./output/gpt2.CEBaB_confounding.food_service_positive.absa.5-class.seed_42
Browse files- all_results.json +16 -0
- eval_results.json +11 -0
- train_results.json +8 -0
- trainer_state.json +421 -0
all_results.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"eval_Macro-F1": 0.7699582479575997,
|
4 |
+
"eval_Weighted-Macro-F1": 0.7739568344973068,
|
5 |
+
"eval_accuracy": 0.7733578131374949,
|
6 |
+
"eval_loss": 0.7406646609306335,
|
7 |
+
"eval_runtime": 19.9292,
|
8 |
+
"eval_samples": 4902,
|
9 |
+
"eval_samples_per_second": 245.971,
|
10 |
+
"eval_steps_per_second": 7.727,
|
11 |
+
"train_loss": 0.48537510767915193,
|
12 |
+
"train_runtime": 260.1502,
|
13 |
+
"train_samples": 4228,
|
14 |
+
"train_samples_per_second": 81.261,
|
15 |
+
"train_steps_per_second": 2.556
|
16 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"eval_Macro-F1": 0.7699582479575997,
|
4 |
+
"eval_Weighted-Macro-F1": 0.7739568344973068,
|
5 |
+
"eval_accuracy": 0.7733578131374949,
|
6 |
+
"eval_loss": 0.7406646609306335,
|
7 |
+
"eval_runtime": 19.9292,
|
8 |
+
"eval_samples": 4902,
|
9 |
+
"eval_samples_per_second": 245.971,
|
10 |
+
"eval_steps_per_second": 7.727
|
11 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"train_loss": 0.48537510767915193,
|
4 |
+
"train_runtime": 260.1502,
|
5 |
+
"train_samples": 4228,
|
6 |
+
"train_samples_per_second": 81.261,
|
7 |
+
"train_steps_per_second": 2.556
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,421 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 5.0,
|
5 |
+
"global_step": 665,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.08,
|
12 |
+
"learning_rate": 1.9699248120300753e-05,
|
13 |
+
"loss": 1.1917,
|
14 |
+
"step": 10
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.15,
|
18 |
+
"learning_rate": 1.9398496240601504e-05,
|
19 |
+
"loss": 1.1026,
|
20 |
+
"step": 20
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.23,
|
24 |
+
"learning_rate": 1.909774436090226e-05,
|
25 |
+
"loss": 1.0748,
|
26 |
+
"step": 30
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.3,
|
30 |
+
"learning_rate": 1.879699248120301e-05,
|
31 |
+
"loss": 1.0498,
|
32 |
+
"step": 40
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.38,
|
36 |
+
"learning_rate": 1.849624060150376e-05,
|
37 |
+
"loss": 1.0187,
|
38 |
+
"step": 50
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.45,
|
42 |
+
"learning_rate": 1.8195488721804512e-05,
|
43 |
+
"loss": 0.98,
|
44 |
+
"step": 60
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.53,
|
48 |
+
"learning_rate": 1.7894736842105264e-05,
|
49 |
+
"loss": 0.9141,
|
50 |
+
"step": 70
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.6,
|
54 |
+
"learning_rate": 1.7593984962406015e-05,
|
55 |
+
"loss": 0.8803,
|
56 |
+
"step": 80
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.68,
|
60 |
+
"learning_rate": 1.729323308270677e-05,
|
61 |
+
"loss": 0.8601,
|
62 |
+
"step": 90
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.75,
|
66 |
+
"learning_rate": 1.699248120300752e-05,
|
67 |
+
"loss": 0.8136,
|
68 |
+
"step": 100
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.83,
|
72 |
+
"learning_rate": 1.6691729323308272e-05,
|
73 |
+
"loss": 0.7096,
|
74 |
+
"step": 110
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.9,
|
78 |
+
"learning_rate": 1.6390977443609023e-05,
|
79 |
+
"loss": 0.7317,
|
80 |
+
"step": 120
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.98,
|
84 |
+
"learning_rate": 1.6090225563909775e-05,
|
85 |
+
"loss": 0.6692,
|
86 |
+
"step": 130
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 1.05,
|
90 |
+
"learning_rate": 1.578947368421053e-05,
|
91 |
+
"loss": 0.6096,
|
92 |
+
"step": 140
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 1.13,
|
96 |
+
"learning_rate": 1.548872180451128e-05,
|
97 |
+
"loss": 0.5641,
|
98 |
+
"step": 150
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 1.2,
|
102 |
+
"learning_rate": 1.5187969924812032e-05,
|
103 |
+
"loss": 0.4964,
|
104 |
+
"step": 160
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 1.28,
|
108 |
+
"learning_rate": 1.4887218045112783e-05,
|
109 |
+
"loss": 0.5387,
