karoladelk
commited on
Commit
•
37b7aa4
1
Parent(s):
cfed181
End of training
Browse files- README.md +3 -3
- all_results.json +10 -10
- eval_results.json +5 -5
- runs/May10_21-58-40_223f6404b016/events.out.tfevents.1715378452.223f6404b016.34.3 +3 -0
- train_results.json +6 -6
- trainer_state.json +53 -37
README.md
CHANGED
@@ -22,7 +22,7 @@ model-index:
|
|
22 |
metrics:
|
23 |
- name: Accuracy
|
24 |
type: accuracy
|
25 |
-
value: 0.
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
32 |
|
33 |
This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
|
34 |
It achieves the following results on the evaluation set:
|
35 |
-
- Loss: 0.
|
36 |
-
- Accuracy: 0.
|
37 |
|
38 |
## Model description
|
39 |
|
|
|
22 |
metrics:
|
23 |
- name: Accuracy
|
24 |
type: accuracy
|
25 |
+
value: 0.9052287581699346
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
32 |
|
33 |
This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
|
34 |
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 0.2288
|
36 |
+
- Accuracy: 0.9052
|
37 |
|
38 |
## Model description
|
39 |
|
all_results.json
CHANGED
@@ -1,13 +1,13 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
"eval_accuracy": 0.9052287581699346,
|
4 |
-
"eval_loss": 0.
|
5 |
-
"eval_runtime": 2.
|
6 |
-
"eval_samples_per_second":
|
7 |
-
"eval_steps_per_second": 2.
|
8 |
-
"total_flos":
|
9 |
-
"train_loss": 0.
|
10 |
-
"train_runtime":
|
11 |
-
"train_samples_per_second":
|
12 |
-
"train_steps_per_second": 0.
|
13 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 3.72,
|
3 |
"eval_accuracy": 0.9052287581699346,
|
4 |
+
"eval_loss": 0.22878025472164154,
|
5 |
+
"eval_runtime": 2.2699,
|
6 |
+
"eval_samples_per_second": 134.807,
|
7 |
+
"eval_steps_per_second": 2.203,
|
8 |
+
"total_flos": 2.5445786921520538e+17,
|
9 |
+
"train_loss": 0.1845790594816208,
|
10 |
+
"train_runtime": 114.4495,
|
11 |
+
"train_samples_per_second": 96.147,
|
12 |
+
"train_steps_per_second": 0.349
|
13 |
}
|
eval_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
"eval_accuracy": 0.9052287581699346,
|
4 |
-
"eval_loss": 0.
|
5 |
-
"eval_runtime": 2.
|
6 |
-
"eval_samples_per_second":
|
7 |
-
"eval_steps_per_second": 2.
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 3.72,
|
3 |
"eval_accuracy": 0.9052287581699346,
|
4 |
+
"eval_loss": 0.22878025472164154,
|
5 |
+
"eval_runtime": 2.2699,
|
6 |
+
"eval_samples_per_second": 134.807,
|
7 |
+
"eval_steps_per_second": 2.203
|
8 |
}
|
runs/May10_21-58-40_223f6404b016/events.out.tfevents.1715378452.223f6404b016.34.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:01dcadaba42b43391879dcd21fe57a3cc23ede3883d40f3bb2c845ec22e20a62
|
3 |
+
size 405
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"total_flos":
|
4 |
-
"train_loss": 0.
|
5 |
-
"train_runtime":
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 3.72,
|
3 |
+
"total_flos": 2.5445786921520538e+17,
|
4 |
+
"train_loss": 0.1845790594816208,
|
5 |
+
"train_runtime": 114.4495,
|
6 |
+
"train_samples_per_second": 96.147,
|
7 |
+
"train_steps_per_second": 0.349
|
8 |
}
|
trainer_state.json
CHANGED
@@ -1,77 +1,93 @@
|
|
1 |
{
|
2 |
"best_metric": 0.9052287581699346,
|
3 |
-
"best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-
|
4 |
-
"epoch":
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.93,
|
13 |
-
"grad_norm":
|
14 |
-
"learning_rate":
|
15 |
-
"loss": 0.
|
16 |
"step": 10
|
17 |
},
|
18 |
{
|
19 |
"epoch": 0.93,
|
20 |
-
"eval_accuracy": 0.
|
21 |
-
"eval_loss": 0.
|
22 |
-
"eval_runtime":
|
23 |
-
"eval_samples_per_second":
|
24 |
-
"eval_steps_per_second":
|
25 |
"step": 10
|
26 |
},
|
27 |
{
|
28 |
"epoch": 1.86,
|
29 |
-
"grad_norm":
|
30 |
-
"learning_rate":
|
31 |
-
"loss": 0.
|
32 |
"step": 20
|
33 |
},
|
34 |
{
|
35 |
"epoch": 1.95,
|
36 |
"eval_accuracy": 0.8954248366013072,
|
37 |
-
"eval_loss": 0.
|
38 |
-
"eval_runtime": 1.
|
39 |
-
"eval_samples_per_second":
|
40 |
-
"eval_steps_per_second": 3.
