End of training
Browse files- README.md +2 -0
- all_results.json +21 -0
- eval_results.json +12 -0
- predict_results.txt +1012 -0
- runs/May19_00-25-30_indolem-petl-vm/events.out.tfevents.1716080305.indolem-petl-vm.2015492.1 +3 -0
- test_results.json +6 -0
- train_results.json +8 -0
- trainer_state.json +410 -0
README.md
CHANGED
@@ -1,4 +1,6 @@
|
|
1 |
---
|
|
|
|
|
2 |
license: mit
|
3 |
base_model: indolem/indobert-base-uncased
|
4 |
tags:
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
+
- id
|
4 |
license: mit
|
5 |
base_model: indolem/indobert-base-uncased
|
6 |
tags:
|
all_results.json
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"accuracy": 0.8704253214638972,
|
3 |
+
"epoch": 20.0,
|
4 |
+
"eval_accuracy": 0.8621553884711779,
|
5 |
+
"eval_f1": 0.8279052989013229,
|
6 |
+
"eval_loss": 0.33124828338623047,
|
7 |
+
"eval_precision": 0.8414113428943938,
|
8 |
+
"eval_recall": 0.8174668121476631,
|
9 |
+
"eval_runtime": 5.0093,
|
10 |
+
"eval_samples": 399,
|
11 |
+
"eval_samples_per_second": 79.652,
|
12 |
+
"eval_steps_per_second": 9.981,
|
13 |
+
"f1": 0.8458025043514708,
|
14 |
+
"precision": 0.8423782258733714,
|
15 |
+
"recall": 0.8495392377420297,
|
16 |
+
"train_loss": 0.35801424432973394,
|
17 |
+
"train_runtime": 1952.1205,
|
18 |
+
"train_samples": 3638,
|
19 |
+
"train_samples_per_second": 37.272,
|
20 |
+
"train_steps_per_second": 1.25
|
21 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 20.0,
|
3 |
+
"eval_accuracy": 0.8621553884711779,
|
4 |
+
"eval_f1": 0.8279052989013229,
|
5 |
+
"eval_loss": 0.33124828338623047,
|
6 |
+
"eval_precision": 0.8414113428943938,
|
7 |
+
"eval_recall": 0.8174668121476631,
|
8 |
+
"eval_runtime": 5.0093,
|
9 |
+
"eval_samples": 399,
|
10 |
+
"eval_samples_per_second": 79.652,
|
11 |
+
"eval_steps_per_second": 9.981
|
12 |
+
}
|
predict_results.txt
ADDED
@@ -0,0 +1,1012 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
index prediction
|
2 |
+
0 1
|
3 |
+
1 1
|
4 |
+
2 0
|
5 |
+
3 1
|
6 |
+
4 0
|
7 |
+
5 0
|
8 |
+
6 1
|
9 |
+
7 1
|
10 |
+
8 0
|
11 |
+
9 0
|
12 |
+
10 1
|
13 |
+
11 1
|
14 |
+
12 1
|
15 |
+
13 1
|
16 |
+
14 1
|
17 |
+
15 1
|
18 |
+
16 1
|
19 |
+
17 1
|
20 |
+
18 1
|
21 |
+
19 1
|
22 |
+
20 0
|
23 |
+
21 1
|
24 |
+
22 1
|
25 |
+
23 1
|
26 |
+
24 1
|
27 |
+
25 0
|
28 |
+
26 0
|
29 |
+
27 1
|
30 |
+
28 1
|
31 |
+
29 1
|
32 |
+
30 1
|
33 |
+
31 1
|
34 |
+
32 1
|
35 |
+
33 1
|
36 |
+
34 0
|
37 |
+
35 1
|
38 |
+
36 0
|
39 |
+
37 1
|
40 |
+
38 1
|
41 |
+
39 1
|
42 |
+
40 1
|
43 |
+
41 0
|
44 |
+
42 1
|
45 |
+
43 1
|
46 |
+
44 1
|
47 |
+
45 0
|
48 |
+
46 1
|
49 |
+
47 1
|
50 |
+
48 1
|
51 |
+
49 1
|
52 |
+
50 1
|
53 |
+
51 0
|
54 |
+
52 0
|
55 |
+
53 1
|
56 |
+
54 0
|
57 |
+
55 1
|
58 |
+
56 1
|
59 |
+
57 0
|
60 |
+
58 1
|
61 |
+
59 1
|
62 |
+
60 0
|
63 |
+
61 1
|
64 |
+
62 1
|
65 |
+
63 1
|
66 |
+
64 1
|
67 |
+
65 1
|
68 |
+
66 1
|
69 |
+
67 0
|
70 |
+
68 0
|
71 |
+
69 1
|
72 |
+
70 1
|
73 |
+
71 1
|
74 |
+
72 1
|
75 |
+
73 1
|
76 |
+
74 1
|
77 |
+
75 0
|
78 |
+
76 1
|
79 |
+
77 1
|
80 |
+
78 1
|
81 |
+
79 0
|
82 |
+
80 1
|
83 |
+
81 1
|
84 |
+
82 0
|
85 |
+
83 0
|
86 |
+
84 1
|
87 |
+
85 1
|
88 |
+
86 1
|
89 |
+
87 1
|
90 |
+
88 1
|
91 |
+
89 1
|
92 |
+
90 0
|
93 |
+
91 0
|
94 |
+
92 1
|
95 |
+
93 1
|
96 |
+
94 1
|
97 |
+
95 1
|
98 |
+
96 1
|
99 |
+
97 1
|
100 |
+
98 1
|
101 |
+
99 1
|
102 |
+
100 1
|
103 |
+
101 1
|
104 |
+
102 0
|
105 |
+
103 1
|
106 |
+
104 1
|
107 |
+
105 0
|
108 |
+
106 1
|
109 |
+
107 0
|
110 |
+
108 1
|
111 |
+
109 1
|
112 |
+
110 1
|
113 |
+
111 1
|
114 |
+
112 1
|
115 |
+
113 1
|
116 |
+
114 1
|
117 |
+
115 0
|
118 |
+
116 1
|
119 |
+
117 1
|
120 |
+
118 1
|
121 |
+
119 1
|
122 |
+
120 1
|
123 |
+
121 0
|
124 |
+
122 1
|
125 |
+
123 1
|
126 |
+
124 0
|
127 |
+
125 1
|
128 |
+
126 1
|
129 |
+
127 0
|
130 |
+
128 0
|
131 |
+
129 1
|
132 |
+
130 0
|
133 |
+
131 1
|
134 |
+
132 1
|
135 |
+
133 1
|
136 |
+
134 1
|
137 |
+
135 1
|
138 |
+
136 1
|
139 |
