aryaadhi commited on
Commit
8514db0
1 Parent(s): fa5e291

End of training

Browse files
README.md CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [bigscience/bloom-560m](https://huggingface.co/bigscience/bloom-560m) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 1.9628
20
 
21
  ## Model description
22
 
@@ -35,612 +35,255 @@ More information needed
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
- - learning_rate: 0.0001
39
- - train_batch_size: 4
40
- - eval_batch_size: 4
41
  - seed: 42
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: cosine
44
- - num_epochs: 5
45
 
46
  ### Training results
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:------:|:----:|:---------------:|
50
- | No log | 0.0084 | 10 | 2.7413 |
51
- | No log | 0.0168 | 20 | 2.5065 |
52
- | No log | 0.0253 | 30 | 2.3701 |
53
- | No log | 0.0337 | 40 | 2.3103 |
54
- | No log | 0.0421 | 50 | 2.2831 |
55
- | No log | 0.0505 | 60 | 2.2652 |
56
- | No log | 0.0589 | 70 | 2.2498 |
57
- | No log | 0.0673 | 80 | 2.2374 |
58
- | No log | 0.0758 | 90 | 2.2281 |
59
- | 2.3686 | 0.0842 | 100 | 2.2183 |
60
- | 2.3686 | 0.0926 | 110 | 2.2133 |
61
- | 2.3686 | 0.1010 | 120 | 2.2091 |
62
- | 2.3686 | 0.1094 | 130 | 2.2030 |
63
- | 2.3686 | 0.1178 | 140 | 2.1965 |
64
- | 2.3686 | 0.1263 | 150 | 2.1939 |
65
- | 2.3686 | 0.1347 | 160 | 2.1885 |
66
- | 2.3686 | 0.1431 | 170 | 2.1814 |
67
- | 2.3686 | 0.1515 | 180 | 2.1808 |
68
- | 2.3686 | 0.1599 | 190 | 2.1746 |
69
- | 2.1271 | 0.1684 | 200 | 2.1743 |
70
- | 2.1271 | 0.1768 | 210 | 2.1719 |
71
- | 2.1271 | 0.1852 | 220 | 2.1679 |
72
- | 2.1271 | 0.1936 | 230 | 2.1720 |
73
- | 2.1271 | 0.2020 | 240 | 2.1648 |
74
- | 2.1271 | 0.2104 | 250 | 2.1624 |
75
- | 2.1271 | 0.2189 | 260 | 2.1563 |
76
- | 2.1271 | 0.2273 | 270 | 2.1489 |
77
- | 2.1271 | 0.2357 | 280 | 2.1451 |
78
- | 2.1271 | 0.2441 | 290 | 2.1420 |
79
- | 2.0973 | 0.2525 | 300 | 2.1438 |
80
- | 2.0973 | 0.2609 | 310 | 2.1409 |
81
- | 2.0973 | 0.2694 | 320 | 2.1397 |
82
- | 2.0973 | 0.2778 | 330 | 2.1371 |
83
- | 2.0973 | 0.2862 | 340 | 2.1320 |
84
- | 2.0973 | 0.2946 | 350 | 2.1353 |
85
- | 2.0973 | 0.3030 | 360 | 2.1321 |
86
- | 2.0973 | 0.3114 | 370 | 2.1279 |
87
- | 2.0973 | 0.3199 | 380 | 2.1283 |
88
- | 2.0973 | 0.3283 | 390 | 2.1244 |
89
- | 2.1201 | 0.3367 | 400 | 2.1242 |
90
- | 2.1201 | 0.3451 | 410 | 2.1205 |
91
- | 2.1201 | 0.3535 | 420 | 2.1179 |
92
- | 2.1201 | 0.3620 | 430 | 2.1162 |
93
- | 2.1201 | 0.3704 | 440 | 2.1129 |
94
- | 2.1201 | 0.3788 | 450 | 2.1123 |
95
- | 2.1201 | 0.3872 | 460 | 2.1120 |
96
- | 2.1201 | 0.3956 | 470 | 2.1114 |
97
- | 2.1201 | 0.4040 | 480 | 2.1121 |
98
- | 2.1201 | 0.4125 | 490 | 2.1089 |
99
- | 2.0368 | 0.4209 | 500 | 2.1085 |
100
- | 2.0368 | 0.4293 | 510 | 2.1065 |
101
- | 2.0368 | 0.4377 | 520 | 2.1041 |
102
- | 2.0368 | 0.4461 | 530 | 2.1016 |
103
- | 2.0368 | 0.4545 | 540 | 2.1042 |
104
- | 2.0368 | 0.4630 | 550 | 2.0996 |
105
- | 2.0368 | 0.4714 | 560 | 2.1002 |
106
- | 2.0368 | 0.4798 | 570 | 2.0997 |
107
- | 2.0368 | 0.4882 | 580 | 2.0959 |
108
- | 2.0368 | 0.4966 | 590 | 2.0952 |
109
- | 2.0816 | 0.5051 | 600 | 2.0964 |
110
- | 2.0816 | 0.5135 | 610 | 2.0969 |
111
- | 2.0816 | 0.5219 | 620 | 2.0963 |
112
- | 2.0816 | 0.5303 | 630 | 2.0928 |
113
- | 2.0816 | 0.5387 | 640 | 2.0892 |
114
- | 2.0816 | 0.5471 | 650 | 2.0889 |
115
- | 2.0816 | 0.5556 | 660 | 2.0860 |
116
- | 2.0816 | 0.5640 | 670 | 2.0873 |
