./output/gpt2.CEBaB_confounding.food_service_positive.absa.5-class.seed_43
Browse files- all_results.json +16 -0
- eval_results.json +11 -0
- train_results.json +8 -0
- trainer_state.json +427 -0
all_results.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"eval_Macro-F1": 0.7651102213573747,
|
4 |
+
"eval_Weighted-Macro-F1": 0.7691539102859193,
|
5 |
+
"eval_accuracy": 0.7688698490412077,
|
6 |
+
"eval_loss": 0.8080414533615112,
|
7 |
+
"eval_runtime": 19.8924,
|
8 |
+
"eval_samples": 4902,
|
9 |
+
"eval_samples_per_second": 246.426,
|
10 |
+
"eval_steps_per_second": 7.742,
|
11 |
+
"train_loss": 0.49670425315401445,
|
12 |
+
"train_runtime": 261.2142,
|
13 |
+
"train_samples": 4258,
|
14 |
+
"train_samples_per_second": 81.504,
|
15 |
+
"train_steps_per_second": 2.565
|
16 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"eval_Macro-F1": 0.7651102213573747,
|
4 |
+
"eval_Weighted-Macro-F1": 0.7691539102859193,
|
5 |
+
"eval_accuracy": 0.7688698490412077,
|
6 |
+
"eval_loss": 0.8080414533615112,
|
7 |
+
"eval_runtime": 19.8924,
|
8 |
+
"eval_samples": 4902,
|
9 |
+
"eval_samples_per_second": 246.426,
|
10 |
+
"eval_steps_per_second": 7.742
|
11 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"train_loss": 0.49670425315401445,
|
4 |
+
"train_runtime": 261.2142,
|
5 |
+
"train_samples": 4258,
|
6 |
+
"train_samples_per_second": 81.504,
|
7 |
+
"train_steps_per_second": 2.565
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,427 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 5.0,
|
5 |
+
"global_step": 670,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.07,
|
12 |
+
"learning_rate": 1.9701492537313435e-05,
|
13 |
+
"loss": 1.1334,
|
14 |
+
"step": 10
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.15,
|
18 |
+
"learning_rate": 1.9402985074626868e-05,
|
19 |
+
"loss": 1.1003,
|
20 |
+
"step": 20
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.22,
|
24 |
+
"learning_rate": 1.9104477611940298e-05,
|
25 |
+
"loss": 1.0769,
|
26 |
+
"step": 30
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.3,
|
30 |
+
"learning_rate": 1.8805970149253735e-05,
|
31 |
+
"loss": 1.0546,
|
32 |
+
"step": 40
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.37,
|
36 |
+
"learning_rate": 1.8507462686567165e-05,
|
37 |
+
"loss": 1.0465,
|
38 |
+
"step": 50
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.45,
|
42 |
+
"learning_rate": 1.8208955223880598e-05,
|
43 |
+
"loss": 0.9684,
|
44 |
+
"step": 60
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.52,
|
48 |
+
"learning_rate": 1.791044776119403e-05,
|
49 |
+
"loss": 0.9276,
|
50 |
+
"step": 70
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.6,
|
54 |
+
"learning_rate": 1.7611940298507464e-05,
|
55 |
+
"loss": 0.8279,
|
56 |
+
"step": 80
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.67,
|
60 |
+
"learning_rate": 1.7313432835820894e-05,
|
61 |
+
"loss": 0.816,
|
62 |
+
"step": 90
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.75,
|
66 |
+
"learning_rate": 1.701492537313433e-05,
|
67 |
+
"loss": 0.7778,
|
68 |
+
"step": 100
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.82,
|
72 |
+
"learning_rate": 1.671641791044776e-05,
|
73 |
+
"loss": 0.7261,
|
74 |
+
"step": 110
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.9,
|
78 |
+
"learning_rate": 1.6417910447761197e-05,
|
79 |
+
"loss": 0.7208,
|
80 |
+
"step": 120
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.97,
|
84 |
+
"learning_rate": 1.6119402985074627e-05,
|
85 |
+
"loss": 0.6404,
|
86 |
+
"step": 130
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 1.04,
|
90 |
+
"learning_rate": 1.582089552238806e-05,
|
91 |
+
"loss": 0.6556,
|
92 |
+
"step": 140
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 1.12,
|
96 |
+
"learning_rate": 1.5522388059701494e-05,
|
97 |
+
"loss": 0.6484,
|
98 |
+
"step": 150
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 1.19,
|
102 |
+
"learning_rate": 1.5223880597014925e-05,
|
103 |
+
"loss": 0.6387,
|
104 |
+
"step": 160
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 1.27,
|
108 |
+
"learning_rate": 1.492537313432836e-05,
|
109 |
+
"loss": 0.545,
|
110 |
+
"step": 170