+
137 1
|
140 |
+
138 1
|
141 |
+
139 1
|
142 |
+
140 1
|
143 |
+
141 1
|
144 |
+
142 1
|
145 |
+
143 1
|
146 |
+
144 1
|
147 |
+
145 1
|
148 |
+
146 0
|
149 |
+
147 1
|
150 |
+
148 1
|
151 |
+
149 0
|
152 |
+
150 1
|
153 |
+
151 0
|
154 |
+
152 1
|
155 |
+
153 1
|
156 |
+
154 1
|
157 |
+
155 1
|
158 |
+
156 1
|
159 |
+
157 1
|
160 |
+
158 1
|
161 |
+
159 1
|
162 |
+
160 1
|
163 |
+
161 1
|
164 |
+
162 1
|
165 |
+
163 1
|
166 |
+
164 1
|
167 |
+
165 1
|
168 |
+
166 1
|
169 |
+
167 0
|
170 |
+
168 1
|
171 |
+
169 1
|
172 |
+
170 0
|
173 |
+
171 0
|
174 |
+
172 1
|
175 |
+
173 1
|
176 |
+
174 0
|
177 |
+
175 1
|
178 |
+
176 1
|
179 |
+
177 1
|
180 |
+
178 1
|
181 |
+
179 0
|
182 |
+
180 1
|
183 |
+
181 0
|
184 |
+
182 1
|
185 |
+
183 1
|
186 |
+
184 1
|
187 |
+
185 0
|
188 |
+
186 1
|
189 |
+
187 1
|
190 |
+
188 1
|
191 |
+
189 1
|
192 |
+
190 1
|
193 |
+
191 1
|
194 |
+
192 0
|
195 |
+
193 1
|
196 |
+
194 1
|
197 |
+
195 1
|
198 |
+
196 1
|
199 |
+
197 1
|
200 |
+
198 1
|
201 |
+
199 1
|
202 |
+
200 1
|
203 |
+
201 1
|
204 |
+
202 1
|
205 |
+
203 1
|
206 |
+
204 1
|
207 |
+
205 1
|
208 |
+
206 1
|
209 |
+
207 1
|
210 |
+
208 1
|
211 |
+
209 1
|
212 |
+
210 1
|
213 |
+
211 1
|
214 |
+
212 1
|
215 |
+
213 1
|
216 |
+
214 1
|
217 |
+
215 0
|
218 |
+
216 1
|
219 |
+
217 1
|
220 |
+
218 0
|
221 |
+
219 1
|
222 |
+
220 1
|
223 |
+
221 1
|
224 |
+
222 1
|
225 |
+
223 1
|
226 |
+
224 0
|
227 |
+
225 1
|
228 |
+
226 1
|
229 |
+
227 1
|
230 |
+
228 1
|
231 |
+
229 1
|
232 |
+
230 1
|
233 |
+
231 1
|
234 |
+
232 1
|
235 |
+
233 1
|
236 |
+
234 1
|
237 |
+
235 0
|
238 |
+
236 1
|
239 |
+
237 0
|
240 |
+
238 1
|
241 |
+
239 1
|
242 |
+
240 1
|
243 |
+
241 1
|
244 |
+
242 1
|
245 |
+
243 1
|
246 |
+
244 1
|
247 |
+
245 1
|
248 |
+
246 1
|
249 |
+
247 1
|
250 |
+
248 0
|
251 |
+
249 1
|
252 |
+
250 1
|
253 |
+
251 1
|
254 |
+
252 1
|
255 |
+
253 0
|
256 |
+
254 1
|
257 |
+
255 1
|
258 |
+
256 1
|
259 |
+
257 1
|
260 |
+
258 1
|
261 |
+
259 1
|
262 |
+
260 0
|
263 |
+
261 1
|
264 |
+
262 1
|
265 |
+
263 1
|
266 |
+
264 1
|
267 |
+
265 1
|
268 |
+
266 1
|
269 |
+
267 1
|
270 |
+
268 0
|
271 |
+
269 1
|
272 |
+
270 1
|
273 |
+
271 1
|
274 |
+
272 0
|
275 |
+
273 0
|
276 |
+
274 0
|
277 |
+
275 0
|
278 |
+
276 0
|
279 |
+
277 1
|
280 |
+
278 1
|
281 |
+
279 1
|
282 |
+
280 1
|
283 |
+
281 0
|
284 |
+
282 1
|
285 |
+
283 1
|
286 |
+
284 1
|
287 |
+
285 1
|
288 |
+
286 1
|
289 |
+
287 1
|
290 |
+
288 1
|
291 |
+
289 1
|
292 |
+
290 1
|
293 |
+
291 1
|
294 |
+
292 1
|
295 |
+
293 1
|
296 |
+
294 1
|
297 |
+
295 1
|
298 |
+
296 1
|
299 |
+
297 1
|
300 |
+
298 0
|
301 |
+
299 0
|
302 |
+
300 0
|
303 |
+
301 1
|
304 |
+
302 0
|
305 |
+
303 0
|
306 |
+
304 0
|
307 |
+
305 0
|
308 |
+
306 0
|
309 |
+
307 0
|
310 |
+
308 0
|
311 |
+
309 1
|
312 |
+
310 0
|
313 |
+
311 0
|
314 |
+
312 0
|
315 |
+
313 0
|
316 |
+
314 0
|
317 |
+
315 0
|
318 |
+
316 0
|
319 |
+
317 0
|
320 |
+
318 0
|
321 |
+
319 0
|
322 |
+
320 0
|
323 |
+
321 0
|
324 |
+
322 0
|
325 |
+
323 0
|
326 |
+
324 1
|
327 |
+
325 0
|
328 |
+
326 0
|
329 |
+
327 0
|
330 |
+
328 0
|
331 |
+
329 1
|
332 |
+
330 0
|
333 |
+
331 0
|
334 |
+
332 0
|
335 |
+
333 0
|
336 |
+
334 0
|
337 |
+
335 0
|
338 |
+
336 0
|
339 |
+
337 0
|
340 |
+
338 1
|
341 |
+
339 0
|
342 |
+
340 0
|
343 |
+
341 0
|
344 |
+
342 1
|
345 |
+
343 0
|
346 |
+
344 0
|
347 |
+
345 0
|
348 |
+
346 0
|
349 |
+
347 1
|
350 |
+
348 0
|
351 |
+
349 0
|
352 |
+
350 0
|
353 |
+
351 0
|
354 |
+
352 0
|
355 |
+
353 0
|
356 |
+
354 0
|
357 |
+
355 0
|
358 |
+
356 0
|
359 |
+
357 0
|
360 |
+
358 0
|
361 |
+
359 0
|
362 |
+
360 0
|
363 |
+
361 0
|
364 |
+
362 0
|
365 |
+
363 0
|
366 |
+
364 0
|
367 |
+
365 1
|
368 |
+
366 0
|
369 |
+
367 0
|
370 |
+
368 0
|
371 |
+
369 0
|
372 |
+
370 0
|
373 |
+
371 0
|
374 |
+
372 0
|
375 |
+
373 0
|
376 |
+
374 0
|
377 |
+
375 0
|
378 |
+
376 0
|
379 |
+
377 1
|
380 |
+
378 0
|
381 |
+
379 0
|
382 |
+
380 0
|
383 |
+
381 0
|
384 |
+
382 0
