Natthanarong
commited on
Commit
•
f695df5
1
Parent(s):
ad4b0ab
Upload folder using huggingface_hub
Browse files- README.md +41 -0
- checkpoint-1835/config.json +47 -0
- checkpoint-1835/model.safetensors +3 -0
- checkpoint-1835/optimizer.pt +3 -0
- checkpoint-1835/rng_state.pth +3 -0
- checkpoint-1835/scheduler.pt +3 -0
- checkpoint-1835/trainer_state.json +839 -0
- checkpoint-1835/training_args.bin +3 -0
- config.json +47 -0
- model.safetensors +3 -0
- preprocessor_config.json +22 -0
- runs/Jul05_03-45-25_r-natthanarong-petsona-cat-zquzvar2-ccfe8-vk5fo/events.out.tfevents.1720151127.r-natthanarong-petsona-cat-zquzvar2-ccfe8-vk5fo.161.0 +2 -2
- runs/Jul05_03-45-25_r-natthanarong-petsona-cat-zquzvar2-ccfe8-vk5fo/events.out.tfevents.1720184445.r-natthanarong-petsona-cat-zquzvar2-ccfe8-vk5fo.161.1 +3 -0
- training_args.bin +3 -0
- training_params.json +29 -0
README.md
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
tags:
|
4 |
+
- autotrain
|
5 |
+
- image-classification
|
6 |
+
base_model: google/vit-large-patch32-384
|
7 |
+
widget:
|
8 |
+
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/tiger.jpg
|
9 |
+
example_title: Tiger
|
10 |
+
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/teapot.jpg
|
11 |
+
example_title: Teapot
|
12 |
+
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/palace.jpg
|
13 |
+
example_title: Palace
|
14 |
+
---
|
15 |
+
|
16 |
+
# Model Trained Using AutoTrain
|
17 |
+
|
18 |
+
- Problem type: Image Classification
|
19 |
+
|
20 |
+
## Validation Metrics
|
21 |
+
loss: 0.6790379881858826
|
22 |
+
|
23 |
+
f1_macro: 0.7441167259748385
|
24 |
+
|
25 |
+
f1_micro: 0.7953615279672579
|
26 |
+
|
27 |
+
f1_weighted: 0.7877909517913628
|
28 |
+
|
29 |
+
precision_macro: 0.7576756562000598
|
30 |
+
|
31 |
+
precision_micro: 0.7953615279672579
|
32 |
+
|
33 |
+
precision_weighted: 0.7895482398510546
|
34 |
+
|
35 |
+
recall_macro: 0.7464961607949413
|
36 |
+
|
37 |
+
recall_micro: 0.7953615279672579
|
38 |
+
|
39 |
+
recall_weighted: 0.7953615279672579
|
40 |
+
|
41 |
+
accuracy: 0.7953615279672579
|
checkpoint-1835/config.json
ADDED
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/vit-large-patch32-384",
|
3 |
+
"_num_labels": 9,
|
4 |
+
"architectures": [
|
5 |
+
"ViTForImageClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.0,
|
8 |
+
"encoder_stride": 16,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.0,
|
11 |
+
"hidden_size": 1024,
|
12 |
+
"id2label": {
|
13 |
+
"0": "big_sturcture",
|
14 |
+
"1": "curly_fur",
|
15 |
+
"2": "exotic_face",
|
16 |
+
"3": "grey_colour",
|
17 |
+
"4": "hairless",
|
18 |
+
"5": "point_face",
|
19 |
+
"6": "shorthair",
|
20 |
+
"7": "shortleg",
|
21 |
+
"8": "tri_colour"
|
22 |
+
},
|
23 |
+
"image_size": 384,
|
24 |
+
"initializer_range": 0.02,
|
25 |
+
"intermediate_size": 4096,
|
26 |
+
"label2id": {
|
27 |
+
"big_sturcture": 0,
|
28 |
+
"curly_fur": 1,
|
29 |
+
"exotic_face": 2,
|
30 |
+
"grey_colour": 3,
|
31 |
+
"hairless": 4,
|
32 |
+
"point_face": 5,
|
33 |
+
"shorthair": 6,
|
34 |
+
"shortleg": 7,
|
35 |
+
"tri_colour": 8
|
36 |
+
},
|
37 |
+
"layer_norm_eps": 1e-12,
|
38 |
+
"model_type": "vit",
|
39 |
+
"num_attention_heads": 16,
|
40 |
+
"num_channels": 3,
|
41 |
+
"num_hidden_layers": 24,
|
42 |
+
"patch_size": 32,
|
43 |
+
"problem_type": "single_label_classification",
|
44 |
+
"qkv_bias": true,
|
45 |
+
"torch_dtype": "float32",
|
46 |
+
"transformers_version": "4.42.2"
|
47 |
+
}
|
checkpoint-1835/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f935be9821c1816118898217c3d9bc6f8f884ce8a6bb4c32c89722c049041109
|
3 |
+
size 1222514188
|
checkpoint-1835/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f6634eff6845db6ac5fba0b5ba8395e54d8fd9e89d449b2c225aa5329adc0bd1
|
3 |
+
size 2445252266
|
checkpoint-1835/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:01149e5c518eec950897664aa67ae3c45b9f4645767e59fd53e539b821695674
|
3 |
+
size 13990
|
checkpoint-1835/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a556c01e276e34ab90167d0b7af01adc0a544ae17c8ad1bd00515b73978d7b1
|
3 |
+
size 1064
|
checkpoint-1835/trainer_state.json
ADDED
@@ -0,0 +1,839 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.6790379881858826,
