All Dunn!!!
Browse files- all_results.json +7 -0
- train_results.json +7 -0
- trainer_state.json +715 -0
all_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"train_loss": 0.5799241374931839,
|
4 |
+
"train_runtime": 32322.6365,
|
5 |
+
"train_samples_per_second": 12.916,
|
6 |
+
"train_steps_per_second": 1.615
|
7 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"train_loss": 0.5799241374931839,
|
4 |
+
"train_runtime": 32322.6365,
|
5 |
+
"train_samples_per_second": 12.916,
|
6 |
+
"train_steps_per_second": 1.615
|
7 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,715 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 5.0,
|
5 |
+
"global_step": 52190,
|
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": 0.000999980839241234,
|
13 |
+
"loss": 0.7834,
|
14 |
+
"step": 1
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.05,
|
18 |
+
"learning_rate": 0.0009899980839241235,
|
19 |
+
"loss": 0.7384,
|
20 |
+
"step": 522
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.1,
|
24 |
+
"learning_rate": 0.000979996167848247,
|
25 |
+
"loss": 0.7597,
|
26 |
+
"step": 1044
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.15,
|
30 |
+
"learning_rate": 0.0009699942517723703,
|
31 |
+
"loss": 0.7401,
|
32 |
+
"step": 1566
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.2,
|
36 |
+
"learning_rate": 0.0009599923356964936,
|
37 |
+
"loss": 0.7495,
|
38 |
+
"step": 2088
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.25,
|
42 |
+
"learning_rate": 0.000949990419620617,
|
43 |
+
"loss": 0.7017,
|
44 |
+
"step": 2610
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.3,
|
48 |
+
"learning_rate": 0.0009399885035447404,
|
49 |
+
"loss": 0.7398,
|
50 |
+
"step": 3132
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.35,
|
54 |
+
"learning_rate": 0.0009299865874688638,
|
55 |
+
"loss": 0.6949,
|
56 |
+
"step": 3654
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.4,
|
60 |
+
"learning_rate": 0.0009199846713929871,
|
61 |
+
"loss": 0.6335,
|
62 |
+
"step": 4176
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.45,
|
66 |
+
"learning_rate": 0.0009099827553171107,
|
67 |
+
"loss": 0.648,
|
68 |
+
"step": 4698
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.5,
|
72 |
+
"learning_rate": 0.000899980839241234,
|
73 |
+
"loss": 0.6445,
|
74 |
+
"step": 5220
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.55,
|
78 |
+
"learning_rate": 0.0008899789231653573,
|
79 |
+
"loss": 0.6429,
|
80 |
+
"step": 5742
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.6,
|
84 |
+
"learning_rate": 0.0008799770070894808,
|
85 |
+
"loss": 0.6316,
|
86 |
+
"step": 6264
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.65,
|
90 |
+
"learning_rate": 0.0008699750910136041,
|
91 |
+
"loss": 0.6066,
|
92 |
+
"step": 6786
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.7,
|
96 |
+
"learning_rate": 0.0008599731749377275,
|
97 |
+
"loss": 0.6397,
|
98 |
+
"step": 7308
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.75,
|
102 |
+
"learning_rate": 0.0008499712588618509,
|
103 |
+
"loss": 0.6243,
|
104 |
+
"step": 7830
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.8,
|
108 |
+
"learning_rate": 0.0008399693427859744,
|
109 |
+
"loss": 0.6271,
|
110 |
+
"step": 8352
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.85,
|
114 |
+
"learning_rate": 0.0008299674267100977,
|
115 |
+
"loss": 0.614,
|
116 |
+
"step": 8874