|
385 |
+
383 0
|
386 |
+
384 0
|
387 |
+
385 0
|
388 |
+
386 0
|
389 |
+
387 0
|
390 |
+
388 0
|
391 |
+
389 0
|
392 |
+
390 0
|
393 |
+
391 0
|
394 |
+
392 0
|
395 |
+
393 0
|
396 |
+
394 0
|
397 |
+
395 0
|
398 |
+
396 0
|
399 |
+
397 0
|
400 |
+
398 0
|
401 |
+
399 0
|
402 |
+
400 0
|
403 |
+
401 0
|
404 |
+
402 0
|
405 |
+
403 0
|
406 |
+
404 0
|
407 |
+
405 1
|
408 |
+
406 0
|
409 |
+
407 0
|
410 |
+
408 0
|
411 |
+
409 0
|
412 |
+
410 0
|
413 |
+
411 0
|
414 |
+
412 0
|
415 |
+
413 0
|
416 |
+
414 0
|
417 |
+
415 0
|
418 |
+
416 0
|
419 |
+
417 0
|
420 |
+
418 0
|
421 |
+
419 0
|
422 |
+
420 0
|
423 |
+
421 0
|
424 |
+
422 0
|
425 |
+
423 0
|
426 |
+
424 0
|
427 |
+
425 1
|
428 |
+
426 0
|
429 |
+
427 0
|
430 |
+
428 0
|
431 |
+
429 1
|
432 |
+
430 0
|
433 |
+
431 0
|
434 |
+
432 0
|
435 |
+
433 0
|
436 |
+
434 0
|
437 |
+
435 1
|
438 |
+
436 0
|
439 |
+
437 0
|
440 |
+
438 0
|
441 |
+
439 0
|
442 |
+
440 0
|
443 |
+
441 0
|
444 |
+
442 0
|
445 |
+
443 0
|
446 |
+
444 0
|
447 |
+
445 0
|
448 |
+
446 0
|
449 |
+
447 0
|
450 |
+
448 0
|
451 |
+
449 1
|
452 |
+
450 0
|
453 |
+
451 0
|
454 |
+
452 0
|
455 |
+
453 0
|
456 |
+
454 0
|
457 |
+
455 1
|
458 |
+
456 0
|
459 |
+
457 1
|
460 |
+
458 0
|
461 |
+
459 0
|
462 |
+
460 0
|
463 |
+
461 0
|
464 |
+
462 0
|
465 |
+
463 1
|
466 |
+
464 0
|
467 |
+
465 1
|
468 |
+
466 0
|
469 |
+
467 0
|
470 |
+
468 0
|
471 |
+
469 0
|
472 |
+
470 0
|
473 |
+
471 0
|
474 |
+
472 1
|
475 |
+
473 0
|
476 |
+
474 0
|
477 |
+
475 0
|
478 |
+
476 0
|
479 |
+
477 0
|
480 |
+
478 0
|
481 |
+
479 0
|
482 |
+
480 0
|
483 |
+
481 0
|
484 |
+
482 0
|
485 |
+
483 0
|
486 |
+
484 0
|
487 |
+
485 0
|
488 |
+
486 0
|
489 |
+
487 1
|
490 |
+
488 0
|
491 |
+
489 0
|
492 |
+
490 0
|
493 |
+
491 0
|
494 |
+
492 0
|
495 |
+
493 0
|
496 |
+
494 0
|
497 |
+
495 0
|
498 |
+
496 0
|
499 |
+
497 0
|
500 |
+
498 1
|
501 |
+
499 0
|
502 |
+
500 0
|
503 |
+
501 0
|
504 |
+
502 0
|
505 |
+
503 1
|
506 |
+
504 0
|
507 |
+
505 1
|
508 |
+
506 0
|
509 |
+
507 0
|
510 |
+
508 0
|
511 |
+
509 1
|
512 |
+
510 0
|
513 |
+
511 0
|
514 |
+
512 1
|
515 |
+
513 0
|
516 |
+
514 0
|
517 |
+
515 1
|
518 |
+
516 0
|
519 |
+
517 0
|
520 |
+
518 0
|
521 |
+
519 0
|
522 |
+
520 0
|
523 |
+
521 0
|
524 |
+
522 1
|
525 |
+
523 1
|
526 |
+
524 0
|
527 |
+
525 0
|
528 |
+
526 0
|
529 |
+
527 0
|
530 |
+
528 0
|
531 |
+
529 0
|
532 |
+
530 0
|
533 |
+
531 0
|
534 |
+
532 0
|
535 |
+
533 0
|
536 |
+
534 0
|
537 |
+
535 0
|
538 |
+
536 0
|
539 |
+
537 0
|
540 |
+
538 0
|
541 |
+
539 0
|
542 |
+
540 0
|
543 |
+
541 0
|
544 |
+
542 0
|
545 |
+
543 0
|
546 |
+
544 0
|
547 |
+
545 0
|
548 |
+
546 0
|
549 |
+
547 0
|
550 |
+
548 0
|
551 |
+
549 0
|
552 |
+
550 0
|
553 |
+
551 0
|
554 |
+
552 0
|
555 |
+
553 0
|
556 |
+
554 0
|
557 |
+
555 0
|
558 |
+
556 0
|
559 |
+
557 0
|
560 |
+
558 0
|
561 |
+
559 0
|
562 |
+
560 0
|
563 |
+
561 0
|
564 |
+
562 1
|
565 |
+
563 0
|
566 |
+
564 0
|
567 |
+
565 0
|
568 |
+
566 0
|
569 |
+
567 0
|
570 |
+
568 0
|
571 |
+
569 0
|
572 |
+
570 0
|
573 |
+
571 0
|
574 |
+
572 0
|
575 |
+
573 0
|
576 |
+
574 0
|
577 |
+
575 0
|
578 |
+
576 0
|
579 |
+
577 0
|
580 |
+
578 0
|
581 |
+
579 1
|
582 |
+
580 0
|
583 |
+
581 0
|
584 |
+
582 1
|
585 |
+
583 0
|
586 |
+
584 1
|
587 |
+
585 0
|
588 |
+
586 0
|
589 |
+
587 0
|
590 |
+
588 1
|
591 |
+
589 0
|
592 |
+
590 0
|
593 |
+
591 1
|
594 |
+
592 1
|
595 |
+
593 0
|
596 |
+
594 0
|
597 |
+
595 0
|
598 |
+
596 0
|
599 |
+
597 0
|
600 |
+
598 0
|
601 |
+
599 1
|
602 |
+
600 0
|
603 |
+
601 0
|
604 |
+
602 0
|
605 |
+
603 0
|
606 |
+
604 0
|
607 |
+
605 0
|
608 |
+
606 0
|
609 |
+
607 0
|
610 |
+
608 0
|
611 |
+
609 0
|
612 |
+
610 0
|
613 |
+
611 0
|
614 |
+
612 0
|
615 |
+
613 0
|
616 |
+
614 0
|
617 |
+
615 0
|
618 |
+
616 0
|
619 |
+
617 0
|
620 |
+
618 0
|
621 |
+
619 0
|
622 |
+
620 0
|
623 |
+
621 0
|
624 |
+
622 0
|
625 |
+
623 0
|
626 |
+
624 0
|
627 |
+
625 0
|
628 |
+
626 0
|
629 |
+
627 0
|