117
- | 2.0816 | 0.5724 | 680 | 2.0827 |
118
- | 2.0816 | 0.5808 | 690 | 2.0814 |
119
- | 2.0766 | 0.5892 | 700 | 2.0824 |
120
- | 2.0766 | 0.5976 | 710 | 2.0810 |
121
- | 2.0766 | 0.6061 | 720 | 2.0802 |
122
- | 2.0766 | 0.6145 | 730 | 2.0800 |
123
- | 2.0766 | 0.6229 | 740 | 2.0790 |
124
- | 2.0766 | 0.6313 | 750 | 2.0811 |
125
- | 2.0766 | 0.6397 | 760 | 2.0810 |
126
- | 2.0766 | 0.6481 | 770 | 2.0778 |
127
- | 2.0766 | 0.6566 | 780 | 2.0770 |
128
- | 2.0766 | 0.6650 | 790 | 2.0753 |
129
- | 2.0604 | 0.6734 | 800 | 2.0752 |
130
- | 2.0604 | 0.6818 | 810 | 2.0719 |
131
- | 2.0604 | 0.6902 | 820 | 2.0759 |
132
- | 2.0604 | 0.6987 | 830 | 2.0743 |
133
- | 2.0604 | 0.7071 | 840 | 2.0682 |
134
- | 2.0604 | 0.7155 | 850 | 2.0686 |
135
- | 2.0604 | 0.7239 | 860 | 2.0661 |
136
- | 2.0604 | 0.7323 | 870 | 2.0669 |
137
- | 2.0604 | 0.7407 | 880 | 2.0670 |
138
- | 2.0604 | 0.7492 | 890 | 2.0694 |
139
- | 2.0319 | 0.7576 | 900 | 2.0645 |
140
- | 2.0319 | 0.7660 | 910 | 2.0633 |
141
- | 2.0319 | 0.7744 | 920 | 2.0592 |
142
- | 2.0319 | 0.7828 | 930 | 2.0618 |
143
- | 2.0319 | 0.7912 | 940 | 2.0613 |
144
- | 2.0319 | 0.7997 | 950 | 2.0620 |
145
- | 2.0319 | 0.8081 | 960 | 2.0589 |
146
- | 2.0319 | 0.8165 | 970 | 2.0599 |
147
- | 2.0319 | 0.8249 | 980 | 2.0576 |
148
- | 2.0319 | 0.8333 | 990 | 2.0564 |
149
- | 2.0554 | 0.8418 | 1000 | 2.0555 |
150
- | 2.0554 | 0.8502 | 1010 | 2.0574 |
151
- | 2.0554 | 0.8586 | 1020 | 2.0555 |
152
- | 2.0554 | 0.8670 | 1030 | 2.0531 |
153
- | 2.0554 | 0.8754 | 1040 | 2.0546 |
154
- | 2.0554 | 0.8838 | 1050 | 2.0533 |
155
- | 2.0554 | 0.8923 | 1060 | 2.0526 |
156
- | 2.0554 | 0.9007 | 1070 | 2.0515 |
157
- | 2.0554 | 0.9091 | 1080 | 2.0492 |
158
- | 2.0554 | 0.9175 | 1090 | 2.0490 |
159
- | 2.0078 | 0.9259 | 1100 | 2.0514 |
160
- | 2.0078 | 0.9343 | 1110 | 2.0493 |
161
- | 2.0078 | 0.9428 | 1120 | 2.0454 |
162
- | 2.0078 | 0.9512 | 1130 | 2.0472 |
163
- | 2.0078 | 0.9596 | 1140 | 2.0481 |
164
- | 2.0078 | 0.9680 | 1150 | 2.0448 |
165
- | 2.0078 | 0.9764 | 1160 | 2.0423 |
166
- | 2.0078 | 0.9848 | 1170 | 2.0424 |
167
- | 2.0078 | 0.9933 | 1180 | 2.0413 |
168
- | 2.0078 | 1.0017 | 1190 | 2.0376 |
169
- | 2.0269 | 1.0101 | 1200 | 2.0380 |
170
- | 2.0269 | 1.0185 | 1210 | 2.0383 |
171
- | 2.0269 | 1.0269 | 1220 | 2.0385 |
172
- | 2.0269 | 1.0354 | 1230 | 2.0381 |
173
- | 2.0269 | 1.0438 | 1240 | 2.0416 |
174
- | 2.0269 | 1.0522 | 1250 | 2.0406 |
175
- | 2.0269 | 1.0606 | 1260 | 2.0399 |
176
- | 2.0269 | 1.0690 | 1270 | 2.0407 |
177
- | 2.0269 | 1.0774 | 1280 | 2.0414 |
178
- | 2.0269 | 1.0859 | 1290 | 2.0404 |
179
- | 1.9814 | 1.0943 | 1300 | 2.0383 |
180
- | 1.9814 | 1.1027 | 1310 | 2.0376 |
181
- | 1.9814 | 1.1111 | 1320 | 2.0361 |
182
- | 1.9814 | 1.1195 | 1330 | 2.0326 |
183
- | 1.9814 | 1.1279 | 1340 | 2.0351 |
184
- | 1.9814 | 1.1364 | 1350 | 2.0322 |
185
- | 1.9814 | 1.1448 | 1360 | 2.0285 |
186
- | 1.9814 | 1.1532 | 1370 | 2.0276 |
187
- | 1.9814 | 1.1616 | 1380 | 2.0278 |
188
- | 1.9814 | 1.1700 | 1390 | 2.0309 |
189
- | 1.9846 | 1.1785 | 1400 | 2.0319 |
190
- | 1.9846 | 1.1869 | 1410 | 2.0311 |
191
- | 1.9846 | 1.1953 | 1420 | 2.0321 |
192
- | 1.9846 | 1.2037 | 1430 | 2.0322 |
193
- | 1.9846 | 1.2121 | 1440 | 2.0368 |
194
- | 1.9846 | 1.2205 | 1450 | 2.0330 |
195
- | 1.9846 | 1.2290 | 1460 | 2.0270 |
196
- | 1.9846 | 1.2374 | 1470 | 2.0256 |
197
- | 1.9846 | 1.2458 | 1480 | 2.0243 |
198
- | 1.9846 | 1.2542 | 1490 | 2.0239 |
