End of training
Browse files- README.md +2 -0
- all_results.json +6 -6
- eval_results.json +3 -3
- predict_results.json +6 -0
- runs/May25_12-26-28_indolem-petl-vm/events.out.tfevents.1716642699.indolem-petl-vm.2175139.1 +3 -0
- train_results.json +3 -3
- trainer_state.json +63 -63
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
@@ -6,16 +6,16 @@
|
|
6 |
"eval_loss": 0.8104944229125977,
|
7 |
"eval_precision": 0.8827677592299257,
|
8 |
"eval_recall": 0.8808419712675032,
|
9 |
-
"eval_runtime": 4.
|
10 |
"eval_samples": 399,
|
11 |
-
"eval_samples_per_second": 84.
|
12 |
-
"eval_steps_per_second": 10.
|
13 |
"f1": 0.8920886346170267,
|
14 |
"precision": 0.8953297623033144,
|
15 |
"recall": 0.8890334817436486,
|
16 |
"train_loss": 0.05662053943168922,
|
17 |
-
"train_runtime":
|
18 |
"train_samples": 3638,
|
19 |
-
"train_samples_per_second":
|
20 |
-
"train_steps_per_second": 0.
|
21 |
}
|
|
|
6 |
"eval_loss": 0.8104944229125977,
|
7 |
"eval_precision": 0.8827677592299257,
|
8 |
"eval_recall": 0.8808419712675032,
|
9 |
+
"eval_runtime": 4.7093,
|
10 |
"eval_samples": 399,
|
11 |
+
"eval_samples_per_second": 84.725,
|
12 |
+
"eval_steps_per_second": 10.617,
|
13 |
"f1": 0.8920886346170267,
|
14 |
"precision": 0.8953297623033144,
|
15 |
"recall": 0.8890334817436486,
|
16 |
"train_loss": 0.05662053943168922,
|
17 |
+
"train_runtime": 2686.8503,
|
18 |
"train_samples": 3638,
|
19 |
+
"train_samples_per_second": 27.08,
|
20 |
+
"train_steps_per_second": 0.908
|
21 |
}
|
eval_results.json
CHANGED
@@ -5,8 +5,8 @@
|
|
5 |
"eval_loss": 0.8104944229125977,
|
6 |
"eval_precision": 0.8827677592299257,
|
7 |
"eval_recall": 0.8808419712675032,
|
8 |
-
"eval_runtime": 4.
|
9 |
"eval_samples": 399,
|
10 |
-
"eval_samples_per_second": 84.
|
11 |
-
"eval_steps_per_second": 10.
|
12 |
}
|
|
|
5 |
"eval_loss": 0.8104944229125977,
|
6 |
"eval_precision": 0.8827677592299257,
|
7 |
"eval_recall": 0.8808419712675032,
|
8 |
+
"eval_runtime": 4.7093,
|
9 |
"eval_samples": 399,
|
10 |
+
"eval_samples_per_second": 84.725,
|
11 |
+
"eval_steps_per_second": 10.617
|
12 |
}
|
predict_results.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"accuracy": 0.9109792284866469,
|
3 |
+
"f1": 0.8920886346170267,
|
4 |
+
"precision": 0.8953297623033144,
|
5 |
+
"recall": 0.8890334817436486
|
6 |
+
}
|
runs/May25_12-26-28_indolem-petl-vm/events.out.tfevents.1716642699.indolem-petl-vm.2175139.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:36cb90b1bfb7cd01947a58958f42738513dd30727d9669df8160093723248ba6
|
3 |
+
size 560
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 20.0,
|
3 |
"train_loss": 0.05662053943168922,
|
4 |
-
"train_runtime":
|
5 |
"train_samples": 3638,
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 20.0,
|
3 |
"train_loss": 0.05662053943168922,
|
4 |
+
"train_runtime": 2686.8503,
|
5 |
"train_samples": 3638,
|
6 |
+
"train_samples_per_second": 27.08,
|
7 |
+
"train_steps_per_second": 0.908
|
8 |
}
|
trainer_state.json
CHANGED
@@ -22,9 +22,9 @@
|
|
22 |
"eval_loss": 0.35864609479904175,
|
23 |
"eval_precision": 0.8892469089546646,
|
24 |
"eval_recall": 0.8148754318967084,
|
25 |
-
"eval_runtime": 4.
|
26 |
-
"eval_samples_per_second":
|
27 |
-
"eval_steps_per_second": 10.
|
28 |
"step": 122
|
29 |
},
|
30 |
{
|
@@ -41,9 +41,9 @@
|
|
41 |
"eval_loss": 0.36683306097984314,
|
42 |
"eval_precision": 0.8394707327494125,
|
43 |
"eval_recall": 0.8852973267866885,
|
44 |
-
"eval_runtime": 4.