|
3 |
+
"best_model_checkpoint": "petsona-cat/checkpoint-1835",
|
4 |
+
"epoch": 5.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1835,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.04904632152588556,
|
13 |
+
"grad_norm": 13.090154647827148,
|
14 |
+
"learning_rate": 4.891304347826087e-06,
|
15 |
+
"loss": 2.2711,
|
16 |
+
"step": 18
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.09809264305177112,
|
20 |
+
"grad_norm": 10.665365219116211,
|
21 |
+
"learning_rate": 9.782608695652175e-06,
|
22 |
+
"loss": 2.2911,
|
23 |
+
"step": 36
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.14713896457765668,
|
27 |
+
"grad_norm": 9.563919067382812,
|
28 |
+
"learning_rate": 1.4673913043478263e-05,
|
29 |
+
"loss": 2.059,
|
30 |
+
"step": 54
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.19618528610354224,
|
34 |
+
"grad_norm": 11.644034385681152,
|
35 |
+
"learning_rate": 1.956521739130435e-05,
|
36 |
+
"loss": 1.9083,
|
37 |
+
"step": 72
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.2452316076294278,
|
41 |
+
"grad_norm": 9.686708450317383,
|
42 |
+
"learning_rate": 2.4456521739130436e-05,
|
43 |
+
"loss": 1.7345,
|
44 |
+
"step": 90
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.29427792915531337,
|
48 |
+
"grad_norm": 8.462738037109375,
|
49 |
+
"learning_rate": 2.9347826086956526e-05,
|
50 |
+
"loss": 1.5031,
|
51 |
+
"step": 108
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.34332425068119893,
|
55 |
+
"grad_norm": 10.496886253356934,
|
56 |
+
"learning_rate": 3.423913043478261e-05,
|
57 |
+
"loss": 1.3148,
|
58 |
+
"step": 126
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.3923705722070845,
|
62 |
+
"grad_norm": 10.159104347229004,
|
63 |
+
"learning_rate": 3.91304347826087e-05,
|
64 |
+
"loss": 1.2048,
|
65 |
+
"step": 144
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.44141689373297005,
|
69 |
+
"grad_norm": 7.318648338317871,
|
70 |
+
"learning_rate": 4.4021739130434786e-05,
|
71 |
+
"loss": 1.2868,
|
72 |
+
"step": 162
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.4904632152588556,
|
76 |
+
"grad_norm": 11.507461547851562,
|
77 |
+
"learning_rate": 4.891304347826087e-05,
|
78 |
+
"loss": 1.2105,
|
79 |
+
"step": 180
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.5395095367847411,
|
83 |
+
"grad_norm": 5.680470943450928,
|
84 |
+
"learning_rate": 4.957601453664446e-05,
|
85 |
+
"loss": 1.0724,
|
86 |
+
"step": 198
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.5885558583106267,
|
90 |
+
"grad_norm": 8.683788299560547,
|
91 |
+
"learning_rate": 4.9030890369473045e-05,
|
92 |
+
"loss": 1.1899,
|
93 |
+
"step": 216
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.6376021798365122,
|
97 |
+
"grad_norm": 7.334160804748535,
|
98 |
+
"learning_rate": 4.848576620230164e-05,
|
99 |
+
"loss": 1.0224,
|
100 |
+
"step": 234
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.6866485013623979,
|
104 |
+
"grad_norm": 8.717308044433594,
|
105 |
+
"learning_rate": 4.794064203513023e-05,
|
106 |
+
"loss": 0.9976,
|
107 |
+
"step": 252
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.7356948228882834,
|
111 |
+
"grad_norm": 12.613802909851074,
|
112 |
+
"learning_rate": 4.739551786795882e-05,
|
113 |
+
"loss": 0.9753,
|
114 |
+
"step": 270
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.784741144414169,
|
118 |
+
"grad_norm": 7.462376594543457,
|
119 |
+
"learning_rate": 4.6850393700787405e-05,
|
120 |
+
"loss": 1.1063,
|
121 |
+
"step": 288
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.8337874659400545,
|
125 |
+
"grad_norm": 8.719904899597168,
|
126 |
+
"learning_rate": 4.630526953361599e-05,
|
127 |
+
"loss": 1.0311,
|
128 |
+
"step": 306
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.8828337874659401,
|
132 |
+
"grad_norm": 9.132880210876465,
|
133 |
+
"learning_rate": 4.576014536644458e-05,
|
134 |
+
"loss": 0.9735,
|
135 |
+
"step": 324
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.9318801089918256,
|
139 |
+
"grad_norm": 8.101548194885254,
|
140 |
+
"learning_rate": 4.521502119927317e-05,
|
141 |
+
"loss": 1.0608,
|
142 |
+
"step": 342
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.9809264305177112,
