End of training
Browse files- README.md +4 -2
- all_results.json +13 -0
- eval_results.json +8 -0
- runs/Oct23_00-54-45_pop-os/events.out.tfevents.1729668341.pop-os.162283.1 +3 -0
- train_results.json +8 -0
- trainer_state.json +255 -0
README.md
CHANGED
@@ -3,6 +3,8 @@ library_name: transformers
|
|
3 |
license: apache-2.0
|
4 |
base_model: google/vit-base-patch16-224-in21k
|
5 |
tags:
|
|
|
|
|
6 |
- generated_from_trainer
|
7 |
datasets:
|
8 |
- arrow
|
@@ -15,7 +17,7 @@ model-index:
|
|
15 |
name: Image Classification
|
16 |
type: image-classification
|
17 |
dataset:
|
18 |
-
name:
|
19 |
type: arrow
|
20 |
config: default
|
21 |
split: validation
|
@@ -31,7 +33,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
31 |
|
32 |
# tcg-magic-classifier
|
33 |
|
34 |
-
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the
|
35 |
It achieves the following results on the evaluation set:
|
36 |
- Loss: 7.9836
|
37 |
- Accuracy: 0.2545
|
|
|
3 |
license: apache-2.0
|
4 |
base_model: google/vit-base-patch16-224-in21k
|
5 |
tags:
|
6 |
+
- image-classification
|
7 |
+
- vision
|
8 |
- generated_from_trainer
|
9 |
datasets:
|
10 |
- arrow
|
|
|
17 |
name: Image Classification
|
18 |
type: image-classification
|
19 |
dataset:
|
20 |
+
name: acidtib/tcg-magic-cards
|
21 |
type: arrow
|
22 |
config: default
|
23 |
split: validation
|
|
|
33 |
|
34 |
# tcg-magic-classifier
|
35 |
|
36 |
+
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the acidtib/tcg-magic-cards dataset.
|
37 |
It achieves the following results on the evaluation set:
|
38 |
- Loss: 7.9836
|
39 |
- Accuracy: 0.2545
|
all_results.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"eval_accuracy": 0.25452380952380954,
|
4 |
+
"eval_loss": 7.983619689941406,
|
5 |
+
"eval_runtime": 36.7429,
|
6 |
+
"eval_samples_per_second": 114.308,
|
7 |
+
"eval_steps_per_second": 3.593,
|
8 |
+
"total_flos": 6.271796898791424e+18,
|
9 |
+
"train_loss": 8.131903288794346,
|
10 |
+
"train_runtime": 1755.8039,
|
11 |
+
"train_samples_per_second": 44.424,
|
12 |
+
"train_steps_per_second": 1.39
|
13 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"eval_accuracy": 0.25452380952380954,
|
4 |
+
"eval_loss": 7.983619689941406,
|
5 |
+
"eval_runtime": 36.7429,
|
6 |
+
"eval_samples_per_second": 114.308,
|
7 |
+
"eval_steps_per_second": 3.593
|
8 |
+
}
|
runs/Oct23_00-54-45_pop-os/events.out.tfevents.1729668341.pop-os.162283.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e2cc982742d1bcaf4293554263cf965b557272b9439437012382ef228c53e3d
|
3 |
+
size 411
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"total_flos": 6.271796898791424e+18,
|
4 |
+
"train_loss": 8.131903288794346,
|
5 |
+
"train_runtime": 1755.8039,
|
6 |
+
"train_samples_per_second": 44.424,
|
7 |
+
"train_steps_per_second": 1.39
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,255 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 7.983619689941406,
|
3 |
+
"best_model_checkpoint": "./models/magic/checkpoint-2440",
|
4 |
+
"epoch": 5.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 2440,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.20491803278688525,
|
13 |
+
"grad_norm": 66683.3203125,
|
14 |
+
"learning_rate": 1.918032786885246e-05,
|
15 |
+
"loss": 8.3446,
|
16 |
+
"step": 100
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.4098360655737705,
|
20 |
+
"grad_norm": 88343.609375,
|
21 |
+
"learning_rate": 1.836065573770492e-05,
|
22 |
+
"loss": 8.344,
|
23 |