|
45 |
-
"eval_samples_per_second":
|
46 |
-
"eval_steps_per_second": 10.
|
47 |
"step": 244
|
48 |
},
|
49 |
{
|
@@ -60,9 +60,9 @@
|
|
60 |
"eval_loss": 0.4554330110549927,
|
61 |
"eval_precision": 0.8632157235517781,
|
62 |
"eval_recall": 0.8937534097108566,
|
63 |
-
"eval_runtime": 4.
|
64 |
-
"eval_samples_per_second": 80.
|
65 |
-
"eval_steps_per_second": 10.
|
66 |
"step": 366
|
67 |
},
|
68 |
{
|
@@ -79,9 +79,9 @@
|
|
79 |
"eval_loss": 0.44412538409233093,
|
80 |
"eval_precision": 0.8956662848415425,
|
81 |
"eval_recall": 0.8768867066739408,
|
82 |
-
"eval_runtime": 4.
|
83 |
-
"eval_samples_per_second": 80.
|
84 |
-
"eval_steps_per_second": 10.
|
85 |
"step": 488
|
86 |
},
|
87 |
{
|
@@ -98,9 +98,9 @@
|
|
98 |
"eval_loss": 0.4922772943973541,
|
99 |
"eval_precision": 0.8880654743486602,
|
100 |
"eval_recall": 0.880114566284779,
|
101 |
-
"eval_runtime": 4.
|
102 |
-
"eval_samples_per_second":
|
103 |
-
"eval_steps_per_second": 10.
|
104 |
"step": 610
|
105 |
},
|
106 |
{
|
@@ -117,9 +117,9 @@
|
|
117 |
"eval_loss": 0.6796092391014099,
|
118 |
"eval_precision": 0.8748029197080291,
|
119 |
"eval_recall": 0.8890707401345699,
|
120 |
-
"eval_runtime": 4.
|
121 |
-
"eval_samples_per_second": 80.
|
122 |
-
"eval_steps_per_second": 10.
|
123 |
"step": 732
|
124 |
},
|
125 |
{
|
@@ -136,9 +136,9 @@
|
|
136 |
"eval_loss": 0.5746134519577026,
|
137 |
"eval_precision": 0.8934835488413775,
|
138 |
"eval_recall": 0.8726132024004365,
|
139 |
-
"eval_runtime": 4.
|
140 |
-
"eval_samples_per_second": 80.
|
141 |
-
"eval_steps_per_second": 10.
|
142 |
"step": 854
|
143 |
},
|
144 |
{
|
@@ -155,9 +155,9 @@
|
|
155 |
"eval_loss": 0.5952700972557068,
|
156 |
"eval_precision": 0.8718487394957983,
|
157 |
"eval_recall": 0.8755228223313329,
|
158 |
-
"eval_runtime": 4.
|
159 |
-
"eval_samples_per_second": 80.
|
160 |
-
"eval_steps_per_second": 10.
|
161 |
"step": 976
|
162 |
},
|
163 |
{
|
@@ -174,9 +174,9 @@
|
|
174 |
"eval_loss": 0.6506014466285706,
|
175 |
"eval_precision": 0.8891156462585035,
|
176 |
"eval_recall": 0.864066193853428,
|
177 |
-
"eval_runtime": 4.
|
178 |
-
"eval_samples_per_second": 80.
|
179 |
-
"eval_steps_per_second": 10.
|
180 |
"step": 1098
|
181 |
},
|
182 |
{
|
@@ -193,9 +193,9 @@
|
|
193 |
"eval_loss": 0.6854431629180908,
|
194 |
"eval_precision": 0.8814464081066409,
|
195 |
"eval_recall": 0.8833424258956174,
|
196 |
-
"eval_runtime": 4.
|
197 |
-
"eval_samples_per_second": 80.
|
198 |
-
"eval_steps_per_second": 10.
|
199 |
"step": 1220
|
200 |
},
|
201 |
{
|
@@ -212,9 +212,9 @@
|
|
212 |
"eval_loss": 0.7218220829963684,
|
213 |
"eval_precision": 0.8814464081066409,
|
214 |
"eval_recall": 0.8833424258956174,
|
215 |
-
"eval_runtime": 4.
|
216 |
-
"eval_samples_per_second": 80.
|
217 |
-
"eval_steps_per_second": 10.
