./output/gpt2.CEBaB_confounding.food_service_positive.absa.5-class.seed_44
Browse files- all_results.json +16 -0
- eval_results.json +11 -0
- train_results.json +8 -0
- trainer_state.json +433 -0
all_results.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"eval_Macro-F1": 0.7495133845414649,
|
4 |
+
"eval_Weighted-Macro-F1": 0.7542170485338111,
|
5 |
+
"eval_accuracy": 0.7527539779681762,
|
6 |
+
"eval_loss": 0.8418129086494446,
|
7 |
+
"eval_runtime": 19.9766,
|
8 |
+
"eval_samples": 4902,
|
9 |
+
"eval_samples_per_second": 245.386,
|
10 |
+
"eval_steps_per_second": 7.709,
|
11 |
+
"train_loss": 0.4640252302674686,
|
12 |
+
"train_runtime": 266.3348,
|
13 |
+
"train_samples": 4331,
|
14 |
+
"train_samples_per_second": 81.307,
|
15 |
+
"train_steps_per_second": 2.553
|
16 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"eval_Macro-F1": 0.7495133845414649,
|
4 |
+
"eval_Weighted-Macro-F1": 0.7542170485338111,
|
5 |
+
"eval_accuracy": 0.7527539779681762,
|
6 |
+
"eval_loss": 0.8418129086494446,
|
7 |
+
"eval_runtime": 19.9766,
|
8 |
+
"eval_samples": 4902,
|
9 |
+
"eval_samples_per_second": 245.386,
|
10 |
+
"eval_steps_per_second": 7.709
|
11 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"train_loss": 0.4640252302674686,
|
4 |
+
"train_runtime": 266.3348,
|
5 |
+
"train_samples": 4331,
|
6 |
+
"train_samples_per_second": 81.307,
|
7 |
+
"train_steps_per_second": 2.553
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,433 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 5.0,
|
5 |
+
"global_step": 680,
|
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": 1.9705882352941178e-05,
|
13 |
+
"loss": 1.1551,
|
14 |
+
"step": 10
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.15,
|
18 |
+
"learning_rate": 1.9411764705882355e-05,
|
19 |
+
"loss": 1.1371,
|
20 |
+
"step": 20
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.22,
|
24 |
+
"learning_rate": 1.911764705882353e-05,
|
25 |
+
"loss": 1.0677,
|
26 |
+
"step": 30
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.29,
|
30 |
+
"learning_rate": 1.8823529411764708e-05,
|
31 |
+
"loss": 1.0166,
|
32 |
+
"step": 40
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.37,
|
36 |
+
"learning_rate": 1.8529411764705884e-05,
|
37 |
+
"loss": 0.9691,
|
38 |
+
"step": 50
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.44,
|
42 |
+
"learning_rate": 1.823529411764706e-05,
|
43 |
+
"loss": 0.8892,
|
44 |
+
"step": 60
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.51,
|
48 |
+
"learning_rate": 1.7941176470588237e-05,
|
49 |
+
"loss": 0.8899,
|
50 |
+
"step": 70
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.59,
|
54 |
+
"learning_rate": 1.7647058823529414e-05,
|
55 |
+
"loss": 0.7734,
|
56 |
+
"step": 80
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.66,
|
60 |
+
"learning_rate": 1.735294117647059e-05,
|
61 |
+
"loss": 0.6878,
|
62 |
+
"step": 90
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.74,
|
66 |
+
"learning_rate": 1.7058823529411767e-05,
|
67 |
+
"loss": 0.6863,
|
68 |
+
"step": 100
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.81,
|
72 |
+
"learning_rate": 1.6764705882352943e-05,
|
73 |
+
"loss": 0.5821,
|
74 |
+
"step": 110
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.88,
|
78 |
+
"learning_rate": 1.647058823529412e-05,
|
79 |
+
"loss": 0.5557,
|
80 |
+
"step": 120
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.96,
|
84 |
+
"learning_rate": 1.6176470588235296e-05,
|
85 |
+
"loss": 0.6057,
|
86 |
+
"step": 130
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 1.03,
|
90 |
+
"learning_rate": 1.5882352941176473e-05,
|
91 |
+
"loss": 0.5279,
|
92 |
+
"step": 140
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 1.1,
|
96 |
+
"learning_rate": 1.558823529411765e-05,
|
97 |
+
"loss": 0.5189,
|
98 |
+
"step": 150
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 1.18,
|
102 |
+
"learning_rate": 1.5294117647058822e-05,
|
103 |
+
"loss": 0.5309,
|
104 |
+
"step": 160
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 1.25,
|
108 |
+
"learning_rate": 1.5000000000000002e-05,
|
109 |
+
"loss": 0.5113,
|
110 |
+
"step": 170
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 1.32,
|
114 |
+
