End of training
Browse files- README.md +2 -0
- all_results.json +15 -15
- eval_results.json +8 -8
- predict_results.json +3 -3
- predict_results.txt +32 -32
- runs/Jun03_15-48-01_a358b85c7679/events.out.tfevents.1717430443.a358b85c7679.183185.1 +3 -0
- train_results.json +4 -4
- trainer_state.json +203 -203
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
CHANGED
@@ -1,21 +1,21 @@
|
|
1 |
{
|
2 |
"accuracy": 0.9090009891196835,
|
3 |
"epoch": 20.0,
|
4 |
-
"eval_accuracy": 0.
|
5 |
-
"eval_f1": 0.
|
6 |
-
"eval_loss": 0.
|
7 |
-
"eval_precision": 0.
|
8 |
-
"eval_recall": 0.
|
9 |
-
"eval_runtime":
|
10 |
"eval_samples": 399,
|
11 |
-
"eval_samples_per_second":
|
12 |
-
"eval_steps_per_second":
|
13 |
-
"f1": 0.
|
14 |
-
"precision": 0.
|
15 |
-
"recall": 0.
|
16 |
-
"train_loss": 0.
|
17 |
-
"train_runtime":
|
18 |
"train_samples": 3638,
|
19 |
-
"train_samples_per_second":
|
20 |
-
"train_steps_per_second":
|
21 |
}
|
|
|
1 |
{
|
2 |
"accuracy": 0.9090009891196835,
|
3 |
"epoch": 20.0,
|
4 |
+
"eval_accuracy": 0.8872180451127819,
|
5 |
+
"eval_f1": 0.8662440310793597,
|
6 |
+
"eval_loss": 0.3288058042526245,
|
7 |
+
"eval_precision": 0.8606158357771261,
|
8 |
+
"eval_recall": 0.872704128023277,
|
9 |
+
"eval_runtime": 2.0252,
|
10 |
"eval_samples": 399,
|
11 |
+
"eval_samples_per_second": 197.016,
|
12 |
+
"eval_steps_per_second": 24.689,
|
13 |
+
"f1": 0.8918102806521253,
|
14 |
+
"precision": 0.8875983617873084,
|
15 |
+
"recall": 0.8964202678916009,
|
16 |
+
"train_loss": 0.2203434850348801,
|
17 |
+
"train_runtime": 746.002,
|
18 |
"train_samples": 3638,
|
19 |
+
"train_samples_per_second": 97.533,
|
20 |
+
"train_steps_per_second": 3.271
|
21 |
}
|
eval_results.json
CHANGED
@@ -1,12 +1,12 @@
|
|
1 |
{
|
2 |
"epoch": 20.0,
|
3 |
-
"eval_accuracy": 0.
|
4 |
-
"eval_f1": 0.
|
5 |
-
"eval_loss": 0.
|
6 |
-
"eval_precision": 0.
|
7 |
-
"eval_recall": 0.
|
8 |
-
"eval_runtime":
|
9 |
"eval_samples": 399,
|
10 |
-
"eval_samples_per_second":
|
11 |
-
"eval_steps_per_second":
|
12 |
}
|
|
|
1 |
{
|
2 |
"epoch": 20.0,
|
3 |
+
"eval_accuracy": 0.8872180451127819,
|
4 |
+
"eval_f1": 0.8662440310793597,
|
5 |
+
"eval_loss": 0.3288058042526245,
|
6 |
+
"eval_precision": 0.8606158357771261,
|
7 |
+
"eval_recall": 0.872704128023277,
|
8 |
+
"eval_runtime": 2.0252,
|
9 |
"eval_samples": 399,
|
10 |
+
"eval_samples_per_second": 197.016,
|
11 |
+
"eval_steps_per_second": 24.689
|
12 |
}
|
predict_results.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"accuracy": 0.9090009891196835,
|
3 |
-
"f1": 0.
|
4 |
-
"precision": 0.
|
5 |
-
"recall": 0.
|
6 |
}
|
|
|
1 |
{
|
2 |
"accuracy": 0.9090009891196835,
|
3 |
+
"f1": 0.8918102806521253,
|
4 |
+
"precision": 0.8875983617873084,
|
5 |
+
"recall": 0.8964202678916009
|
6 |
}
|
predict_results.txt
CHANGED
@@ -21,7 +21,7 @@ index prediction
|
|
21 |
19 1
|
22 |
20 1
|
23 |
21 1
|
24 |
-
22
|
25 |
23 1
|
26 |
24 1
|
27 |
25 0
|
@@ -40,12 +40,12 @@ index prediction
|
|
40 |
38 1
|
41 |
39 1
|
42 |
40 1
|
43 |
-
41
|
44 |
42 1
|
45 |
43 1
|
46 |
44 1
|
47 |
45 0
|
48 |
-
46
|
49 |
47 1
|
50 |
48 1
|
51 |
49 1
|
@@ -67,7 +67,7 @@ index prediction
|
|
67 |
65 1
|
68 |
66 1
|
69 |
67 0
|
70 |
-
68
|
71 |
69 1
|
72 |
70 1
|
73 |
71 1
|
@@ -75,7 +75,7 @@ index prediction
|
|
75 |
73 1
|
76 |
74 1
|
77 |
75 0
|
78 |
-
76
|
79 |
77 1
|
80 |
78 1
|
81 |
79 1
|
@@ -104,9 +104,9 @@ index prediction
|
|
104 |
102 0
|
105 |
103 1
|
106 |
104 1
|
107 |
-
105
|
108 |
106 1
|
109 |
-
107
|
110 |
108 1
|
111 |
109 1
|
112 |
110 1
|
@@ -166,7 +166,7 @@ index prediction
|
|
166 |
164 1
|
167 |
165 1
|
168 |
166 1
|
169 |
-
167
|
170 |
168 1
|
171 |
169 1
|
172 |
170 0
|
@@ -180,18 +180,18 @@ index prediction
|
|
180 |
178 1
|
181 |
179 0
|
182 |
180 1
|
183 |
-
181
|
184 |
182 1
|
185 |
183 1
|
186 |