|
218 |
"step": 1342
|
219 |
},
|
220 |
{
|
@@ -231,9 +231,9 @@
|
|
231 |
"eval_loss": 0.7694610357284546,
|
232 |
"eval_precision": 0.8814464081066409,
|
233 |
"eval_recall": 0.8833424258956174,
|
234 |
-
"eval_runtime": 4.
|
235 |
-
"eval_samples_per_second":
|
236 |
-
"eval_steps_per_second": 10.
|
237 |
"step": 1464
|
238 |
},
|
239 |
{
|
@@ -250,9 +250,9 @@
|
|
250 |
"eval_loss": 0.9004446268081665,
|
251 |
"eval_precision": 0.849624060150376,
|
252 |
"eval_recall": 0.8748863429714493,
|
253 |
-
"eval_runtime": 4.
|
254 |
-
"eval_samples_per_second": 80.
|
255 |
-
"eval_steps_per_second": 10.
|
256 |
"step": 1586
|
257 |
},
|
258 |
{
|
@@ -269,9 +269,9 @@
|
|
269 |
"eval_loss": 0.7978267073631287,
|
270 |
"eval_precision": 0.8791501449961532,
|
271 |
"eval_recall": 0.8883433351518457,
|
272 |
-
"eval_runtime": 4.
|
273 |
-
"eval_samples_per_second": 80.
|
274 |
-
"eval_steps_per_second": 10.
|
275 |
"step": 1708
|
276 |
},
|
277 |
{
|
@@ -288,9 +288,9 @@
|
|
288 |
"eval_loss": 0.8251467943191528,
|
289 |
"eval_precision": 0.8790689216221131,
|
290 |
"eval_recall": 0.8790689216221131,
|
291 |
-
"eval_runtime": 4.
|
292 |
-
"eval_samples_per_second": 80.
|
293 |
-
"eval_steps_per_second": 10.
|
294 |
"step": 1830
|
295 |
},
|
296 |
{
|
@@ -307,9 +307,9 @@
|
|
307 |
"eval_loss": 0.7715300917625427,
|
308 |
"eval_precision": 0.8814464081066409,
|
309 |
"eval_recall": 0.8833424258956174,
|
310 |
-
"eval_runtime": 4.
|
311 |
-
"eval_samples_per_second": 80.
|
312 |
-
"eval_steps_per_second": 10.
|
313 |
"step": 1952
|
314 |
},
|
315 |
{
|
@@ -326,9 +326,9 @@
|
|
326 |
"eval_loss": 0.7821339964866638,
|
327 |
"eval_precision": 0.89198606271777,
|
328 |
"eval_recall": 0.8818876159301692,
|
329 |
-
"eval_runtime": 4.
|
330 |
-
"eval_samples_per_second": 80.
|
331 |
-
"eval_steps_per_second": 10.
|
332 |
"step": 2074
|
333 |
},
|
334 |
{
|
@@ -345,9 +345,9 @@
|
|
345 |
"eval_loss": 0.8211472630500793,
|
346 |
"eval_precision": 0.8754297605404427,
|
347 |
"eval_recall": 0.877295871976723,
|
348 |
-
"eval_runtime": 4.
|
349 |
-
"eval_samples_per_second": 80.
|
350 |
-
"eval_steps_per_second": 10.
|
351 |
"step": 2196
|
352 |
},
|
353 |
{
|
@@ -364,9 +364,9 @@
|
|
364 |
"eval_loss": 0.8161725401878357,
|
365 |
"eval_precision": 0.8790689216221131,
|
366 |
"eval_recall": 0.8790689216221131,
|
367 |
-
"eval_runtime": 4.
|
368 |
-
"eval_samples_per_second": 80.
|
369 |
-
"eval_steps_per_second": 10.
|
370 |
"step": 2318
|
371 |
},
|
372 |
{
|
@@ -383,9 +383,9 @@
|
|
383 |
"eval_loss": 0.8104944229125977,
|
384 |
"eval_precision": 0.8827677592299257,
|
385 |
"eval_recall": 0.8808419712675032,
|
386 |
-
"eval_runtime": 4.
|
387 |
-
"eval_samples_per_second": 80.
|
388 |
-
"eval_steps_per_second": 10.
|
389 |
"step": 2440
|
390 |
},
|
391 |
{
|
@@ -393,9 +393,9 @@
|
|
393 |
"step": 2440,
|
394 |
"total_flos": 7584162436176000.0,
|
395 |
"train_loss": 0.05662053943168922,
|
396 |
-
"train_runtime":
|
397 |
-
"train_samples_per_second":
|
398 |
-
"train_steps_per_second": 0.
