End of training
Browse files- all_results.json +7 -0
- train_results.json +7 -0
- trainer_state.json +397 -0
all_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"train_loss": 0.17273353269466987,
|
4 |
+
"train_runtime": 60970.1196,
|
5 |
+
"train_samples_per_second": 1.311,
|
6 |
+
"train_steps_per_second": 0.01
|
7 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"train_loss": 0.17273353269466987,
|
4 |
+
"train_runtime": 60970.1196,
|
5 |
+
"train_samples_per_second": 1.311,
|
6 |
+
"train_steps_per_second": 0.01
|
7 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,397 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.9963985594237696,
|
5 |
+
"global_step": 624,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.0,
|
12 |
+
"learning_rate": 7.936507936507937e-07,
|
13 |
+
"loss": 1.0855,
|
14 |
+
"step": 1
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.06,
|
18 |
+
"learning_rate": 9.523809523809523e-06,
|
19 |
+
"loss": 0.9105,
|
20 |
+
"step": 12
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.12,
|
24 |
+
"learning_rate": 1.9047619047619046e-05,
|
25 |
+
"loss": 0.4616,
|
26 |
+
"step": 24
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.17,
|
30 |
+
"learning_rate": 2.857142857142857e-05,
|
31 |
+
"loss": 0.3415,
|
32 |
+
"step": 36
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.23,
|
36 |
+
"learning_rate": 3.809523809523809e-05,
|
37 |
+
"loss": 0.2655,
|
38 |
+
"step": 48
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.29,
|
42 |
+
"learning_rate": 4.761904761904762e-05,
|
43 |
+
"loss": 0.265,
|
44 |
+
"step": 60
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.35,
|
48 |
+
"learning_rate": 4.919786096256685e-05,
|
49 |
+
"loss": 0.2216,
|
50 |
+
"step": 72
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.4,
|
54 |
+
"learning_rate": 4.8128342245989304e-05,
|
55 |
+
"loss": 0.2317,
|
56 |
+
"step": 84
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.46,
|
60 |
+
"learning_rate": 4.705882352941177e-05,
|
61 |
+
"loss": 0.194,
|
62 |
+
"step": 96
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.52,
|
66 |
+
"learning_rate": 4.598930481283423e-05,
|
67 |
+
"loss": 0.1895,
|
68 |
+
"step": 108
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.58,
|
72 |
+
"learning_rate": 4.491978609625669e-05,
|
73 |
+
"loss": 0.1928,
|
74 |
+
"step": 120
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.63,
|
78 |
+
"learning_rate": 4.385026737967914e-05,
|
79 |
+
"loss": 0.1852,
|
80 |
+
"step": 132
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.69,
|
84 |
+
"learning_rate": 4.2780748663101606e-05,
|
85 |
+
"loss": 0.1881,
|
86 |
+
"step": 144
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.75,
|
90 |
+
"learning_rate": 4.171122994652407e-05,
|
91 |
+
"loss": 0.1763,
|
92 |
+
"step": 156
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.81,
|
96 |
+
"learning_rate": 4.0641711229946525e-05,
|
97 |
+
"loss": 0.1852,
|
98 |
+
"step": 168
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.86,
|
102 |
+
"learning_rate": 3.957219251336899e-05,
|
103 |
+
"loss": 0.1757,
|
104 |
+
"step": 180
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.92,
|
108 |
+
"learning_rate": 3.8502673796791445e-05,
|
109 |
+
"loss": 0.1675,
|
110 |
+
"step": 192
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.98,
|
114 |
+
"learning_rate": 3.743315508021391e-05,
|
115 |
+
"loss": 0.1535,
|
116 |
+
"step": 204
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 1.0,
|
120 |
+
"eval_Macro F1": 0.571105133243632,
|
121 |
+
"eval_Macro Precision": 0.5530940794496672,
|
122 |
+
"eval_Macro Recall": 0.5924688273721617,
|
123 |
+
"eval_Micro F1": 0.9622476495882223,
|
124 |
+
"eval_Micro Precision": 0.9622476495882224,
|
125 |
+
"eval_Micro Recall": 0.9622476495882224,
|
126 |
+
"eval_Weighted F1": 0.9596774503435738,
|
127 |
+
"eval_Weighted Precision": 0.9577464168056835,