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 1.34,
|
114 |
+
"learning_rate": 1.4626865671641792e-05,
|
115 |
+
"loss": 0.5693,
|
116 |
+
"step": 180
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 1.42,
|
120 |
+
"learning_rate": 1.4328358208955224e-05,
|
121 |
+
"loss": 0.4667,
|
122 |
+
"step": 190
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 1.49,
|
126 |
+
"learning_rate": 1.4029850746268658e-05,
|
127 |
+
"loss": 0.5243,
|
128 |
+
"step": 200
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 1.57,
|
132 |
+
"learning_rate": 1.373134328358209e-05,
|
133 |
+
"loss": 0.4737,
|
134 |
+
"step": 210
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 1.64,
|
138 |
+
"learning_rate": 1.3432835820895525e-05,
|
139 |
+
"loss": 0.4586,
|
140 |
+
"step": 220
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 1.72,
|
144 |
+
"learning_rate": 1.3134328358208957e-05,
|
145 |
+
"loss": 0.4561,
|
146 |
+
"step": 230
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 1.79,
|
150 |
+
"learning_rate": 1.2835820895522388e-05,
|
151 |
+
"loss": 0.5476,
|
152 |
+
"step": 240
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 1.87,
|
156 |
+
"learning_rate": 1.2537313432835823e-05,
|
157 |
+
"loss": 0.4314,
|
158 |
+
"step": 250
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 1.94,
|
162 |
+
"learning_rate": 1.2238805970149255e-05,
|
163 |
+
"loss": 0.4875,
|
164 |
+
"step": 260
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 2.01,
|
168 |
+
"learning_rate": 1.1940298507462686e-05,
|
169 |
+
"loss": 0.5459,
|
170 |
+
"step": 270
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 2.09,
|
174 |
+
"learning_rate": 1.1641791044776121e-05,
|
175 |
+
"loss": 0.4429,
|
176 |
+
"step": 280
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 2.16,
|
180 |
+
"learning_rate": 1.1343283582089553e-05,
|
181 |
+
"loss": 0.3935,
|
182 |
+
"step": 290
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 2.24,
|
186 |
+
"learning_rate": 1.1044776119402986e-05,
|
187 |
+
"loss": 0.4531,
|
188 |
+
"step": 300
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 2.31,
|
192 |
+
"learning_rate": 1.074626865671642e-05,
|
193 |
+
"loss": 0.3705,
|
194 |
+
"step": 310
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 2.39,
|
198 |
+
"learning_rate": 1.0447761194029851e-05,
|
199 |
+
"loss": 0.3925,
|
200 |
+
"step": 320
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 2.46,
|
204 |
+
"learning_rate": 1.0149253731343284e-05,
|
205 |
+
"loss": 0.4739,
|
206 |
+
"step": 330
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 2.54,
|
210 |
+
"learning_rate": 9.850746268656717e-06,
|
211 |
+
"loss": 0.3975,
|
212 |
+
"step": 340
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 2.61,
|
216 |
+
"learning_rate": 9.552238805970149e-06,
|
217 |
+
"loss": 0.4335,
|
218 |
+
"step": 350
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 2.69,
|
222 |
+
"learning_rate": 9.253731343283582e-06,
|
223 |
+
"loss": 0.443,
|
224 |
+
"step": 360
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 2.76,
|
228 |
+
"learning_rate": 8.955223880597016e-06,
|
229 |
+
"loss": 0.3843,
|
230 |
+
"step": 370
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 2.84,
|
234 |
+
"learning_rate": 8.656716417910447e-06,
|
235 |
+
"loss": 0.333,
|
236 |
+
"step": 380
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 2.91,
|
240 |
+
"learning_rate": 8.35820895522388e-06,
|
241 |
+
"loss": 0.3555,
|
242 |
+
"step": 390
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 2.99,
|
246 |
+
"learning_rate": 8.059701492537314e-06,
|
247 |
+
"loss": 0.39,
|
248 |
+
"step": 400
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 3.06,
|
252 |
+
"learning_rate": 7.761194029850747e-06,
|
253 |
+
"loss": 0.3848,
|
254 |
+
"step": 410
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 3.13,
|
258 |
+
"learning_rate": 7.46268656716418e-06,
|
259 |
+
"loss": 0.3658,
|
260 |
+
"step": 420
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 3.21,
|
264 |
+
"learning_rate": 7.164179104477612e-06,
|
265 |
+
"loss": 0.3329,
|
266 |
+
"step": 430
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 3.28,
|
270 |
+