+
"step": 200
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.6147540983606558,
|
27 |
+
"grad_norm": 112013.890625,
|
28 |
+
"learning_rate": 1.7540983606557377e-05,
|
29 |
+
"loss": 8.3305,
|
30 |
+
"step": 300
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.819672131147541,
|
34 |
+
"grad_norm": 107013.5390625,
|
35 |
+
"learning_rate": 1.6721311475409837e-05,
|
36 |
+
"loss": 8.3148,
|
37 |
+
"step": 400
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 1.0,
|
41 |
+
"eval_accuracy": 0.0054761904761904765,
|
42 |
+
"eval_loss": 8.26321792602539,
|
43 |
+
"eval_runtime": 37.0437,
|
44 |
+
"eval_samples_per_second": 113.38,
|
45 |
+
"eval_steps_per_second": 3.563,
|
46 |
+
"step": 488
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 1.0245901639344261,
|
50 |
+
"grad_norm": 109507.2734375,
|
51 |
+
"learning_rate": 1.5901639344262295e-05,
|
52 |
+
"loss": 8.2911,
|
53 |
+
"step": 500
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 1.2295081967213115,
|
57 |
+
"grad_norm": 107816.046875,
|
58 |
+
"learning_rate": 1.5081967213114754e-05,
|
59 |
+
"loss": 8.2472,
|
60 |
+
"step": 600
|
61 |
+
},
|
62 |
+
{
|
63 |
+
"epoch": 1.4344262295081966,
|
64 |
+
"grad_norm": 108237.4453125,
|
65 |
+
"learning_rate": 1.4262295081967214e-05,
|
66 |
+
"loss": 8.2257,
|
67 |
+
"step": 700
|
68 |
+
},
|
69 |
+
{
|
70 |
+
"epoch": 1.639344262295082,
|
71 |
+
"grad_norm": 111140.1640625,
|
72 |
+
"learning_rate": 1.3442622950819673e-05,
|
73 |
+
"loss": 8.2074,
|
74 |
+
"step": 800
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 1.8442622950819674,
|
78 |
+
"grad_norm": 107701.734375,
|
79 |
+
"learning_rate": 1.2622950819672132e-05,
|
80 |
+
"loss": 8.1958,
|
81 |
+
"step": 900
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 2.0,
|
85 |
+
"eval_accuracy": 0.05976190476190476,
|
86 |
+
"eval_loss": 8.151880264282227,
|
87 |
+
"eval_runtime": 37.1118,
|
88 |
+
"eval_samples_per_second": 113.172,
|
89 |
+
"eval_steps_per_second": 3.557,
|
90 |
+
"step": 976
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 2.0491803278688523,
|
94 |
+
"grad_norm": 111871.875,
|
95 |
+
"learning_rate": 1.1803278688524591e-05,
|
96 |
+
"loss": 8.1707,
|
97 |
+
"step": 1000
|
98 |
+
},
|
99 |
+
{
|
100 |
+
"epoch": 2.2540983606557377,
|
101 |
+
"grad_norm": 117045.8203125,
|
102 |
+
"learning_rate": 1.0983606557377052e-05,
|
103 |
+
"loss": 8.1275,
|
104 |
+
"step": 1100
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 2.459016393442623,
|
108 |
+
"grad_norm": 110316.90625,
|
109 |
+
"learning_rate": 1.0163934426229509e-05,
|
110 |
+
"loss": 8.1193,
|
111 |
+
"step": 1200
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 2.663934426229508,
|
115 |
+
"grad_norm": 114694.4609375,
|
116 |
+
"learning_rate": 9.344262295081968e-06,
|
117 |
+
"loss": 8.1023,
|
118 |
+
"step": 1300
|
119 |
+
},
|
120 |
+
{
|
121 |
+
"epoch": 2.8688524590163933,
|
122 |
+
"grad_norm": 113438.8828125,
|
123 |
+
"learning_rate": 8.524590163934427e-06,
|
124 |
+
"loss": 8.089,
|
125 |
+
"step": 1400
|
126 |
+
},
|
127 |
+
{
|
128 |
+
"epoch": 3.0,
|
129 |
+
"eval_accuracy": 0.15666666666666668,
|
130 |
+
"eval_loss": 8.05963134765625,
|
131 |
+
"eval_runtime": 36.9672,
|
132 |
+
"eval_samples_per_second": 113.614,
|
133 |
+
"eval_steps_per_second": 3.571,
|
134 |
+
"step": 1464
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 3.0737704918032787,
|
138 |
+
"grad_norm": 130567.7890625,
|
139 |
+
