synergyai-jaeung
commited on
Commit
•
c1ebc49
1
Parent(s):
3031ed7
Training in progress, epoch 1
Browse files- all_results.json +13 -13
- eval_results.json +8 -8
- model.safetensors +1 -1
- runs/May28_14-57-40_RTX3090/events.out.tfevents.1716876157.RTX3090.403009.1 +3 -0
- runs/May28_16-57-52_RTX3090/events.out.tfevents.1716883073.RTX3090.462376.0 +3 -0
- train_results.json +5 -5
- trainer_state.json +138 -138
- training_args.bin +1 -1
all_results.json
CHANGED
@@ -1,17 +1,17 @@
|
|
1 |
{
|
2 |
"epoch": 12.0,
|
3 |
-
"eval_AUC": 0.
|
4 |
-
"eval_F1": 0.
|
5 |
-
"eval_Precision": 0.
|
6 |
"eval_Recall": 1.0,
|
7 |
-
"eval_accuracy": 0.
|
8 |
-
"eval_loss": 0.
|
9 |
-
"eval_runtime":
|
10 |
-
"eval_samples_per_second":
|
11 |
-
"eval_steps_per_second": 3.
|
12 |
-
"total_flos":
|
13 |
-
"train_loss": 0.
|
14 |
-
"train_runtime":
|
15 |
-
"train_samples_per_second":
|
16 |
-
"train_steps_per_second": 2.
|
17 |
}
|
|
|
1 |
{
|
2 |
"epoch": 12.0,
|
3 |
+
"eval_AUC": 0.5,
|
4 |
+
"eval_F1": 0.47572815533980584,
|
5 |
+
"eval_Precision": 0.9074074074074074,
|
6 |
"eval_Recall": 1.0,
|
7 |
+
"eval_accuracy": 0.9074074074074074,
|
8 |
+
"eval_loss": 0.3346473276615143,
|
9 |
+
"eval_runtime": 5.474,
|
10 |
+
"eval_samples_per_second": 59.189,
|
11 |
+
"eval_steps_per_second": 3.836,
|
12 |
+
"total_flos": 6.862690600268268e+17,
|
13 |
+
"train_loss": 0.03526242822408676,
|
14 |
+
"train_runtime": 251.233,
|
15 |
+
"train_samples_per_second": 35.25,
|
16 |
+
"train_steps_per_second": 2.245
|
17 |
}
|
eval_results.json
CHANGED
@@ -1,12 +1,12 @@
|
|
1 |
{
|
2 |
"epoch": 12.0,
|
3 |
-
"eval_AUC": 0.
|
4 |
-
"eval_F1": 0.
|
5 |
-
"eval_Precision": 0.
|
6 |
"eval_Recall": 1.0,
|
7 |
-
"eval_accuracy": 0.
|
8 |
-
"eval_loss": 0.
|
9 |
-
"eval_runtime":
|
10 |
-
"eval_samples_per_second":
|
11 |
-
"eval_steps_per_second": 3.
|
12 |
}
|
|
|
1 |
{
|
2 |
"epoch": 12.0,
|
3 |
+
"eval_AUC": 0.5,
|
4 |
+
"eval_F1": 0.47572815533980584,
|
5 |
+
"eval_Precision": 0.9074074074074074,
|
6 |
"eval_Recall": 1.0,
|
7 |
+
"eval_accuracy": 0.9074074074074074,
|
8 |
+
"eval_loss": 0.3346473276615143,
|
9 |
+
"eval_runtime": 5.474,
|
10 |
+
"eval_samples_per_second": 59.189,
|
11 |
+
"eval_steps_per_second": 3.836
|
12 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 343223968
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:760373362287b69643cb264294c3cdca3c69105ed8734ed2b2cb181e5b3d2411
|
3 |
size 343223968
|
runs/May28_14-57-40_RTX3090/events.out.tfevents.1716876157.RTX3090.403009.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f12bff649f6e82654f424ea5b85d1e418260fe8ed73237ec9b7d9baddfbbe000
|
3 |
+
size 607
|
runs/May28_16-57-52_RTX3090/events.out.tfevents.1716883073.RTX3090.462376.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e62d86463f7c212e69f5465846e3d3f7c8215cf17e293ba833e7ddfc7a674f2c
|
3 |
+
size 5634
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 12.0,
|
3 |
-
"total_flos":
|
4 |
-
"train_loss": 0.
