Upload folder using huggingface_hub
Browse files- checkpoint-2380/config.json +40 -0
- checkpoint-2380/model.safetensors +3 -0
- checkpoint-2380/optimizer.pt +3 -0
- checkpoint-2380/preprocessor_config.json +22 -0
- checkpoint-2380/rng_state.pth +3 -0
- checkpoint-2380/scheduler.pt +3 -0
- checkpoint-2380/trainer_state.json +112 -0
- checkpoint-2380/training_args.bin +3 -0
- model.safetensors +1 -1
- training_args.bin +1 -1
checkpoint-2380/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-2380/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f018e758f1819004a33e22282cff6a2bf32fc0cd62710cbab6c19c2a48697c67
|
3 |
+
size 343236280
|
checkpoint-2380/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5d26fd99a3c3d6bedf78e1511d13bab8c30ee6374956ce29022bf1bd915ff60a
|
3 |
+
size 686593029
|
checkpoint-2380/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-2380/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c23370e6a484d11b58233c4f3e406e80c78625d6742db91235a43e16772c2af5
|
3 |
+
size 14575
|
checkpoint-2380/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:481aab4ad0eed39c882e37037927476faf130b12bcfe0dd4fdbd62e2553159d9
|
3 |
+
size 627
|
checkpoint-2380/trainer_state.json
ADDED
@@ -0,0 +1,112 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.7416653633117676,
|
3 |
+
"best_model_checkpoint": "face_emotions_image_detection/checkpoint-2380",
|
4 |
+
"epoch": 7.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 2380,
|
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": 0.7815473727761688,
|
14 |
+
"eval_loss": 0.7615271210670471,
|
15 |
+
"eval_runtime": 35.3314,
|
16 |
+
"eval_samples_per_second": 68.409,
|
17 |
+
"eval_steps_per_second": 2.151,
|
18 |
+
"step": 340
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 1.47,
|
22 |
+
"grad_norm": 2.714886426925659,
|
23 |
+
"learning_rate": 2.4206008583690987e-07,
|
24 |
+
"loss": 0.6933,
|
25 |
+
"step": 500
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 2.0,
|
29 |
+
"eval_accuracy": 0.78113363673976,
|
30 |
+
"eval_loss": 0.7570552825927734,
|
31 |
+
"eval_runtime": 35.8902,
|
32 |
+
"eval_samples_per_second": 67.344,
|
33 |
+
"eval_steps_per_second": 2.118,
|
34 |
+
"step": 680
|
35 |
+
},
|
36 |
+
{
|
37 |
+
"epoch": 2.94,
|
38 |
+
"grad_norm": 2.760270595550537,
|
39 |
+
"learning_rate": 1.7768240343347639e-07,
|
40 |
+
"loss": 0.6836,
|
41 |
+
"step": 1000
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 3.0,
|
45 |
+
"eval_accuracy": 0.7807199007033513,
|
46 |
+
"eval_loss": 0.7524998188018799,
|
47 |
+
"eval_runtime": 35.2486,
|
48 |
+
"eval_samples_per_second": 68.57,
|
49 |
+
"eval_steps_per_second": 2.156,
|
50 |
+
"step": 1020
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 4.0,
|
54 |
+
"eval_accuracy": 0.7852709971038477,
|
55 |
+
"eval_loss": 0.7466434240341187,
|
56 |
+
"eval_runtime": 35.4191,
|
57 |
+
"eval_samples_per_second": 68.24,
|
58 |
+
"eval_steps_per_second": 2.146,
|
59 |
+
"step": 1360
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 4.41,
|
63 |
+
"grad_norm": 2.9822440147399902,
|
64 |
+
"learning_rate": 1.1330472103004292e-07,
|
65 |
+
"loss": 0.6746,
|
66 |
+
"step": 1500
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 5.0,
|
70 |
+
"eval_accuracy": 0.7860984691766653,
|
71 |
+
"eval_loss": 0.7431991696357727,
|
72 |
+
"eval_runtime": 35.5228,
|
73 |
+
"eval_samples_per_second": 68.041,
|
74 |
+
"eval_steps_per_second": 2.139,
|
75 |
+
"step": 1700
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 5.88,
|
79 |
+
"grad_norm": 2.6914942264556885,
|
80 |
+
"learning_rate": 4.8927038626609435e-08,
|
81 |
+
"loss": 0.6715,
|
82 |
+
"step": 2000
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"epoch": 6.0,
|
86 |
+
"eval_accuracy": 0.7877534133223004,
|
87 |
+
"eval_loss": 0.7418521642684937,
|
88 |
+
"eval_runtime": 34.9484,
|
89 |
+
"eval_samples_per_second": 69.159,
|
90 |
+
"eval_steps_per_second": 2.175,
|
91 |
+
"step": 2040
|
92 |
+
},
|
93 |
+
{
|
94 |
+
"epoch": 7.0,
|
95 |
+
"eval_accuracy": 0.7869259412494828,
|
96 |
+
"eval_loss": 0.7416653633117676,
|
97 |
+
"eval_runtime": 34.4685,
|
98 |
+
"eval_samples_per_second": 70.122,
|
99 |
+
"eval_steps_per_second": 2.205,
|
100 |
+
"step": 2380
|
101 |
+
}
|
102 |
+
],
|
103 |
+
"logging_steps": 500,
|
104 |
+
"max_steps": 2380,
|
105 |
+
"num_input_tokens_seen": 0,
|
106 |
+
"num_train_epochs": 7,
|
107 |
+
"save_steps": 500,
|
108 |
+
"total_flos": 1.1795866074490982e+19,
|
109 |
+
"train_batch_size": 64,
|
110 |
+
"trial_name": null,
|
111 |
+
"trial_params": null
|
112 |
+
}
|
checkpoint-2380/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f68550f185cdb52019d0c1f7dfcfd5c27c7f9240920f1876c5eaf2eaefacb27
|
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:f018e758f1819004a33e22282cff6a2bf32fc0cd62710cbab6c19c2a48697c67
|
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 sha256:0f68550f185cdb52019d0c1f7dfcfd5c27c7f9240920f1876c5eaf2eaefacb27
|
3 |
size 4411
|