184 1
|
187 |
-
185
|
188 |
186 1
|
189 |
187 1
|
190 |
188 1
|
191 |
189 1
|
192 |
190 1
|
193 |
191 1
|
194 |
-
192
|
195 |
193 1
|
196 |
194 1
|
197 |
195 1
|
@@ -228,7 +228,7 @@ index prediction
|
|
228 |
226 1
|
229 |
227 1
|
230 |
228 1
|
231 |
-
229
|
232 |
230 1
|
233 |
231 1
|
234 |
232 1
|
@@ -236,7 +236,7 @@ index prediction
|
|
236 |
234 1
|
237 |
235 0
|
238 |
236 1
|
239 |
-
237
|
240 |
238 1
|
241 |
239 1
|
242 |
240 1
|
@@ -247,21 +247,21 @@ index prediction
|
|
247 |
245 1
|
248 |
246 1
|
249 |
247 1
|
250 |
-
248
|
251 |
249 1
|
252 |
250 1
|
253 |
251 1
|
254 |
252 1
|
255 |
-
253
|
256 |
254 1
|
257 |
255 1
|
258 |
256 1
|
259 |
-
257
|
260 |
258 1
|
261 |
259 1
|
262 |
260 1
|
263 |
261 1
|
264 |
-
262
|
265 |
263 1
|
266 |
264 1
|
267 |
265 1
|
@@ -277,13 +277,13 @@ index prediction
|
|
277 |
275 0
|
278 |
276 0
|
279 |
277 1
|
280 |
-
278
|
281 |
279 1
|
282 |
280 1
|
283 |
281 0
|
284 |
282 1
|
285 |
283 1
|
286 |
-
284
|
287 |
285 1
|
288 |
286 1
|
289 |
287 1
|
@@ -322,13 +322,13 @@ index prediction
|
|
322 |
320 0
|
323 |
321 0
|
324 |
322 0
|
325 |
-
323
|
326 |
324 1
|
327 |
325 0
|
328 |
326 0
|
329 |
327 0
|
330 |
328 0
|
331 |
-
329
|
332 |
330 0
|
333 |
331 0
|
334 |
332 0
|
@@ -346,7 +346,7 @@ index prediction
|
|
346 |
344 0
|
347 |
345 0
|
348 |
346 0
|
349 |
-
347
|
350 |
348 0
|
351 |
349 0
|
352 |
350 0
|
@@ -382,7 +382,7 @@ index prediction
|
|
382 |
380 0
|
383 |
381 0
|
384 |
382 1
|
385 |
-
383
|
386 |
384 0
|
387 |
385 0
|
388 |
386 0
|
@@ -470,7 +470,7 @@ index prediction
|
|
470 |
468 0
|
471 |
469 0
|
472 |
470 0
|
473 |
-
471
|
474 |
472 0
|
475 |
473 0
|
476 |
474 0
|
@@ -490,19 +490,19 @@ index prediction
|
|
490 |
488 0
|
491 |
489 0
|
492 |
490 0
|
493 |
-
491
|
494 |
492 0
|
495 |
493 0
|
496 |
494 0
|
497 |
495 0
|
498 |
496 0
|
499 |
497 0
|
500 |
-
498
|
501 |
499 0
|
502 |
500 0
|
503 |
501 0
|
504 |
502 0
|
505 |
-
503
|
506 |
504 0
|
507 |
505 0
|
508 |
506 0
|
@@ -587,11 +587,11 @@ index prediction
|
|
587 |
585 0
|
588 |
586 0
|
589 |
587 0
|
590 |
-
588
|
591 |
589 0
|
592 |
590 0
|
593 |
591 1
|
594 |
-
592
|
595 |
593 0
|
596 |
594 0
|
597 |
595 0
|
@@ -642,7 +642,7 @@ index prediction
|
|
642 |
640 0
|
643 |
641 0
|
644 |
642 0
|
645 |
-
643
|
646 |
644 0
|
647 |
645 0
|
648 |
646 0
|
@@ -678,7 +678,7 @@ index prediction
|
|
678 |
676 0
|
679 |
677 0
|
680 |
678 0
|
681 |
-
679
|
682 |
680 0
|
683 |
681 0
|
684 |
682 0
|
@@ -953,7 +953,7 @@ index prediction
|
|
953 |
951 0
|
954 |
952 0
|
955 |
953 0
|
956 |
-
954
|
957 |
955 0
|
958 |
956 0
|
959 |
957 0
|
|
|
21 |
19 1
|
22 |
20 1
|
23 |
21 1
|
24 |
+
22 1
|
25 |
23 1
|
26 |
24 1
|
27 |
25 0
|
|
|
40 |
38 1
|
41 |
39 1
|
42 |
40 1
|
43 |
+
41 1
|
44 |
42 1
|
45 |
43 1
|
46 |
44 1
|
47 |
45 0
|
48 |
+
46 1
|
49 |
47 1
|
50 |
48 1
|
51 |
49 1
|
|
|
67 |
65 1
|
68 |
66 1
|
69 |
67 0
|
70 |
+
68 0
|
71 |
69 1
|
72 |
70 1
|
73 |
71 1
|
|
|
75 |
73 1
|
76 |
74 1
|
77 |
75 0
|
78 |
+
76 1
|
79 |
77 1
|
80 |
78 1
|
81 |
79 1
|
|
|
104 |
102 0
|
105 |
103 1
|
106 |
104 1
|
107 |
+
105 1
|
108 |
106 1
|
109 |
+
107 0
|
110 |
108 1
|
111 |
109 1
|
112 |
110 1
|
|
|
166 |
164 1
|
167 |
165 1
|
168 |
166 1
|
169 |
+
167 1
|
170 |
168 1
|
171 |
169 1
|
172 |
170 0
|
|
|
180 |
178 1
|
181 |
179 0
|
182 |
180 1
|
183 |
+
181 1
|
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 1
|
195 |
193 1
|
196 |
194 1
|
197 |
195 1
|
|
|
228 |
226 1
|
229 |
227 1
|
230 |
228 1
|
231 |
+
229 1
|
232 |
230 1
|
233 |
231 1
|
234 |
232 1
|
|
|
236 |
234 1
|
237 |
235 0
|
238 |
236 1
|
239 |
+
237 1
|
240 |
238 1
|
241 |
239 1
|
242 |
240 1
|
|
|
247 |
245 1
|
248 |
246 1
|
249 |
247 1
|
250 |
+
248 1
|
251 |
249 1
|
252 |
250 1
|
253 |
251 1
|
254 |
252 1
|
255 |
+
253 1
|
256 |
254 1
|
257 |
255 1
|
258 |
256 1
|
259 |
+
257 0
|