"learning_rate": 1.4705882352941179e-05,
|
115 |
+
"loss": 0.4926,
|
116 |
+
"step": 180
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 1.4,
|
120 |
+
"learning_rate": 1.4411764705882353e-05,
|
121 |
+
"loss": 0.4805,
|
122 |
+
"step": 190
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 1.47,
|
126 |
+
"learning_rate": 1.4117647058823532e-05,
|
127 |
+
"loss": 0.4077,
|
128 |
+
"step": 200
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 1.54,
|
132 |
+
"learning_rate": 1.3823529411764706e-05,
|
133 |
+
"loss": 0.4727,
|
134 |
+
"step": 210
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 1.62,
|
138 |
+
"learning_rate": 1.3529411764705885e-05,
|
139 |
+
"loss": 0.5212,
|
140 |
+
"step": 220
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 1.69,
|
144 |
+
"learning_rate": 1.323529411764706e-05,
|
145 |
+
"loss": 0.3975,
|
146 |
+
"step": 230
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 1.76,
|
150 |
+
"learning_rate": 1.2941176470588238e-05,
|
151 |
+
"loss": 0.4245,
|
152 |
+
"step": 240
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 1.84,
|
156 |
+
"learning_rate": 1.2647058823529412e-05,
|
157 |
+
"loss": 0.4479,
|
158 |
+
"step": 250
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 1.91,
|
162 |
+
"learning_rate": 1.235294117647059e-05,
|
163 |
+
"loss": 0.4941,
|
164 |
+
"step": 260
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 1.99,
|
168 |
+
"learning_rate": 1.2058823529411765e-05,
|
169 |
+
"loss": 0.4887,
|
170 |
+
"step": 270
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 2.06,
|
174 |
+
"learning_rate": 1.1764705882352942e-05,
|
175 |
+
"loss": 0.4574,
|
176 |
+
"step": 280
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 2.13,
|
180 |
+
"learning_rate": 1.1470588235294118e-05,
|
181 |
+
"loss": 0.4053,
|
182 |
+
"step": 290
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 2.21,
|
186 |
+
"learning_rate": 1.1176470588235295e-05,
|
187 |
+
"loss": 0.3969,
|
188 |
+
"step": 300
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 2.28,
|
192 |
+
"learning_rate": 1.0882352941176471e-05,
|
193 |
+
"loss": 0.3647,
|
194 |
+
"step": 310
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 2.35,
|
198 |
+
"learning_rate": 1.0588235294117648e-05,
|
199 |
+
"loss": 0.4327,
|
200 |
+
"step": 320
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 2.43,
|
204 |
+
"learning_rate": 1.0294117647058823e-05,
|
205 |
+
"loss": 0.3734,
|
206 |
+
"step": 330
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 2.5,
|
210 |
+
"learning_rate": 1e-05,
|
211 |
+
"loss": 0.4301,
|
212 |
+
"step": 340
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 2.57,
|
216 |
+
"learning_rate": 9.705882352941177e-06,
|
217 |
+
"loss": 0.3485,
|
218 |
+
"step": 350
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 2.65,
|
222 |
+
"learning_rate": 9.411764705882354e-06,
|
223 |
+
"loss": 0.3999,
|
224 |
+
"step": 360
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 2.72,
|
228 |
+
"learning_rate": 9.11764705882353e-06,
|
229 |
+
"loss": 0.2864,
|
230 |
+
"step": 370
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 2.79,
|
234 |
+
"learning_rate": 8.823529411764707e-06,
|
235 |
+
"loss": 0.3797,
|
236 |
+
"step": 380
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 2.87,
|
240 |
+
"learning_rate": 8.529411764705883e-06,
|
241 |
+
"loss": 0.3573,
|
242 |
+
"step": 390
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 2.94,
|
246 |
+
"learning_rate": 8.23529411764706e-06,
|
247 |
+
"loss": 0.3832,
|
248 |
+
"step": 400
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 3.01,
|
252 |
+
"learning_rate": 7.941176470588236e-06,
|
253 |
+
"loss": 0.3876,
|
254 |
+
"step": 410
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 3.09,
|
258 |
+
"learning_rate": 7.647058823529411e-06,
|
259 |
+
"loss": 0.3669,
|
260 |
+
"step": 420
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 3.16,
|
264 |
+
"learning_rate": 7.352941176470589e-06,
|
265 |
+
"loss": 0.3032,
|
266 |
+
"step": 430
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 3.24,
|
270 |
+
"learning_rate": 7.058823529411766e-06,
|
271 |
+
"loss": 0.3374,
|
272 |
+
"step": 440
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 3.31,