|
5 |
-
"train_runtime":
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second": 2.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 12.0,
|
3 |
+
"total_flos": 6.862690600268268e+17,
|
4 |
+
"train_loss": 0.03526242822408676,
|
5 |
+
"train_runtime": 251.233,
|
6 |
+
"train_samples_per_second": 35.25,
|
7 |
+
"train_steps_per_second": 2.245
|
8 |
}
|
trainer_state.json
CHANGED
@@ -1,195 +1,195 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "google/vit-base-patch16-224-in21k_covid_19_ct_scans/checkpoint-
|
4 |
"epoch": 12.0,
|
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.
|
13 |
-
"grad_norm":
|
14 |
-
"learning_rate": 0.
|
15 |
-
"loss": 0.
|
16 |
"step": 1
|
17 |
},
|
18 |
{
|
19 |
"epoch": 1.0,
|
20 |
"eval_AUC": 0.5,
|
21 |
-
"eval_F1": 0.
|
22 |
-
"eval_Precision": 0.
|
23 |
"eval_Recall": 1.0,
|
24 |
-
"eval_accuracy": 0.
|
25 |
-
"eval_loss": 0.
|
26 |
-
"eval_runtime":
|
27 |
-
"eval_samples_per_second":
|
28 |
-
"eval_steps_per_second": 3.
|
29 |
-
"step":
|
30 |
},
|
31 |
{
|
32 |
"epoch": 2.0,
|
33 |
-
"eval_AUC": 0.
|
34 |
-
"eval_F1": 0.
|
35 |
-
"eval_Precision": 0.
|
36 |
-
"eval_Recall":
|
37 |
-
"eval_accuracy": 0.
|
38 |
-
"eval_loss": 0.
|
39 |
-
"eval_runtime":
|
40 |
-
"eval_samples_per_second":
|
41 |
-
"eval_steps_per_second": 3.
|
42 |
-
"step":
|
43 |
},
|
44 |
{
|
45 |
"epoch": 3.0,
|
46 |
-
"eval_AUC": 0.
|
47 |
-
"eval_F1": 0.
|
48 |
-
"eval_Precision": 0.
|
49 |
"eval_Recall": 1.0,
|
50 |
-
"eval_accuracy": 0.
|
51 |
-
"eval_loss": 0.
|
52 |
-
"eval_runtime":
|
53 |
-
"eval_samples_per_second":
|
54 |
-
"eval_steps_per_second": 3.
|
55 |
-
"step":
|
56 |
},
|
57 |
{
|
58 |
"epoch": 4.0,
|
59 |
-
"eval_AUC": 0.
|
60 |
-
"eval_F1": 0.
|
61 |
-
"eval_Precision": 0.
|
62 |
-
"eval_Recall":
|
63 |
-
"eval_accuracy": 0.
|
64 |
-
"eval_loss": 0.
|
65 |
-
"eval_runtime":
|
66 |
-
"eval_samples_per_second":
|
67 |
-
"eval_steps_per_second": 3.
|
68 |
-
"step":
|
69 |
},
|
70 |
{
|
71 |
"epoch": 5.0,
|
72 |
-
"eval_AUC": 0.
|
73 |
-
"eval_F1": 0.
|
74 |
-
"eval_Precision": 0.
|
75 |
-
"eval_Recall":
|
76 |
-
"eval_accuracy": 0.