260 |
258 1
|
261 |
259 1
|
262 |
260 1
|
263 |
261 1
|
264 |
+
262 0
|
265 |
263 1
|
266 |
264 1
|
267 |
265 1
|
|
|
277 |
275 0
|
278 |
276 0
|
279 |
277 1
|
280 |
+
278 0
|
281 |
279 1
|
282 |
280 1
|
283 |
281 0
|
284 |
282 1
|
285 |
283 1
|
286 |
+
284 0
|
287 |
285 1
|
288 |
286 1
|
289 |
287 1
|
|
|
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
|
|
|
346 |
344 0
|
347 |
345 0
|
348 |
346 0
|
349 |
+
347 1
|
350 |
348 0
|
351 |
349 0
|
352 |
350 0
|
|
|
382 |
380 0
|
383 |
381 0
|
384 |
382 1
|
385 |
+
383 1
|
386 |
384 0
|
387 |
385 0
|
388 |
386 0
|
|
|
470 |
468 0
|
471 |
469 0
|
472 |
470 0
|
473 |
+
471 1
|
474 |
472 0
|
475 |
473 0
|
476 |
474 0
|
|
|
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 0
|
501 |
499 0
|
502 |
500 0
|
503 |
501 0
|
504 |
502 0
|
505 |
+
503 0
|
506 |
504 0
|
507 |
505 0
|
508 |
506 0
|
|
|
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
|
|
|
642 |
640 0
|
643 |
641 0
|
644 |
642 0
|
645 |
+
643 1
|
646 |
644 0
|
647 |
645 0
|
648 |
646 0
|
|
|
678 |
676 0
|
679 |
677 0
|
680 |
678 0
|
681 |
+
679 1
|
682 |
680 0
|
683 |
681 0
|
684 |
682 0
|
|
|
953 |
951 0
|
954 |
952 0
|
955 |
953 0
|
956 |
+
954 1
|
957 |
955 0
|
958 |
956 0
|
959 |
957 0
|
runs/Jun03_15-48-01_a358b85c7679/events.out.tfevents.1717430443.a358b85c7679.183185.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:25b94d9bcf029836ebd4c3bcf6a7b0e59fc0deaf499f3fd73103deebfdc1809a
|
3 |
+
size 560
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 20.0,
|
3 |
-
"train_loss": 0.
|
4 |
-
"train_runtime":
|
5 |
"train_samples": 3638,
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second":
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 20.0,
|
3 |
+
"train_loss": 0.2203434850348801,
|
4 |
+
"train_runtime": 746.002,
|
5 |
"train_samples": 3638,
|
6 |
+
"train_samples_per_second": 97.533,
|
7 |
+
"train_steps_per_second": 3.271
|
8 |
}
|
trainer_state.json
CHANGED
@@ -10,392 +10,392 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
-
"grad_norm":
|
14 |
"learning_rate": 4.75e-05,
|
15 |
-
"loss": 0.
|
16 |
"step": 122
|
17 |
},
|
18 |
{
|
19 |
"epoch": 1.0,
|
20 |
-
"eval_accuracy": 0.
|
21 |
-
"eval_f1": 0.
|
22 |
-
"eval_loss": 0.
|
23 |
-
"eval_precision": 0.
|
24 |
-
"eval_recall": 0.
|
25 |
-
"eval_runtime":
|
26 |
-
"eval_samples_per_second":
|
27 |
-
"eval_steps_per_second":
|
28 |
"step": 122
|
29 |
},
|
30 |
{
|
31 |
"epoch": 2.0,
|
32 |
-
"grad_norm": 4.
|
33 |
"learning_rate": 4.5e-05,
|
34 |
-
"loss": 0.
|
35 |
"step": 244
|
36 |
},
|
37 |
{
|
38 |
"epoch": 2.0,
|
39 |
-
"eval_accuracy": 0.
|
40 |
-
"eval_f1": 0.
|
41 |
-
"eval_loss": 0.
|
42 |
-
"eval_precision": 0.
|
43 |
-
"eval_recall": 0.
|
44 |
-
"eval_runtime":
|
45 |
-
"eval_samples_per_second":
|
46 |
-
"eval_steps_per_second":
|
47 |
"step": 244
|
48 |
},
|
49 |
{
|
50 |
"epoch": 3.0,
|
51 |
-
"grad_norm":
|
52 |
"learning_rate": 4.25e-05,
|
53 |
-
"loss": 0.
|
54 |
"step": 366
|
55 |
},
|
56 |
{
|
57 |
"epoch": 3.0,
|
58 |
-
"eval_accuracy": 0.
|
59 |
-
"eval_f1": 0.
|
60 |
-
"eval_loss": 0.
|
61 |
-
"eval_precision": 0.
|
62 |
-
"eval_recall": 0.
|
63 |
-
"eval_runtime":
|
64 |
-
"eval_samples_per_second":
|
65 |
-
"eval_steps_per_second":
|
66 |
"step": 366
|
67 |
},
|
68 |
{
|
69 |
"epoch": 4.0,
|
70 |
-
"grad_norm":
|
71 |
"learning_rate": 4e-05,
|
72 |
-
"loss": 0.
|
73 |
"step": 488
|
74 |
},
|
75 |
{
|
76 |
"epoch": 4.0,
|
77 |
"eval_accuracy": 0.8721804511278195,
|
78 |
-
"eval_f1": 0.
|
79 |
-
"eval_loss": 0.
|
80 |
-
"eval_precision": 0.
|
81 |
-
"eval_recall": 0.
|
82 |
-
"eval_runtime":
|
83 |
-
"eval_samples_per_second":
|
84 |
-
"eval_steps_per_second":
|
85 |
"step": 488
|
86 |
},
|
87 |
{
|
88 |
"epoch": 5.0,
|
89 |
-
"grad_norm":
|
90 |
"learning_rate": 3.7500000000000003e-05,
|
91 |
-
"loss": 0.