|
146 |
+
"grad_norm": 9.457178115844727,
|
147 |
+
"learning_rate": 4.466989703210176e-05,
|
148 |
+
"loss": 1.0543,
|
149 |
+
"step": 360
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 1.0,
|
153 |
+
"eval_accuracy": 0.7394270122783083,
|
154 |
+
"eval_f1_macro": 0.6775647712813081,
|
155 |
+
"eval_f1_micro": 0.7394270122783083,
|
156 |
+
"eval_f1_weighted": 0.7229253713683983,
|
157 |
+
"eval_loss": 0.7820252180099487,
|
158 |
+
"eval_precision_macro": 0.6673572429051899,
|
159 |
+
"eval_precision_micro": 0.7394270122783083,
|
160 |
+
"eval_precision_weighted": 0.7129395935578096,
|
161 |
+
"eval_recall_macro": 0.6932339656729901,
|
162 |
+
"eval_recall_micro": 0.7394270122783083,
|
163 |
+
"eval_recall_weighted": 0.7394270122783083,
|
164 |
+
"eval_runtime": 501.3115,
|
165 |
+
"eval_samples_per_second": 1.462,
|
166 |
+
"eval_steps_per_second": 0.092,
|
167 |
+
"step": 367
|
168 |
+
},
|
169 |
+
{
|
170 |
+
"epoch": 1.0299727520435966,
|
171 |
+
"grad_norm": 6.45409631729126,
|
172 |
+
"learning_rate": 4.4124772864930345e-05,
|
173 |
+
"loss": 0.8511,
|
174 |
+
"step": 378
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 1.0790190735694822,
|
178 |
+
"grad_norm": 4.8151164054870605,
|
179 |
+
"learning_rate": 4.357964869775893e-05,
|
180 |
+
"loss": 0.7645,
|
181 |
+
"step": 396
|
182 |
+
},
|
183 |
+
{
|
184 |
+
"epoch": 1.1280653950953679,
|
185 |
+
"grad_norm": 6.06305456161499,
|
186 |
+
"learning_rate": 4.3034524530587525e-05,
|
187 |
+
"loss": 0.7095,
|
188 |
+
"step": 414
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 1.1771117166212535,
|
192 |
+
"grad_norm": 8.338302612304688,
|
193 |
+
"learning_rate": 4.248940036341612e-05,
|
194 |
+
"loss": 0.7537,
|
195 |
+
"step": 432
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 1.226158038147139,
|
199 |
+
"grad_norm": 8.91988754272461,
|
200 |
+
"learning_rate": 4.1944276196244705e-05,
|
201 |
+
"loss": 1.0268,
|
202 |
+
"step": 450
|
203 |
+
},
|
204 |
+
{
|
205 |
+
"epoch": 1.2752043596730245,
|
206 |
+
"grad_norm": 8.219625473022461,
|
207 |
+
"learning_rate": 4.139915202907329e-05,
|
208 |
+
"loss": 0.7882,
|
209 |
+
"step": 468
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 1.32425068119891,
|
213 |
+
"grad_norm": 6.649393081665039,
|
214 |
+
"learning_rate": 4.085402786190188e-05,
|
215 |
+
"loss": 0.9177,
|
216 |
+
"step": 486
|
217 |
+
},
|
218 |
+
{
|
219 |
+
"epoch": 1.3732970027247957,
|
220 |
+
"grad_norm": 10.92117977142334,
|
221 |
+
"learning_rate": 4.030890369473047e-05,
|
222 |
+
"loss": 0.8006,
|
223 |
+
"step": 504
|
224 |
+
},
|
225 |
+
{
|
226 |
+
"epoch": 1.422343324250681,
|
227 |
+
"grad_norm": 7.338125705718994,
|
228 |
+
"learning_rate": 3.976377952755906e-05,
|
229 |
+
"loss": 0.7833,
|
230 |
+
"step": 522
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 1.4713896457765667,
|
234 |
+
"grad_norm": 7.391980171203613,
|
235 |
+
"learning_rate": 3.9218655360387645e-05,
|
236 |
+
"loss": 0.794,
|
237 |
+
"step": 540
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 1.5204359673024523,
|
241 |
+
"grad_norm": 7.255425930023193,
|
242 |
+
"learning_rate": 3.867353119321623e-05,
|
243 |
+
"loss": 0.6818,
|
244 |
+
"step": 558
|
245 |
+
},
|
246 |
+
{
|
247 |
+
"epoch": 1.569482288828338,
|
248 |
+
"grad_norm": 9.407766342163086,
|
249 |
+
"learning_rate": 3.812840702604482e-05,
|
250 |
+
"loss": 0.7966,
|
251 |
+
"step": 576
|
252 |
+
},
|
253 |
+
{
|
254 |
+
"epoch": 1.6185286103542236,
|
255 |
+
"grad_norm": 8.508045196533203,
|
256 |
+
"learning_rate": 3.758328285887341e-05,
|
257 |
+
"loss": 0.7673,
|
258 |
+
"step": 594
|
259 |
+
},
|
260 |
+
{
|
261 |
+
"epoch": 1.667574931880109,
|
262 |
+
"grad_norm": 10.17292308807373,
|
263 |
+
"learning_rate": 3.7038158691702005e-05,
|
264 |
+
"loss": 0.8005,
|
265 |
+
"step": 612
|
266 |
+
},
|
267 |
+
{
|
268 |
+
"epoch": 1.7166212534059946,
|
269 |
+
"grad_norm": 7.042759895324707,
|
270 |
+
"learning_rate": 3.649303452453059e-05,
|
271 |
+
"loss": 0.7716,
|
272 |
+
"step": 630
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 1.76566757493188,
|
276 |
+
"grad_norm": 10.45976448059082,
|
277 |
+
"learning_rate": 3.594791035735918e-05,