630 |
+
628 0
|
631 |
+
629 0
|
632 |
+
630 0
|
633 |
+
631 0
|
634 |
+
632 0
|
635 |
+
633 0
|
636 |
+
634 0
|
637 |
+
635 0
|
638 |
+
636 0
|
639 |
+
637 0
|
640 |
+
638 0
|
641 |
+
639 0
|
642 |
+
640 0
|
643 |
+
641 0
|
644 |
+
642 0
|
645 |
+
643 1
|
646 |
+
644 0
|
647 |
+
645 0
|
648 |
+
646 0
|
649 |
+
647 0
|
650 |
+
648 0
|
651 |
+
649 0
|
652 |
+
650 0
|
653 |
+
651 1
|
654 |
+
652 0
|
655 |
+
653 0
|
656 |
+
654 0
|
657 |
+
655 0
|
658 |
+
656 0
|
659 |
+
657 0
|
660 |
+
658 0
|
661 |
+
659 0
|
662 |
+
660 0
|
663 |
+
661 0
|
664 |
+
662 0
|
665 |
+
663 0
|
666 |
+
664 0
|
667 |
+
665 1
|
668 |
+
666 0
|
669 |
+
667 1
|
670 |
+
668 0
|
671 |
+
669 0
|
672 |
+
670 0
|
673 |
+
671 0
|
674 |
+
672 0
|
675 |
+
673 1
|
676 |
+
674 0
|
677 |
+
675 0
|
678 |
+
676 0
|
679 |
+
677 0
|
680 |
+
678 0
|
681 |
+
679 1
|
682 |
+
680 0
|
683 |
+
681 0
|
684 |
+
682 0
|
685 |
+
683 0
|
686 |
+
684 0
|
687 |
+
685 1
|
688 |
+
686 0
|
689 |
+
687 0
|
690 |
+
688 1
|
691 |
+
689 0
|
692 |
+
690 0
|
693 |
+
691 0
|
694 |
+
692 0
|
695 |
+
693 0
|
696 |
+
694 0
|
697 |
+
695 0
|
698 |
+
696 0
|
699 |
+
697 0
|
700 |
+
698 0
|
701 |
+
699 1
|
702 |
+
700 0
|
703 |
+
701 0
|
704 |
+
702 1
|
705 |
+
703 0
|
706 |
+
704 0
|
707 |
+
705 0
|
708 |
+
706 0
|
709 |
+
707 0
|
710 |
+
708 0
|
711 |
+
709 0
|
712 |
+
710 1
|
713 |
+
711 0
|
714 |
+
712 1
|
715 |
+
713 0
|
716 |
+
714 0
|
717 |
+
715 1
|
718 |
+
716 0
|
719 |
+
717 0
|
720 |
+
718 0
|
721 |
+
719 0
|
722 |
+
720 0
|
723 |
+
721 0
|
724 |
+
722 0
|
725 |
+
723 0
|
726 |
+
724 1
|
727 |
+
725 0
|
728 |
+
726 0
|
729 |
+
727 0
|
730 |
+
728 0
|
731 |
+
729 0
|
732 |
+
730 0
|
733 |
+
731 0
|
734 |
+
732 0
|
735 |
+
733 0
|
736 |
+
734 1
|
737 |
+
735 0
|
738 |
+
736 0
|
739 |
+
737 1
|
740 |
+
738 0
|
741 |
+
739 0
|
742 |
+
740 0
|
743 |
+
741 0
|
744 |
+
742 0
|
745 |
+
743 0
|
746 |
+
744 1
|
747 |
+
745 0
|
748 |
+
746 0
|
749 |
+
747 0
|
750 |
+
748 0
|
751 |
+
749 0
|
752 |
+
750 0
|
753 |
+
751 0
|
754 |
+
752 0
|
755 |
+
753 0
|
756 |
+
754 0
|
757 |
+
755 0
|
758 |
+
756 0
|
759 |
+
757 0
|
760 |
+
758 0
|
761 |
+
759 0
|
762 |
+
760 0
|
763 |
+
761 0
|
764 |
+
762 1
|
765 |
+
763 0
|
766 |
+
764 0
|
767 |
+
765 0
|
768 |
+
766 0
|
769 |
+
767 0
|
770 |
+
768 0
|
771 |
+
769 0
|
772 |
+
770 0
|
773 |
+
771 0
|
774 |
+
772 0
|
775 |
+
773 0
|
776 |
+
774 1
|
777 |
+
775 0
|
778 |
+
776 0
|
779 |
+
777 0
|
780 |
+
778 0
|
781 |
+
779 0
|
782 |
+
780 0
|
783 |
+
781 0
|
784 |
+
782 0
|
785 |
+
783 0
|
786 |
+
784 0
|
787 |
+
785 0
|
788 |
+
786 1
|
789 |
+
787 0
|
790 |
+
788 0
|
791 |
+
789 0
|
792 |
+
790 0
|
793 |
+
791 0
|
794 |
+
792 0
|
795 |
+
793 0
|
796 |
+
794 0
|
797 |
+
795 0
|
798 |
+
796 0
|
799 |
+
797 0
|
800 |
+
798 0
|
801 |
+
799 0
|
802 |
+
800 0
|
803 |
+
801 0
|
804 |
+
802 0
|
805 |
+
803 0
|
806 |
+
804 1
|
807 |
+
805 0
|
808 |
+
806 0
|
809 |
+
807 0
|
810 |
+
808 0
|
811 |
+
809 0
|
812 |
+
810 0
|
813 |
+
811 0
|
814 |
+
812 0
|
815 |
+
813 0
|
816 |
+
814 0
|
817 |
+
815 0
|
818 |
+
816 0
|
819 |
+
817 0
|
820 |
+
818 0
|
821 |
+
819 0
|
822 |
+
820 0
|
823 |
+
821 0
|
824 |
+
822 0
|
825 |
+
823 0
|
826 |
+
824 0
|
827 |
+
825 0
|
828 |
+
826 0
|
829 |
+
827 0
|
830 |
+
828 0
|
831 |
+
829 0
|
832 |
+
830 0
|
833 |
+
831 0
|
834 |
+
832 0
|
835 |
+
833 0
|
836 |
+
834 0
|
837 |
+
835 0
|
838 |
+
836 1
|
839 |
+
837 0
|
840 |
+
838 0
|
841 |
+
839 0
|
842 |
+
840 0
|
843 |
+
841 0
|
844 |
+
842 0
|
845 |
+
843 0
|
846 |
+
844 1
|
847 |
+
845 0
|
848 |
+
846 0
|
849 |
+
847 0
|
850 |
+
848 0
|
851 |
+
849 0
|
852 |
+
850 0
|
853 |
+
851 0
|
854 |
+
852 0
|
855 |
+
853 0
|
856 |
+
854 1
|
857 |
+
855 0
|
858 |
+
856 0
|
859 |
+
857 1
|
860 |
+
858 0
|
861 |
+
859 0
|
862 |
+
860 0
|
863 |
+
861 0
|
864 |
+
862 0
|
865 |
+
863 0
|
866 |
+
864 0
|
867 |
+
865 1
|
868 |
+
866 0
|
869 |
+
867 0
|
870 |
+
868 0
|
871 |
+
869 0
|
872 |
+
870 0
|
873 |
+
871 0
|
874 |
+
872 0
|
875 |