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.9,
|
120 |
+
"learning_rate": 0.0008199655106342211,
|
121 |
+
"loss": 0.6358,
|
122 |
+
"step": 9396
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.95,
|
126 |
+
"learning_rate": 0.0008099635945583445,
|
127 |
+
"loss": 0.633,
|
128 |
+
"step": 9918
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 1.0,
|
132 |
+
"eval_Macro F1": 0.5744881635875178,
|
133 |
+
"eval_Macro Precision": 0.6541570568719827,
|
134 |
+
"eval_Macro Recall": 0.564346253205228,
|
135 |
+
"eval_Micro F1": 0.826105701864693,
|
136 |
+
"eval_Micro Precision": 0.826105701864693,
|
137 |
+
"eval_Micro Recall": 0.826105701864693,
|
138 |
+
"eval_Weighted F1": 0.7913544313349856,
|
139 |
+
"eval_Weighted Precision": 0.7843732666581203,
|
140 |
+
"eval_Weighted Recall": 0.826105701864693,
|
141 |
+
"eval_accuracy": 0.826105701864693,
|
142 |
+
"eval_loss": 0.5608153343200684,
|
143 |
+
"eval_runtime": 2136.2944,
|
144 |
+
"eval_samples_per_second": 13.029,
|
145 |
+
"eval_steps_per_second": 1.629,
|
146 |
+
"step": 10438
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 1.0,
|
150 |
+
"learning_rate": 0.0007999616784824679,
|
151 |
+
"loss": 0.6139,
|
152 |
+
"step": 10440
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 1.05,
|
156 |
+
"learning_rate": 0.0007899597624065913,
|
157 |
+
"loss": 0.5945,
|
158 |
+
"step": 10962
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 1.1,
|
162 |
+
"learning_rate": 0.0007799578463307148,
|
163 |
+
"loss": 0.6018,
|
164 |
+
"step": 11484
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 1.15,
|
168 |
+
"learning_rate": 0.0007699559302548381,
|
169 |
+
"loss": 0.597,
|
170 |
+
"step": 12006
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 1.2,
|
174 |
+
"learning_rate": 0.0007599540141789615,
|
175 |
+
"loss": 0.5891,
|
176 |
+
"step": 12528
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 1.25,
|
180 |
+
"learning_rate": 0.0007499520981030848,
|
181 |
+
"loss": 0.6139,
|
182 |
+
"step": 13050
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 1.3,
|
186 |
+
"learning_rate": 0.0007399501820272084,
|
187 |
+
"loss": 0.5878,
|
188 |
+
"step": 13572
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 1.35,
|
192 |
+
"learning_rate": 0.0007299482659513317,
|
193 |
+
"loss": 0.6183,
|
194 |
+
"step": 14094
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 1.4,
|
198 |
+
"learning_rate": 0.0007199463498754551,
|
199 |
+
"loss": 0.6038,
|
200 |
+
"step": 14616
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 1.45,
|
204 |
+
"learning_rate": 0.0007099444337995785,
|
205 |
+
"loss": 0.6506,
|
206 |
+
"step": 15138
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 1.5,
|
210 |
+
"learning_rate": 0.0006999425177237019,
|
211 |
+
"loss": 0.6063,
|
212 |
+
"step": 15660
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 1.55,
|
216 |
+
"learning_rate": 0.0006899406016478252,
|
217 |
+
"loss": 0.5931,
|
218 |
+
"step": 16182
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 1.6,
|
222 |
+
"learning_rate": 0.0006799386855719488,
|
223 |
+
"loss": 0.5828,
|
224 |
+
"step": 16704
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 1.65,
|
228 |
+
"learning_rate": 0.0006699367694960721,
|
229 |
+
"loss": 0.5912,
|
230 |
+
"step": 17226
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 1.7,
|
234 |
+
"learning_rate": 0.0006599348534201954,
|
235 |
+
"loss": 0.6105,
|
236 |
+
"step": 17748