199
- | 1.9862 | 1.2626 | 1500 | 2.0211 |
200
- | 1.9862 | 1.2710 | 1510 | 2.0203 |
201
- | 1.9862 | 1.2795 | 1520 | 2.0216 |
202
- | 1.9862 | 1.2879 | 1530 | 2.0205 |
203
- | 1.9862 | 1.2963 | 1540 | 2.0214 |
204
- | 1.9862 | 1.3047 | 1550 | 2.0214 |
205
- | 1.9862 | 1.3131 | 1560 | 2.0171 |
206
- | 1.9862 | 1.3215 | 1570 | 2.0198 |
207
- | 1.9862 | 1.3300 | 1580 | 2.0220 |
208
- | 1.9862 | 1.3384 | 1590 | 2.0202 |
209
- | 1.9507 | 1.3468 | 1600 | 2.0211 |
210
- | 1.9507 | 1.3552 | 1610 | 2.0191 |
211
- | 1.9507 | 1.3636 | 1620 | 2.0187 |
212
- | 1.9507 | 1.3721 | 1630 | 2.0187 |
213
- | 1.9507 | 1.3805 | 1640 | 2.0165 |
214
- | 1.9507 | 1.3889 | 1650 | 2.0185 |
215
- | 1.9507 | 1.3973 | 1660 | 2.0192 |
216
- | 1.9507 | 1.4057 | 1670 | 2.0160 |
217
- | 1.9507 | 1.4141 | 1680 | 2.0153 |
218
- | 1.9507 | 1.4226 | 1690 | 2.0163 |
219
- | 1.9746 | 1.4310 | 1700 | 2.0180 |
220
- | 1.9746 | 1.4394 | 1710 | 2.0172 |
221
- | 1.9746 | 1.4478 | 1720 | 2.0176 |
222
- | 1.9746 | 1.4562 | 1730 | 2.0176 |
223
- | 1.9746 | 1.4646 | 1740 | 2.0181 |
224
- | 1.9746 | 1.4731 | 1750 | 2.0217 |
225
- | 1.9746 | 1.4815 | 1760 | 2.0169 |
226
- | 1.9746 | 1.4899 | 1770 | 2.0165 |
227
- | 1.9746 | 1.4983 | 1780 | 2.0155 |
228
- | 1.9746 | 1.5067 | 1790 | 2.0160 |
229
- | 1.9464 | 1.5152 | 1800 | 2.0110 |
230
- | 1.9464 | 1.5236 | 1810 | 2.0142 |
231
- | 1.9464 | 1.5320 | 1820 | 2.0143 |
232
- | 1.9464 | 1.5404 | 1830 | 2.0145 |
233
- | 1.9464 | 1.5488 | 1840 | 2.0121 |
234
- | 1.9464 | 1.5572 | 1850 | 2.0115 |
235
- | 1.9464 | 1.5657 | 1860 | 2.0114 |
236
- | 1.9464 | 1.5741 | 1870 | 2.0107 |
237
- | 1.9464 | 1.5825 | 1880 | 2.0143 |
238
- | 1.9464 | 1.5909 | 1890 | 2.0151 |
239
- | 1.9539 | 1.5993 | 1900 | 2.0120 |
240
- | 1.9539 | 1.6077 | 1910 | 2.0087 |
241
- | 1.9539 | 1.6162 | 1920 | 2.0083 |
242
- | 1.9539 | 1.6246 | 1930 | 2.0092 |
243
- | 1.9539 | 1.6330 | 1940 | 2.0126 |
244
- | 1.9539 | 1.6414 | 1950 | 2.0111 |
245
- | 1.9539 | 1.6498 | 1960 | 2.0081 |
246
- | 1.9539 | 1.6582 | 1970 | 2.0076 |
247
- | 1.9539 | 1.6667 | 1980 | 2.0076 |
248
- | 1.9539 | 1.6751 | 1990 | 2.0081 |
249
- | 1.9227 | 1.6835 | 2000 | 2.0064 |
250
- | 1.9227 | 1.6919 | 2010 | 2.0079 |
251
- | 1.9227 | 1.7003 | 2020 | 2.0054 |
252
- | 1.9227 | 1.7088 | 2030 | 2.0047 |
253
- | 1.9227 | 1.7172 | 2040 | 2.0066 |
254
- | 1.9227 | 1.7256 | 2050 | 2.0059 |
255
- | 1.9227 | 1.7340 | 2060 | 2.0048 |
256
- | 1.9227 | 1.7424 | 2070 | 2.0054 |
257
- | 1.9227 | 1.7508 | 2080 | 2.0052 |
258
- | 1.9227 | 1.7593 | 2090 | 2.0062 |
259
- | 1.9588 | 1.7677 | 2100 | 2.0074 |
260
- | 1.9588 | 1.7761 | 2110 | 2.0065 |
261
- | 1.9588 | 1.7845 | 2120 | 2.0022 |
262
- | 1.9588 | 1.7929 | 2130 | 2.0014 |
263
- | 1.9588 | 1.8013 | 2140 | 1.9998 |
264
- | 1.9588 | 1.8098 | 2150 | 2.0009 |
265
- | 1.9588 | 1.8182 | 2160 | 2.0026 |
266
- | 1.9588 | 1.8266 | 2170 | 2.0038 |
267
- | 1.9588 | 1.8350 | 2180 | 2.0019 |
268
- | 1.9588 | 1.8434 | 2190 | 2.0002 |
269
- | 1.9351 | 1.8519 | 2200 | 2.0010 |
270
- | 1.9351 | 1.8603 | 2210 | 2.0016 |
271
- | 1.9351 | 1.8687 | 2220 | 2.0031 |
272
- | 1.9351 | 1.8771 | 2230 | 1.9999 |
273
- | 1.9351 | 1.8855 | 2240 | 1.9981 |
274
- | 1.9351 | 1.8939 | 2250 | 1.9963 |
275
- | 1.9351 | 1.9024 | 2260 | 1.9965 |
276
- | 1.9351 | 1.9108 | 2270 | 1.9990 |
277
- | 1.9351 | 1.9192 | 2280 | 1.9989 |
278
- | 1.9351 | 1.9276 | 2290 | 1.9954 |
279
- | 1.9219 | 1.9360 | 2300 | 1.9965 |
