Training in progress, epoch 1
Browse files- all_results.json +8 -0
- config.json +2 -2
- pytorch_model.bin +1 -1
- train_results.json +8 -0
- trainer_state.json +79 -0
- training_args.bin +1 -1
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"total_flos": 4.424366039482368e+16,
|
4 |
+
"train_loss": 0.5553644498189291,
|
5 |
+
"train_runtime": 37.7029,
|
6 |
+
"train_samples_per_second": 47.211,
|
7 |
+
"train_steps_per_second": 0.398
|
8 |
+
}
|
config.json
CHANGED
@@ -18,13 +18,13 @@
|
|
18 |
"hidden_size": 768,
|
19 |
"id2label": {
|
20 |
"0": "m",
|
21 |
-
"1": "
|
22 |
},
|
23 |
"image_size": 224,
|
24 |
"initializer_range": 0.02,
|
25 |
"label2id": {
|
26 |
"m": 0,
|
27 |
-
"
|
28 |
},
|
29 |
"layer_norm_eps": 1e-05,
|
30 |
"mlp_ratio": 4.0,
|
|
|
18 |
"hidden_size": 768,
|
19 |
"id2label": {
|
20 |
"0": "m",
|
21 |
+
"1": "nonm"
|
22 |
},
|
23 |
"image_size": 224,
|
24 |
"initializer_range": 0.02,
|
25 |
"label2id": {
|
26 |
"m": 0,
|
27 |
+
"nonm": 1
|
28 |
},
|
29 |
"layer_norm_eps": 1e-05,
|
30 |
"mlp_ratio": 4.0,
|
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 sha256:733058975269c0a806feab2c801f474a58f2ae1d16e0c79d3ea2d1e3cc2ceec8
|
3 |
size 110394865
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"total_flos": 4.424366039482368e+16,
|
4 |
+
"train_loss": 0.5553644498189291,
|
5 |
+
"train_runtime": 37.7029,
|
6 |
+
"train_samples_per_second": 47.211,
|
7 |
+
"train_steps_per_second": 0.398
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.6578947368421053,
|
3 |
+
"best_model_checkpoint": "swin-tiny-patch4-window7-224-finetunedo/checkpoint-12",
|
4 |
+
"epoch": 5.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 15,
|
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_loss": 0.8087626695632935,
|
14 |
+
"eval_roc_auc": 0.5,
|
15 |
+
"eval_runtime": 0.4279,
|
16 |
+
"eval_samples_per_second": 93.481,
|
17 |
+
"eval_steps_per_second": 4.674,
|
18 |
+
"step": 3
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 2.0,
|
22 |
+
"eval_loss": 0.7895530462265015,
|
23 |
+
"eval_roc_auc": 0.5,
|
24 |
+
"eval_runtime": 0.327,
|
25 |
+
"eval_samples_per_second": 122.313,
|
26 |
+
"eval_steps_per_second": 6.116,
|
27 |
+
"step": 6
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 3.0,
|
31 |
+
"eval_loss": 0.6320240497589111,
|
32 |
+
"eval_roc_auc": 0.631578947368421,
|
33 |
+
"eval_runtime": 0.3977,
|
34 |
+
"eval_samples_per_second": 100.58,
|
35 |
+
"eval_steps_per_second": 5.029,
|
36 |
+
"step": 9
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 3.33,
|
40 |
+
"learning_rate": 1.5384615384615387e-05,
|
41 |
+
"loss": 0.5949,
|
42 |
+
"step": 10
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"epoch": 4.0,
|
46 |
+
"eval_loss": 0.5968085527420044,
|
47 |
+
"eval_roc_auc": 0.6578947368421053,
|
48 |
+
"eval_runtime": 0.3218,
|
49 |
+
"eval_samples_per_second": 124.283,
|
50 |
+
"eval_steps_per_second": 6.214,
|
51 |
+
"step": 12
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 5.0,
|
55 |
+
"eval_loss": 0.609512448310852,
|
56 |
+
"eval_roc_auc": 0.6578947368421053,
|
57 |
+
"eval_runtime": 0.3214,
|
58 |
+
"eval_samples_per_second": 124.448,
|
59 |
+
"eval_steps_per_second": 6.222,
|
60 |
+
"step": 15
|
61 |
+
},
|
62 |
+
{
|
63 |
+
"epoch": 5.0,
|
64 |
+
"step": 15,
|
65 |
+
"total_flos": 4.424366039482368e+16,
|
66 |
+
"train_loss": 0.5553644498189291,
|
67 |
+
"train_runtime": 37.7029,
|
68 |
+
"train_samples_per_second": 47.211,
|
69 |
+
"train_steps_per_second": 0.398
|
70 |
+
}
|
71 |
+
],
|
72 |
+
"logging_steps": 10,
|
73 |
+
"max_steps": 15,
|
74 |
+
"num_train_epochs": 5,
|
75 |
+
"save_steps": 500,
|
76 |
+
"total_flos": 4.424366039482368e+16,
|
77 |
+
"trial_name": null,
|
78 |
+
"trial_params": null
|
79 |
+
}
|
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:eea4de495e06875ef2eab3f1b5c6a32583f13435ce4556666d7cb0193f9ecd46
|
3 |
size 4091
|