|
128 |
+
"eval_Weighted Recall": 0.9622476495882224,
|
129 |
+
"eval_accuracy": 0.9622476495882224,
|
130 |
+
"eval_loss": 0.11255443841218948,
|
131 |
+
"eval_runtime": 2995.4719,
|
132 |
+
"eval_samples_per_second": 4.581,
|
133 |
+
"eval_steps_per_second": 0.143,
|
134 |
+
"step": 208
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 1.04,
|
138 |
+
"learning_rate": 3.6363636363636364e-05,
|
139 |
+
"loss": 0.1777,
|
140 |
+
"step": 216
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 1.09,
|
144 |
+
"learning_rate": 3.529411764705883e-05,
|
145 |
+
"loss": 0.1577,
|
146 |
+
"step": 228
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 1.15,
|
150 |
+
"learning_rate": 3.4224598930481284e-05,
|
151 |
+
"loss": 0.1372,
|
152 |
+
"step": 240
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 1.21,
|
156 |
+
"learning_rate": 3.3155080213903747e-05,
|
157 |
+
"loss": 0.1446,
|
158 |
+
"step": 252
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 1.27,
|
162 |
+
"learning_rate": 3.20855614973262e-05,
|
163 |
+
"loss": 0.1367,
|
164 |
+
"step": 264
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 1.33,
|
168 |
+
"learning_rate": 3.1016042780748666e-05,
|
169 |
+
"loss": 0.1283,
|
170 |
+
"step": 276
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 1.38,
|
174 |
+
"learning_rate": 2.9946524064171122e-05,
|
175 |
+
"loss": 0.1521,
|
176 |
+
"step": 288
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 1.44,
|
180 |
+
"learning_rate": 2.8877005347593582e-05,
|
181 |
+
"loss": 0.1703,
|
182 |
+
"step": 300
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 1.5,
|
186 |
+
"learning_rate": 2.7807486631016045e-05,
|
187 |
+
"loss": 0.1481,
|
188 |
+
"step": 312
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 1.56,
|
192 |
+
"learning_rate": 2.6737967914438505e-05,
|
193 |
+
"loss": 0.1353,
|
194 |
+
"step": 324
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 1.61,
|
198 |
+
"learning_rate": 2.5668449197860968e-05,
|
199 |
+
"loss": 0.1283,
|
200 |
+
"step": 336
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 1.67,
|
204 |
+
"learning_rate": 2.4598930481283424e-05,
|
205 |
+
"loss": 0.1317,
|
206 |
+
"step": 348
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 1.73,
|
210 |
+
"learning_rate": 2.3529411764705884e-05,
|
211 |
+
"loss": 0.1344,
|
212 |
+
"step": 360
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 1.79,
|
216 |
+
"learning_rate": 2.2459893048128343e-05,
|
217 |
+
"loss": 0.12,
|
218 |
+
"step": 372
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 1.84,
|
222 |
+
"learning_rate": 2.1390374331550803e-05,
|
223 |
+
"loss": 0.1232,
|
224 |
+
"step": 384
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 1.9,
|
228 |
+
"learning_rate": 2.0320855614973263e-05,
|
229 |
+
"loss": 0.1463,
|
230 |
+
"step": 396
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 1.96,
|
234 |
+
"learning_rate": 1.9251336898395722e-05,
|
235 |
+
"loss": 0.1195,
|
236 |
+
"step": 408
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 2.0,
|
240 |
+
"eval_Macro F1": 0.8501706517182783,
|
241 |
+
"eval_Macro Precision": 0.9287080582761646,
|
242 |
+
"eval_Macro Recall": 0.8036955912090624,
|
243 |
+
"eval_Micro F1": 0.973835726259019,
|
244 |
+
"eval_Micro Precision": 0.973835726259019,
|
245 |
+
"eval_Micro Recall": 0.973835726259019,
|
246 |
+
"eval_Weighted F1": 0.9735756522364626,
|
247 |
+
"eval_Weighted Precision": 0.9741111567981213,
|
248 |
+
"eval_Weighted Recall": 0.973835726259019,
|
249 |
+
"eval_accuracy": 0.973835726259019,
|
250 |
+
"eval_loss": 0.08434688299894333,
|
251 |
+
"eval_runtime": 2834.0055,
|
252 |
+
"eval_samples_per_second": 4.842,
|
253 |
+
"eval_steps_per_second": 0.151,
|
254 |
+
"step": 416
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 2.02,
|
258 |
+
"learning_rate": 1.8181818181818182e-05,
|
259 |
+
"loss": 0.1102,
|
260 |
+
"step": 420
