dungeon-geo-morphs
Browse files- README.md +6 -5
- all_results.json +13 -0
- eval_results.json +8 -0
- runs/Nov28_19-22-51_c84079d71601/events.out.tfevents.1732822323.c84079d71601.1724.11 +3 -0
- train_results.json +8 -0
- trainer_state.json +170 -0
README.md
CHANGED
@@ -3,6 +3,7 @@ library_name: transformers
|
|
3 |
license: apache-2.0
|
4 |
base_model: google/vit-large-patch16-224
|
5 |
tags:
|
|
|
6 |
- generated_from_trainer
|
7 |
datasets:
|
8 |
- imagefolder
|
@@ -15,7 +16,7 @@ model-index:
|
|
15 |
name: Image Classification
|
16 |
type: image-classification
|
17 |
dataset:
|
18 |
-
name:
|
19 |
type: imagefolder
|
20 |
config: default
|
21 |
split: validation
|
@@ -23,7 +24,7 @@ model-index:
|
|
23 |
metrics:
|
24 |
- name: Accuracy
|
25 |
type: accuracy
|
26 |
-
value: 0.
|
27 |
---
|
28 |
|
29 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -31,10 +32,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
31 |
|
32 |
# vit-large-patch16-224-dungeon-geo-morphs-0-4-28Nov24-006
|
33 |
|
34 |
-
This model is a fine-tuned version of [google/vit-large-patch16-224](https://huggingface.co/google/vit-large-patch16-224) on the
|
35 |
It achieves the following results on the evaluation set:
|
36 |
-
- Loss: 0.
|
37 |
-
- Accuracy: 0.
|
38 |
|
39 |
## Model description
|
40 |
|
|
|
3 |
license: apache-2.0
|
4 |
base_model: google/vit-large-patch16-224
|
5 |
tags:
|
6 |
+
- image-classification
|
7 |
- generated_from_trainer
|
8 |
datasets:
|
9 |
- imagefolder
|
|
|
16 |
name: Image Classification
|
17 |
type: image-classification
|
18 |
dataset:
|
19 |
+
name: dungeon-geo-morphs
|
20 |
type: imagefolder
|
21 |
config: default
|
22 |
split: validation
|
|
|
24 |
metrics:
|
25 |
- name: Accuracy
|
26 |
type: accuracy
|
27 |
+
value: 0.9821428571428571
|
28 |
---
|
29 |
|
30 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
32 |
|
33 |
# vit-large-patch16-224-dungeon-geo-morphs-0-4-28Nov24-006
|
34 |
|
35 |
+
This model is a fine-tuned version of [google/vit-large-patch16-224](https://huggingface.co/google/vit-large-patch16-224) on the dungeon-geo-morphs dataset.
|
36 |
It achieves the following results on the evaluation set:
|
37 |
+
- Loss: 0.0747
|
38 |
+
- Accuracy: 0.9821
|
39 |
|
40 |
## Model description
|
41 |
|
all_results.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 32.0,
|
3 |
+
"eval_accuracy": 0.9821428571428571,
|
4 |
+
"eval_loss": 0.07470609247684479,
|
5 |
+
"eval_runtime": 8.0684,
|
6 |
+
"eval_samples_per_second": 69.406,
|
7 |
+
"eval_steps_per_second": 8.676,
|
8 |
+
"total_flos": 7.012786101918106e+17,
|
9 |
+
"train_loss": 0.34752421248704196,
|
10 |
+
"train_runtime": 465.741,
|
11 |
+
"train_samples_per_second": 6.871,
|
12 |
+
"train_steps_per_second": 0.172
|
13 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 32.0,
|
3 |
+
"eval_accuracy": 0.9821428571428571,
|
4 |
+
"eval_loss": 0.07470609247684479,
|
5 |
+
"eval_runtime": 8.0684,
|
6 |
+
"eval_samples_per_second": 69.406,
|
7 |
+
"eval_steps_per_second": 8.676
|
8 |
+
}
|
runs/Nov28_19-22-51_c84079d71601/events.out.tfevents.1732822323.c84079d71601.1724.11
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fdc90d6e9f9d03e846355b7f8e3462a4ddfdfced0e1ab8d652fab75f53bd8ceb
|
3 |
+
size 405
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 32.0,
|
3 |
+
"total_flos": 7.012786101918106e+17,
|
4 |
+
"train_loss": 0.34752421248704196,
|
5 |
+
"train_runtime": 465.741,
|
6 |
+
"train_samples_per_second": 6.871,
|
7 |
+
"train_steps_per_second": 0.172
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,170 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.9821428571428571,
|
3 |
+
"best_model_checkpoint": "vit-large-patch16-224-dungeon-geo-morphs-0-4-28Nov24-006/checkpoint-60",
|
4 |
+
"epoch": 32.0,
|
5 |
+
"eval_steps": 10,
|
6 |
+
"global_step": 80,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 4.0,
|
13 |
+
"grad_norm": 24.072080612182617,
|
14 |
+
"learning_rate": 9.861111111111112e-06,
|
15 |
+
"loss": 1.6194,
|
16 |
+
"step": 10
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 4.0,
|
20 |
+
"eval_accuracy": 0.6214285714285714,
|
21 |
+
"eval_loss": 1.232202172279358,
|
22 |
+
"eval_runtime": 7.6519,
|
23 |
+
"eval_samples_per_second": 73.185,
|
24 |
+
"eval_steps_per_second": 9.148,
|
25 |
+
"step": 10