|
92 |
"step": 610
|
93 |
},
|
94 |
{
|
95 |
"epoch": 5.0,
|
96 |
-
"eval_accuracy": 0.
|
97 |
-
"eval_f1": 0.
|
98 |
-
"eval_loss": 0.
|
99 |
-
"eval_precision": 0.
|
100 |
-
"eval_recall": 0.
|
101 |
-
"eval_runtime":
|
102 |
-
"eval_samples_per_second":
|
103 |
-
"eval_steps_per_second":
|
104 |
"step": 610
|
105 |
},
|
106 |
{
|
107 |
"epoch": 6.0,
|
108 |
-
"grad_norm":
|
109 |
"learning_rate": 3.5e-05,
|
110 |
-
"loss": 0.
|
111 |
"step": 732
|
112 |
},
|
113 |
{
|
114 |
"epoch": 6.0,
|
115 |
-
"eval_accuracy": 0.
|
116 |
-
"eval_f1": 0.
|
117 |
-
"eval_loss": 0.
|
118 |
-
"eval_precision": 0.
|
119 |
-
"eval_recall": 0.
|
120 |
-
"eval_runtime":
|
121 |
-
"eval_samples_per_second":
|
122 |
-
"eval_steps_per_second":
|
123 |
"step": 732
|
124 |
},
|
125 |
{
|
126 |
"epoch": 7.0,
|
127 |
-
"grad_norm": 0.
|
128 |
"learning_rate": 3.2500000000000004e-05,
|
129 |
-
"loss": 0.
|
130 |
"step": 854
|
131 |
},
|
132 |
{
|
133 |
"epoch": 7.0,
|
134 |
-
"eval_accuracy": 0.
|
135 |
-
"eval_f1": 0.
|
136 |
-
"eval_loss": 0.
|
137 |
-
"eval_precision": 0.
|
138 |
-
"eval_recall": 0.
|
139 |
-
"eval_runtime":
|
140 |
-
"eval_samples_per_second":
|
141 |
-
"eval_steps_per_second":
|
142 |
"step": 854
|
143 |
},
|
144 |
{
|
145 |
"epoch": 8.0,
|
146 |
-
"grad_norm":
|
147 |
"learning_rate": 3e-05,
|
148 |
-
"loss": 0.
|
149 |
"step": 976
|
150 |
},
|
151 |
{
|
152 |
"epoch": 8.0,
|
153 |
-
"eval_accuracy": 0.
|
154 |
-
"eval_f1": 0.
|
155 |
-
"eval_loss": 0.
|
156 |
-
"eval_precision": 0.
|
157 |
-
"eval_recall": 0.
|
158 |
-
"eval_runtime":
|
159 |
-
"eval_samples_per_second":
|
160 |
-
"eval_steps_per_second":
|
161 |
"step": 976
|
162 |
},
|
163 |
{
|
164 |
"epoch": 9.0,
|
165 |
-
"grad_norm": 8.
|
166 |
"learning_rate": 2.7500000000000004e-05,
|
167 |
-
"loss": 0.
|
168 |
"step": 1098
|
169 |
},
|
170 |
{
|
171 |
"epoch": 9.0,
|
172 |
-
"eval_accuracy": 0.
|
173 |
-
"eval_f1": 0.
|
174 |
-
"eval_loss": 0.
|
175 |
-
"eval_precision": 0.
|
176 |
-
"eval_recall": 0.
|
177 |
-
"eval_runtime":
|
178 |
-
"eval_samples_per_second":
|
179 |
-
"eval_steps_per_second":
|
180 |
"step": 1098
|
181 |
},
|
182 |
{
|
183 |
"epoch": 10.0,
|
184 |
-
"grad_norm":
|
185 |
"learning_rate": 2.5e-05,
|
186 |
-
"loss": 0.
|
187 |
"step": 1220
|
188 |
},
|
189 |
{
|
190 |
"epoch": 10.0,
|
191 |
-
"eval_accuracy": 0.
|
192 |
-
"eval_f1": 0.
|
193 |
-
"eval_loss": 0.
|
194 |
-
"eval_precision": 0.
|
195 |
-
"eval_recall": 0.
|
196 |
-
"eval_runtime":
|
197 |
-
"eval_samples_per_second":
|
198 |
-
"eval_steps_per_second":
|
199 |
"step": 1220
|
200 |
},
|
201 |
{
|
202 |
"epoch": 11.0,
|
203 |
-
"grad_norm":
|
204 |
"learning_rate": 2.25e-05,
|
205 |
-
"loss": 0.
|
206 |
"step": 1342
|
207 |
},
|
208 |
{
|
209 |
"epoch": 11.0,
|
210 |
-
"eval_accuracy": 0.
|
211 |
-
"eval_f1": 0.
|
212 |
-
"eval_loss": 0.
|
213 |
-
"eval_precision": 0.
|
214 |
-
"eval_recall": 0.
|
215 |
-
"eval_runtime":
|
216 |
-
"eval_samples_per_second":
|
217 |
-
"eval_steps_per_second":
|
218 |
"step": 1342
|
219 |
},
|
220 |
{
|
221 |
"epoch": 12.0,
|
222 |
-
"grad_norm":
|
223 |
"learning_rate": 2e-05,
|
224 |
-
"loss": 0.
|
225 |
"step": 1464
|
226 |
},
|
227 |
{
|
228 |
"epoch": 12.0,
|
229 |
-
"eval_accuracy": 0.
|
230 |
-
"eval_f1": 0.
|
231 |
-
"eval_loss": 0.
|
232 |
-
"eval_precision": 0.
|
233 |
-
"eval_recall": 0.
|
234 |
-
"eval_runtime":
|
235 |
-
"eval_samples_per_second":
|
236 |
-
"eval_steps_per_second":
|
237 |
"step": 1464
|
238 |
},
|
239 |
{
|
240 |
"epoch": 13.0,
|
241 |
-
"grad_norm":
|
242 |
"learning_rate": 1.75e-05,
|
243 |
-
"loss": 0.