|
278 |
+
"loss": 0.722,
|
279 |
+
"step": 648
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 1.8147138964577656,
|
283 |
+
"grad_norm": 10.023469924926758,
|
284 |
+
"learning_rate": 3.5402786190187765e-05,
|
285 |
+
"loss": 0.6968,
|
286 |
+
"step": 666
|
287 |
+
},
|
288 |
+
{
|
289 |
+
"epoch": 1.8637602179836512,
|
290 |
+
"grad_norm": 8.609762191772461,
|
291 |
+
"learning_rate": 3.485766202301636e-05,
|
292 |
+
"loss": 0.8295,
|
293 |
+
"step": 684
|
294 |
+
},
|
295 |
+
{
|
296 |
+
"epoch": 1.9128065395095368,
|
297 |
+
"grad_norm": 5.7018842697143555,
|
298 |
+
"learning_rate": 3.4312537855844944e-05,
|
299 |
+
"loss": 0.7729,
|
300 |
+
"step": 702
|
301 |
+
},
|
302 |
+
{
|
303 |
+
"epoch": 1.9618528610354224,
|
304 |
+
"grad_norm": 9.336709022521973,
|
305 |
+
"learning_rate": 3.376741368867353e-05,
|
306 |
+
"loss": 0.8679,
|
307 |
+
"step": 720
|
308 |
+
},
|
309 |
+
{
|
310 |
+
"epoch": 2.0,
|
311 |
+
"eval_accuracy": 0.7708049113233287,
|
312 |
+
"eval_f1_macro": 0.744396838344231,
|
313 |
+
"eval_f1_micro": 0.7708049113233287,
|
314 |
+
"eval_f1_weighted": 0.769490062085142,
|
315 |
+
"eval_loss": 0.7198029160499573,
|
316 |
+
"eval_precision_macro": 0.7471497356802382,
|
317 |
+
"eval_precision_micro": 0.7708049113233287,
|
318 |
+
"eval_precision_weighted": 0.7700316353146535,
|
319 |
+
"eval_recall_macro": 0.7438821138211381,
|
320 |
+
"eval_recall_micro": 0.7708049113233287,
|
321 |
+
"eval_recall_weighted": 0.7708049113233287,
|
322 |
+
"eval_runtime": 526.4938,
|
323 |
+
"eval_samples_per_second": 1.392,
|
324 |
+
"eval_steps_per_second": 0.087,
|
325 |
+
"step": 734
|
326 |
+
},
|
327 |
+
{
|
328 |
+
"epoch": 2.010899182561308,
|
329 |
+
"grad_norm": 3.749079942703247,
|
330 |
+
"learning_rate": 3.322228952150212e-05,
|
331 |
+
"loss": 0.7638,
|
332 |
+
"step": 738
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 2.0599455040871932,
|
336 |
+
"grad_norm": 5.066211223602295,
|
337 |
+
"learning_rate": 3.2677165354330704e-05,
|
338 |
+
"loss": 0.7479,
|
339 |
+
"step": 756
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 2.108991825613079,
|
343 |
+
"grad_norm": 5.5539116859436035,
|
344 |
+
"learning_rate": 3.21320411871593e-05,
|
345 |
+
"loss": 0.6329,
|
346 |
+
"step": 774
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"epoch": 2.1580381471389645,
|
350 |
+
"grad_norm": 7.377701282501221,
|
351 |
+
"learning_rate": 3.158691701998789e-05,
|
352 |
+
"loss": 0.5928,
|
353 |
+
"step": 792
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 2.20708446866485,
|
357 |
+
"grad_norm": 1.7499698400497437,
|
358 |
+
"learning_rate": 3.104179285281648e-05,
|
359 |
+
"loss": 0.5315,
|
360 |
+
"step": 810
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 2.2561307901907357,
|
364 |
+
"grad_norm": 12.155342102050781,
|
365 |
+
"learning_rate": 3.0496668685645064e-05,
|
366 |
+
"loss": 0.6642,
|
367 |
+
"step": 828
|
368 |
+
},
|
369 |
+
{
|
370 |
+
"epoch": 2.3051771117166213,
|
371 |
+
"grad_norm": 7.592235088348389,
|
372 |
+
"learning_rate": 2.9951544518473658e-05,
|
373 |
+
"loss": 0.5364,
|
374 |
+
"step": 846
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 2.354223433242507,
|
378 |
+
"grad_norm": 8.232931137084961,
|
379 |
+
"learning_rate": 2.9406420351302244e-05,
|
380 |
+
"loss": 0.5136,
|
381 |
+
"step": 864
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 2.4032697547683926,
|
385 |
+
"grad_norm": 7.107213497161865,
|
386 |
+
"learning_rate": 2.886129618413083e-05,
|
387 |
+
"loss": 0.5777,
|
388 |
+
"step": 882
|
389 |
+
},
|
390 |
+
{
|
391 |
+
"epoch": 2.452316076294278,
|
392 |
+
"grad_norm": 4.498622894287109,
|
393 |
+
"learning_rate": 2.8316172016959417e-05,
|
394 |
+
"loss": 0.6736,
|
395 |
+
"step": 900
|
396 |
+
},
|
397 |
+
{
|
398 |
+
"epoch": 2.5013623978201633,
|
399 |
+
"grad_norm": 13.404940605163574,
|
400 |
+
"learning_rate": 2.7771047849788007e-05,
|
401 |
+
"loss": 0.6628,
|
402 |
+
"step": 918
|
403 |
+
},
|
404 |
+
{
|
405 |
+
"epoch": 2.550408719346049,
|
406 |
+
"grad_norm": 10.440755844116211,
|
407 |
+
"learning_rate": 2.72259236826166e-05,
|
408 |
+
"loss": 0.5867,
|
409 |
+
"step": 936
|
410 |
+
},
|
411 |
+
{
|
412 |