|
77 |
-
"eval_loss": 0.
|
78 |
-
"eval_runtime":
|
79 |
-
"eval_samples_per_second":
|
80 |
-
"eval_steps_per_second": 3.
|
81 |
-
"step":
|
82 |
},
|
83 |
{
|
84 |
"epoch": 6.0,
|
85 |
-
"eval_AUC": 0.
|
86 |
-
"eval_F1": 0.
|
87 |
-
"eval_Precision": 0.
|
88 |
-
"eval_Recall": 0.
|
89 |
-
"eval_accuracy": 0.
|
90 |
-
"eval_loss": 0.
|
91 |
-
"eval_runtime":
|
92 |
-
"eval_samples_per_second":
|
93 |
-
"eval_steps_per_second":
|
94 |
-
"step":
|
95 |
},
|
96 |
{
|
97 |
"epoch": 7.0,
|
98 |
-
"eval_AUC": 0.
|
99 |
-
"eval_F1": 0.
|
100 |
-
"eval_Precision": 0.
|
101 |
-
"eval_Recall": 0.
|
102 |
-
"eval_accuracy": 0.
|
103 |
-
"eval_loss": 0.
|
104 |
-
"eval_runtime":
|
105 |
-
"eval_samples_per_second":
|
106 |
-
"eval_steps_per_second": 3.
|
107 |
-
"step":
|
108 |
},
|
109 |
{
|
110 |
"epoch": 8.0,
|
111 |
-
"eval_AUC": 0.
|
112 |
-
"eval_F1": 0.
|
113 |
-
"eval_Precision": 0.
|
114 |
-
"eval_Recall":
|
115 |
-
"eval_accuracy": 0.
|
116 |
-
"eval_loss": 0.
|
117 |
-
"eval_runtime":
|
118 |
-
"eval_samples_per_second":
|
119 |
-
"eval_steps_per_second": 3.
|
120 |
-
"step":
|
121 |
},
|
122 |
{
|
123 |
"epoch": 9.0,
|
124 |
-
"eval_AUC": 0.
|
125 |
-
"eval_F1": 0.
|
126 |
-
"eval_Precision": 0.
|
127 |
-
"eval_Recall":
|
128 |
-
"eval_accuracy": 0.
|
129 |
-
"eval_loss": 0.
|
130 |
-
"eval_runtime":
|
131 |
-
"eval_samples_per_second":
|
132 |
-
"eval_steps_per_second": 3.
|
133 |
-
"step":
|
134 |
},
|
135 |
{
|
136 |
-
"epoch":
|
137 |
-
"
|
138 |
-
"
|
139 |
-
"
|
140 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
141 |
},
|
142 |
{
|
143 |
-
"epoch": 10.
|
144 |
-
"
|
145 |
-
"
|
146 |
-
"
|
147 |
-
"
|
148 |
-
"eval_accuracy": 0.9765258215962441,
|
149 |
-
"eval_loss": 0.10092553496360779,
|
150 |
-
"eval_runtime": 4.2027,
|
151 |
-
"eval_samples_per_second": 50.682,
|
152 |
-
"eval_steps_per_second": 3.331,
|
153 |
-
"step": 540
|
154 |
},
|
155 |
{
|
156 |
"epoch": 11.0,
|
157 |
-
"eval_AUC": 0.
|
158 |
-
"eval_F1": 0.
|
159 |
-
"eval_Precision": 0.
|
160 |
-
"eval_Recall":
|
161 |
-
"eval_accuracy": 0.
|
162 |
-
"eval_loss": 0.
|
163 |
-
"eval_runtime":
|
164 |
-
"eval_samples_per_second":
|
165 |
-
"eval_steps_per_second": 3.
|
166 |
-
"step":
|
167 |
},
|
168 |
{
|
169 |
"epoch": 12.0,
|
170 |
-
"eval_AUC": 0.
|
171 |
-
"eval_F1": 0.