|
244 |
"step": 1586
|
245 |
},
|
246 |
{
|
247 |
"epoch": 13.0,
|
248 |
-
"eval_accuracy": 0.
|
249 |
-
"eval_f1": 0.
|
250 |
-
"eval_loss": 0.
|
251 |
-
"eval_precision": 0.
|
252 |
-
"eval_recall": 0.
|
253 |
-
"eval_runtime":
|
254 |
-
"eval_samples_per_second":
|
255 |
-
"eval_steps_per_second":
|
256 |
"step": 1586
|
257 |
},
|
258 |
{
|
259 |
"epoch": 14.0,
|
260 |
-
"grad_norm":
|
261 |
"learning_rate": 1.5e-05,
|
262 |
-
"loss": 0.
|
263 |
"step": 1708
|
264 |
},
|
265 |
{
|
266 |
"epoch": 14.0,
|
267 |
-
"eval_accuracy": 0.
|
268 |
-
"eval_f1": 0.
|
269 |
-
"eval_loss": 0.
|
270 |
-
"eval_precision": 0.
|
271 |
-
"eval_recall": 0.
|
272 |
-
"eval_runtime":
|
273 |
-
"eval_samples_per_second":
|
274 |
-
"eval_steps_per_second":
|
275 |
"step": 1708
|
276 |
},
|
277 |
{
|
278 |
"epoch": 15.0,
|
279 |
-
"grad_norm": 0.
|
280 |
"learning_rate": 1.25e-05,
|
281 |
-
"loss": 0.
|
282 |
"step": 1830
|
283 |
},
|
284 |
{
|
285 |
"epoch": 15.0,
|
286 |
-
"eval_accuracy": 0.
|
287 |
-
"eval_f1": 0.
|
288 |
-
"eval_loss": 0.
|
289 |
-
"eval_precision": 0.
|
290 |
-
"eval_recall": 0.
|
291 |
-
"eval_runtime":
|
292 |
-
"eval_samples_per_second":
|
293 |
-
"eval_steps_per_second":
|
294 |
"step": 1830
|
295 |
},
|
296 |
{
|
297 |
"epoch": 16.0,
|
298 |
-
"grad_norm":
|
299 |
"learning_rate": 1e-05,
|
300 |
-
"loss": 0.
|
301 |
"step": 1952
|
302 |
},
|
303 |
{
|
304 |
"epoch": 16.0,
|
305 |
-
"eval_accuracy": 0.
|
306 |
-
"eval_f1": 0.
|
307 |
-
"eval_loss": 0.
|
308 |
-
"eval_precision": 0.
|
309 |
-
"eval_recall": 0.
|
310 |
-
"eval_runtime":
|
311 |
-
"eval_samples_per_second":
|
312 |
-
"eval_steps_per_second":
|
313 |
"step": 1952
|
314 |
},
|
315 |
{
|
316 |
"epoch": 17.0,
|
317 |
-
"grad_norm":
|
318 |
"learning_rate": 7.5e-06,
|
319 |
-
"loss": 0.
|
320 |
"step": 2074
|
321 |
},
|
322 |
{
|
323 |
"epoch": 17.0,
|
324 |
-
"eval_accuracy": 0.
|
325 |
-
"eval_f1": 0.
|
326 |
-
"eval_loss": 0.
|
327 |
-
"eval_precision": 0.
|
328 |
-
"eval_recall": 0.
|
329 |
-
"eval_runtime":
|
330 |
-
"eval_samples_per_second":
|
331 |
-
"eval_steps_per_second":
|
332 |
"step": 2074
|
333 |
},
|
334 |
{
|
335 |
"epoch": 18.0,
|
336 |
-
"grad_norm":
|
337 |
"learning_rate": 5e-06,
|
338 |
-
"loss": 0.
|
339 |
"step": 2196
|
340 |
},
|
341 |
{
|
342 |
"epoch": 18.0,
|
343 |
-
"eval_accuracy": 0.
|
344 |
-
"eval_f1": 0.
|
345 |
-
"eval_loss": 0.
|
346 |
-
"eval_precision": 0.
|
347 |
-
"eval_recall": 0.
|
348 |
-
"eval_runtime":
|
349 |
-
"eval_samples_per_second":
|
350 |
-
"eval_steps_per_second":
|
351 |
"step": 2196
|
352 |
},
|
353 |
{
|
354 |
"epoch": 19.0,
|
355 |
-
"grad_norm":
|
356 |
"learning_rate": 2.5e-06,
|
357 |
-
"loss": 0.
|
358 |
"step": 2318
|
359 |
},
|
360 |
{
|
361 |
"epoch": 19.0,
|
362 |
-
"eval_accuracy": 0.
|
363 |
-
"eval_f1": 0.
|
364 |
-
"eval_loss": 0.
|
365 |
-
"eval_precision": 0.
|
366 |
-
"eval_recall": 0.
|
367 |
-
"eval_runtime":
|
368 |
-
"eval_samples_per_second":
|
369 |
-
"eval_steps_per_second":
|
370 |
"step": 2318
|
371 |
},
|
372 |
{
|
373 |
"epoch": 20.0,
|
374 |
-
"grad_norm":
|
375 |
"learning_rate": 0.0,
|
376 |
-
"loss": 0.
|
377 |
"step": 2440
|
378 |
},
|
379 |
{
|
380 |
"epoch": 20.0,
|
381 |
-
"eval_accuracy": 0.
|
382 |
-
"eval_f1": 0.
|
383 |
-
"eval_loss": 0.
|
384 |
-
"eval_precision": 0.
|
385 |
-
"eval_recall": 0.
|
386 |
-
"eval_runtime":
|
387 |
-
"eval_samples_per_second":
|
388 |
-
"eval_steps_per_second":
|
389 |
"step": 2440
|
390 |
},
|
391 |
{
|
392 |
"epoch": 20.0,
|
393 |
"step": 2440,
|
394 |
"total_flos": 8551203605328000.0,
|
395 |
-
"train_loss": 0.
