HorcruxNo13
commited on
Commit
•
9e2f2c2
1
Parent(s):
e7e9feb
Training in progress, epoch 1
Browse files- all_results.json +8 -0
- pytorch_model.bin +1 -1
- train_results.json +8 -0
- trainer_state.json +76 -0
- training_args.bin +1 -1
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"total_flos": 7.4567966957568e+16,
|
4 |
+
"train_loss": 0.5813349982102712,
|
5 |
+
"train_runtime": 56.867,
|
6 |
+
"train_samples_per_second": 52.755,
|
7 |
+
"train_steps_per_second": 0.422
|
8 |
+
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 110394865
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a6e2b2e7bbea0f0172ae441a6d3c98264adcfc764cb19e33548be2523e39076a
|
3 |
size 110394865
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"total_flos": 7.4567966957568e+16,
|
4 |
+
"train_loss": 0.5813349982102712,
|
5 |
+
"train_runtime": 56.867,
|
6 |
+
"train_samples_per_second": 52.755,
|
7 |
+
"train_steps_per_second": 0.422
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.7375,
|
3 |
+
"best_model_checkpoint": "swin-tiny-patch4-window7-224/checkpoint-24",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 24,
|
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": 0.7333333333333333,
|
14 |
+
"eval_loss": 0.5740450024604797,
|
15 |
+
"eval_runtime": 1.7884,
|
16 |
+
"eval_samples_per_second": 134.201,
|
17 |
+
"eval_steps_per_second": 4.473,
|
18 |
+
"step": 8
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 1.25,
|
22 |
+
"learning_rate": 3.3333333333333335e-05,
|
23 |
+
"loss": 0.6033,
|
24 |
+
"step": 10
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 2.0,
|
28 |
+
"eval_accuracy": 0.7333333333333333,
|
29 |
+
"eval_loss": 0.5640280246734619,
|
30 |
+
"eval_runtime": 1.8333,
|
31 |
+
"eval_samples_per_second": 130.909,
|
32 |
+
"eval_steps_per_second": 4.364,
|
33 |
+
"step": 16
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 2.5,
|
37 |
+
"learning_rate": 9.523809523809523e-06,
|
38 |
+
"loss": 0.5751,
|
39 |
+
"step": 20
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 3.0,
|
43 |
+
"eval_accuracy": 0.7375,
|
44 |
+
"eval_loss": 0.5567867159843445,
|
45 |
+
"eval_runtime": 1.9734,
|
46 |
+
"eval_samples_per_second": 121.615,
|
47 |
+
"eval_steps_per_second": 4.054,
|
48 |
+
"step": 24
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 3.0,
|
52 |
+
"step": 24,
|
53 |
+
"total_flos": 7.4567966957568e+16,
|
54 |
+
"train_loss": 0.5813349982102712,
|
55 |
+
"train_runtime": 56.867,
|
56 |
+
"train_samples_per_second": 52.755,
|
57 |
+
"train_steps_per_second": 0.422
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 3.0,
|
61 |
+
"eval_accuracy": 0.73,
|
62 |
+
"eval_loss": 0.5407183766365051,
|
63 |
+
"eval_runtime": 70.3286,
|
64 |
+
"eval_samples_per_second": 4.266,
|
65 |
+
"eval_steps_per_second": 0.142,
|
66 |
+
"step": 24
|
67 |
+
}
|
68 |
+
],
|
69 |
+
"logging_steps": 10,
|
70 |
+
"max_steps": 24,
|
71 |
+
"num_train_epochs": 3,
|
72 |
+
"save_steps": 500,
|
73 |
+
"total_flos": 7.4567966957568e+16,
|
74 |
+
"trial_name": null,
|
75 |
+
"trial_params": null
|
76 |
+
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4091
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c65c717272eaaf96c5bf910ae2ffddb125d47dbf1e8a7b421de93e681c21d85
|
3 |
size 4091
|