|
276 |
+
"learning_rate": 6.764705882352942e-06,
|
277 |
+
"loss": 0.3674,
|
278 |
+
"step": 450
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 3.38,
|
282 |
+
"learning_rate": 6.470588235294119e-06,
|
283 |
+
"loss": 0.4074,
|
284 |
+
"step": 460
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 3.46,
|
288 |
+
"learning_rate": 6.176470588235295e-06,
|
289 |
+
"loss": 0.3051,
|
290 |
+
"step": 470
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 3.53,
|
294 |
+
"learning_rate": 5.882352941176471e-06,
|
295 |
+
"loss": 0.3102,
|
296 |
+
"step": 480
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 3.6,
|
300 |
+
"learning_rate": 5.588235294117647e-06,
|
301 |
+
"loss": 0.2872,
|
302 |
+
"step": 490
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 3.68,
|
306 |
+
"learning_rate": 5.294117647058824e-06,
|
307 |
+
"loss": 0.3004,
|
308 |
+
"step": 500
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 3.75,
|
312 |
+
"learning_rate": 5e-06,
|
313 |
+
"loss": 0.3081,
|
314 |
+
"step": 510
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 3.82,
|
318 |
+
"learning_rate": 4.705882352941177e-06,
|
319 |
+
"loss": 0.331,
|
320 |
+
"step": 520
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 3.9,
|
324 |
+
"learning_rate": 4.411764705882353e-06,
|
325 |
+
"loss": 0.2992,
|
326 |
+
"step": 530
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 3.97,
|
330 |
+
"learning_rate": 4.11764705882353e-06,
|
331 |
+
"loss": 0.3127,
|
332 |
+
"step": 540
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 4.04,
|
336 |
+
"learning_rate": 3.8235294117647055e-06,
|
337 |
+
"loss": 0.267,
|
338 |
+
"step": 550
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 4.12,
|
342 |
+
"learning_rate": 3.529411764705883e-06,
|
343 |
+
"loss": 0.3539,
|
344 |
+
"step": 560
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 4.19,
|
348 |
+
"learning_rate": 3.2352941176470594e-06,
|
349 |
+
"loss": 0.2743,
|
350 |
+
"step": 570
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 4.26,
|
354 |
+
"learning_rate": 2.9411764705882355e-06,
|
355 |
+
"loss": 0.3714,
|
356 |
+
"step": 580
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 4.34,
|
360 |
+
"learning_rate": 2.647058823529412e-06,
|
361 |
+
"loss": 0.2308,
|
362 |
+
"step": 590
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 4.41,
|
366 |
+
"learning_rate": 2.3529411764705885e-06,
|
367 |
+
"loss": 0.2479,
|
368 |
+
"step": 600
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 4.49,
|
372 |
+
"learning_rate": 2.058823529411765e-06,
|
373 |
+
"loss": 0.3552,
|
374 |
+
"step": 610
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 4.56,
|
378 |
+
"learning_rate": 1.7647058823529414e-06,
|
379 |
+
"loss": 0.2959,
|
380 |
+
"step": 620
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 4.63,
|
384 |
+
"learning_rate": 1.4705882352941177e-06,
|
385 |
+
"loss": 0.2703,
|
386 |
+
"step": 630
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 4.71,
|
390 |
+
"learning_rate": 1.1764705882352942e-06,
|
391 |
+
"loss": 0.3112,
|
392 |
+
"step": 640
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 4.78,
|
396 |
+
"learning_rate": 8.823529411764707e-07,
|
397 |
+
"loss": 0.3164,
|
398 |
+
"step": 650
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 4.85,
|
402 |
+
"learning_rate": 5.882352941176471e-07,
|
403 |
+
"loss": 0.3118,
|
404 |
+
"step": 660
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 4.93,
|
408 |
+
"learning_rate": 2.9411764705882356e-07,
|
409 |
+
"loss": 0.3163,
|
410 |
+
"step": 670
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 5.0,
|
414 |
+
"learning_rate": 0.0,
|
415 |
+
"loss": 0.2601,
|
416 |
+
"step": 680
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 5.0,
|
420 |
+
"step": 680,
|
421 |
+
"total_flos": 1424430265224960.0,
|
422 |
+
"train_loss": 0.4640252302674686,
|
423 |
+
"train_runtime": 266.3348,
|
424 |
+
"train_samples_per_second": 81.307,
|
425 |
+
"train_steps_per_second": 2.553
|
426 |
+
}
|
427 |
+
],
|
428 |
+
"max_steps": 680,
|
429 |
+
"num_train_epochs": 5,
|
430 |
+
"total_flos": 1424430265224960.0,
|
431 |
+
"trial_name": null,
|
432 |
+
"trial_params": null
|
433 |
+
}
|