|
396 |
-
"train_runtime":
|
397 |
-
"train_samples_per_second":
|
398 |
-
"train_steps_per_second":
|
399 |
}
|
400 |
],
|
401 |
"logging_steps": 500,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
+
"grad_norm": 6.6789751052856445,
|
14 |
"learning_rate": 4.75e-05,
|
15 |
+
"loss": 0.5528,
|
16 |
"step": 122
|
17 |
},
|
18 |
{
|
19 |
"epoch": 1.0,
|
20 |
+
"eval_accuracy": 0.7167919799498746,
|
21 |
+
"eval_f1": 0.6444270944235455,
|
22 |
+
"eval_loss": 0.5050782561302185,
|
23 |
+
"eval_precision": 0.6520598138245197,
|
24 |
+
"eval_recall": 0.639616293871613,
|
25 |
+
"eval_runtime": 1.9903,
|
26 |
+
"eval_samples_per_second": 200.468,
|
27 |
+
"eval_steps_per_second": 25.121,
|
28 |
"step": 122
|
29 |
},
|
30 |
{
|
31 |
"epoch": 2.0,
|
32 |
+
"grad_norm": 4.4306488037109375,
|
33 |
"learning_rate": 4.5e-05,
|
34 |
+
"loss": 0.4431,
|
35 |
"step": 244
|
36 |
},
|
37 |
{
|
38 |
"epoch": 2.0,
|
39 |
+
"eval_accuracy": 0.7969924812030075,
|
40 |
+
"eval_f1": 0.7789473684210526,
|
41 |
+
"eval_loss": 0.4333195090293884,
|
42 |
+
"eval_precision": 0.7711038961038961,
|
43 |
+
"eval_recall": 0.8188761593016912,
|
44 |
+
"eval_runtime": 1.9992,
|
45 |
+
"eval_samples_per_second": 199.58,
|
46 |
+
"eval_steps_per_second": 25.01,
|
47 |
"step": 244
|
48 |
},
|
49 |
{
|
50 |
"epoch": 3.0,
|
51 |
+
"grad_norm": 3.0677573680877686,
|
52 |
"learning_rate": 4.25e-05,
|
53 |
+
"loss": 0.3491,
|
54 |
"step": 366
|
55 |
},
|
56 |
{
|
57 |
"epoch": 3.0,
|
58 |
+
"eval_accuracy": 0.8671679197994987,
|
59 |
+
"eval_f1": 0.8292627788498026,
|
60 |
+
"eval_loss": 0.32689258456230164,
|
61 |
+
"eval_precision": 0.8579176839902337,
|
62 |
+
"eval_recall": 0.8110110929259866,
|
63 |
+
"eval_runtime": 1.9988,
|
64 |
+
"eval_samples_per_second": 199.624,
|
65 |
+
"eval_steps_per_second": 25.015,
|
66 |
"step": 366
|
67 |
},
|
68 |
{
|
69 |
"epoch": 4.0,
|
70 |
+
"grad_norm": 2.5607471466064453,
|
71 |
"learning_rate": 4e-05,
|
72 |
+
"loss": 0.2886,
|
73 |
"step": 488
|
74 |
},
|
75 |
{
|
76 |
"epoch": 4.0,
|
77 |
"eval_accuracy": 0.8721804511278195,
|
78 |
+
"eval_f1": 0.8430067043674827,
|
79 |
+
"eval_loss": 0.2994827926158905,
|
80 |
+
"eval_precision": 0.8498269896193772,
|
81 |
+
"eval_recall": 0.8370612838697945,
|
82 |
+
"eval_runtime": 2.0374,
|
83 |
+
"eval_samples_per_second": 195.834,
|
84 |
+
"eval_steps_per_second": 24.541,
|
85 |
"step": 488
|
86 |
},
|
87 |
{
|
88 |
"epoch": 5.0,
|
89 |
+
"grad_norm": 2.971632957458496,
|
90 |
"learning_rate": 3.7500000000000003e-05,
|
91 |
+
"loss": 0.2671,
|
92 |
"step": 610
|
93 |
},
|
94 |
{
|
95 |
"epoch": 5.0,
|
96 |
+
"eval_accuracy": 0.8696741854636592,
|
97 |
+
"eval_f1": 0.842789598108747,
|
98 |
+
"eval_loss": 0.29669511318206787,
|
99 |
+
"eval_precision": 0.842789598108747,
|
100 |
+
"eval_recall": 0.842789598108747,
|
101 |
+
"eval_runtime": 2.0319,
|
102 |
+
"eval_samples_per_second": 196.364,
|
103 |
+
"eval_steps_per_second": 24.607,
|
104 |
"step": 610
|
105 |
},
|
106 |
{
|
107 |
"epoch": 6.0,
|
108 |
+
"grad_norm": 4.395784854888916,
|
109 |
"learning_rate": 3.5e-05,
|
110 |
+
"loss": 0.2481,
|
111 |
"step": 732
|
112 |
},
|
113 |
{
|
114 |
"epoch": 6.0,
|
115 |
+
"eval_accuracy": 0.8546365914786967,
|
116 |
+
"eval_f1": 0.8364661654135338,
|
117 |
+
"eval_loss": 0.33456894755363464,
|
118 |
+
"eval_precision": 0.8229932885906039,
|
119 |
+
"eval_recall": 0.8646572104018913,
|
120 |
+
"eval_runtime": 2.0674,
|
121 |
+
"eval_samples_per_second": 192.992,
|
122 |
+
"eval_steps_per_second": 24.184,
|
123 |
"step": 732
|
124 |
},
|
125 |
{
|
126 |
"epoch": 7.0,
|
127 |
+
"grad_norm": 0.19698984920978546,
|
128 |
"learning_rate": 3.2500000000000004e-05,
|
129 |
+
"loss": 0.2339,
|
130 |
"step": 854
|
131 |
},
|
132 |
{
|
133 |
"epoch": 7.0,
|
134 |
+
"eval_accuracy": 0.8671679197994987,
|
135 |
+
"eval_f1": 0.8424651921601347,
|
136 |
+
"eval_loss": 0.2965049147605896,
|
137 |
+
"eval_precision": 0.8372140762463343,
|
138 |
+
"eval_recall": 0.8485179123476996,
|
139 |
+