+
"epoch": 2.5994550408719346,
|
413 |
+
"grad_norm": 5.166727066040039,
|
414 |
+
"learning_rate": 2.6680799515445187e-05,
|
415 |
+
"loss": 0.6759,
|
416 |
+
"step": 954
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 2.64850136239782,
|
420 |
+
"grad_norm": 6.91835355758667,
|
421 |
+
"learning_rate": 2.6135675348273774e-05,
|
422 |
+
"loss": 0.8065,
|
423 |
+
"step": 972
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 2.697547683923706,
|
427 |
+
"grad_norm": 5.450559139251709,
|
428 |
+
"learning_rate": 2.5590551181102364e-05,
|
429 |
+
"loss": 0.5886,
|
430 |
+
"step": 990
|
431 |
+
},
|
432 |
+
{
|
433 |
+
"epoch": 2.7465940054495914,
|
434 |
+
"grad_norm": 11.601627349853516,
|
435 |
+
"learning_rate": 2.504542701393095e-05,
|
436 |
+
"loss": 0.8291,
|
437 |
+
"step": 1008
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 2.7956403269754766,
|
441 |
+
"grad_norm": 6.433958530426025,
|
442 |
+
"learning_rate": 2.450030284675954e-05,
|
443 |
+
"loss": 0.6658,
|
444 |
+
"step": 1026
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 2.844686648501362,
|
448 |
+
"grad_norm": 8.672781944274902,
|
449 |
+
"learning_rate": 2.395517867958813e-05,
|
450 |
+
"loss": 0.577,
|
451 |
+
"step": 1044
|
452 |
+
},
|
453 |
+
{
|
454 |
+
"epoch": 2.893732970027248,
|
455 |
+
"grad_norm": 5.865307807922363,
|
456 |
+
"learning_rate": 2.3410054512416717e-05,
|
457 |
+
"loss": 0.6015,
|
458 |
+
"step": 1062
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 2.9427792915531334,
|
462 |
+
"grad_norm": 7.018499374389648,
|
463 |
+
"learning_rate": 2.2864930345245307e-05,
|
464 |
+
"loss": 0.5292,
|
465 |
+
"step": 1080
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 2.991825613079019,
|
469 |
+
"grad_norm": 8.684929847717285,
|
470 |
+
"learning_rate": 2.2319806178073897e-05,
|
471 |
+
"loss": 0.6743,
|
472 |
+
"step": 1098
|
473 |
+
},
|
474 |
+
{
|
475 |
+
"epoch": 3.0,
|
476 |
+
"eval_accuracy": 0.7762619372442019,
|
477 |
+
"eval_f1_macro": 0.7352337273015235,
|
478 |
+
"eval_f1_micro": 0.7762619372442019,
|
479 |
+
"eval_f1_weighted": 0.7700415467128165,
|
480 |
+
"eval_loss": 0.7334316372871399,
|
481 |
+
"eval_precision_macro": 0.7602211726711597,
|
482 |
+
"eval_precision_micro": 0.7762619372442019,
|
483 |
+
"eval_precision_weighted": 0.7759104610468709,
|
484 |
+
"eval_recall_macro": 0.7309406052393856,
|
485 |
+
"eval_recall_micro": 0.7762619372442019,
|
486 |
+
"eval_recall_weighted": 0.7762619372442019,
|
487 |
+
"eval_runtime": 468.0039,
|
488 |
+
"eval_samples_per_second": 1.566,
|
489 |
+
"eval_steps_per_second": 0.098,
|
490 |
+
"step": 1101
|
491 |
+
},
|
492 |
+
{
|
493 |
+
"epoch": 3.0408719346049047,
|
494 |
+
"grad_norm": 5.529566287994385,
|
495 |
+
"learning_rate": 2.1774682010902484e-05,
|
496 |
+
"loss": 0.5119,
|
497 |
+
"step": 1116
|
498 |
+
},
|
499 |
+
{
|
500 |
+
"epoch": 3.0899182561307903,
|
501 |
+
"grad_norm": 8.672910690307617,
|
502 |
+
"learning_rate": 2.1229557843731074e-05,
|
503 |
+
"loss": 0.3846,
|
504 |
+
"step": 1134
|
505 |
+
},
|
506 |
+
{
|
507 |
+
"epoch": 3.138964577656676,
|
508 |
+
"grad_norm": 6.369070529937744,
|
509 |
+
"learning_rate": 2.068443367655966e-05,
|
510 |
+
"loss": 0.4705,
|
511 |
+
"step": 1152
|
512 |
+
},
|
513 |
+
{
|
514 |
+
"epoch": 3.1880108991825615,
|
515 |
+
"grad_norm": 6.632961273193359,
|
516 |
+
"learning_rate": 2.013930950938825e-05,
|
517 |
+
"loss": 0.5078,
|
518 |
+
"step": 1170
|
519 |
+
},
|
520 |
+
{
|
521 |
+
"epoch": 3.2370572207084467,
|
522 |
+
"grad_norm": 13.185933113098145,
|
523 |
+
"learning_rate": 1.959418534221684e-05,
|
524 |
+
"loss": 0.4132,
|
525 |
+
"step": 1188
|
526 |
+
},
|
527 |
+
{
|
528 |
+
"epoch": 3.2861035422343323,
|
529 |
+
"grad_norm": 2.94797682762146,
|
530 |
+
"learning_rate": 1.9049061175045427e-05,
|
531 |
+
"loss": 0.5002,
|
532 |
+
"step": 1206
|
533 |
+
},
|
534 |
+
{
|
535 |
+
"epoch": 3.335149863760218,
|
536 |
+
"grad_norm": 8.657658576965332,
|
537 |
+
"learning_rate": 1.8503937007874017e-05,
|
538 |
+
"loss": 0.7647,
|
539 |
+
"step": 1224
|
540 |
+
},
|
541 |
+
{
|
542 |
+
"epoch": 3.3841961852861036,
|
543 |
+
"grad_norm": 7.174124717712402,
|
544 |
+
"learning_rate": 1.7958812840702604e-05,