+
873 0
|
876 |
+
874 0
|
877 |
+
875 0
|
878 |
+
876 0
|
879 |
+
877 0
|
880 |
+
878 0
|
881 |
+
879 0
|
882 |
+
880 0
|
883 |
+
881 0
|
884 |
+
882 0
|
885 |
+
883 0
|
886 |
+
884 0
|
887 |
+
885 0
|
888 |
+
886 0
|
889 |
+
887 0
|
890 |
+
888 0
|
891 |
+
889 0
|
892 |
+
890 0
|
893 |
+
891 0
|
894 |
+
892 0
|
895 |
+
893 1
|
896 |
+
894 1
|
897 |
+
895 0
|
898 |
+
896 0
|
899 |
+
897 1
|
900 |
+
898 0
|
901 |
+
899 0
|
902 |
+
900 0
|
903 |
+
901 0
|
904 |
+
902 0
|
905 |
+
903 0
|
906 |
+
904 0
|
907 |
+
905 0
|
908 |
+
906 0
|
909 |
+
907 0
|
910 |
+
908 0
|
911 |
+
909 0
|
912 |
+
910 0
|
913 |
+
911 0
|
914 |
+
912 0
|
915 |
+
913 0
|
916 |
+
914 0
|
917 |
+
915 1
|
918 |
+
916 0
|
919 |
+
917 0
|
920 |
+
918 0
|
921 |
+
919 0
|
922 |
+
920 0
|
923 |
+
921 0
|
924 |
+
922 0
|
925 |
+
923 0
|
926 |
+
924 0
|
927 |
+
925 0
|
928 |
+
926 0
|
929 |
+
927 0
|
930 |
+
928 0
|
931 |
+
929 0
|
932 |
+
930 1
|
933 |
+
931 0
|
934 |
+
932 0
|
935 |
+
933 0
|
936 |
+
934 0
|
937 |
+
935 0
|
938 |
+
936 1
|
939 |
+
937 0
|
940 |
+
938 0
|
941 |
+
939 0
|
942 |
+
940 0
|
943 |
+
941 0
|
944 |
+
942 0
|
945 |
+
943 0
|
946 |
+
944 0
|
947 |
+
945 0
|
948 |
+
946 0
|
949 |
+
947 0
|
950 |
+
948 0
|
951 |
+
949 0
|
952 |
+
950 0
|
953 |
+
951 0
|
954 |
+
952 0
|
955 |
+
953 0
|
956 |
+
954 1
|
957 |
+
955 0
|
958 |
+
956 0
|
959 |
+
957 0
|
960 |
+
958 0
|
961 |
+
959 0
|
962 |
+
960 0
|
963 |
+
961 0
|
964 |
+
962 0
|
965 |
+
963 0
|
966 |
+
964 0
|
967 |
+
965 0
|
968 |
+
966 0
|
969 |
+
967 0
|
970 |
+
968 0
|
971 |
+
969 0
|
972 |
+
970 0
|
973 |
+
971 0
|
974 |
+
972 0
|
975 |
+
973 0
|
976 |
+
974 0
|
977 |
+
975 0
|
978 |
+
976 0
|
979 |
+
977 0
|
980 |
+
978 0
|
981 |
+
979 0
|
982 |
+
980 0
|
983 |
+
981 0
|
984 |
+
982 0
|
985 |
+
983 0
|
986 |
+
984 0
|
987 |
+
985 0
|
988 |
+
986 0
|
989 |
+
987 0
|
990 |
+
988 0
|
991 |
+
989 0
|
992 |
+
990 0
|
993 |
+
991 0
|
994 |
+
992 0
|
995 |
+
993 1
|
996 |
+
994 0
|
997 |
+
995 1
|
998 |
+
996 0
|
999 |
+
997 0
|
1000 |
+
998 0
|
1001 |
+
999 0
|
1002 |
+
1000 0
|
1003 |
+
1001 0
|
1004 |
+
1002 0
|
1005 |
+
1003 0
|
1006 |
+
1004 0
|
1007 |
+
1005 0
|
1008 |
+
1006 0
|
1009 |
+
1007 0
|
1010 |
+
1008 0
|
1011 |
+
1009 0
|
1012 |
+
1010 0
|
runs/May19_00-25-30_indolem-petl-vm/events.out.tfevents.1716080305.indolem-petl-vm.2015492.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a6b9ed5267f2abdee499af4a4f9d0606dca22337e43fa8ee951e967e47339fed
|
3 |
+
size 560
|
test_results.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"accuracy": 0.8704253214638972,
|
3 |
+
"f1": 0.8458025043514708,
|
4 |
+
"precision": 0.8423782258733714,
|
5 |
+
"recall": 0.8495392377420297
|
6 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 20.0,
|
3 |
+
"train_loss": 0.35801424432973394,
|
4 |
+
"train_runtime": 1952.1205,
|
5 |
+
"train_samples": 3638,
|
6 |
+
"train_samples_per_second": 37.272,
|
7 |
+
"train_steps_per_second": 1.25
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,410 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 20.0,
|
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": 1.0,
|
13 |
+
"grad_norm": 5.062061786651611,
|
14 |
+
"learning_rate": 4.75e-05,
|
15 |
+
"loss": 0.566,
|
16 |
+
"step": 122
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.0,
|
20 |
+
"eval_accuracy": 0.7142857142857143,
|
21 |
+
"eval_f1": 0.6402562480227776,
|
22 |
+
"eval_loss": 0.5205540657043457,
|
23 |
+
"eval_precision": 0.6483653398896937,
|
24 |
+
"eval_recall": 0.6353427895981087,
|
25 |
+
"eval_runtime": 5.1327,
|
26 |
+
"eval_samples_per_second": 77.737,
|
27 |
+
"eval_steps_per_second": 9.741,
|
28 |
+
"step": 122
|
29 |
+
},
|
30 |
+
{
|
31 |
+
"epoch": 2.0,
|
32 |
+
"grad_norm": 4.104482173919678,
|
33 |
+
"learning_rate": 4.5e-05,
|
34 |
+
"loss": 0.5117,
|
35 |
+
"step": 244
|
36 |
+
},
|
37 |
+
{
|
38 |
+
"epoch": 2.0,
|
39 |
+
"eval_accuracy": 0.7343358395989975,
|
40 |
+
"eval_f1": 0.69391211208893,