"eval_runtime": 2.0387,
|
140 |
+
"eval_samples_per_second": 195.713,
|
141 |
+
"eval_steps_per_second": 24.525,
|
142 |
"step": 854
|
143 |
},
|
144 |
{
|
145 |
"epoch": 8.0,
|
146 |
+
"grad_norm": 1.805320143699646,
|
147 |
"learning_rate": 3e-05,
|
148 |
+
"loss": 0.217,
|
149 |
"step": 976
|
150 |
},
|
151 |
{
|
152 |
"epoch": 8.0,
|
153 |
+
"eval_accuracy": 0.8771929824561403,
|
154 |
+
"eval_f1": 0.8483536940081443,
|
155 |
+
"eval_loss": 0.29290771484375,
|
156 |
+
"eval_precision": 0.8575792287132493,
|
157 |
+
"eval_recall": 0.8406073831605747,
|
158 |
+
"eval_runtime": 2.0519,
|
159 |
+
"eval_samples_per_second": 194.45,
|
160 |
+
"eval_steps_per_second": 24.367,
|
161 |
"step": 976
|
162 |
},
|
163 |
{
|
164 |
"epoch": 9.0,
|
165 |
+
"grad_norm": 8.52855396270752,
|
166 |
"learning_rate": 2.7500000000000004e-05,
|
167 |
+
"loss": 0.1984,
|
168 |
"step": 1098
|
169 |
},
|
170 |
{
|
171 |
"epoch": 9.0,
|
172 |
+
"eval_accuracy": 0.8796992481203008,
|
173 |
+
"eval_f1": 0.8533986527862829,
|
174 |
+
"eval_loss": 0.2778124511241913,
|
175 |
+
"eval_precision": 0.8572003218020917,
|
176 |
+
"eval_recall": 0.8498817966903074,
|
177 |
+
"eval_runtime": 2.0595,
|
178 |
+
"eval_samples_per_second": 193.734,
|
179 |
+
"eval_steps_per_second": 24.277,
|
180 |
"step": 1098
|
181 |
},
|
182 |
{
|
183 |
"epoch": 10.0,
|
184 |
+
"grad_norm": 4.634001731872559,
|
185 |
"learning_rate": 2.5e-05,
|
186 |
+
"loss": 0.1937,
|
187 |
"step": 1220
|
188 |
},
|
189 |
{
|
190 |
"epoch": 10.0,
|
191 |
+
"eval_accuracy": 0.8771929824561403,
|
192 |
+
"eval_f1": 0.8458135188208294,
|
193 |
+
"eval_loss": 0.29049694538116455,
|
194 |
+
"eval_precision": 0.8627946127946129,
|
195 |
+
"eval_recall": 0.8331060192762321,
|
196 |
+
"eval_runtime": 2.0594,
|
197 |
+
"eval_samples_per_second": 193.746,
|
198 |
+
"eval_steps_per_second": 24.279,
|
199 |
"step": 1220
|
200 |
},
|
201 |
{
|
202 |
"epoch": 11.0,
|
203 |
+
"grad_norm": 4.496700763702393,
|
204 |
"learning_rate": 2.25e-05,
|
205 |
+
"loss": 0.1734,
|
206 |
"step": 1342
|
207 |
},
|
208 |
{
|
209 |
"epoch": 11.0,
|
210 |
+
"eval_accuracy": 0.8872180451127819,
|
211 |
+
"eval_f1": 0.8649563392675828,
|
212 |
+
"eval_loss": 0.2918776869773865,
|
213 |
+
"eval_precision": 0.8623655913978494,
|
214 |
+
"eval_recall": 0.8677032187670486,
|
215 |
+
"eval_runtime": 2.0871,
|
216 |
+
"eval_samples_per_second": 191.171,
|
217 |
+
"eval_steps_per_second": 23.956,
|
218 |
"step": 1342
|
219 |
},
|
220 |
{
|
221 |
"epoch": 12.0,
|
222 |
+
"grad_norm": 5.332368850708008,
|
223 |
"learning_rate": 2e-05,
|
224 |
+
"loss": 0.1561,
|
225 |
"step": 1464
|
226 |
},
|
227 |
{
|
228 |
"epoch": 12.0,
|
229 |
+
"eval_accuracy": 0.8796992481203008,
|
230 |
+
"eval_f1": 0.8556004584112431,
|
231 |
+
"eval_loss": 0.31261545419692993,
|
232 |
+
"eval_precision": 0.8538865546218487,
|
233 |
+
"eval_recall": 0.85738316057465,
|
234 |
+
"eval_runtime": 2.0745,
|
235 |
+
"eval_samples_per_second": 192.331,
|
236 |
+
"eval_steps_per_second": 24.102,
|
237 |
"step": 1464
|
238 |
},
|
239 |
{
|
240 |
"epoch": 13.0,
|
241 |
+
"grad_norm": 0.6808285713195801,
|
242 |
"learning_rate": 1.75e-05,
|
243 |
+
"loss": 0.1579,
|
244 |
"step": 1586
|
245 |
},
|
246 |
{
|
247 |
"epoch": 13.0,
|
248 |
+
"eval_accuracy": 0.8822055137844611,
|
249 |
+
"eval_f1": 0.8560793854229822,
|
250 |
+
"eval_loss": 0.3164937198162079,
|
251 |
+
"eval_precision": 0.8609538327526132,
|
252 |
+
"eval_recall": 0.8516548463356974,
|
253 |
+
"eval_runtime": 2.07,
|
254 |
+
"eval_samples_per_second": 192.753,
|
255 |
+
"eval_steps_per_second": 24.155,
|
256 |
"step": 1586
|
257 |
},
|
258 |
{
|
259 |
"epoch": 14.0,
|
260 |
+
"grad_norm": 11.75323486328125,
|
261 |
"learning_rate": 1.5e-05,
|
262 |
+
"loss": 0.1459,
|
263 |
"step": 1708
|
264 |
},
|
265 |
{
|
266 |
"epoch": 14.0,
|
267 |
+
"eval_accuracy": 0.8972431077694235,
|
268 |
+
"eval_f1": 0.8787009231453675,
|
269 |
+
"eval_loss": 0.3108453154563904,
|
270 |
+
"eval_precision": 0.8714896214896215,