280
- | 1.9219 | 1.9444 | 2310 | 1.9982 |
281
- | 1.9219 | 1.9529 | 2320 | 1.9991 |
282
- | 1.9219 | 1.9613 | 2330 | 1.9970 |
283
- | 1.9219 | 1.9697 | 2340 | 1.9957 |
284
- | 1.9219 | 1.9781 | 2350 | 1.9954 |
285
- | 1.9219 | 1.9865 | 2360 | 1.9947 |
286
- | 1.9219 | 1.9949 | 2370 | 1.9948 |
287
- | 1.9219 | 2.0034 | 2380 | 1.9933 |
288
- | 1.9219 | 2.0118 | 2390 | 1.9943 |
289
- | 1.9129 | 2.0202 | 2400 | 1.9956 |
290
- | 1.9129 | 2.0286 | 2410 | 1.9949 |
291
- | 1.9129 | 2.0370 | 2420 | 1.9961 |
292
- | 1.9129 | 2.0455 | 2430 | 1.9950 |
293
- | 1.9129 | 2.0539 | 2440 | 1.9956 |
294
- | 1.9129 | 2.0623 | 2450 | 1.9950 |
295
- | 1.9129 | 2.0707 | 2460 | 1.9941 |
296
- | 1.9129 | 2.0791 | 2470 | 1.9946 |
297
- | 1.9129 | 2.0875 | 2480 | 1.9928 |
298
- | 1.9129 | 2.0960 | 2490 | 1.9951 |
299
- | 1.8814 | 2.1044 | 2500 | 1.9968 |
300
- | 1.8814 | 2.1128 | 2510 | 1.9928 |
301
- | 1.8814 | 2.1212 | 2520 | 1.9948 |
302
- | 1.8814 | 2.1296 | 2530 | 1.9925 |
303
- | 1.8814 | 2.1380 | 2540 | 1.9923 |
304
- | 1.8814 | 2.1465 | 2550 | 1.9924 |
305
- | 1.8814 | 2.1549 | 2560 | 1.9915 |
306
- | 1.8814 | 2.1633 | 2570 | 1.9918 |
307
- | 1.8814 | 2.1717 | 2580 | 1.9913 |
308
- | 1.8814 | 2.1801 | 2590 | 1.9900 |
309
- | 1.914 | 2.1886 | 2600 | 1.9894 |
310
- | 1.914 | 2.1970 | 2610 | 1.9902 |
311
- | 1.914 | 2.2054 | 2620 | 1.9896 |
312
- | 1.914 | 2.2138 | 2630 | 1.9896 |
313
- | 1.914 | 2.2222 | 2640 | 1.9889 |
314
- | 1.914 | 2.2306 | 2650 | 1.9887 |
315
- | 1.914 | 2.2391 | 2660 | 1.9884 |
316
- | 1.914 | 2.2475 | 2670 | 1.9877 |
317
- | 1.914 | 2.2559 | 2680 | 1.9882 |
318
- | 1.914 | 2.2643 | 2690 | 1.9887 |
319
- | 1.8883 | 2.2727 | 2700 | 1.9896 |
320
- | 1.8883 | 2.2811 | 2710 | 1.9909 |
321
- | 1.8883 | 2.2896 | 2720 | 1.9905 |
322
- | 1.8883 | 2.2980 | 2730 | 1.9902 |
323
- | 1.8883 | 2.3064 | 2740 | 1.9886 |
324
- | 1.8883 | 2.3148 | 2750 | 1.9888 |
325
- | 1.8883 | 2.3232 | 2760 | 1.9889 |
326
- | 1.8883 | 2.3316 | 2770 | 1.9905 |
327
- | 1.8883 | 2.3401 | 2780 | 1.9899 |
328
- | 1.8883 | 2.3485 | 2790 | 1.9896 |
329
- | 1.8748 | 2.3569 | 2800 | 1.9878 |
330
- | 1.8748 | 2.3653 | 2810 | 1.9873 |
331
- | 1.8748 | 2.3737 | 2820 | 1.9861 |
332
- | 1.8748 | 2.3822 | 2830 | 1.9873 |
333
- | 1.8748 | 2.3906 | 2840 | 1.9847 |
334
- | 1.8748 | 2.3990 | 2850 | 1.9827 |
335
- | 1.8748 | 2.4074 | 2860 | 1.9823 |
336
- | 1.8748 | 2.4158 | 2870 | 1.9822 |
337
- | 1.8748 | 2.4242 | 2880 | 1.9851 |
338
- | 1.8748 | 2.4327 | 2890 | 1.9857 |
339
- | 1.9119 | 2.4411 | 2900 | 1.9847 |
340
- | 1.9119 | 2.4495 | 2910 | 1.9828 |
341
- | 1.9119 | 2.4579 | 2920 | 1.9824 |
342
- | 1.9119 | 2.4663 | 2930 | 1.9828 |
343
- | 1.9119 | 2.4747 | 2940 | 1.9839 |
344
- | 1.9119 | 2.4832 | 2950 | 1.9829 |
345
- | 1.9119 | 2.4916 | 2960 | 1.9815 |
346
- | 1.9119 | 2.5 | 2970 | 1.9804 |
347
- | 1.9119 | 2.5084 | 2980 | 1.9832 |
348
- | 1.9119 | 2.5168 | 2990 | 1.9858 |
349
- | 1.8855 | 2.5253 | 3000 | 1.9858 |
350
- | 1.8855 | 2.5337 | 3010 | 1.9844 |
351
- | 1.8855 | 2.5421 | 3020 | 1.9842 |
352
- | 1.8855 | 2.5505 | 3030 | 1.9811 |
353
- | 1.8855 | 2.5589 | 3040 | 1.9796 |
354
- | 1.8855 | 2.5673 | 3050 | 1.9804 |
355
- | 1.8855 | 2.5758 | 3060 | 1.9821 |
356
- | 1.8855 | 2.5842 | 3070 | 1.9805 |
357
- | 1.8855 | 2.5926 | 3080 | 1.9784 |
358
- | 1.8855 | 2.6010 | 3090 | 1.9787 |
359
- | 1.88 | 2.6094 | 3100 | 1.9784 |
360
- | 1.88 | 2.6178 | 3110 | 1.9776 |
361