|
41 |
"step": 21
|
42 |
},
|
43 |
{
|
44 |
"epoch": 2.79,
|
45 |
-
"grad_norm": 3.
|
46 |
-
"learning_rate":
|
47 |
-
"loss": 0.
|
48 |
"step": 30
|
49 |
},
|
50 |
{
|
51 |
-
"epoch": 2.
|
52 |
"eval_accuracy": 0.9052287581699346,
|
53 |
-
"eval_loss": 0.
|
54 |
-
"eval_runtime": 1.
|
55 |
-
"eval_samples_per_second": 180.
|
56 |
-
"eval_steps_per_second": 2.
|
57 |
-
"step":
|
58 |
},
|
59 |
{
|
60 |
-
"epoch":
|
61 |
-
"
|
62 |
-
"
|
63 |
-
"
|
64 |
-
"
|
65 |
-
|
66 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
67 |
}
|
68 |
],
|
69 |
"logging_steps": 10,
|
70 |
-
"max_steps":
|
71 |
"num_input_tokens_seen": 0,
|
72 |
-
"num_train_epochs":
|
73 |
"save_steps": 500,
|
74 |
-
"total_flos":
|
75 |
"train_batch_size": 64,
|
76 |
"trial_name": null,
|
77 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 0.9052287581699346,
|
3 |
+
"best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-10",
|
4 |
+
"epoch": 3.7209302325581395,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 40,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.93,
|
13 |
+
"grad_norm": 4.222448825836182,
|
14 |
+
"learning_rate": 4.166666666666667e-05,
|
15 |
+
"loss": 0.207,
|
16 |
"step": 10
|
17 |
},
|
18 |
{
|
19 |
"epoch": 0.93,
|
20 |
+
"eval_accuracy": 0.9052287581699346,
|
21 |
+
"eval_loss": 0.22878025472164154,
|
22 |
+
"eval_runtime": 1.601,
|
23 |
+
"eval_samples_per_second": 191.126,
|
24 |
+
"eval_steps_per_second": 3.123,
|
25 |
"step": 10
|
26 |
},
|
27 |
{
|
28 |
"epoch": 1.86,
|
29 |
+
"grad_norm": 3.6448166370391846,
|
30 |
+
"learning_rate": 2.777777777777778e-05,
|
31 |
+
"loss": 0.1873,
|
32 |
"step": 20
|
33 |
},
|
34 |
{
|
35 |
"epoch": 1.95,
|
36 |
"eval_accuracy": 0.8954248366013072,
|
37 |
+
"eval_loss": 0.24186921119689941,
|
38 |
+
"eval_runtime": 1.5552,
|
39 |
+
"eval_samples_per_second": 196.755,
|
40 |
+
"eval_steps_per_second": 3.215,
|
41 |
"step": 21
|
42 |
},
|
43 |
{
|
44 |
"epoch": 2.79,
|
45 |
+
"grad_norm": 3.7166202068328857,
|
46 |
+
"learning_rate": 1.388888888888889e-05,
|
47 |
+
"loss": 0.1808,
|
48 |
"step": 30
|
49 |
},
|
50 |
{
|
51 |
+
"epoch": 2.98,
|
52 |
"eval_accuracy": 0.9052287581699346,
|
53 |
+
"eval_loss": 0.23222029209136963,
|
54 |
+
"eval_runtime": 1.6942,
|
55 |
+
"eval_samples_per_second": 180.612,
|
56 |
+
"eval_steps_per_second": 2.951,
|
57 |
+
"step": 32
|
58 |
},
|
59 |
{
|
60 |
+
"epoch": 3.72,
|
61 |
+
"grad_norm": 5.479237079620361,
|
62 |
+
"learning_rate": 0.0,
|
63 |
+
"loss": 0.1632,
|
64 |
+
"step": 40
|
65 |
+
},
|
66 |
+
{
|
67 |
+
"epoch": 3.72,
|
68 |
+
"eval_accuracy": 0.9019607843137255,
|
69 |
+
"eval_loss": 0.2268960028886795,
|
70 |
+
"eval_runtime": 1.7412,
|
71 |
+
"eval_samples_per_second": 175.742,
|
72 |
+
"eval_steps_per_second": 2.872,
|
73 |
+
"step": 40
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 3.72,
|
77 |
+
"step": 40,
|
78 |
+
"total_flos": 2.5445786921520538e+17,
|
79 |
+
"train_loss": 0.1845790594816208,
|
80 |
+
"train_runtime": 114.4495,
|
81 |
+
"train_samples_per_second": 96.147,
|
82 |
+
"train_steps_per_second": 0.349
|
83 |
}
|
84 |
],
|
85 |
"logging_steps": 10,
|
86 |
+
"max_steps": 40,
|
87 |
"num_input_tokens_seen": 0,
|
88 |
+
"num_train_epochs": 4,
|
89 |
"save_steps": 500,
|
90 |
+
"total_flos": 2.5445786921520538e+17,
|
91 |
"train_batch_size": 64,
|
92 |
"trial_name": null,
|
93 |
"trial_params": null
|