|
271 |
+
"eval_recall": 0.8872976904891798,
|
272 |
+
"eval_runtime": 2.0849,
|
273 |
+
"eval_samples_per_second": 191.373,
|
274 |
+
"eval_steps_per_second": 23.982,
|
275 |
"step": 1708
|
276 |
},
|
277 |
{
|
278 |
"epoch": 15.0,
|
279 |
+
"grad_norm": 0.21581852436065674,
|
280 |
"learning_rate": 1.25e-05,
|
281 |
+
"loss": 0.1399,
|
282 |
"step": 1830
|
283 |
},
|
284 |
{
|
285 |
"epoch": 15.0,
|
286 |
+
"eval_accuracy": 0.8922305764411027,
|
287 |
+
"eval_f1": 0.8727838950061173,
|
288 |
+
"eval_loss": 0.3192116618156433,
|
289 |
+
"eval_precision": 0.8656898656898657,
|
290 |
+
"eval_recall": 0.8812511365702855,
|
291 |
+
"eval_runtime": 2.0655,
|
292 |
+
"eval_samples_per_second": 193.177,
|
293 |
+
"eval_steps_per_second": 24.208,
|
294 |
"step": 1830
|
295 |
},
|
296 |
{
|
297 |
"epoch": 16.0,
|
298 |
+
"grad_norm": 1.523335337638855,
|
299 |
"learning_rate": 1e-05,
|
300 |
+
"loss": 0.1377,
|
301 |
"step": 1952
|
302 |
},
|
303 |
{
|
304 |
"epoch": 16.0,
|
305 |
+
"eval_accuracy": 0.8847117794486216,
|
306 |
+
"eval_f1": 0.8642214594306682,
|
307 |
+
"eval_loss": 0.32000479102134705,
|
308 |
+
"eval_precision": 0.8566755442334414,
|
309 |
+
"eval_recall": 0.8734315330060011,
|
310 |
+
"eval_runtime": 2.0706,
|
311 |
+
"eval_samples_per_second": 192.702,
|
312 |
+
"eval_steps_per_second": 24.148,
|
313 |
"step": 1952
|
314 |
},
|
315 |
{
|
316 |
"epoch": 17.0,
|
317 |
+
"grad_norm": 9.250269889831543,
|
318 |
"learning_rate": 7.5e-06,
|
319 |
+
"loss": 0.1259,
|
320 |
"step": 2074
|
321 |
},
|
322 |
{
|
323 |
"epoch": 17.0,
|
324 |
+
"eval_accuracy": 0.8847117794486216,
|
325 |
+
"eval_f1": 0.8622899159663866,
|
326 |
+
"eval_loss": 0.3303412199020386,
|
327 |
+
"eval_precision": 0.8589244307033712,
|
328 |
+
"eval_recall": 0.8659301691216585,
|
329 |
+
"eval_runtime": 2.084,
|
330 |
+
"eval_samples_per_second": 191.461,
|
331 |
+
"eval_steps_per_second": 23.993,
|
332 |
"step": 2074
|
333 |
},
|
334 |
{
|
335 |
"epoch": 18.0,
|
336 |
+
"grad_norm": 7.081236362457275,
|
337 |
"learning_rate": 5e-06,
|
338 |
+
"loss": 0.1293,
|
339 |
"step": 2196
|
340 |
},
|
341 |
{
|
342 |
"epoch": 18.0,
|
343 |
+
"eval_accuracy": 0.8922305764411027,
|
344 |
+
"eval_f1": 0.8727838950061173,
|
345 |
+
"eval_loss": 0.3265065848827362,
|
346 |
+
"eval_precision": 0.8656898656898657,
|
347 |
+
"eval_recall": 0.8812511365702855,
|
348 |
+
"eval_runtime": 2.0665,
|
349 |
+
"eval_samples_per_second": 193.079,
|
350 |
+
"eval_steps_per_second": 24.195,
|
351 |
"step": 2196
|
352 |
},
|
353 |
{
|
354 |
"epoch": 19.0,
|
355 |
+
"grad_norm": 1.5093868970870972,
|
356 |
"learning_rate": 2.5e-06,
|
357 |
+
"loss": 0.1187,
|
358 |
"step": 2318
|
359 |
},
|
360 |
{
|
361 |
"epoch": 19.0,
|
362 |
+
"eval_accuracy": 0.8847117794486216,
|
363 |
+
"eval_f1": 0.8622899159663866,
|
364 |
+
"eval_loss": 0.33049851655960083,
|
365 |
+
"eval_precision": 0.8589244307033712,
|
366 |
+
"eval_recall": 0.8659301691216585,
|
367 |
+
"eval_runtime": 2.0389,
|
368 |
+
"eval_samples_per_second": 195.69,
|
369 |
+
"eval_steps_per_second": 24.523,
|
370 |
"step": 2318
|
371 |
},
|
372 |
{
|
373 |
"epoch": 20.0,
|
374 |
+
"grad_norm": 0.4667631983757019,
|
375 |
"learning_rate": 0.0,
|
376 |
+
"loss": 0.1302,
|
377 |
"step": 2440
|
378 |
},
|
379 |
{
|
380 |
"epoch": 20.0,
|
381 |
+
"eval_accuracy": 0.8872180451127819,
|
382 |
+
"eval_f1": 0.8662440310793597,
|
383 |
+
"eval_loss": 0.3288058042526245,
|
384 |
+
"eval_precision": 0.8606158357771261,
|
385 |
+
"eval_recall": 0.872704128023277,
|
386 |
+
"eval_runtime": 2.0647,
|
387 |
+
"eval_samples_per_second": 193.253,
|
388 |
+
"eval_steps_per_second": 24.217,
|
389 |
"step": 2440
|
390 |
},
|
391 |
{
|
392 |
"epoch": 20.0,
|
393 |
"step": 2440,
|
394 |
"total_flos": 8551203605328000.0,
|
395 |
+
"train_loss": 0.2203434850348801,
|
396 |
+
"train_runtime": 746.002,
|
397 |
+
"train_samples_per_second": 97.533,
|
398 |
+
"train_steps_per_second": 3.271
|
399 |
}
|
400 |
],
|
401 |
"logging_steps": 500,
|