|
110 |
+
"step": 170
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 1.35,
|
114 |
+
"learning_rate": 1.4586466165413536e-05,
|
115 |
+
"loss": 0.5217,
|
116 |
+
"step": 180
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 1.43,
|
120 |
+
"learning_rate": 1.4285714285714287e-05,
|
121 |
+
"loss": 0.5162,
|
122 |
+
"step": 190
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 1.5,
|
126 |
+
"learning_rate": 1.3984962406015038e-05,
|
127 |
+
"loss": 0.5539,
|
128 |
+
"step": 200
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 1.58,
|
132 |
+
"learning_rate": 1.3684210526315791e-05,
|
133 |
+
"loss": 0.5228,
|
134 |
+
"step": 210
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 1.65,
|
138 |
+
"learning_rate": 1.3383458646616543e-05,
|
139 |
+
"loss": 0.4894,
|
140 |
+
"step": 220
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 1.73,
|
144 |
+
"learning_rate": 1.3082706766917295e-05,
|
145 |
+
"loss": 0.4383,
|
146 |
+
"step": 230
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 1.8,
|
150 |
+
"learning_rate": 1.2781954887218047e-05,
|
151 |
+
"loss": 0.4828,
|
152 |
+
"step": 240
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 1.88,
|
156 |
+
"learning_rate": 1.2481203007518798e-05,
|
157 |
+
"loss": 0.4547,
|
158 |
+
"step": 250
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 1.95,
|
162 |
+
"learning_rate": 1.2180451127819551e-05,
|
163 |
+
"loss": 0.4474,
|
164 |
+
"step": 260
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 2.03,
|
168 |
+
"learning_rate": 1.1879699248120302e-05,
|
169 |
+
"loss": 0.4464,
|
170 |
+
"step": 270
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 2.11,
|
174 |
+
"learning_rate": 1.1578947368421053e-05,
|
175 |
+
"loss": 0.3985,
|
176 |
+
"step": 280
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 2.18,
|
180 |
+
"learning_rate": 1.1278195488721806e-05,
|
181 |
+
"loss": 0.4307,
|
182 |
+
"step": 290
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 2.26,
|
186 |
+
"learning_rate": 1.0977443609022558e-05,
|
187 |
+
"loss": 0.3886,
|
188 |
+
"step": 300
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 2.33,
|
192 |
+
"learning_rate": 1.0676691729323309e-05,
|
193 |
+
"loss": 0.3797,
|
194 |
+
"step": 310
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 2.41,
|
198 |
+
"learning_rate": 1.0375939849624062e-05,
|
199 |
+
"loss": 0.4167,
|
200 |
+
"step": 320
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 2.48,
|
204 |
+
"learning_rate": 1.0075187969924813e-05,
|
205 |
+
"loss": 0.3893,
|
206 |
+
"step": 330
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 2.56,
|
210 |
+
"learning_rate": 9.774436090225564e-06,
|
211 |
+
"loss": 0.3829,
|
212 |
+
"step": 340
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 2.63,
|
216 |
+
"learning_rate": 9.473684210526315e-06,
|
217 |
+
"loss": 0.3509,
|
218 |
+
"step": 350
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 2.71,
|
222 |
+
"learning_rate": 9.172932330827068e-06,
|
223 |
+
"loss": 0.3744,
|
224 |
+
"step": 360
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 2.78,
|
228 |
+
"learning_rate": 8.87218045112782e-06,
|
229 |
+
"loss": 0.3572,
|
230 |
+
"step": 370
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 2.86,
|
234 |
+
"learning_rate": 8.571428571428571e-06,
|
235 |
+
"loss": 0.3117,
|
236 |
+
"step": 380
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 2.93,
|
240 |
+
"learning_rate": 8.270676691729324e-06,
|
241 |
+
"loss": 0.3674,
|
242 |
+
"step": 390
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 3.01,
|
246 |
+
"learning_rate": 7.969924812030075e-06,
|
247 |
+
"loss": 0.4052,
|
248 |
+
"step": 400
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 3.08,
|
252 |
+
"learning_rate": 7.669172932330828e-06,
|
253 |
+
"loss": 0.3358,
|
254 |
+
"step": 410
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 3.16,
|
258 |
+
"learning_rate": 7.368421052631579e-06,
|
259 |
+
"loss": 0.3145,
|
260 |
+
"step": 420
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 3.23,
|
264 |
+
"learning_rate": 7.067669172932331e-06,
|
265 |
+
"loss": 0.2775,
|
266 |
+
"step": 430