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 8.0,
|
29 |
+
"grad_norm": 17.304100036621094,
|
30 |
+
"learning_rate": 8.472222222222223e-06,
|
31 |
+
"loss": 0.7978,
|
32 |
+
"step": 20
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 8.0,
|
36 |
+
"eval_accuracy": 0.925,
|
37 |
+
"eval_loss": 0.5918735861778259,
|
38 |
+
"eval_runtime": 7.3658,
|
39 |
+
"eval_samples_per_second": 76.027,
|
40 |
+
"eval_steps_per_second": 9.503,
|
41 |
+
"step": 20
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 12.0,
|
45 |
+
"grad_norm": 11.8755464553833,
|
46 |
+
"learning_rate": 7.083333333333335e-06,
|
47 |
+
"loss": 0.2576,
|
48 |
+
"step": 30
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 12.0,
|
52 |
+
"eval_accuracy": 0.9678571428571429,
|
53 |
+
"eval_loss": 0.2720572352409363,
|
54 |
+
"eval_runtime": 7.6632,
|
55 |
+
"eval_samples_per_second": 73.077,
|
56 |
+
"eval_steps_per_second": 9.135,
|
57 |
+
"step": 30
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 16.0,
|
61 |
+
"grad_norm": 2.4268698692321777,
|
62 |
+
"learning_rate": 5.694444444444445e-06,
|
63 |
+
"loss": 0.0723,
|
64 |
+
"step": 40
|
65 |
+
},
|
66 |
+
{
|
67 |
+
"epoch": 16.0,
|
68 |
+
"eval_accuracy": 0.9785714285714285,
|
69 |
+
"eval_loss": 0.15481743216514587,
|
70 |
+
"eval_runtime": 7.6991,
|
71 |
+
"eval_samples_per_second": 72.736,
|
72 |
+
"eval_steps_per_second": 9.092,
|
73 |
+
"step": 40
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 20.0,
|
77 |
+
"grad_norm": 1.032953143119812,
|
78 |
+
"learning_rate": 4.305555555555556e-06,
|
79 |
+
"loss": 0.0202,
|
80 |
+
"step": 50
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 20.0,
|
84 |
+
"eval_accuracy": 0.9767857142857143,
|
85 |
+
"eval_loss": 0.10659553855657578,
|
86 |
+
"eval_runtime": 8.3338,
|
87 |
+
"eval_samples_per_second": 67.196,
|
88 |
+
"eval_steps_per_second": 8.4,
|
89 |
+
"step": 50
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 24.0,
|
93 |
+
"grad_norm": 0.3209587633609772,
|
94 |
+
"learning_rate": 2.916666666666667e-06,
|
95 |
+
"loss": 0.0067,
|
96 |
+
"step": 60
|
97 |
+
},
|
98 |
+
{
|
99 |
+
"epoch": 24.0,
|
100 |
+
"eval_accuracy": 0.9821428571428571,
|
101 |
+
"eval_loss": 0.07470609247684479,
|
102 |
+
"eval_runtime": 8.1625,
|
103 |
+
"eval_samples_per_second": 68.606,
|
104 |
+
"eval_steps_per_second": 8.576,
|
105 |
+
"step": 60
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 28.0,
|
109 |
+
"grad_norm": 0.22312191128730774,
|
110 |
+
"learning_rate": 1.527777777777778e-06,
|
111 |
+
"loss": 0.0035,
|
112 |
+
"step": 70
|
113 |
+
},
|
114 |
+
{
|
115 |
+
"epoch": 28.0,
|
116 |
+
"eval_accuracy": 0.9767857142857143,
|
117 |
+
"eval_loss": 0.07538952678442001,
|
118 |
+
"eval_runtime": 7.554,
|
119 |
+
"eval_samples_per_second": 74.133,
|
120 |
+
"eval_steps_per_second": 9.267,
|
121 |
+
"step": 70
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 32.0,
|
125 |
+
"grad_norm": 0.1788581758737564,
|
126 |
+
"learning_rate": 1.3888888888888888e-07,
|
127 |
+
"loss": 0.0027,
|
128 |
+
"step": 80
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 32.0,
|
132 |
+
"eval_accuracy": 0.9785714285714285,
|
133 |
+
"eval_loss": 0.07296328991651535,
|
134 |
+
"eval_runtime": 7.9971,
|
135 |
+
"eval_samples_per_second": 70.026,
|
136 |
+
"eval_steps_per_second": 8.753,
|
137 |
+
"step": 80
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 32.0,
|
141 |
+
"step": 80,
|
142 |
+
"total_flos": 7.012786101918106e+17,
|
143 |
+
"train_loss": 0.34752421248704196,
|
144 |
+
"train_runtime": 465.741,
|
145 |
+
"train_samples_per_second": 6.871,
|
146 |
+
"train_steps_per_second": 0.172
|
147 |
+
}
|
148 |
+
],
|
149 |
+
"logging_steps": 10,
|
150 |
+
"max_steps": 80,
|
151 |
+
"num_input_tokens_seen": 0,
|
152 |
+
"num_train_epochs": 40,
|
153 |
+
"save_steps": 10,
|
154 |
+
"stateful_callbacks": {
|
155 |
+
"TrainerControl": {
|
156 |
+
"args": {
|
157 |
+
"should_epoch_stop": false,
|
158 |
+
"should_evaluate": false,
|
159 |
+
"should_log": false,
|
160 |
+
"should_save": true,
|
161 |
+
"should_training_stop": true
|
162 |
+
},
|
163 |
+
"attributes": {}
|
164 |
+
}
|
165 |
+
},
|
166 |
+
"total_flos": 7.012786101918106e+17,
|
167 |
+
"train_batch_size": 8,
|
168 |
+
"trial_name": null,
|
169 |
+
"trial_params": null
|
170 |
+
}
|