- | 1.88 | 2.6263 | 3120 | 1.9782 |
362
- | 1.88 | 2.6347 | 3130 | 1.9764 |
363
- | 1.88 | 2.6431 | 3140 | 1.9749 |
364
- | 1.88 | 2.6515 | 3150 | 1.9749 |
365
- | 1.88 | 2.6599 | 3160 | 1.9759 |
366
- | 1.88 | 2.6684 | 3170 | 1.9768 |
367
- | 1.88 | 2.6768 | 3180 | 1.9778 |
368
- | 1.88 | 2.6852 | 3190 | 1.9770 |
369
- | 1.8669 | 2.6936 | 3200 | 1.9770 |
370
- | 1.8669 | 2.7020 | 3210 | 1.9749 |
371
- | 1.8669 | 2.7104 | 3220 | 1.9738 |
372
- | 1.8669 | 2.7189 | 3230 | 1.9748 |
373
- | 1.8669 | 2.7273 | 3240 | 1.9749 |
374
- | 1.8669 | 2.7357 | 3250 | 1.9764 |
375
- | 1.8669 | 2.7441 | 3260 | 1.9756 |
376
- | 1.8669 | 2.7525 | 3270 | 1.9755 |
377
- | 1.8669 | 2.7609 | 3280 | 1.9746 |
378
- | 1.8669 | 2.7694 | 3290 | 1.9747 |
379
- | 1.8636 | 2.7778 | 3300 | 1.9758 |
380
- | 1.8636 | 2.7862 | 3310 | 1.9753 |
381
- | 1.8636 | 2.7946 | 3320 | 1.9735 |
382
- | 1.8636 | 2.8030 | 3330 | 1.9733 |
383
- | 1.8636 | 2.8114 | 3340 | 1.9746 |
384
- | 1.8636 | 2.8199 | 3350 | 1.9753 |
385
- | 1.8636 | 2.8283 | 3360 | 1.9764 |
386
- | 1.8636 | 2.8367 | 3370 | 1.9764 |
387
- | 1.8636 | 2.8451 | 3380 | 1.9755 |
388
- | 1.8636 | 2.8535 | 3390 | 1.9751 |
389
- | 1.8587 | 2.8620 | 3400 | 1.9753 |
390
- | 1.8587 | 2.8704 | 3410 | 1.9759 |
391
- | 1.8587 | 2.8788 | 3420 | 1.9764 |
392
- | 1.8587 | 2.8872 | 3430 | 1.9747 |
393
- | 1.8587 | 2.8956 | 3440 | 1.9730 |
394
- | 1.8587 | 2.9040 | 3450 | 1.9731 |
395
- | 1.8587 | 2.9125 | 3460 | 1.9719 |
396
- | 1.8587 | 2.9209 | 3470 | 1.9703 |
397
- | 1.8587 | 2.9293 | 3480 | 1.9704 |
398
- | 1.8587 | 2.9377 | 3490 | 1.9699 |
399
- | 1.8189 | 2.9461 | 3500 | 1.9705 |
400
- | 1.8189 | 2.9545 | 3510 | 1.9724 |
401
- | 1.8189 | 2.9630 | 3520 | 1.9729 |
402
- | 1.8189 | 2.9714 | 3530 | 1.9728 |
403
- | 1.8189 | 2.9798 | 3540 | 1.9725 |
404
- | 1.8189 | 2.9882 | 3550 | 1.9709 |
405
- | 1.8189 | 2.9966 | 3560 | 1.9705 |
406
- | 1.8189 | 3.0051 | 3570 | 1.9715 |
407
- | 1.8189 | 3.0135 | 3580 | 1.9727 |
408
- | 1.8189 | 3.0219 | 3590 | 1.9723 |
409
- | 1.8332 | 3.0303 | 3600 | 1.9728 |
410
- | 1.8332 | 3.0387 | 3610 | 1.9732 |
411
- | 1.8332 | 3.0471 | 3620 | 1.9738 |
412
- | 1.8332 | 3.0556 | 3630 | 1.9734 |
413
- | 1.8332 | 3.0640 | 3640 | 1.9729 |
414
- | 1.8332 | 3.0724 | 3650 | 1.9734 |
415
- | 1.8332 | 3.0808 | 3660 | 1.9726 |
416
- | 1.8332 | 3.0892 | 3670 | 1.9729 |
417
- | 1.8332 | 3.0976 | 3680 | 1.9743 |
418
- | 1.8332 | 3.1061 | 3690 | 1.9754 |
419
- | 1.8035 | 3.1145 | 3700 | 1.9744 |
420
- | 1.8035 | 3.1229 | 3710 | 1.9741 |
421
- | 1.8035 | 3.1313 | 3720 | 1.9749 |
422
- | 1.8035 | 3.1397 | 3730 | 1.9757 |
423
- | 1.8035 | 3.1481 | 3740 | 1.9760 |
424
- | 1.8035 | 3.1566 | 3750 | 1.9760 |
425
- | 1.8035 | 3.1650 | 3760 | 1.9751 |
426
- | 1.8035 | 3.1734 | 3770 | 1.9743 |
427
- | 1.8035 | 3.1818 | 3780 | 1.9737 |
428
- | 1.8035 | 3.1902 | 3790 | 1.9725 |
429
- | 1.8222 | 3.1987 | 3800 | 1.9716 |
430
- | 1.8222 | 3.2071 | 3810 | 1.9708 |
431
- | 1.8222 | 3.2155 | 3820 | 1.9705 |
432
- | 1.8222 | 3.2239 | 3830 | 1.9713 |
433
- | 1.8222 | 3.2323 | 3840 | 1.9720 |
434
- | 1.8222 | 3.2407 | 3850 | 1.9713 |
435
- | 1.8222 | 3.2492 | 3860 | 1.9712 |
436
- | 1.8222 | 3.2576 | 3870 | 1.9732 |
437
- | 1.8222 | 3.2660 | 3880 | 1.9726 |
438
- | 1.8222 | 3.2744 | 3890 | 1.9725 |
439
- | 1.8209 | 3.2828 | 3900 | 1.9724 |
440
- | 1.8209 | 3.2912 | 3910 | 1.9723 |
441
- | 1.8209 | 3.2997 | 3920 | 1.9719 |
442
- | 1.8209 | 3.3081 | 3930 | 1.9710 |