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 1.75,
|
240 |
+
"learning_rate": 0.0006499329373443188,
|
241 |
+
"loss": 0.5893,
|
242 |
+
"step": 18270
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 1.8,
|
246 |
+
"learning_rate": 0.0006399310212684422,
|
247 |
+
"loss": 0.611,
|
248 |
+
"step": 18792
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 1.85,
|
252 |
+
"learning_rate": 0.0006299291051925656,
|
253 |
+
"loss": 0.6371,
|
254 |
+
"step": 19314
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 1.9,
|
258 |
+
"learning_rate": 0.000619927189116689,
|
259 |
+
"loss": 0.5925,
|
260 |
+
"step": 19836
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 1.95,
|
264 |
+
"learning_rate": 0.0006099252730408125,
|
265 |
+
"loss": 0.6029,
|
266 |
+
"step": 20358
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 2.0,
|
270 |
+
"eval_Macro F1": 0.5060450221643912,
|
271 |
+
"eval_Macro Precision": 0.6929448637916937,
|
272 |
+
"eval_Macro Recall": 0.5239477514921818,
|
273 |
+
"eval_Micro F1": 0.8330758452197032,
|
274 |
+
"eval_Micro Precision": 0.8330758452197032,
|
275 |
+
"eval_Micro Recall": 0.8330758452197032,
|
276 |
+
"eval_Weighted F1": 0.7724263350491593,
|
277 |
+
"eval_Weighted Precision": 0.7892310862523967,
|
278 |
+
"eval_Weighted Recall": 0.8330758452197032,
|
279 |
+
"eval_accuracy": 0.8330758452197032,
|
280 |
+
"eval_loss": 0.6489848494529724,
|
281 |
+
"eval_runtime": 1320.9895,
|
282 |
+
"eval_samples_per_second": 21.07,
|
283 |
+
"eval_steps_per_second": 2.634,
|
284 |
+
"step": 20876
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 2.0,
|
288 |
+
"learning_rate": 0.0005999233569649358,
|
289 |
+
"loss": 0.5882,
|
290 |
+
"step": 20880
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 2.05,
|
294 |
+
"learning_rate": 0.0005899214408890592,
|
295 |
+
"loss": 0.5831,
|
296 |
+
"step": 21402
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 2.1,
|
300 |
+
"learning_rate": 0.0005799195248131826,
|
301 |
+
"loss": 0.5755,
|
302 |
+
"step": 21924
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 2.15,
|
306 |
+
"learning_rate": 0.000569917608737306,
|
307 |
+
"loss": 0.5822,
|
308 |
+
"step": 22446
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 2.2,
|
312 |
+
"learning_rate": 0.0005599156926614294,
|
313 |
+
"loss": 0.5632,
|
314 |
+
"step": 22968
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 2.25,
|
318 |
+
"learning_rate": 0.0005499137765855528,
|
319 |
+
"loss": 0.5756,
|
320 |
+
"step": 23490
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 2.3,
|
324 |
+
"learning_rate": 0.0005399118605096762,
|
325 |
+
"loss": 0.6018,
|
326 |
+
"step": 24012
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 2.35,
|
330 |
+
"learning_rate": 0.0005299099444337996,
|
331 |
+
"loss": 0.5978,
|
332 |
+
"step": 24534
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 2.4,
|
336 |
+
"learning_rate": 0.0005199080283579229,
|
337 |
+
"loss": 0.5767,
|
338 |
+
"step": 25056
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 2.45,
|
342 |
+
"learning_rate": 0.0005099061122820464,
|
343 |
+
"loss": 0.5538,
|
344 |
+
"step": 25578
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 2.5,
|
348 |
+
"learning_rate": 0.0004999041962061698,
|
349 |
+
"loss": 0.5621,
|
350 |
+
"step": 26100
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 2.55,
|
354 |
+
"learning_rate": 0.0004899022801302932,
|
355 |
+
"loss": 0.594,
|
356 |
+