|
545 |
+
"loss": 0.5301,
|
546 |
+
"step": 1242
|
547 |
+
},
|
548 |
+
{
|
549 |
+
"epoch": 3.433242506811989,
|
550 |
+
"grad_norm": 8.120543479919434,
|
551 |
+
"learning_rate": 1.7413688673531194e-05,
|
552 |
+
"loss": 0.4428,
|
553 |
+
"step": 1260
|
554 |
+
},
|
555 |
+
{
|
556 |
+
"epoch": 3.482288828337875,
|
557 |
+
"grad_norm": 10.651689529418945,
|
558 |
+
"learning_rate": 1.6868564506359784e-05,
|
559 |
+
"loss": 0.6033,
|
560 |
+
"step": 1278
|
561 |
+
},
|
562 |
+
{
|
563 |
+
"epoch": 3.53133514986376,
|
564 |
+
"grad_norm": 14.153423309326172,
|
565 |
+
"learning_rate": 1.6323440339188374e-05,
|
566 |
+
"loss": 0.5152,
|
567 |
+
"step": 1296
|
568 |
+
},
|
569 |
+
{
|
570 |
+
"epoch": 3.5803814713896456,
|
571 |
+
"grad_norm": 8.533557891845703,
|
572 |
+
"learning_rate": 1.577831617201696e-05,
|
573 |
+
"loss": 0.6689,
|
574 |
+
"step": 1314
|
575 |
+
},
|
576 |
+
{
|
577 |
+
"epoch": 3.629427792915531,
|
578 |
+
"grad_norm": 12.795997619628906,
|
579 |
+
"learning_rate": 1.5233192004845548e-05,
|
580 |
+
"loss": 0.4701,
|
581 |
+
"step": 1332
|
582 |
+
},
|
583 |
+
{
|
584 |
+
"epoch": 3.678474114441417,
|
585 |
+
"grad_norm": 8.181031227111816,
|
586 |
+
"learning_rate": 1.4688067837674138e-05,
|
587 |
+
"loss": 0.4875,
|
588 |
+
"step": 1350
|
589 |
+
},
|
590 |
+
{
|
591 |
+
"epoch": 3.7275204359673024,
|
592 |
+
"grad_norm": 8.397069931030273,
|
593 |
+
"learning_rate": 1.4142943670502725e-05,
|
594 |
+
"loss": 0.4234,
|
595 |
+
"step": 1368
|
596 |
+
},
|
597 |
+
{
|
598 |
+
"epoch": 3.776566757493188,
|
599 |
+
"grad_norm": 6.6668548583984375,
|
600 |
+
"learning_rate": 1.3597819503331317e-05,
|
601 |
+
"loss": 0.4799,
|
602 |
+
"step": 1386
|
603 |
+
},
|
604 |
+
{
|
605 |
+
"epoch": 3.8256130790190737,
|
606 |
+
"grad_norm": 3.7310755252838135,
|
607 |
+
"learning_rate": 1.3052695336159903e-05,
|
608 |
+
"loss": 0.4241,
|
609 |
+
"step": 1404
|
610 |
+
},
|
611 |
+
{
|
612 |
+
"epoch": 3.8746594005449593,
|
613 |
+
"grad_norm": 7.294261455535889,
|
614 |
+
"learning_rate": 1.2507571168988492e-05,
|
615 |
+
"loss": 0.4828,
|
616 |
+
"step": 1422
|
617 |
+
},
|
618 |
+
{
|
619 |
+
"epoch": 3.923705722070845,
|
620 |
+
"grad_norm": 11.431266784667969,
|
621 |
+
"learning_rate": 1.1962447001817082e-05,
|
622 |
+
"loss": 0.4837,
|
623 |
+
"step": 1440
|
624 |
+
},
|
625 |
+
{
|
626 |
+
"epoch": 3.9727520435967305,
|
627 |
+
"grad_norm": 10.630217552185059,
|
628 |
+
"learning_rate": 1.141732283464567e-05,
|
629 |
+
"loss": 0.4148,
|
630 |
+
"step": 1458
|
631 |
+
},
|
632 |
+
{
|
633 |
+
"epoch": 4.0,
|
634 |
+
"eval_accuracy": 0.7926330150068213,
|
635 |
+
"eval_f1_macro": 0.7482822112088491,
|
636 |
+
"eval_f1_micro": 0.7926330150068213,
|
637 |
+
"eval_f1_weighted": 0.7859610744604464,
|
638 |
+
"eval_loss": 0.680126428604126,
|
639 |
+
"eval_precision_macro": 0.7591045700614258,
|
640 |
+
"eval_precision_micro": 0.7926330150068213,
|
641 |
+
"eval_precision_weighted": 0.7865124628151742,
|
642 |
+
"eval_recall_macro": 0.7507125112917796,
|
643 |
+
"eval_recall_micro": 0.7926330150068213,
|
644 |
+
"eval_recall_weighted": 0.7926330150068213,
|
645 |
+
"eval_runtime": 446.0494,
|
646 |
+
"eval_samples_per_second": 1.643,
|
647 |
+
"eval_steps_per_second": 0.103,
|
648 |
+
"step": 1468
|
649 |
+
},
|
650 |
+
{
|
651 |
+
"epoch": 4.021798365122616,
|
652 |
+
"grad_norm": 8.096855163574219,
|
653 |
+
"learning_rate": 1.0872198667474258e-05,
|
654 |
+
"loss": 0.4162,
|
655 |
+
"step": 1476
|
656 |
+
},
|
657 |
+
{
|
658 |
+
"epoch": 4.070844686648502,
|
659 |
+
"grad_norm": 4.436280250549316,
|
660 |
+
"learning_rate": 1.0327074500302846e-05,
|
661 |
+
"loss": 0.3999,
|
662 |
+
"step": 1494
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 4.1198910081743865,
|
666 |
+
"grad_norm": 3.2468502521514893,
|
667 |
+
"learning_rate": 9.781950333131436e-06,
|
668 |
+
"loss": 0.269,
|
669 |
+
"step": 1512
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 4.168937329700272,
|
673 |
+
"grad_norm": 5.88806676864624,
|
674 |
+
"learning_rate": 9.236826165960025e-06,
|
675 |
+
"loss": 0.3749,
|
676 |
+
"step": 1530
|
677 |
+
},
|
678 |
+
{
|
679 |
+
"epoch": 4.217983651226158,
|
680 |