443
- | 1.8209 | 3.3165 | 3940 | 1.9706 |
444
- | 1.8209 | 3.3249 | 3950 | 1.9711 |
445
- | 1.8209 | 3.3333 | 3960 | 1.9718 |
446
- | 1.8209 | 3.3418 | 3970 | 1.9724 |
447
- | 1.8209 | 3.3502 | 3980 | 1.9722 |
448
- | 1.8209 | 3.3586 | 3990 | 1.9712 |
449
- | 1.8311 | 3.3670 | 4000 | 1.9710 |
450
- | 1.8311 | 3.3754 | 4010 | 1.9704 |
451
- | 1.8311 | 3.3838 | 4020 | 1.9711 |
452
- | 1.8311 | 3.3923 | 4030 | 1.9710 |
453
- | 1.8311 | 3.4007 | 4040 | 1.9698 |
454
- | 1.8311 | 3.4091 | 4050 | 1.9689 |
455
- | 1.8311 | 3.4175 | 4060 | 1.9683 |
456
- | 1.8311 | 3.4259 | 4070 | 1.9683 |
457
- | 1.8311 | 3.4343 | 4080 | 1.9693 |
458
- | 1.8311 | 3.4428 | 4090 | 1.9696 |
459
- | 1.8518 | 3.4512 | 4100 | 1.9695 |
460
- | 1.8518 | 3.4596 | 4110 | 1.9687 |
461
- | 1.8518 | 3.4680 | 4120 | 1.9690 |
462
- | 1.8518 | 3.4764 | 4130 | 1.9701 |
463
- | 1.8518 | 3.4848 | 4140 | 1.9699 |
464
- | 1.8518 | 3.4933 | 4150 | 1.9696 |
465
- | 1.8518 | 3.5017 | 4160 | 1.9685 |
466
- | 1.8518 | 3.5101 | 4170 | 1.9682 |
467
- | 1.8518 | 3.5185 | 4180 | 1.9684 |
468
- | 1.8518 | 3.5269 | 4190 | 1.9695 |
469
- | 1.8257 | 3.5354 | 4200 | 1.9695 |
470
- | 1.8257 | 3.5438 | 4210 | 1.9683 |
471
- | 1.8257 | 3.5522 | 4220 | 1.9676 |
472
- | 1.8257 | 3.5606 | 4230 | 1.9678 |
473
- | 1.8257 | 3.5690 | 4240 | 1.9672 |
474
- | 1.8257 | 3.5774 | 4250 | 1.9660 |
475
- | 1.8257 | 3.5859 | 4260 | 1.9656 |
476
- | 1.8257 | 3.5943 | 4270 | 1.9662 |
477
- | 1.8257 | 3.6027 | 4280 | 1.9664 |
478
- | 1.8257 | 3.6111 | 4290 | 1.9668 |
479
- | 1.8107 | 3.6195 | 4300 | 1.9665 |
480
- | 1.8107 | 3.6279 | 4310 | 1.9661 |
481
- | 1.8107 | 3.6364 | 4320 | 1.9659 |
482
- | 1.8107 | 3.6448 | 4330 | 1.9653 |
483
- | 1.8107 | 3.6532 | 4340 | 1.9654 |
484
- | 1.8107 | 3.6616 | 4350 | 1.9662 |
485
- | 1.8107 | 3.6700 | 4360 | 1.9665 |
486
- | 1.8107 | 3.6785 | 4370 | 1.9660 |
487
- | 1.8107 | 3.6869 | 4380 | 1.9660 |
488
- | 1.8107 | 3.6953 | 4390 | 1.9661 |
489
- | 1.7929 | 3.7037 | 4400 | 1.9655 |
490
- | 1.7929 | 3.7121 | 4410 | 1.9646 |
491
- | 1.7929 | 3.7205 | 4420 | 1.9638 |
492
- | 1.7929 | 3.7290 | 4430 | 1.9635 |
493
- | 1.7929 | 3.7374 | 4440 | 1.9631 |
494
- | 1.7929 | 3.7458 | 4450 | 1.9626 |
495
- | 1.7929 | 3.7542 | 4460 | 1.9621 |
496
- | 1.7929 | 3.7626 | 4470 | 1.9621 |
497
- | 1.7929 | 3.7710 | 4480 | 1.9625 |
498
- | 1.7929 | 3.7795 | 4490 | 1.9627 |
499
- | 1.8177 | 3.7879 | 4500 | 1.9631 |
500
- | 1.8177 | 3.7963 | 4510 | 1.9627 |
501
- | 1.8177 | 3.8047 | 4520 | 1.9618 |
502
- | 1.8177 | 3.8131 | 4530 | 1.9615 |
503
- | 1.8177 | 3.8215 | 4540 | 1.9616 |
504
- | 1.8177 | 3.8300 | 4550 | 1.9618 |
505
- | 1.8177 | 3.8384 | 4560 | 1.9625 |
506
- | 1.8177 | 3.8468 | 4570 | 1.9626 |
507
- | 1.8177 | 3.8552 | 4580 | 1.9632 |
508
- | 1.8177 | 3.8636 | 4590 | 1.9636 |
509
- | 1.7996 | 3.8721 | 4600 | 1.9640 |
510
- | 1.7996 | 3.8805 | 4610 | 1.9637 |
511
- | 1.7996 | 3.8889 | 4620 | 1.9635 |
512
- | 1.7996 | 3.8973 | 4630 | 1.9633 |
513
- | 1.7996 | 3.9057 | 4640 | 1.9634 |
514
- | 1.7996 | 3.9141 | 4650 | 1.9633 |
515
- | 1.7996 | 3.9226 | 4660 | 1.9632 |
516
- | 1.7996 | 3.9310 | 4670 | 1.9632 |
517
- | 1.7996 | 3.9394 | 4680 | 1.9629 |
518
- | 1.7996 | 3.9478 | 4690 | 1.9628 |
519
- | 1.8443 | 3.9562 | 4700 | 1.9628 |
520
- | 1.8443 | 3.9646 | 4710 | 1.9623 |
521
- | 1.8443 | 3.9731 | 4720 | 1.9624 |
522
- | 1.8443 | 3.9815 | 4730 | 1.9622 |
523
- | 1.8443 | 3.9899 | 4740 | 1.9619 |