|
172 |
-
"eval_Precision": 0.
|
173 |
-
"eval_Recall":
|
174 |
-
"eval_accuracy": 0.
|
175 |
-
"eval_loss": 0.
|
176 |
-
"eval_runtime":
|
177 |
-
"eval_samples_per_second":
|
178 |
-
"eval_steps_per_second": 3.
|
179 |
-
"step":
|
180 |
},
|
181 |
{
|
182 |
"epoch": 12.0,
|
183 |
-
"step":
|
184 |
-
"total_flos":
|
185 |
-
"train_loss": 0.
|
186 |
-
"train_runtime":
|
187 |
-
"train_samples_per_second":
|
188 |
-
"train_steps_per_second": 2.
|
189 |
}
|
190 |
],
|
191 |
"logging_steps": 500,
|
192 |
-
"max_steps":
|
193 |
"num_input_tokens_seen": 0,
|
194 |
"num_train_epochs": 12,
|
195 |
"save_steps": 500,
|
@@ -205,7 +205,7 @@
|
|
205 |
"attributes": {}
|
206 |
}
|
207 |
},
|
208 |
-
"total_flos":
|
209 |
"train_batch_size": 16,
|
210 |
"trial_name": null,
|
211 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.3346473276615143,
|
3 |
+
"best_model_checkpoint": "google/vit-base-patch16-224-in21k_covid_19_ct_scans/checkpoint-47",
|
4 |
"epoch": 12.0,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 564,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
+
"epoch": 0.02127659574468085,
|
13 |
+
"grad_norm": 4.243431091308594,
|
14 |
+
"learning_rate": 0.000199645390070922,
|
15 |
+
"loss": 0.7767,
|
16 |
"step": 1
|
17 |
},
|
18 |
{
|
19 |
"epoch": 1.0,
|
20 |
"eval_AUC": 0.5,
|
21 |
+
"eval_F1": 0.47572815533980584,
|
22 |
+
"eval_Precision": 0.9074074074074074,
|
23 |
"eval_Recall": 1.0,
|
24 |
+
"eval_accuracy": 0.9074074074074074,
|
25 |
+
"eval_loss": 0.3346473276615143,
|
26 |
+
"eval_runtime": 5.5299,
|
27 |
+
"eval_samples_per_second": 58.591,
|
28 |
+
"eval_steps_per_second": 3.798,
|
29 |
+
"step": 47
|
30 |
},
|
31 |
{
|
32 |
"epoch": 2.0,
|
33 |
+
"eval_AUC": 0.6204081632653061,
|
34 |
+
"eval_F1": 0.5919028340080972,
|
35 |
+
"eval_Precision": 0.9311594202898551,
|
36 |
+
"eval_Recall": 0.8741496598639455,
|
37 |
+
"eval_accuracy": 0.8271604938271605,
|
38 |
+
"eval_loss": 0.5513330698013306,
|
39 |
+
"eval_runtime": 5.5902,
|
40 |
+
"eval_samples_per_second": 57.959,
|
41 |
+
"eval_steps_per_second": 3.757,
|
42 |
+
"step": 94
|
43 |
},
|
44 |
{
|
45 |
"epoch": 3.0,
|
46 |
+
"eval_AUC": 0.5,
|
47 |
+
"eval_F1": 0.47572815533980584,
|
48 |
+
"eval_Precision": 0.9074074074074074,
|
49 |
"eval_Recall": 1.0,
|
50 |
+
"eval_accuracy": 0.9074074074074074,
|
51 |
+
"eval_loss": 0.4290040135383606,
|
52 |
+
"eval_runtime": 5.491,
|
53 |
+
"eval_samples_per_second": 59.005,
|
54 |
+
"eval_steps_per_second": 3.824,
|
55 |
+
"step": 141
|
56 |
},
|
57 |
{
|
58 |