+
"grad_norm": 1.9926618337631226,
|
681 |
+
"learning_rate": 8.691701998788613e-06,
|
682 |
+
"loss": 0.3893,
|
683 |
+
"step": 1548
|
684 |
+
},
|
685 |
+
{
|
686 |
+
"epoch": 4.267029972752043,
|
687 |
+
"grad_norm": 7.686309814453125,
|
688 |
+
"learning_rate": 8.146577831617203e-06,
|
689 |
+
"loss": 0.3134,
|
690 |
+
"step": 1566
|
691 |
+
},
|
692 |
+
{
|
693 |
+
"epoch": 4.316076294277929,
|
694 |
+
"grad_norm": 3.9294235706329346,
|
695 |
+
"learning_rate": 7.6014536644457905e-06,
|
696 |
+
"loss": 0.3415,
|
697 |
+
"step": 1584
|
698 |
+
},
|
699 |
+
{
|
700 |
+
"epoch": 4.3651226158038146,
|
701 |
+
"grad_norm": 4.247501850128174,
|
702 |
+
"learning_rate": 7.056329497274379e-06,
|
703 |
+
"loss": 0.4167,
|
704 |
+
"step": 1602
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 4.4141689373297,
|
708 |
+
"grad_norm": 8.502470970153809,
|
709 |
+
"learning_rate": 6.511205330102968e-06,
|
710 |
+
"loss": 0.5261,
|
711 |
+
"step": 1620
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 4.463215258855586,
|
715 |
+
"grad_norm": 5.880737781524658,
|
716 |
+
"learning_rate": 5.966081162931557e-06,
|
717 |
+
"loss": 0.5806,
|
718 |
+
"step": 1638
|
719 |
+
},
|
720 |
+
{
|
721 |
+
"epoch": 4.512261580381471,
|
722 |
+
"grad_norm": 10.550583839416504,
|
723 |
+
"learning_rate": 5.420956995760146e-06,
|
724 |
+
"loss": 0.3798,
|
725 |
+
"step": 1656
|
726 |
+
},
|
727 |
+
{
|
728 |
+
"epoch": 4.561307901907357,
|
729 |
+
"grad_norm": 6.919607639312744,
|
730 |
+
"learning_rate": 4.875832828588734e-06,
|
731 |
+
"loss": 0.4235,
|
732 |
+
"step": 1674
|
733 |
+
},
|
734 |
+
{
|
735 |
+
"epoch": 4.610354223433243,
|
736 |
+
"grad_norm": 11.466157913208008,
|
737 |
+
"learning_rate": 4.330708661417323e-06,
|
738 |
+
"loss": 0.4009,
|
739 |
+
"step": 1692
|
740 |
+
},
|
741 |
+
{
|
742 |
+
"epoch": 4.659400544959128,
|
743 |
+
"grad_norm": 7.428606033325195,
|
744 |
+
"learning_rate": 3.785584494245912e-06,
|
745 |
+
"loss": 0.3749,
|
746 |
+
"step": 1710
|
747 |
+
},
|
748 |
+
{
|
749 |
+
"epoch": 4.708446866485014,
|
750 |
+
"grad_norm": 14.596545219421387,
|
751 |
+
"learning_rate": 3.2404603270745003e-06,
|
752 |
+
"loss": 0.3822,
|
753 |
+
"step": 1728
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 4.7574931880108995,
|
757 |
+
"grad_norm": 1.3340034484863281,
|
758 |
+
"learning_rate": 2.695336159903089e-06,
|
759 |
+
"loss": 0.402,
|
760 |
+
"step": 1746
|
761 |
+
},
|
762 |
+
{
|
763 |
+
"epoch": 4.806539509536785,
|
764 |
+
"grad_norm": 12.544507026672363,
|
765 |
+
"learning_rate": 2.150211992731678e-06,
|
766 |
+
"loss": 0.3577,
|
767 |
+
"step": 1764
|
768 |
+
},
|
769 |
+
{
|
770 |
+
"epoch": 4.855585831062671,
|
771 |
+
"grad_norm": 7.779797077178955,
|
772 |
+
"learning_rate": 1.6050878255602666e-06,
|
773 |
+
"loss": 0.5092,
|
774 |
+
"step": 1782
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 4.904632152588556,
|
778 |
+
"grad_norm": 4.97097110748291,
|
779 |
+
"learning_rate": 1.0599636583888554e-06,
|
780 |
+
"loss": 0.3382,
|
781 |
+
"step": 1800
|
782 |
+
},
|
783 |
+
{
|
784 |
+
"epoch": 4.953678474114441,
|
785 |
+
"grad_norm": 2.9842166900634766,
|
786 |
+
"learning_rate": 5.14839491217444e-07,
|
787 |
+
"loss": 0.2765,
|
788 |
+
"step": 1818
|
789 |
+
},
|
790 |
+
{
|
791 |
+
"epoch": 5.0,
|
792 |
+
"eval_accuracy": 0.7953615279672579,
|
793 |
+
"eval_f1_macro": 0.7441167259748385,
|
794 |
+
"eval_f1_micro": 0.7953615279672579,
|
795 |
+
"eval_f1_weighted": 0.7877909517913628,
|
796 |
+
"eval_loss": 0.6790379881858826,
|
797 |
+
"eval_precision_macro": 0.7576756562000598,
|
798 |
+
"eval_precision_micro": 0.7953615279672579,
|
799 |
+
"eval_precision_weighted": 0.7895482398510546,
|
800 |
+
"eval_recall_macro": 0.7464961607949413,
|
801 |
+
"eval_recall_micro": 0.7953615279672579,
|
802 |
+
"eval_recall_weighted": 0.7953615279672579,
|
803 |
+
"eval_runtime": 505.8176,
|
804 |
+
"eval_samples_per_second": 1.449,
|
805 |
+
"eval_steps_per_second": 0.091,
|
806 |
+
"step": 1835
|
807 |
+
}
|
808 |
+
],
|
809 |
+
"logging_steps": 18,
|
810 |
+
"max_steps": 1835,
|
811 |
+
"num_input_tokens_seen": 0,
|
812 |
+
"num_train_epochs": 5,
|
813 |
+
"save_steps": 500,
|
814 |
+