524
- | 1.8443 | 3.9983 | 4750 | 1.9617 |
525
- | 1.8443 | 4.0067 | 4760 | 1.9620 |
526
- | 1.8443 | 4.0152 | 4770 | 1.9623 |
527
- | 1.8443 | 4.0236 | 4780 | 1.9626 |
528
- | 1.8443 | 4.0320 | 4790 | 1.9632 |
529
- | 1.8409 | 4.0404 | 4800 | 1.9635 |
530
- | 1.8409 | 4.0488 | 4810 | 1.9641 |
531
- | 1.8409 | 4.0572 | 4820 | 1.9639 |
532
- | 1.8409 | 4.0657 | 4830 | 1.9636 |
533
- | 1.8409 | 4.0741 | 4840 | 1.9636 |
534
- | 1.8409 | 4.0825 | 4850 | 1.9636 |
535
- | 1.8409 | 4.0909 | 4860 | 1.9635 |
536
- | 1.8409 | 4.0993 | 4870 | 1.9629 |
537
- | 1.8409 | 4.1077 | 4880 | 1.9625 |
538
- | 1.8409 | 4.1162 | 4890 | 1.9624 |
539
- | 1.8261 | 4.1246 | 4900 | 1.9623 |
540
- | 1.8261 | 4.1330 | 4910 | 1.9626 |
541
- | 1.8261 | 4.1414 | 4920 | 1.9632 |
542
- | 1.8261 | 4.1498 | 4930 | 1.9639 |
543
- | 1.8261 | 4.1582 | 4940 | 1.9643 |
544
- | 1.8261 | 4.1667 | 4950 | 1.9646 |
545
- | 1.8261 | 4.1751 | 4960 | 1.9645 |
546
- | 1.8261 | 4.1835 | 4970 | 1.9642 |
547
- | 1.8261 | 4.1919 | 4980 | 1.9641 |
548
- | 1.8261 | 4.2003 | 4990 | 1.9642 |
549
- | 1.7684 | 4.2088 | 5000 | 1.9641 |
550
- | 1.7684 | 4.2172 | 5010 | 1.9641 |
551
- | 1.7684 | 4.2256 | 5020 | 1.9639 |
552
- | 1.7684 | 4.2340 | 5030 | 1.9637 |
553
- | 1.7684 | 4.2424 | 5040 | 1.9633 |
554
- | 1.7684 | 4.2508 | 5050 | 1.9630 |
555
- | 1.7684 | 4.2593 | 5060 | 1.9630 |
556
- | 1.7684 | 4.2677 | 5070 | 1.9629 |
557
- | 1.7684 | 4.2761 | 5080 | 1.9629 |
558
- | 1.7684 | 4.2845 | 5090 | 1.9632 |
559
- | 1.7933 | 4.2929 | 5100 | 1.9633 |
560
- | 1.7933 | 4.3013 | 5110 | 1.9637 |
561
- | 1.7933 | 4.3098 | 5120 | 1.9638 |
562
- | 1.7933 | 4.3182 | 5130 | 1.9639 |
563
- | 1.7933 | 4.3266 | 5140 | 1.9639 |
564
- | 1.7933 | 4.3350 | 5150 | 1.9636 |
565
- | 1.7933 | 4.3434 | 5160 | 1.9633 |
566
- | 1.7933 | 4.3519 | 5170 | 1.9630 |
567
- | 1.7933 | 4.3603 | 5180 | 1.9630 |
568
- | 1.7933 | 4.3687 | 5190 | 1.9628 |
569
- | 1.8192 | 4.3771 | 5200 | 1.9628 |
570
- | 1.8192 | 4.3855 | 5210 | 1.9628 |
571
- | 1.8192 | 4.3939 | 5220 | 1.9629 |
572
- | 1.8192 | 4.4024 | 5230 | 1.9630 |
573
- | 1.8192 | 4.4108 | 5240 | 1.9631 |
574
- | 1.8192 | 4.4192 | 5250 | 1.9633 |
575
- | 1.8192 | 4.4276 | 5260 | 1.9635 |
576
- | 1.8192 | 4.4360 | 5270 | 1.9637 |
577
- | 1.8192 | 4.4444 | 5280 | 1.9636 |
578
- | 1.8192 | 4.4529 | 5290 | 1.9636 |
579
- | 1.7583 | 4.4613 | 5300 | 1.9637 |
580
- | 1.7583 | 4.4697 | 5310 | 1.9637 |
581
- | 1.7583 | 4.4781 | 5320 | 1.9637 |
582
- | 1.7583 | 4.4865 | 5330 | 1.9637 |
583
- | 1.7583 | 4.4949 | 5340 | 1.9637 |
584
- | 1.7583 | 4.5034 | 5350 | 1.9637 |
585
- | 1.7583 | 4.5118 | 5360 | 1.9638 |
586
- | 1.7583 | 4.5202 | 5370 | 1.9640 |
587
- | 1.7583 | 4.5286 | 5380 | 1.9640 |
588
- | 1.7583 | 4.5370 | 5390 | 1.9638 |
589
- | 1.7977 | 4.5455 | 5400 | 1.9637 |
590
- | 1.7977 | 4.5539 | 5410 | 1.9635 |
591
- | 1.7977 | 4.5623 | 5420 | 1.9635 |
592
- | 1.7977 | 4.5707 | 5430 | 1.9634 |
593
- | 1.7977 | 4.5791 | 5440 | 1.9633 |
594
- | 1.7977 | 4.5875 | 5450 | 1.9633 |
595
- | 1.7977 | 4.5960 | 5460 | 1.9633 |
596
- | 1.7977 | 4.6044 | 5470 | 1.9633 |
597
- | 1.7977 | 4.6128 | 5480 | 1.9632 |
598
- | 1.7977 | 4.6212 | 5490 | 1.9633 |
599
- | 1.803 | 4.6296 | 5500 | 1.9633 |
600
- | 1.803 | 4.6380 | 5510 | 1.9632 |
601
- | 1.803 | 4.6465 | 5520 | 1.9632 |
602
- | 1.803 | 4.6549 | 5530 | 1.9632 |
603
- | 1.803 | 4.6633 | 5540 | 1.9631 |
604
- | 1.803 | 4.6717 | 5550 | 1.9631 |
605