"step": 26622
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 2.6,
|
360 |
+
"learning_rate": 0.00047990036405441656,
|
361 |
+
"loss": 0.5616,
|
362 |
+
"step": 27144
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 2.65,
|
366 |
+
"learning_rate": 0.00046989844797853996,
|
367 |
+
"loss": 0.5444,
|
368 |
+
"step": 27666
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 2.7,
|
372 |
+
"learning_rate": 0.00045989653190266336,
|
373 |
+
"loss": 0.5558,
|
374 |
+
"step": 28188
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 2.75,
|
378 |
+
"learning_rate": 0.00044989461582678675,
|
379 |
+
"loss": 0.5415,
|
380 |
+
"step": 28710
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 2.8,
|
384 |
+
"learning_rate": 0.0004398926997509101,
|
385 |
+
"loss": 0.5452,
|
386 |
+
"step": 29232
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 2.85,
|
390 |
+
"learning_rate": 0.00042989078367503355,
|
391 |
+
"loss": 0.5595,
|
392 |
+
"step": 29754
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 2.9,
|
396 |
+
"learning_rate": 0.00041988886759915695,
|
397 |
+
"loss": 0.565,
|
398 |
+
"step": 30276
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 2.95,
|
402 |
+
"learning_rate": 0.0004098869515232803,
|
403 |
+
"loss": 0.5478,
|
404 |
+
"step": 30798
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 3.0,
|
408 |
+
"eval_Macro F1": 0.6188634906559709,
|
409 |
+
"eval_Macro Precision": 0.6783819638851676,
|
410 |
+
"eval_Macro Recall": 0.6003398559173716,
|
411 |
+
"eval_Micro F1": 0.8304530593180757,
|
412 |
+
"eval_Micro Precision": 0.8304530593180757,
|
413 |
+
"eval_Micro Recall": 0.8304530593180757,
|
414 |
+
"eval_Weighted F1": 0.8070780134214183,
|
415 |
+
"eval_Weighted Precision": 0.8001960025950923,
|
416 |
+
"eval_Weighted Recall": 0.8304530593180757,
|
417 |
+
"eval_accuracy": 0.8304530593180757,
|
418 |
+
"eval_loss": 0.5508156418800354,
|
419 |
+
"eval_runtime": 1285.8765,
|
420 |
+
"eval_samples_per_second": 21.645,
|
421 |
+
"eval_steps_per_second": 2.706,
|
422 |
+
"step": 31314
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 3.0,
|
426 |
+
"learning_rate": 0.00039988503544740374,
|
427 |
+
"loss": 0.5593,
|
428 |
+
"step": 31320
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 3.05,
|
432 |
+
"learning_rate": 0.0003898831193715271,
|
433 |
+
"loss": 0.5348,
|
434 |
+
"step": 31842
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 3.1,
|
438 |
+
"learning_rate": 0.0003798812032956505,
|
439 |
+
"loss": 0.5459,
|
440 |
+
"step": 32364
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 3.15,
|
444 |
+
"learning_rate": 0.00036987928721977394,
|
445 |
+
"loss": 0.5544,
|
446 |
+
"step": 32886
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 3.2,
|
450 |
+
"learning_rate": 0.0003598773711438973,
|
451 |
+
"loss": 0.5442,
|
452 |
+
"step": 33408
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 3.25,
|
456 |
+
"learning_rate": 0.00034987545506802074,
|
457 |
+
"loss": 0.542,
|
458 |
+
"step": 33930
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 3.3,
|
462 |
+
"learning_rate": 0.0003398735389921441,
|
463 |
+
"loss": 0.5325,
|
464 |
+
"step": 34452
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 3.35,
|
468 |
+
"learning_rate": 0.0003298716229162675,
|
469 |
+
"loss": 0.5525,
|
470 |
+
"step": 34974
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 3.4,
|
474 |
+
"learning_rate": 0.00031986970684039093,