|
41 |
+
"eval_loss": 0.5062463879585266,
|
42 |
+
"eval_precision": 0.6880119239984399,
|
43 |
+
"eval_recall": 0.7045371885797418,
|
44 |
+
"eval_runtime": 5.055,
|
45 |
+
"eval_samples_per_second": 78.931,
|
46 |
+
"eval_steps_per_second": 9.891,
|
47 |
+
"step": 244
|
48 |
+
},
|
49 |
+
{
|
50 |
+
"epoch": 3.0,
|
51 |
+
"grad_norm": 4.243982791900635,
|
52 |
+
"learning_rate": 4.25e-05,
|
53 |
+
"loss": 0.4804,
|
54 |
+
"step": 366
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 3.0,
|
58 |
+
"eval_accuracy": 0.7669172932330827,
|
59 |
+
"eval_f1": 0.7152209115816456,
|
60 |
+
"eval_loss": 0.46674054861068726,
|
61 |
+
"eval_precision": 0.7182055749128919,
|
62 |
+
"eval_recall": 0.7125841062011276,
|
63 |
+
"eval_runtime": 5.066,
|
64 |
+
"eval_samples_per_second": 78.76,
|
65 |
+
"eval_steps_per_second": 9.87,
|
66 |
+
"step": 366
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 4.0,
|
70 |
+
"grad_norm": 2.68826961517334,
|
71 |
+
"learning_rate": 4e-05,
|
72 |
+
"loss": 0.4345,
|
73 |
+
"step": 488
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 4.0,
|
77 |
+
"eval_accuracy": 0.7919799498746867,
|
78 |
+
"eval_f1": 0.744501107107864,
|
79 |
+
"eval_loss": 0.43496260046958923,
|
80 |
+
"eval_precision": 0.7494180559924504,
|
81 |
+
"eval_recall": 0.7403164211674851,
|
82 |
+
"eval_runtime": 5.0881,
|
83 |
+
"eval_samples_per_second": 78.418,
|
84 |
+
"eval_steps_per_second": 9.827,
|
85 |
+
"step": 488
|
86 |
+
},
|
87 |
+
{
|
88 |
+
"epoch": 5.0,
|
89 |
+
"grad_norm": 2.9247703552246094,
|
90 |
+
"learning_rate": 3.7500000000000003e-05,
|
91 |
+
"loss": 0.4081,
|
92 |
+
"step": 610
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 5.0,
|
96 |
+
"eval_accuracy": 0.7944862155388471,
|
97 |
+
"eval_f1": 0.7660995138690305,
|
98 |
+
"eval_loss": 0.43371620774269104,
|
99 |
+
"eval_precision": 0.7565013111888113,
|
100 |
+
"eval_recall": 0.7845971994908165,
|
101 |
+
"eval_runtime": 5.0664,
|
102 |
+
"eval_samples_per_second": 78.754,
|
103 |
+
"eval_steps_per_second": 9.869,
|
104 |
+
"step": 610
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 6.0,
|
108 |
+
"grad_norm": 3.43408203125,
|
109 |
+
"learning_rate": 3.5e-05,
|
110 |
+
"loss": 0.3793,
|
111 |
+
"step": 732
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 6.0,
|
115 |
+
"eval_accuracy": 0.8195488721804511,
|
116 |
+
"eval_f1": 0.7753378378378378,
|
117 |
+
"eval_loss": 0.39230969548225403,
|
118 |
+
"eval_precision": 0.7857142857142857,
|
119 |
+
"eval_recall": 0.7673213311511184,
|
120 |
+
"eval_runtime": 5.0623,
|
121 |
+
"eval_samples_per_second": 78.818,
|
122 |
+
"eval_steps_per_second": 9.877,
|
123 |
+
"step": 732
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 7.0,
|
127 |
+
"grad_norm": 1.72346031665802,
|
128 |
+
"learning_rate": 3.2500000000000004e-05,
|
129 |
+
"loss": 0.3665,
|
130 |
+
"step": 854
|
131 |
+
},
|
132 |
+
{
|
133 |
+
"epoch": 7.0,
|
134 |
+
"eval_accuracy": 0.8295739348370927,
|
135 |
+
"eval_f1": 0.7933776044839771,
|
136 |
+
"eval_loss": 0.3765198886394501,
|
137 |
+
"eval_precision": 0.7949020208205757,
|
138 |
+
"eval_recall": 0.7919167121294781,
|
139 |
+
"eval_runtime": 5.0479,
|
140 |
+
"eval_samples_per_second": 79.042,
|
141 |
+
"eval_steps_per_second": 9.905,
|
142 |
+
"step": 854
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 8.0,
|
146 |
+
"grad_norm": 3.3123555183410645,
|
147 |
+
"learning_rate": 3e-05,
|
148 |
+
"loss": 0.3471,
|
149 |
+
"step": 976
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 8.0,
|
153 |
+
"eval_accuracy": 0.8370927318295739,
|
154 |
+
"eval_f1": 0.796615353247018,
|
155 |
+
"eval_loss": 0.368134468793869,
|
156 |
+
"eval_precision": 0.8088983050847458,
|
157 |
+
"eval_recall": 0.7872340425531914,
|
158 |
+
"eval_runtime": 5.0574,
|
159 |
+
"eval_samples_per_second": 78.894,
|
160 |
+
"eval_steps_per_second": 9.886,
|
161 |
+
"step": 976
|
162 |
+
},
|
163 |
+
{