|
399 |
}
|
400 |
],
|
401 |
"logging_steps": 500,
|
|
|
22 |
"eval_loss": 0.35864609479904175,
|
23 |
"eval_precision": 0.8892469089546646,
|
24 |
"eval_recall": 0.8148754318967084,
|
25 |
+
"eval_runtime": 4.8207,
|
26 |
+
"eval_samples_per_second": 82.769,
|
27 |
+
"eval_steps_per_second": 10.372,
|
28 |
"step": 122
|
29 |
},
|
30 |
{
|
|
|
41 |
"eval_loss": 0.36683306097984314,
|
42 |
"eval_precision": 0.8394707327494125,
|
43 |
"eval_recall": 0.8852973267866885,
|
44 |
+
"eval_runtime": 4.9471,
|
45 |
+
"eval_samples_per_second": 80.653,
|
46 |
+
"eval_steps_per_second": 10.107,
|
47 |
"step": 244
|
48 |
},
|
49 |
{
|
|
|
60 |
"eval_loss": 0.4554330110549927,
|
61 |
"eval_precision": 0.8632157235517781,
|
62 |
"eval_recall": 0.8937534097108566,
|
63 |
+
"eval_runtime": 4.9562,
|
64 |
+
"eval_samples_per_second": 80.505,
|
65 |
+
"eval_steps_per_second": 10.088,
|
66 |
"step": 366
|
67 |
},
|
68 |
{
|
|
|
79 |
"eval_loss": 0.44412538409233093,
|
80 |
"eval_precision": 0.8956662848415425,
|
81 |
"eval_recall": 0.8768867066739408,
|
82 |
+
"eval_runtime": 4.9565,
|
83 |
+
"eval_samples_per_second": 80.5,
|
84 |
+
"eval_steps_per_second": 10.088,
|
85 |
"step": 488
|
86 |
},
|
87 |
{
|
|
|
98 |
"eval_loss": 0.4922772943973541,
|
99 |
"eval_precision": 0.8880654743486602,
|
100 |
"eval_recall": 0.880114566284779,
|
101 |
+
"eval_runtime": 4.9305,
|
102 |
+
"eval_samples_per_second": 80.925,
|
103 |
+
"eval_steps_per_second": 10.141,
|
104 |
"step": 610
|
105 |
},
|
106 |
{
|
|
|
117 |
"eval_loss": 0.6796092391014099,
|
118 |
"eval_precision": 0.8748029197080291,
|
119 |
"eval_recall": 0.8890707401345699,
|
120 |
+
"eval_runtime": 4.9528,
|
121 |
+
"eval_samples_per_second": 80.56,
|
122 |
+
"eval_steps_per_second": 10.095,
|
123 |
"step": 732
|
124 |
},
|
125 |
{
|
|
|
136 |
"eval_loss": 0.5746134519577026,
|
137 |
"eval_precision": 0.8934835488413775,
|
138 |
"eval_recall": 0.8726132024004365,
|
139 |
+
"eval_runtime": 4.962,
|
140 |
+
"eval_samples_per_second": 80.411,
|
141 |
+
"eval_steps_per_second": 10.077,
|
142 |
"step": 854
|
143 |
},
|
144 |
{
|
|
|
155 |
"eval_loss": 0.5952700972557068,
|
156 |
"eval_precision": 0.8718487394957983,
|
157 |
"eval_recall": 0.8755228223313329,
|
158 |
+
"eval_runtime": 4.9497,
|
159 |
+
"eval_samples_per_second": 80.612,
|
160 |
+
"eval_steps_per_second": 10.102,
|
161 |
"step": 976
|
162 |
},
|
163 |
{
|
|
|
174 |
"eval_loss": 0.6506014466285706,
|
175 |
"eval_precision": 0.8891156462585035,
|
176 |
"eval_recall": 0.864066193853428,
|
177 |
+
"eval_runtime": 4.9626,
|
178 |
+
"eval_samples_per_second": 80.401,
|
179 |
+
"eval_steps_per_second": 10.075,
|
180 |
"step": 1098
|
181 |
},
|
182 |
{
|
|
|
193 |
"eval_loss": 0.6854431629180908,
|
194 |
"eval_precision": 0.8814464081066409,
|
195 |
"eval_recall": 0.8833424258956174,
|
196 |
+
"eval_runtime": 4.945,
|
197 |
+
"eval_samples_per_second": 80.688,
|
198 |
+
"eval_steps_per_second": 10.111,
|
199 |
"step": 1220
|
200 |
},
|
201 |
{
|
|
|
212 |
"eval_loss": 0.7218220829963684,
|
213 |
"eval_precision": 0.8814464081066409,
|
214 |
"eval_recall": 0.8833424258956174,
|
215 |