"learning_rate": 7.704918032786886e-06,
|
140 |
+
"loss": 8.0675,
|
141 |
+
"step": 1500
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 3.278688524590164,
|
145 |
+
"grad_norm": 111654.6484375,
|
146 |
+
"learning_rate": 6.885245901639345e-06,
|
147 |
+
"loss": 8.049,
|
148 |
+
"step": 1600
|
149 |
+
},
|
150 |
+
{
|
151 |
+
"epoch": 3.4836065573770494,
|
152 |
+
"grad_norm": 110857.171875,
|
153 |
+
"learning_rate": 6.065573770491804e-06,
|
154 |
+
"loss": 8.0304,
|
155 |
+
"step": 1700
|
156 |
+
},
|
157 |
+
{
|
158 |
+
"epoch": 3.6885245901639343,
|
159 |
+
"grad_norm": 120024.4765625,
|
160 |
+
"learning_rate": 5.245901639344263e-06,
|
161 |
+
"loss": 8.0182,
|
162 |
+
"step": 1800
|
163 |
+
},
|
164 |
+
{
|
165 |
+
"epoch": 3.8934426229508197,
|
166 |
+
"grad_norm": 113248.8359375,
|
167 |
+
"learning_rate": 4.426229508196722e-06,
|
168 |
+
"loss": 8.0208,
|
169 |
+
"step": 1900
|
170 |
+
},
|
171 |
+
{
|
172 |
+
"epoch": 4.0,
|
173 |
+
"eval_accuracy": 0.2276190476190476,
|
174 |
+
"eval_loss": 8.003293991088867,
|
175 |
+
"eval_runtime": 36.914,
|
176 |
+
"eval_samples_per_second": 113.778,
|
177 |
+
"eval_steps_per_second": 3.576,
|
178 |
+
"step": 1952
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 4.098360655737705,
|
182 |
+
"grad_norm": 114861.390625,
|
183 |
+
"learning_rate": 3.6065573770491806e-06,
|
184 |
+
"loss": 8.0023,
|
185 |
+
"step": 2000
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 4.30327868852459,
|
189 |
+
"grad_norm": 114188.84375,
|
190 |
+
"learning_rate": 2.786885245901639e-06,
|
191 |
+
"loss": 7.9841,
|
192 |
+
"step": 2100
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 4.508196721311475,
|
196 |
+
"grad_norm": 114966.8828125,
|
197 |
+
"learning_rate": 1.9672131147540985e-06,
|
198 |
+
"loss": 7.9843,
|
199 |
+
"step": 2200
|
200 |
+
},
|
201 |
+
{
|
202 |
+
"epoch": 4.713114754098361,
|
203 |
+
"grad_norm": 124759.4375,
|
204 |
+
"learning_rate": 1.1475409836065575e-06,
|
205 |
+
"loss": 7.9772,
|
206 |
+
"step": 2300
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 4.918032786885246,
|
210 |
+
"grad_norm": 110823.4609375,
|
211 |
+
"learning_rate": 3.278688524590164e-07,
|
212 |
+
"loss": 7.983,
|
213 |
+
"step": 2400
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 5.0,
|
217 |
+
"eval_accuracy": 0.25452380952380954,
|
218 |
+
"eval_loss": 7.983619689941406,
|
219 |
+
"eval_runtime": 37.5516,
|
220 |
+
"eval_samples_per_second": 111.846,
|
221 |
+
"eval_steps_per_second": 3.515,
|
222 |
+
"step": 2440
|
223 |
+
},
|
224 |
+
{
|
225 |
+
"epoch": 5.0,
|
226 |
+
"step": 2440,
|
227 |
+
"total_flos": 6.271796898791424e+18,
|
228 |
+
"train_loss": 8.131903288794346,
|
229 |
+
"train_runtime": 1755.8039,
|
230 |
+
"train_samples_per_second": 44.424,
|
231 |
+
"train_steps_per_second": 1.39
|
232 |
+
}
|
233 |
+
],
|
234 |
+
"logging_steps": 100,
|
235 |
+
"max_steps": 2440,
|
236 |
+
"num_input_tokens_seen": 0,
|
237 |
+
"num_train_epochs": 5,
|
238 |
+
"save_steps": 500,
|
239 |
+
"stateful_callbacks": {
|
240 |
+
"TrainerControl": {
|
241 |
+
"args": {
|
242 |
+
"should_epoch_stop": false,
|
243 |
+
"should_evaluate": false,
|
244 |
+
"should_log": false,
|
245 |
+
"should_save": true,
|
246 |
+
"should_training_stop": true
|
247 |
+
},
|
248 |
+
"attributes": {}
|
249 |
+
}
|
250 |
+
},
|
251 |
+
"total_flos": 6.271796898791424e+18,
|
252 |
+
"train_batch_size": 32,
|
253 |
+
"trial_name": null,
|
254 |
+
"trial_params": null
|
255 |
+
}
|