"epoch": 4.0,
|
59 |
+
"eval_AUC": 0.5965986394557823,
|
60 |
+
"eval_F1": 0.6365832614322692,
|
61 |
+
"eval_Precision": 0.9240506329113924,
|
62 |
+
"eval_Recall": 0.9931972789115646,
|
63 |
+
"eval_accuracy": 0.9197530864197531,
|
64 |
+
"eval_loss": 0.433300256729126,
|
65 |
+
"eval_runtime": 5.3718,
|
66 |
+
"eval_samples_per_second": 60.315,
|
67 |
+
"eval_steps_per_second": 3.909,
|
68 |
+
"step": 188
|
69 |
},
|
70 |
{
|
71 |
"epoch": 5.0,
|
72 |
+
"eval_AUC": 0.5897959183673469,
|
73 |
+
"eval_F1": 0.618104667609618,
|
74 |
+
"eval_Precision": 0.9230769230769231,
|
75 |
+
"eval_Recall": 0.9795918367346939,
|
76 |
+
"eval_accuracy": 0.9074074074074074,
|
77 |
+
"eval_loss": 0.5040868520736694,
|
78 |
+
"eval_runtime": 5.759,
|
79 |
+
"eval_samples_per_second": 56.26,
|
80 |
+
"eval_steps_per_second": 3.646,
|
81 |
+
"step": 235
|
82 |
},
|
83 |
{
|
84 |
"epoch": 6.0,
|
85 |
+
"eval_AUC": 0.5948979591836735,
|
86 |
+
"eval_F1": 0.6316786661614249,
|
87 |
+
"eval_Precision": 0.9238095238095239,
|
88 |
+
"eval_Recall": 0.9897959183673469,
|
89 |
+
"eval_accuracy": 0.9166666666666666,
|
90 |
+
"eval_loss": 0.4848092496395111,
|
91 |
+
"eval_runtime": 13.7532,
|
92 |
+
"eval_samples_per_second": 23.558,
|
93 |
+
"eval_steps_per_second": 1.527,
|
94 |
+
"step": 282
|
95 |
},
|
96 |
{
|
97 |
"epoch": 7.0,
|
98 |
+
"eval_AUC": 0.5965986394557823,
|
99 |
+
"eval_F1": 0.6365832614322692,
|
100 |
+
"eval_Precision": 0.9240506329113924,
|
101 |
+
"eval_Recall": 0.9931972789115646,
|
102 |
+
"eval_accuracy": 0.9197530864197531,
|
103 |
+
"eval_loss": 0.48772257566452026,
|
104 |
+
"eval_runtime": 5.5683,
|
105 |
+
"eval_samples_per_second": 58.186,
|
106 |
+
"eval_steps_per_second": 3.771,
|
107 |
+
"step": 329
|
108 |
},
|
109 |
{
|
110 |
"epoch": 8.0,
|
111 |
+
"eval_AUC": 0.5965986394557823,
|
112 |
+
"eval_F1": 0.6365832614322692,
|
113 |
+
"eval_Precision": 0.9240506329113924,
|
114 |
+
"eval_Recall": 0.9931972789115646,
|
115 |
+
"eval_accuracy": 0.9197530864197531,
|
116 |
+
"eval_loss": 0.49257075786590576,
|
117 |
+
"eval_runtime": 5.2567,
|
118 |
+
"eval_samples_per_second": 61.635,
|
119 |
+
"eval_steps_per_second": 3.995,
|
120 |
+
"step": 376
|
121 |
},
|
122 |
{
|
123 |
"epoch": 9.0,
|
124 |
+
"eval_AUC": 0.5965986394557823,
|
125 |
+
"eval_F1": 0.6365832614322692,
|
126 |
+
"eval_Precision": 0.9240506329113924,
|
127 |
+
"eval_Recall": 0.9931972789115646,
|
128 |
+
"eval_accuracy": 0.9197530864197531,
|
129 |
+
"eval_loss": 0.49581947922706604,
|
130 |
+
"eval_runtime": 5.6218,
|