+
"eval_runtime": 4.9612,
|
216 |
+
"eval_samples_per_second": 80.424,
|
217 |
+
"eval_steps_per_second": 10.078,
|
218 |
"step": 1342
|
219 |
},
|
220 |
{
|
|
|
231 |
"eval_loss": 0.7694610357284546,
|
232 |
"eval_precision": 0.8814464081066409,
|
233 |
"eval_recall": 0.8833424258956174,
|
234 |
+
"eval_runtime": 4.9888,
|
235 |
+
"eval_samples_per_second": 79.98,
|
236 |
+
"eval_steps_per_second": 10.023,
|
237 |
"step": 1464
|
238 |
},
|
239 |
{
|
|
|
250 |
"eval_loss": 0.9004446268081665,
|
251 |
"eval_precision": 0.849624060150376,
|
252 |
"eval_recall": 0.8748863429714493,
|
253 |
+
"eval_runtime": 4.9345,
|
254 |
+
"eval_samples_per_second": 80.86,
|
255 |
+
"eval_steps_per_second": 10.133,
|
256 |
"step": 1586
|
257 |
},
|
258 |
{
|
|
|
269 |
"eval_loss": 0.7978267073631287,
|
270 |
"eval_precision": 0.8791501449961532,
|
271 |
"eval_recall": 0.8883433351518457,
|
272 |
+
"eval_runtime": 4.9323,
|
273 |
+
"eval_samples_per_second": 80.895,
|
274 |
+
"eval_steps_per_second": 10.137,
|
275 |
"step": 1708
|
276 |
},
|
277 |
{
|
|
|
288 |
"eval_loss": 0.8251467943191528,
|
289 |
"eval_precision": 0.8790689216221131,
|
290 |
"eval_recall": 0.8790689216221131,
|
291 |
+
"eval_runtime": 4.9785,
|
292 |
+
"eval_samples_per_second": 80.144,
|
293 |
+
"eval_steps_per_second": 10.043,
|
294 |
"step": 1830
|
295 |
},
|
296 |
{
|
|
|
307 |
"eval_loss": 0.7715300917625427,
|
308 |
"eval_precision": 0.8814464081066409,
|
309 |
"eval_recall": 0.8833424258956174,
|
310 |
+
"eval_runtime": 4.9483,
|
311 |
+
"eval_samples_per_second": 80.634,
|
312 |
+
"eval_steps_per_second": 10.104,
|
313 |
"step": 1952
|
314 |
},
|
315 |
{
|
|
|
326 |
"eval_loss": 0.7821339964866638,
|
327 |
"eval_precision": 0.89198606271777,
|
328 |
"eval_recall": 0.8818876159301692,
|
329 |
+
"eval_runtime": 4.951,
|
330 |
+
"eval_samples_per_second": 80.589,
|
331 |
+
"eval_steps_per_second": 10.099,
|
332 |
"step": 2074
|
333 |
},
|
334 |
{
|
|
|
345 |
"eval_loss": 0.8211472630500793,
|
346 |
"eval_precision": 0.8754297605404427,
|
347 |
"eval_recall": 0.877295871976723,
|
348 |
+
"eval_runtime": 4.9494,
|
349 |
+
"eval_samples_per_second": 80.616,
|
350 |
+
"eval_steps_per_second": 10.102,
|
351 |
"step": 2196
|
352 |
},
|
353 |
{
|
|
|
364 |
"eval_loss": 0.8161725401878357,
|
365 |
"eval_precision": 0.8790689216221131,
|
366 |
"eval_recall": 0.8790689216221131,
|
367 |
+
"eval_runtime": 4.9488,
|
368 |
+
"eval_samples_per_second": 80.626,
|
369 |
+
"eval_steps_per_second": 10.104,
|
370 |
"step": 2318
|
371 |
},
|
372 |
{
|
|
|
383 |
"eval_loss": 0.8104944229125977,
|
384 |
"eval_precision": 0.8827677592299257,
|
385 |
"eval_recall": 0.8808419712675032,
|
386 |
+
"eval_runtime": 4.9834,
|
387 |
+
"eval_samples_per_second": 80.065,
|
388 |
+
"eval_steps_per_second": 10.033,
|
389 |
"step": 2440
|
390 |
},
|
391 |
{
|
|
|
393 |
"step": 2440,
|
394 |
"total_flos": 7584162436176000.0,
|
395 |
"train_loss": 0.05662053943168922,
|
396 |
+
"train_runtime": 2686.8503,
|
397 |
+
"train_samples_per_second": 27.08,
|
398 |
+
"train_steps_per_second": 0.908
|
399 |
}
|
400 |
],
|
401 |
"logging_steps": 500,
|