"learning_rate": 6.865671641791045e-06,
|
271 |
+
"loss": 0.4015,
|
272 |
+
"step": 440
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 3.36,
|
276 |
+
"learning_rate": 6.567164179104478e-06,
|
277 |
+
"loss": 0.3598,
|
278 |
+
"step": 450
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 3.43,
|
282 |
+
"learning_rate": 6.2686567164179116e-06,
|
283 |
+
"loss": 0.3306,
|
284 |
+
"step": 460
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 3.51,
|
288 |
+
"learning_rate": 5.970149253731343e-06,
|
289 |
+
"loss": 0.3427,
|
290 |
+
"step": 470
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 3.58,
|
294 |
+
"learning_rate": 5.671641791044776e-06,
|
295 |
+
"loss": 0.2763,
|
296 |
+
"step": 480
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 3.66,
|
300 |
+
"learning_rate": 5.37313432835821e-06,
|
301 |
+
"loss": 0.3242,
|
302 |
+
"step": 490
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 3.73,
|
306 |
+
"learning_rate": 5.074626865671642e-06,
|
307 |
+
"loss": 0.3514,
|
308 |
+
"step": 500
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 3.81,
|
312 |
+
"learning_rate": 4.7761194029850745e-06,
|
313 |
+
"loss": 0.3407,
|
314 |
+
"step": 510
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 3.88,
|
318 |
+
"learning_rate": 4.477611940298508e-06,
|
319 |
+
"loss": 0.3108,
|
320 |
+
"step": 520
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 3.96,
|
324 |
+
"learning_rate": 4.17910447761194e-06,
|
325 |
+
"loss": 0.3061,
|
326 |
+
"step": 530
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 4.03,
|
330 |
+
"learning_rate": 3.8805970149253735e-06,
|
331 |
+
"loss": 0.3153,
|
332 |
+
"step": 540
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 4.1,
|
336 |
+
"learning_rate": 3.582089552238806e-06,
|
337 |
+
"loss": 0.2951,
|
338 |
+
"step": 550
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 4.18,
|
342 |
+
"learning_rate": 3.283582089552239e-06,
|
343 |
+
"loss": 0.3297,
|
344 |
+
"step": 560
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 4.25,
|
348 |
+
"learning_rate": 2.9850746268656716e-06,
|
349 |
+
"loss": 0.339,
|
350 |
+
"step": 570
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 4.33,
|
354 |
+
"learning_rate": 2.686567164179105e-06,
|
355 |
+
"loss": 0.3228,
|
356 |
+
"step": 580
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 4.4,
|
360 |
+
"learning_rate": 2.3880597014925373e-06,
|
361 |
+
"loss": 0.2971,
|
362 |
+
"step": 590
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 4.48,
|
366 |
+
"learning_rate": 2.08955223880597e-06,
|
367 |
+
"loss": 0.3168,
|
368 |
+
"step": 600
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 4.55,
|
372 |
+
"learning_rate": 1.791044776119403e-06,
|
373 |
+
"loss": 0.2814,
|
374 |
+
"step": 610
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 4.63,
|
378 |
+
"learning_rate": 1.4925373134328358e-06,
|
379 |
+
"loss": 0.276,
|
380 |
+
"step": 620
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 4.7,
|
384 |
+
"learning_rate": 1.1940298507462686e-06,
|
385 |
+
"loss": 0.2376,
|
386 |
+
"step": 630
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 4.78,
|
390 |
+
"learning_rate": 8.955223880597015e-07,
|
391 |
+
"loss": 0.2764,
|
392 |
+
"step": 640
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 4.85,
|
396 |
+
"learning_rate": 5.970149253731343e-07,
|
397 |
+
"loss": 0.2799,
|
398 |
+
"step": 650
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 4.93,
|
402 |
+
"learning_rate": 2.9850746268656716e-07,
|
403 |
+
"loss": 0.3265,
|
404 |
+
"step": 660
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 5.0,
|
408 |
+
"learning_rate": 0.0,
|
409 |
+
"loss": 0.4295,
|
410 |
+
"step": 670
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 5.0,
|
414 |
+
"step": 670,
|
415 |
+
"total_flos": 1400421165857280.0,
|
416 |
+
"train_loss": 0.49670425315401445,
|
417 |
+
"train_runtime": 261.2142,
|
418 |
+
"train_samples_per_second": 81.504,
|
419 |
+
"train_steps_per_second": 2.565
|
420 |
+
}
|
421 |
+
],
|
422 |
+
"max_steps": 670,
|
423 |
+
"num_train_epochs": 5,
|
424 |
+
"total_flos": 1400421165857280.0,
|
425 |
+
"trial_name": null,
|
426 |
+
"trial_params": null
|
427 |
+
}
|