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 3.31,
|
270 |
+
"learning_rate": 6.766917293233083e-06,
|
271 |
+
"loss": 0.3636,
|
272 |
+
"step": 440
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 3.38,
|
276 |
+
"learning_rate": 6.466165413533835e-06,
|
277 |
+
"loss": 0.3496,
|
278 |
+
"step": 450
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 3.46,
|
282 |
+
"learning_rate": 6.165413533834587e-06,
|
283 |
+
"loss": 0.3813,
|
284 |
+
"step": 460
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 3.53,
|
288 |
+
"learning_rate": 5.864661654135339e-06,
|
289 |
+
"loss": 0.3815,
|
290 |
+
"step": 470
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 3.61,
|
294 |
+
"learning_rate": 5.56390977443609e-06,
|
295 |
+
"loss": 0.3607,
|
296 |
+
"step": 480
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 3.68,
|
300 |
+
"learning_rate": 5.263157894736842e-06,
|
301 |
+
"loss": 0.3558,
|
302 |
+
"step": 490
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 3.76,
|
306 |
+
"learning_rate": 4.962406015037594e-06,
|
307 |
+
"loss": 0.3188,
|
308 |
+
"step": 500
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 3.83,
|
312 |
+
"learning_rate": 4.661654135338346e-06,
|
313 |
+
"loss": 0.3371,
|
314 |
+
"step": 510
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 3.91,
|
318 |
+
"learning_rate": 4.360902255639098e-06,
|
319 |
+
"loss": 0.2918,
|
320 |
+
"step": 520
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 3.98,
|
324 |
+
"learning_rate": 4.06015037593985e-06,
|
325 |
+
"loss": 0.2726,
|
326 |
+
"step": 530
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 4.06,
|
330 |
+
"learning_rate": 3.7593984962406014e-06,
|
331 |
+
"loss": 0.2971,
|
332 |
+
"step": 540
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 4.14,
|
336 |
+
"learning_rate": 3.4586466165413535e-06,
|
337 |
+
"loss": 0.2796,
|
338 |
+
"step": 550
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 4.21,
|
342 |
+
"learning_rate": 3.157894736842105e-06,
|
343 |
+
"loss": 0.2947,
|
344 |
+
"step": 560
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 4.29,
|
348 |
+
"learning_rate": 2.8571428571428573e-06,
|
349 |
+
"loss": 0.3396,
|
350 |
+
"step": 570
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 4.36,
|
354 |
+
"learning_rate": 2.556390977443609e-06,
|
355 |
+
"loss": 0.2181,
|
356 |
+
"step": 580
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 4.44,
|
360 |
+
"learning_rate": 2.255639097744361e-06,
|
361 |
+
"loss": 0.3021,
|
362 |
+
"step": 590
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 4.51,
|
366 |
+
"learning_rate": 1.9548872180451127e-06,
|
367 |
+
"loss": 0.3,
|
368 |
+
"step": 600
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 4.59,
|
372 |
+
"learning_rate": 1.6541353383458648e-06,
|
373 |
+
"loss": 0.2801,
|
374 |
+
"step": 610
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 4.66,
|
378 |
+
"learning_rate": 1.3533834586466167e-06,
|
379 |
+
"loss": 0.2505,
|
380 |
+
"step": 620
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 4.74,
|
384 |
+
"learning_rate": 1.0526315789473685e-06,
|
385 |
+
"loss": 0.288,
|
386 |
+
"step": 630
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 4.81,
|
390 |
+
"learning_rate": 7.518796992481203e-07,
|
391 |
+
"loss": 0.2711,
|
392 |
+
"step": 640
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 4.89,
|
396 |
+
"learning_rate": 4.511278195488722e-07,
|
397 |
+
"loss": 0.3521,
|
398 |
+
"step": 650
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 4.96,
|
402 |
+
"learning_rate": 1.5037593984962406e-07,
|
403 |
+
"loss": 0.3088,
|
404 |
+
"step": 660
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 5.0,
|
408 |
+
"step": 665,
|
409 |
+
"total_flos": 1390554412692480.0,
|
410 |
+
"train_loss": 0.48537510767915193,
|
411 |
+
"train_runtime": 260.1502,
|
412 |
+
"train_samples_per_second": 81.261,
|
413 |
+
"train_steps_per_second": 2.556
|
414 |
+
}
|
415 |
+
],
|
416 |
+
"max_steps": 665,
|
417 |
+
"num_train_epochs": 5,
|
418 |
+
"total_flos": 1390554412692480.0,
|
419 |
+
"trial_name": null,
|
420 |
+
"trial_params": null
|
421 |
+
}
|