|
475 |
+
"loss": 0.5547,
|
476 |
+
"step": 35496
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 3.45,
|
480 |
+
"learning_rate": 0.0003098677907645143,
|
481 |
+
"loss": 0.5484,
|
482 |
+
"step": 36018
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 3.5,
|
486 |
+
"learning_rate": 0.00029986587468863767,
|
487 |
+
"loss": 0.5368,
|
488 |
+
"step": 36540
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 3.55,
|
492 |
+
"learning_rate": 0.00028986395861276107,
|
493 |
+
"loss": 0.5487,
|
494 |
+
"step": 37062
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 3.6,
|
498 |
+
"learning_rate": 0.00027986204253688447,
|
499 |
+
"loss": 0.5403,
|
500 |
+
"step": 37584
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 3.65,
|
504 |
+
"learning_rate": 0.00026986012646100787,
|
505 |
+
"loss": 0.5459,
|
506 |
+
"step": 38106
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 3.7,
|
510 |
+
"learning_rate": 0.00025985821038513126,
|
511 |
+
"loss": 0.5376,
|
512 |
+
"step": 38628
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 3.75,
|
516 |
+
"learning_rate": 0.00024985629430925466,
|
517 |
+
"loss": 0.5186,
|
518 |
+
"step": 39150
|
519 |
+
},
|
520 |
+
{
|
521 |
+
"epoch": 3.8,
|
522 |
+
"learning_rate": 0.00023985437823337806,
|
523 |
+
"loss": 0.5371,
|
524 |
+
"step": 39672
|
525 |
+
},
|
526 |
+
{
|
527 |
+
"epoch": 3.85,
|
528 |
+
"learning_rate": 0.00022985246215750143,
|
529 |
+
"loss": 0.5413,
|
530 |
+
"step": 40194
|
531 |
+
},
|
532 |
+
{
|
533 |
+
"epoch": 3.9,
|
534 |
+
"learning_rate": 0.00021985054608162483,
|
535 |
+
"loss": 0.5328,
|
536 |
+
"step": 40716
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 3.95,
|
540 |
+
"learning_rate": 0.00020984863000574823,
|
541 |
+
"loss": 0.513,
|
542 |
+
"step": 41238
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 4.0,
|
546 |
+
"eval_Macro F1": 0.6224111150035051,
|
547 |
+
"eval_Macro Precision": 0.6915564589610266,
|
548 |
+
"eval_Macro Recall": 0.60231662265339,
|
549 |
+
"eval_Micro F1": 0.8347285596234686,
|
550 |
+
"eval_Micro Precision": 0.8347285596234686,
|
551 |
+
"eval_Micro Recall": 0.8347285596234686,
|
552 |
+
"eval_Weighted F1": 0.8100695837354521,
|
553 |
+
"eval_Weighted Precision": 0.8049325371288767,
|
554 |
+
"eval_Weighted Recall": 0.8347285596234686,
|
555 |
+
"eval_accuracy": 0.8347285596234686,
|
556 |
+
"eval_loss": 0.5459285974502563,
|
557 |
+
"eval_runtime": 1277.4842,
|
558 |
+
"eval_samples_per_second": 21.787,
|
559 |
+
"eval_steps_per_second": 2.724,
|
560 |
+
"step": 41752
|
561 |
+
},
|
562 |
+
{
|
563 |
+
"epoch": 4.0,
|
564 |
+
"learning_rate": 0.00019984671392987163,
|
565 |
+
"loss": 0.5375,
|
566 |
+
"step": 41760
|
567 |
+
},
|
568 |
+
{
|
569 |
+
"epoch": 4.05,
|
570 |
+
"learning_rate": 0.00018984479785399502,
|
571 |
+
"loss": 0.5505,
|
572 |
+
"step": 42282
|
573 |
+
},
|
574 |
+
{
|
575 |
+
"epoch": 4.1,
|
576 |
+
"learning_rate": 0.00017984288177811842,
|
577 |
+
"loss": 0.5258,
|
578 |
+
"step": 42804
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 4.15,
|
582 |
+
"learning_rate": 0.00016984096570224182,
|
583 |
+
"loss": 0.5132,
|
584 |
+
"step": 43326
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 4.2,
|
588 |
+
"learning_rate": 0.0001598390496263652,
|
589 |
+
"loss": 0.5182,
|
590 |
+
"step": 43848
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 4.25,
|
594 |
+
"learning_rate": 0.00014983713355048862,
|
595 |
+
