0a8933f
3
+ size 343236280
checkpoint-2720/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e161eaaa06521256a37bdfcd41d9ca0bf9175137b42601561cd0c356a49974b1
3
+ size 686593029
checkpoint-2720/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-2720/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf434721ddfc65f25706cd46489df4f5fef8407b84a96098844eced15994518b
3
+ size 14575
checkpoint-2720/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f403e9bebb5c340a868abadfb465f8bc00ed7c65ef6b0f1f564d652194528ea8
3
+ size 627
checkpoint-2720/trainer_state.json ADDED
@@ -0,0 +1,128 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7845879793167114,
3
+ "best_model_checkpoint": "face_emotions_image_detection/checkpoint-2720",
4
+ "epoch": 8.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2720,
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": 0.7579644187008688,
14
+ "eval_loss": 0.8111762404441833,
15
+ "eval_runtime": 35.9132,
16
+ "eval_samples_per_second": 67.301,
17
+ "eval_steps_per_second": 2.116,
18
+ "step": 340
19
+ },
20
+ {
21
+ "epoch": 1.47,
22
+ "grad_norm": 2.4162442684173584,
23
+ "learning_rate": 2.4943820224719103e-07,
24
+ "loss": 0.7317,
25
+ "step": 500
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "eval_accuracy": 0.7608605709557302,
30
+ "eval_loss": 0.8044341802597046,
31
+ "eval_runtime": 36.0193,
32
+ "eval_samples_per_second": 67.103,
33
+ "eval_steps_per_second": 2.11,
34
+ "step": 680
35
+ },
36
+ {
37
+ "epoch": 2.94,
38
+ "grad_norm": 1.9337114095687866,
39
+ "learning_rate": 1.9325842696629212e-07,
40
+ "loss": 0.7215,
41
+ "step": 1000
42
+ },
43
+ {
44
+ "epoch": 3.0,
45
+ "eval_accuracy": 0.7600330988829127,
46
+ "eval_loss": 0.7982105612754822,
47
+ "eval_runtime": 36.0946,
48
+ "eval_samples_per_second": 66.963,
49
+ "eval_steps_per_second": 2.106,
50
+ "step": 1020
51
+ },
52
+ {
53
+ "epoch": 4.0,
54
+ "eval_accuracy": 0.7583781547372777,
55
+ "eval_loss": 0.7944496273994446,
56
+ "eval_runtime": 36.3255,
57
+ "eval_samples_per_second": 66.537,
58
+ "eval_steps_per_second": 2.092,
59
+ "step": 1360
60
+ },
61
+ {
62
+ "epoch": 4.41,
63
+ "grad_norm": 2.389512538909912,
64
+ "learning_rate": 1.3707865168539326e-07,
65
+ "loss": 0.7101,
66
+ "step": 1500
67
+ },
68
+ {
69
+ "epoch": 5.0,
70
+ "eval_accuracy": 0.7596193628465039,
71
+ "eval_loss": 0.7888587713241577,
72
+ "eval_runtime": 36.3724,
73
+ "eval_samples_per_second": 66.451,
74
+ "eval_steps_per_second": 2.089,
75
+ "step": 1700
76
+ },
77
+ {
78
+ "epoch": 5.88,
79
+ "grad_norm": 3.376326322555542,
80
+ "learning_rate": 8.089887640449438e-08,
81
+ "loss": 0.7042,
82
+ "step": 2000
83
+ },
84
+ {
85
+ "epoch": 6.0,
86
+ "eval_accuracy": 0.7600330988829127,
87
+ "eval_loss": 0.7876298427581787,
88
+ "eval_runtime": 35.9709,
89
+ "eval_samples_per_second": 67.193,
90
+ "eval_steps_per_second": 2.113,
91
+ "step": 2040
92
+ },
93
+ {
94
+ "epoch": 7.0,
95
+ "eval_accuracy": 0.7616880430285478,
96
+ "eval_loss": 0.7849792242050171,
97
+ "eval_runtime": 37.3709,
98
+ "eval_samples_per_second": 64.676,
99
+ "eval_steps_per_second": 2.034,
100
+ "step": 2380
101
+ },
102
+ {
103
+ "epoch": 7.35,
104
+ "grad_norm": 1.9469374418258667,
105
+ "learning_rate": 2.47191011235955e-08,
106
+ "loss": 0.697,
107
+ "step": 2500
108
+ },
109
+ {
110
+ "epoch": 8.0,
111
+ "eval_accuracy": 0.7616880430285478,
112
+ "eval_loss": 0.7845879793167114,
113
+ "eval_runtime": 36.0316,
114
+ "eval_samples_per_second": 67.08,
115
+ "eval_steps_per_second": 2.109,
116
+ "step": 2720
117
+ }
118
+ ],
119
+ "logging_steps": 500,
120
+ "max_steps": 2720,
121
+ "num_input_tokens_seen": 0,
122
+ "num_train_epochs": 8,
123
+ "save_steps": 500,
124
+ "total_flos": 1.3480989799418266e+19,
125
+ "train_batch_size": 64,
126
+ "trial_name": null,
127
+ "trial_params": null
128
+ }
checkpoint-2720/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4548d79717afa67fde4b1e4faf580d331d0b07faf116fc8713754712b3c6c439
3
+ size 4411
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:74c1dc788ded66b2c96e14d1c7b3e4b8e6801cbea3cae0d5e7f58835b8b64fda
3
  size 343236280
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eee9038c9276c6d6e40ff864346d278bf4129b3050408403208e88d2a0a8933f
3
  size 343236280
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a464503369e6755437a3db0a12941647b076b859fc51eaad5486515ae6607b59
3
  size 4411
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4548d79717afa67fde4b1e4faf580d331d0b07faf116fc8713754712b3c6c439
3
  size 4411