"stateful_callbacks": {
|
815 |
+
"EarlyStoppingCallback": {
|
816 |
+
"args": {
|
817 |
+
"early_stopping_patience": 5,
|
818 |
+
"early_stopping_threshold": 0.01
|
819 |
+
},
|
820 |
+
"attributes": {
|
821 |
+
"early_stopping_patience_counter": 0
|
822 |
+
}
|
823 |
+
},
|
824 |
+
"TrainerControl": {
|
825 |
+
"args": {
|
826 |
+
"should_epoch_stop": false,
|
827 |
+
"should_evaluate": false,
|
828 |
+
"should_log": false,
|
829 |
+
"should_save": true,
|
830 |
+
"should_training_stop": true
|
831 |
+
},
|
832 |
+
"attributes": {}
|
833 |
+
}
|
834 |
+
},
|
835 |
+
"total_flos": 1.1887708574999347e+19,
|
836 |
+
"train_batch_size": 8,
|
837 |
+
"trial_name": null,
|
838 |
+
"trial_params": null
|
839 |
+
}
|
checkpoint-1835/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ddca1d636fd4270b202941f9ff4f1e16230316e422a99549bd99691fbc1f769
|
3 |
+
size 5176
|
config.json
ADDED
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/vit-large-patch32-384",
|
3 |
+
"_num_labels": 9,
|
4 |
+
"architectures": [
|
5 |
+
"ViTForImageClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.0,
|
8 |
+
"encoder_stride": 16,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.0,
|
11 |
+
"hidden_size": 1024,
|
12 |
+
"id2label": {
|
13 |
+
"0": "big_sturcture",
|
14 |
+
"1": "curly_fur",
|
15 |
+
"2": "exotic_face",
|
16 |
+
"3": "grey_colour",
|
17 |
+
"4": "hairless",
|
18 |
+
"5": "point_face",
|
19 |
+
"6": "shorthair",
|
20 |
+
"7": "shortleg",
|
21 |
+
"8": "tri_colour"
|
22 |
+
},
|
23 |
+
"image_size": 384,
|
24 |
+
"initializer_range": 0.02,
|
25 |
+
"intermediate_size": 4096,
|
26 |
+
"label2id": {
|
27 |
+
"big_sturcture": 0,
|
28 |
+
"curly_fur": 1,
|
29 |
+
"exotic_face": 2,
|
30 |
+
"grey_colour": 3,
|
31 |
+
"hairless": 4,
|
32 |
+
"point_face": 5,
|
33 |
+
"shorthair": 6,
|
34 |
+
"shortleg": 7,
|
35 |
+
"tri_colour": 8
|
36 |
+
},
|
37 |
+
"layer_norm_eps": 1e-12,
|
38 |
+
"model_type": "vit",
|
39 |
+
"num_attention_heads": 16,
|
40 |
+
"num_channels": 3,
|
41 |
+
"num_hidden_layers": 24,
|
42 |
+
"patch_size": 32,
|
43 |
+
"problem_type": "single_label_classification",
|
44 |
+
"qkv_bias": true,
|
45 |
+
"torch_dtype": "float32",
|
46 |
+
"transformers_version": "4.42.2"
|
47 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f935be9821c1816118898217c3d9bc6f8f884ce8a6bb4c32c89722c049041109
|
3 |
+
size 1222514188
|
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": 384,
|
20 |
+
"width": 384
|
21 |
+
}
|
22 |
+
}
|
runs/Jul05_03-45-25_r-natthanarong-petsona-cat-zquzvar2-ccfe8-vk5fo/events.out.tfevents.1720151127.r-natthanarong-petsona-cat-zquzvar2-ccfe8-vk5fo.161.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2be28f5f77ed3c4e9d5020fbe10db434fc9a2aafaaf83f2dea819dda350f5fea
|
3 |
+
size 30995
|
runs/Jul05_03-45-25_r-natthanarong-petsona-cat-zquzvar2-ccfe8-vk5fo/events.out.tfevents.1720184445.r-natthanarong-petsona-cat-zquzvar2-ccfe8-vk5fo.161.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ffaaa47fef08cea83ba3877f458e3a48a3d961a368bf8e0043234580023c733e
|
3 |
+
size 921
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ddca1d636fd4270b202941f9ff4f1e16230316e422a99549bd99691fbc1f769
|
3 |
+
size 5176
|
training_params.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"data_path": "petsona-cat/autotrain-data",
|
3 |
+
"model": "google/vit-large-patch32-384",
|
4 |
+
"username": "Natthanarong",
|
5 |
+
"lr": 5e-05,
|
6 |
+
"epochs": 5,
|
7 |
+
"batch_size": 8,
|
8 |
+
"warmup_ratio": 0.1,
|
9 |
+
"gradient_accumulation": 1,
|
10 |
+
"optimizer": "adamw_torch",
|
11 |
+
"scheduler": "linear",
|
12 |
+
"weight_decay": 0.0,
|
13 |
+
"max_grad_norm": 1.0,
|
14 |
+
"seed": 42,
|
15 |
+
"train_split": "train",
|
16 |
+
"valid_split": "validation",
|
17 |
+
"logging_steps": -1,
|
18 |
+
"project_name": "petsona-cat",
|
19 |
+
"auto_find_batch_size": false,
|
20 |
+
"mixed_precision": "fp16",
|
21 |
+
"save_total_limit": 1,
|
22 |
+
"push_to_hub": true,
|
23 |
+
"eval_strategy": "epoch",
|
24 |
+
"image_column": "autotrain_image",
|
25 |
+
"target_column": "autotrain_label",
|
26 |
+
"log": "tensorboard",
|
27 |
+
"early_stopping_patience": 5,
|
28 |
+
"early_stopping_threshold": 0.01
|
29 |
+
}
|