"loss": 0.5147,
|
596 |
+
"step": 44370
|
597 |
+
},
|
598 |
+
{
|
599 |
+
"epoch": 4.3,
|
600 |
+
"learning_rate": 0.00013983521747461201,
|
601 |
+
"loss": 0.5364,
|
602 |
+
"step": 44892
|
603 |
+
},
|
604 |
+
{
|
605 |
+
"epoch": 4.35,
|
606 |
+
"learning_rate": 0.00012983330139873538,
|
607 |
+
"loss": 0.53,
|
608 |
+
"step": 45414
|
609 |
+
},
|
610 |
+
{
|
611 |
+
"epoch": 4.4,
|
612 |
+
"learning_rate": 0.00011983138532285878,
|
613 |
+
"loss": 0.5288,
|
614 |
+
"step": 45936
|
615 |
+
},
|
616 |
+
{
|
617 |
+
"epoch": 4.45,
|
618 |
+
"learning_rate": 0.00010982946924698218,
|
619 |
+
"loss": 0.5087,
|
620 |
+
"step": 46458
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 4.5,
|
624 |
+
"learning_rate": 9.982755317110558e-05,
|
625 |
+
"loss": 0.5101,
|
626 |
+
"step": 46980
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 4.55,
|
630 |
+
"learning_rate": 8.982563709522898e-05,
|
631 |
+
"loss": 0.5235,
|
632 |
+
"step": 47502
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 4.6,
|
636 |
+
"learning_rate": 7.982372101935238e-05,
|
637 |
+
"loss": 0.5143,
|
638 |
+
"step": 48024
|
639 |
+
},
|
640 |
+
{
|
641 |
+
"epoch": 4.65,
|
642 |
+
"learning_rate": 6.982180494347576e-05,
|
643 |
+
"loss": 0.5299,
|
644 |
+
"step": 48546
|
645 |
+
},
|
646 |
+
{
|
647 |
+
"epoch": 4.7,
|
648 |
+
"learning_rate": 5.981988886759916e-05,
|
649 |
+
"loss": 0.5362,
|
650 |
+
"step": 49068
|
651 |
+
},
|
652 |
+
{
|
653 |
+
"epoch": 4.75,
|
654 |
+
"learning_rate": 4.981797279172255e-05,
|
655 |
+
"loss": 0.5186,
|
656 |
+
"step": 49590
|
657 |
+
},
|
658 |
+
{
|
659 |
+
"epoch": 4.8,
|
660 |
+
"learning_rate": 3.981605671584595e-05,
|
661 |
+
"loss": 0.5256,
|
662 |
+
"step": 50112
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 4.85,
|
666 |
+
"learning_rate": 2.9814140639969346e-05,
|
667 |
+
"loss": 0.5233,
|
668 |
+
"step": 50634
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 4.9,
|
672 |
+
"learning_rate": 1.9812224564092737e-05,
|
673 |
+
"loss": 0.5263,
|
674 |
+
"step": 51156
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 4.95,
|
678 |
+
"learning_rate": 9.810308488216133e-06,
|
679 |
+
"loss": 0.5288,
|
680 |
+
"step": 51678
|
681 |
+
},
|
682 |
+
{
|
683 |
+
"epoch": 5.0,
|
684 |
+
"eval_Macro F1": 0.6307998158823078,
|
685 |
+
"eval_Macro Precision": 0.7029273840489014,
|
686 |
+
"eval_Macro Recall": 0.6089557840149206,
|
687 |
+
"eval_Micro F1": 0.8381417741529839,
|
688 |
+
"eval_Micro Precision": 0.8381417741529839,
|
689 |
+
"eval_Micro Recall": 0.8381417741529839,
|
690 |
+
"eval_Weighted F1": 0.8141748808079556,
|
691 |
+
"eval_Weighted Precision": 0.810121498718634,
|
692 |
+
"eval_Weighted Recall": 0.8381417741529839,
|
693 |
+
"eval_accuracy": 0.8381417741529839,
|
694 |
+
"eval_loss": 0.5336272716522217,
|
695 |
+
"eval_runtime": 1277.7048,
|
696 |
+
"eval_samples_per_second": 21.784,
|
697 |
+
"eval_steps_per_second": 2.724,
|
698 |
+
"step": 52190
|
699 |
+
},
|
700 |
+
{
|
701 |
+
"epoch": 5.0,
|
702 |
+
"step": 52190,
|
703 |
+
"total_flos": 2.1040687845486864e+16,
|
704 |
+
"train_loss": 0.5799241374931839,
|
705 |
+
"train_runtime": 32322.6365,
|
706 |
+
"train_samples_per_second": 12.916,
|
707 |
+
"train_steps_per_second": 1.615
|
708 |
+
}
|
709 |
+
],
|
710 |
+
"max_steps": 52190,
|
711 |
+
"num_train_epochs": 5,
|
712 |
+
"total_flos": 2.1040687845486864e+16,
|
713 |
+
"trial_name": null,
|
714 |
+
"trial_params": null
|
715 |
+
}
|