upload 8 files
Browse files- optimizer.pt +3 -0
- preprocessor_config.json +22 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +115 -0
- training_args.bin +3 -0
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8efdac5468491074615c55936e608c651a8a8fcdbb8b8e8ec94dcf208f508b81
|
3 |
+
size 686524869
|
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": "ViTFeatureExtractor",
|
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 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4a21039daeea51ae26a87bd727d96eec154c647f7c8208d3ffbc2a1c462ac8d4
|
3 |
+
size 343271789
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9ae46c9fc2e6261b72f159e1aea97f31830fdd07cc60689547b223b43e934178
|
3 |
+
size 14575
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a4bb6b5b97538dee498a3902091642365aec05b2c0d53583e9cafeb699c36301
|
3 |
+
size 627
|
trainer_state.json
ADDED
@@ -0,0 +1,115 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.26001426577568054,
|
3 |
+
"best_model_checkpoint": "./vit-base-beans/checkpoint-120",
|
4 |
+
"epoch": 3.1578947368421053,
|
5 |
+
"global_step": 120,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.26,
|
12 |
+
"learning_rate": 0.00018684210526315792,
|
13 |
+
"loss": 0.8842,
|
14 |
+
"step": 10
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.53,
|
18 |
+
"learning_rate": 0.0001736842105263158,
|
19 |
+
"loss": 0.4388,
|
20 |
+
"step": 20
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.79,
|
24 |
+
"learning_rate": 0.0001605263157894737,
|
25 |
+
"loss": 0.3165,
|
26 |
+
"step": 30
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 1.05,
|
30 |
+
"learning_rate": 0.00014736842105263158,
|
31 |
+
"loss": 0.1621,
|
32 |
+
"step": 40
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 1.05,
|
36 |
+
"eval_accuracy": 0.8820224719101124,
|
37 |
+
"eval_loss": 0.3338429927825928,
|
38 |
+
"eval_runtime": 3.9187,
|
39 |
+
"eval_samples_per_second": 45.423,
|
40 |
+
"eval_steps_per_second": 5.869,
|
41 |
+
"step": 40
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 1.32,
|
45 |
+
"learning_rate": 0.00013421052631578948,
|
46 |
+
"loss": 0.0843,
|
47 |
+
"step": 50
|
48 |
+
},
|
49 |
+
{
|
50 |
+
"epoch": 1.58,
|
51 |
+
"learning_rate": 0.00012105263157894738,
|
52 |
+
"loss": 0.1241,
|
53 |
+
"step": 60
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 1.84,
|
57 |
+
"learning_rate": 0.00010789473684210527,
|
58 |
+
"loss": 0.0418,
|
59 |
+
"step": 70
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 2.11,
|
63 |
+
"learning_rate": 9.473684210526316e-05,
|
64 |
+
"loss": 0.0497,
|
65 |
+
"step": 80
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 2.11,
|
69 |
+
"eval_accuracy": 0.8876404494382022,
|
70 |
+
"eval_loss": 0.31701481342315674,
|
71 |
+
"eval_runtime": 5.1269,
|
72 |
+
"eval_samples_per_second": 34.719,
|
73 |
+
"eval_steps_per_second": 4.486,
|
74 |
+
"step": 80
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 2.37,
|
78 |
+
"learning_rate": 8.157894736842105e-05,
|
79 |
+
"loss": 0.057,
|
80 |
+
"step": 90
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 2.63,
|
84 |
+
"learning_rate": 6.842105263157895e-05,
|
85 |
+
"loss": 0.0389,
|
86 |
+
"step": 100
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 2.89,
|
90 |
+
"learning_rate": 5.526315789473685e-05,
|
91 |
+
"loss": 0.0211,
|
92 |
+
"step": 110
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 3.16,
|
96 |
+
"learning_rate": 4.210526315789474e-05,
|
97 |
+
"loss": 0.0357,
|
98 |
+
"step": 120
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 3.16,
|
102 |
+
"eval_accuracy": 0.9157303370786517,
|
103 |
+
"eval_loss": 0.26001426577568054,
|
104 |
+
"eval_runtime": 4.1994,
|
105 |
+
"eval_samples_per_second": 42.387,
|
106 |
+
"eval_steps_per_second": 5.477,
|
107 |
+
"step": 120
|
108 |
+
}
|
109 |
+
],
|
110 |
+
"max_steps": 152,
|
111 |
+
"num_train_epochs": 4,
|
112 |
+
"total_flos": 1.4692612914988646e+17,
|
113 |
+
"trial_name": null,
|
114 |
+
"trial_params": null
|
115 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c49ab027ea17a0070ea421da6e11fd10db8a1d43786da88d29cc05a6f8bf72cf
|
3 |
+
size 3579
|