|
164 |
+
"epoch": 9.0,
|
165 |
+
"grad_norm": 4.656528949737549,
|
166 |
+
"learning_rate": 2.7500000000000004e-05,
|
167 |
+
"loss": 0.3498,
|
168 |
+
"step": 1098
|
169 |
+
},
|
170 |
+
{
|
171 |
+
"epoch": 9.0,
|
172 |
+
"eval_accuracy": 0.8320802005012531,
|
173 |
+
"eval_f1": 0.790357364116157,
|
174 |
+
"eval_loss": 0.3676688075065613,
|
175 |
+
"eval_precision": 0.8023956975228161,
|
176 |
+
"eval_recall": 0.7811874886342971,
|
177 |
+
"eval_runtime": 5.0449,
|
178 |
+
"eval_samples_per_second": 79.09,
|
179 |
+
"eval_steps_per_second": 9.911,
|
180 |
+
"step": 1098
|
181 |
+
},
|
182 |
+
{
|
183 |
+
"epoch": 10.0,
|
184 |
+
"grad_norm": 6.076303482055664,
|
185 |
+
"learning_rate": 2.5e-05,
|
186 |
+
"loss": 0.3282,
|
187 |
+
"step": 1220
|
188 |
+
},
|
189 |
+
{
|
190 |
+
"epoch": 10.0,
|
191 |
+
"eval_accuracy": 0.8345864661654135,
|
192 |
+
"eval_f1": 0.7917273014868713,
|
193 |
+
"eval_loss": 0.363395094871521,
|
194 |
+
"eval_precision": 0.8074456774536514,
|
195 |
+
"eval_recall": 0.780460083651573,
|
196 |
+
"eval_runtime": 5.0444,
|
197 |
+
"eval_samples_per_second": 79.097,
|
198 |
+
"eval_steps_per_second": 9.912,
|
199 |
+
"step": 1220
|
200 |
+
},
|
201 |
+
{
|
202 |
+
"epoch": 11.0,
|
203 |
+
"grad_norm": 4.567991256713867,
|
204 |
+
"learning_rate": 2.25e-05,
|
205 |
+
"loss": 0.3149,
|
206 |
+
"step": 1342
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 11.0,
|
210 |
+
"eval_accuracy": 0.8446115288220551,
|
211 |
+
"eval_f1": 0.8065409159159159,
|
212 |
+
"eval_loss": 0.3537313938140869,
|
213 |
+
"eval_precision": 0.8180272108843537,
|
214 |
+
"eval_recall": 0.7975541007455902,
|
215 |
+
"eval_runtime": 5.0808,
|
216 |
+
"eval_samples_per_second": 78.53,
|
217 |
+
"eval_steps_per_second": 9.841,
|
218 |
+
"step": 1342
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 12.0,
|
222 |
+
"grad_norm": 11.14825439453125,
|
223 |
+
"learning_rate": 2e-05,
|
224 |
+
"loss": 0.3092,
|
225 |
+
"step": 1464
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 12.0,
|
229 |
+
"eval_accuracy": 0.849624060150376,
|
230 |
+
"eval_f1": 0.8167483159828537,
|
231 |
+
"eval_loss": 0.3528764247894287,
|
232 |
+
"eval_precision": 0.8201621387462095,
|
233 |
+
"eval_recall": 0.8136024731769412,
|
234 |
+
"eval_runtime": 5.0935,
|
235 |
+
"eval_samples_per_second": 78.336,
|
236 |
+
"eval_steps_per_second": 9.816,
|
237 |
+
"step": 1464
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 13.0,
|
241 |
+
"grad_norm": 4.867825031280518,
|
242 |
+
"learning_rate": 1.75e-05,
|
243 |
+
"loss": 0.3135,
|
244 |
+
"step": 1586
|
245 |
+
},
|
246 |
+
{
|
247 |
+
"epoch": 13.0,
|
248 |
+
"eval_accuracy": 0.8521303258145363,
|
249 |
+
"eval_f1": 0.8121903546212454,
|
250 |
+
"eval_loss": 0.3471047580242157,
|
251 |
+
"eval_precision": 0.8331751305173232,
|
252 |
+
"eval_recall": 0.7978723404255319,
|
253 |
+
"eval_runtime": 5.0603,
|
254 |
+
"eval_samples_per_second": 78.849,
|
255 |
+
"eval_steps_per_second": 9.881,
|
256 |
+
"step": 1586
|
257 |
+
},
|
258 |
+
{
|
259 |
+
"epoch": 14.0,
|
260 |
+
"grad_norm": 12.051921844482422,
|
261 |
+
"learning_rate": 1.5e-05,
|
262 |
+
"loss": 0.3103,
|
263 |
+
"step": 1708
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"epoch": 14.0,
|
267 |
+
"eval_accuracy": 0.8621553884711779,
|
268 |
+
"eval_f1": 0.8269335415335841,
|
269 |
+
"eval_loss": 0.3426941931247711,
|
270 |
+
"eval_precision": 0.8430382253911666,
|
271 |
+
"eval_recall": 0.8149663575195489,
|
272 |
+
"eval_runtime": 5.0889,
|
273 |
+
"eval_samples_per_second": 78.406,
|
274 |
+
"eval_steps_per_second": 9.825,
|
275 |
+
"step": 1708
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 15.0,
|
279 |
+
"grad_norm": 1.2898627519607544,
|
280 |
+
"learning_rate": 1.25e-05,
|
281 |
+
"loss": 0.2974,
|
282 |
+
"step": 1830
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 15.0,
|
286 |
+
"eval_accuracy": 0.8621553884711779,
|
287 |
+