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 2.07,
|
264 |
+
"learning_rate": 1.7112299465240642e-05,
|
265 |
+
"loss": 0.1248,
|
266 |
+
"step": 432
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 2.13,
|
270 |
+
"learning_rate": 1.60427807486631e-05,
|
271 |
+
"loss": 0.108,
|
272 |
+
"step": 444
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 2.19,
|
276 |
+
"learning_rate": 1.4973262032085561e-05,
|
277 |
+
"loss": 0.118,
|
278 |
+
"step": 456
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 2.25,
|
282 |
+
"learning_rate": 1.3903743315508022e-05,
|
283 |
+
"loss": 0.1131,
|
284 |
+
"step": 468
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 2.3,
|
288 |
+
"learning_rate": 1.2834224598930484e-05,
|
289 |
+
"loss": 0.1177,
|
290 |
+
"step": 480
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 2.36,
|
294 |
+
"learning_rate": 1.1764705882352942e-05,
|
295 |
+
"loss": 0.1409,
|
296 |
+
"step": 492
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 2.42,
|
300 |
+
"learning_rate": 1.0695187165775402e-05,
|
301 |
+
"loss": 0.1261,
|
302 |
+
"step": 504
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 2.48,
|
306 |
+
"learning_rate": 9.625668449197861e-06,
|
307 |
+
"loss": 0.1004,
|
308 |
+
"step": 516
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 2.54,
|
312 |
+
"learning_rate": 8.556149732620321e-06,
|
313 |
+
"loss": 0.1269,
|
314 |
+
"step": 528
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 2.59,
|
318 |
+
"learning_rate": 7.4866310160427806e-06,
|
319 |
+
"loss": 0.1265,
|
320 |
+
"step": 540
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 2.65,
|
324 |
+
"learning_rate": 6.417112299465242e-06,
|
325 |
+
"loss": 0.098,
|
326 |
+
"step": 552
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 2.71,
|
330 |
+
"learning_rate": 5.347593582887701e-06,
|
331 |
+
"loss": 0.126,
|
332 |
+
"step": 564
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 2.77,
|
336 |
+
"learning_rate": 4.2780748663101604e-06,
|
337 |
+
"loss": 0.0876,
|
338 |
+
"step": 576
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 2.82,
|
342 |
+
"learning_rate": 3.208556149732621e-06,
|
343 |
+
"loss": 0.1014,
|
344 |
+
"step": 588
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 2.88,
|
348 |
+
"learning_rate": 2.1390374331550802e-06,
|
349 |
+
"loss": 0.1111,
|
350 |
+
"step": 600
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 2.94,
|
354 |
+
"learning_rate": 1.0695187165775401e-06,
|
355 |
+
"loss": 0.1361,
|
356 |
+
"step": 612
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 3.0,
|
360 |
+
"learning_rate": 0.0,
|
361 |
+
"loss": 0.0979,
|
362 |
+
"step": 624
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 3.0,
|
366 |
+
"eval_Macro F1": 0.9154020288755031,
|
367 |
+
"eval_Macro Precision": 0.9314436651998532,
|
368 |
+
"eval_Macro Recall": 0.9019139504496776,
|
369 |
+
"eval_Micro F1": 0.976678084687705,
|
370 |
+
"eval_Micro Precision": 0.976678084687705,
|
371 |
+
"eval_Micro Recall": 0.976678084687705,
|
372 |
+
"eval_Weighted F1": 0.9768442651021538,
|
373 |
+
"eval_Weighted Precision": 0.9771017843393915,
|
374 |
+
"eval_Weighted Recall": 0.976678084687705,
|
375 |
+
"eval_accuracy": 0.976678084687705,
|
376 |
+
"eval_loss": 0.07859531044960022,
|
377 |
+
"eval_runtime": 3028.7856,
|
378 |
+
"eval_samples_per_second": 4.53,
|
379 |
+
"eval_steps_per_second": 0.142,
|
380 |
+
"step": 624
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 3.0,
|
384 |
+
"step": 624,
|
385 |
+
"total_flos": 6.186805817770303e+18,
|
386 |
+
"train_loss": 0.17273353269466987,
|
387 |
+
"train_runtime": 60970.1196,
|
388 |
+
"train_samples_per_second": 1.311,
|
389 |
+
"train_steps_per_second": 0.01
|
390 |
+
}
|
391 |
+
],
|
392 |
+
"max_steps": 624,
|
393 |
+
"num_train_epochs": 3,
|
394 |
+
"total_flos": 6.186805817770303e+18,
|
395 |
+
"trial_name": null,
|
396 |
+
"trial_params": null
|
397 |
+
}
|