131 |
+
"eval_samples_per_second": 57.633,
|
132 |
+
"eval_steps_per_second": 3.735,
|
133 |
+
"step": 423
|
134 |
},
|
135 |
{
|
136 |
+
"epoch": 10.0,
|
137 |
+
"eval_AUC": 0.5965986394557823,
|
138 |
+
"eval_F1": 0.6365832614322692,
|
139 |
+
"eval_Precision": 0.9240506329113924,
|
140 |
+
"eval_Recall": 0.9931972789115646,
|
141 |
+
"eval_accuracy": 0.9197530864197531,
|
142 |
+
"eval_loss": 0.4980551600456238,
|
143 |
+
"eval_runtime": 5.5112,
|
144 |
+
"eval_samples_per_second": 58.79,
|
145 |
+
"eval_steps_per_second": 3.81,
|
146 |
+
"step": 470
|
147 |
},
|
148 |
{
|
149 |
+
"epoch": 10.638297872340425,
|
150 |
+
"grad_norm": 0.012480547651648521,
|
151 |
+
"learning_rate": 2.269503546099291e-05,
|
152 |
+
"loss": 0.0381,
|
153 |
+
"step": 500
|
|
|
|
|
|
|
|
|
|
|
|
|
154 |
},
|
155 |
{
|
156 |
"epoch": 11.0,
|
157 |
+
"eval_AUC": 0.5965986394557823,
|
158 |
+
"eval_F1": 0.6365832614322692,
|
159 |
+
"eval_Precision": 0.9240506329113924,
|
160 |
+
"eval_Recall": 0.9931972789115646,
|
161 |
+
"eval_accuracy": 0.9197530864197531,
|
162 |
+
"eval_loss": 0.4996081292629242,
|
163 |
+
"eval_runtime": 5.5015,
|
164 |
+
"eval_samples_per_second": 58.893,
|
165 |
+
"eval_steps_per_second": 3.817,
|
166 |
+
"step": 517
|
167 |
},
|
168 |
{
|
169 |
"epoch": 12.0,
|
170 |
+
"eval_AUC": 0.5965986394557823,
|
171 |
+
"eval_F1": 0.6365832614322692,
|
172 |
+
"eval_Precision": 0.9240506329113924,
|
173 |
+
"eval_Recall": 0.9931972789115646,
|
174 |
+
"eval_accuracy": 0.9197530864197531,
|
175 |
+
"eval_loss": 0.5001835823059082,
|
176 |
+
"eval_runtime": 5.5423,
|
177 |
+
"eval_samples_per_second": 58.46,
|
178 |
+
"eval_steps_per_second": 3.789,
|
179 |
+
"step": 564
|
180 |
},
|
181 |
{
|
182 |
"epoch": 12.0,
|
183 |
+
"step": 564,
|
184 |
+
"total_flos": 6.862690600268268e+17,
|
185 |
+
"train_loss": 0.03526242822408676,
|
186 |
+
"train_runtime": 251.233,
|
187 |
+
"train_samples_per_second": 35.25,
|
188 |
+
"train_steps_per_second": 2.245
|
189 |
}
|
190 |
],
|
191 |
"logging_steps": 500,
|
192 |
+
"max_steps": 564,
|
193 |
"num_input_tokens_seen": 0,
|
194 |
"num_train_epochs": 12,
|
195 |
"save_steps": 500,
|
|
|
205 |
"attributes": {}
|
206 |
}
|
207 |
},
|
208 |
+
"total_flos": 6.862690600268268e+17,
|
209 |
"train_batch_size": 16,
|
210 |
"trial_name": null,
|
211 |
"trial_params": null
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4731
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:860ac9cc2700a6acca98170286a713aa05b047089895c0cc3d2037638dcd625e
|
3 |
size 4731
|