"eval_f1": 0.8297847585805701,
|
288 |
+
"eval_loss": 0.33716997504234314,
|
289 |
+
"eval_precision": 0.8385357006491028,
|
290 |
+
"eval_recall": 0.8224677214038916,
|
291 |
+
"eval_runtime": 5.0653,
|
292 |
+
"eval_samples_per_second": 78.772,
|
293 |
+
"eval_steps_per_second": 9.871,
|
294 |
+
"step": 1830
|
295 |
+
},
|
296 |
+
{
|
297 |
+
"epoch": 16.0,
|
298 |
+
"grad_norm": 6.9146409034729,
|
299 |
+
"learning_rate": 1e-05,
|
300 |
+
"loss": 0.2905,
|
301 |
+
"step": 1952
|
302 |
+
},
|
303 |
+
{
|
304 |
+
"epoch": 16.0,
|
305 |
+
"eval_accuracy": 0.8696741854636592,
|
306 |
+
"eval_f1": 0.8386324041811847,
|
307 |
+
"eval_loss": 0.3345378339290619,
|
308 |
+
"eval_precision": 0.8487869670976828,
|
309 |
+
"eval_recall": 0.830287324968176,
|
310 |
+
"eval_runtime": 5.0631,
|
311 |
+
"eval_samples_per_second": 78.806,
|
312 |
+
"eval_steps_per_second": 9.875,
|
313 |
+
"step": 1952
|
314 |
+
},
|
315 |
+
{
|
316 |
+
"epoch": 17.0,
|
317 |
+
"grad_norm": 4.737354278564453,
|
318 |
+
"learning_rate": 7.5e-06,
|
319 |
+
"loss": 0.2895,
|
320 |
+
"step": 2074
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 17.0,
|
324 |
+
"eval_accuracy": 0.8621553884711779,
|
325 |
+
"eval_f1": 0.8269335415335841,
|
326 |
+
"eval_loss": 0.3339170217514038,
|
327 |
+
"eval_precision": 0.8430382253911666,
|
328 |
+
"eval_recall": 0.8149663575195489,
|
329 |
+
"eval_runtime": 5.0593,
|
330 |
+
"eval_samples_per_second": 78.864,
|
331 |
+
"eval_steps_per_second": 9.883,
|
332 |
+
"step": 2074
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 18.0,
|
336 |
+
"grad_norm": 3.6233842372894287,
|
337 |
+
"learning_rate": 5e-06,
|
338 |
+
"loss": 0.2922,
|
339 |
+
"step": 2196
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 18.0,
|
343 |
+
"eval_accuracy": 0.8696741854636592,
|
344 |
+
"eval_f1": 0.8386324041811847,
|
345 |
+
"eval_loss": 0.3318663537502289,
|
346 |
+
"eval_precision": 0.8487869670976828,
|
347 |
+
"eval_recall": 0.830287324968176,
|
348 |
+
"eval_runtime": 5.0649,
|
349 |
+
"eval_samples_per_second": 78.778,
|
350 |
+
"eval_steps_per_second": 9.872,
|
351 |
+
"step": 2196
|
352 |
+
},
|
353 |
+
{
|
354 |
+
"epoch": 19.0,
|
355 |
+
"grad_norm": 4.824616432189941,
|
356 |
+
"learning_rate": 2.5e-06,
|
357 |
+
"loss": 0.2843,
|
358 |
+
"step": 2318
|
359 |
+
},
|
360 |
+
{
|
361 |
+
"epoch": 19.0,
|
362 |
+
"eval_accuracy": 0.8621553884711779,
|
363 |
+
"eval_f1": 0.8269335415335841,
|
364 |
+
"eval_loss": 0.3319249749183655,
|
365 |
+
"eval_precision": 0.8430382253911666,
|
366 |
+
"eval_recall": 0.8149663575195489,
|
367 |
+
"eval_runtime": 5.072,
|
368 |
+
"eval_samples_per_second": 78.668,
|
369 |
+
"eval_steps_per_second": 9.858,
|
370 |
+
"step": 2318
|
371 |
+
},
|
372 |
+
{
|
373 |
+
"epoch": 20.0,
|
374 |
+
"grad_norm": 7.412130832672119,
|
375 |
+
"learning_rate": 0.0,
|
376 |
+
"loss": 0.287,
|
377 |
+
"step": 2440
|
378 |
+
},
|
379 |
+
{
|
380 |
+
"epoch": 20.0,
|
381 |
+
"eval_accuracy": 0.8621553884711779,
|
382 |
+
"eval_f1": 0.8279052989013229,
|
383 |
+
"eval_loss": 0.33124828338623047,
|
384 |
+
"eval_precision": 0.8414113428943938,
|
385 |
+
"eval_recall": 0.8174668121476631,
|
386 |
+
"eval_runtime": 5.1086,
|
387 |
+
"eval_samples_per_second": 78.104,
|
388 |
+
"eval_steps_per_second": 9.788,
|
389 |
+
"step": 2440
|
390 |
+
},
|
391 |
+
{
|
392 |
+
"epoch": 20.0,
|
393 |
+
"step": 2440,
|
394 |
+
"total_flos": 7597037114448000.0,
|
395 |
+
"train_loss": 0.35801424432973394,
|
396 |
+
"train_runtime": 1952.1205,
|
397 |
+
"train_samples_per_second": 37.272,
|
398 |
+
"train_steps_per_second": 1.25
|
399 |
+
}
|
400 |
+
],
|
401 |
+
"logging_steps": 500,
|
402 |
+
"max_steps": 2440,
|
403 |
+
"num_input_tokens_seen": 0,
|
404 |
+
"num_train_epochs": 20,
|
405 |
+
"save_steps": 500,
|
406 |
+
"total_flos": 7597037114448000.0,
|
407 |
+
"train_batch_size": 30,
|
408 |
+
"trial_name": null,
|
409 |
+
"trial_params": null
|
410 |
+
}
|