- | 1.803 | 4.6801 | 5560 | 1.9630 |
606
- | 1.803 | 4.6886 | 5570 | 1.9631 |
607
- | 1.803 | 4.6970 | 5580 | 1.9630 |
608
- | 1.803 | 4.7054 | 5590 | 1.9630 |
609
- | 1.7817 | 4.7138 | 5600 | 1.9630 |
610
- | 1.7817 | 4.7222 | 5610 | 1.9629 |
611
- | 1.7817 | 4.7306 | 5620 | 1.9629 |
612
- | 1.7817 | 4.7391 | 5630 | 1.9628 |
613
- | 1.7817 | 4.7475 | 5640 | 1.9629 |
614
- | 1.7817 | 4.7559 | 5650 | 1.9629 |
615
- | 1.7817 | 4.7643 | 5660 | 1.9629 |
616
- | 1.7817 | 4.7727 | 5670 | 1.9629 |
617
- | 1.7817 | 4.7811 | 5680 | 1.9629 |
618
- | 1.7817 | 4.7896 | 5690 | 1.9629 |
619
- | 1.808 | 4.7980 | 5700 | 1.9629 |
620
- | 1.808 | 4.8064 | 5710 | 1.9629 |
621
- | 1.808 | 4.8148 | 5720 | 1.9629 |
622
- | 1.808 | 4.8232 | 5730 | 1.9629 |
623
- | 1.808 | 4.8316 | 5740 | 1.9629 |
624
- | 1.808 | 4.8401 | 5750 | 1.9628 |
625
- | 1.808 | 4.8485 | 5760 | 1.9628 |
626
- | 1.808 | 4.8569 | 5770 | 1.9628 |
627
- | 1.808 | 4.8653 | 5780 | 1.9628 |
628
- | 1.808 | 4.8737 | 5790 | 1.9628 |
629
- | 1.8047 | 4.8822 | 5800 | 1.9628 |
630
- | 1.8047 | 4.8906 | 5810 | 1.9628 |
631
- | 1.8047 | 4.8990 | 5820 | 1.9628 |
632
- | 1.8047 | 4.9074 | 5830 | 1.9628 |
633
- | 1.8047 | 4.9158 | 5840 | 1.9628 |
634
- | 1.8047 | 4.9242 | 5850 | 1.9628 |
635
- | 1.8047 | 4.9327 | 5860 | 1.9628 |
636
- | 1.8047 | 4.9411 | 5870 | 1.9628 |
637
- | 1.8047 | 4.9495 | 5880 | 1.9628 |
638
- | 1.8047 | 4.9579 | 5890 | 1.9628 |
639
- | 1.7728 | 4.9663 | 5900 | 1.9628 |
640
- | 1.7728 | 4.9747 | 5910 | 1.9628 |
641
- | 1.7728 | 4.9832 | 5920 | 1.9628 |
642
- | 1.7728 | 4.9916 | 5930 | 1.9628 |
643
- | 1.7728 | 5.0 | 5940 | 1.9628 |
644
 
645
 
646
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [bigscience/bloom-560m](https://huggingface.co/bigscience/bloom-560m) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 1.9682
20
 
21
  ## Model description
22
 
 
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
+ - learning_rate: 0.0002
39
+ - train_batch_size: 8
40
+ - eval_batch_size: 8
41
  - seed: 42
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: cosine
44
+ - num_epochs: 4
45
 
46
  ### Training results
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:------:|:----:|:---------------:|
50
+ | No log | 0.0168 | 10 | 2.5135 |
51
+ | No log | 0.0337 | 20 | 2.3298 |
52
+ | No log | 0.0505 | 30 | 2.2756 |
53
+ | No log | 0.0673 | 40 | 2.2419 |
54
+ | No log | 0.0842 | 50 | 2.2270 |
55
+ | No log | 0.1010 | 60 | 2.2102 |
56
+ | No log | 0.1178 | 70 | 2.1931 |
57
+ | No log | 0.1347 | 80 | 2.1846 |
58
+ | No log | 0.1515 | 90 | 2.1749 |
59
+ | 2.2471 | 0.1684 | 100 | 2.1645 |
60
+ | 2.2471 | 0.1852 | 110 | 2.1594 |
61
+ | 2.2471 | 0.2020 | 120 | 2.1557 |
62
+ | 2.2471 | 0.2189 | 130 | 2.1526 |
63
+ | 2.2471 | 0.2357 | 140 | 2.1495 |
64
+ | 2.2471 | 0.2525 | 150 | 2.1498 |
65
+ | 2.2471 | 0.2694 | 160 | 2.1401 |
66
+ | 2.2471 | 0.2862 | 170 | 2.1374 |
67
+ | 2.2471 | 0.3030 | 180 | 2.1317 |
68
+ | 2.2471 | 0.3199 | 190 | 2.1259 |
69
+ | 2.1174 | 0.3367 | 200 | 2.1248 |
70
+ | 2.1174 | 0.3535 | 210 | 2.1240 |
71
+ | 2.1174 | 0.3704 | 220 | 2.1179 |
72
+ | 2.1174 | 0.3872 | 230 | 2.1162 |
73
+ | 2.1174 | 0.4040 | 240 | 2.1163 |
74
+ | 2.1174 | 0.4209 | 250 | 2.1079 |
75
+ | 2.1174 | 0.4377 | 260 | 2.1075 |
76
+ | 2.1174 | 0.4545 | 270 | 2.1035 |
77
+ | 2.1174 | 0.4714 | 280 | 2.1030 |
78
+ | 2.1174 | 0.4882 | 290 | 2.0973 |
79
+ | 2.0744 | 0.5051 | 300 | 2.0895 |
80
+ | 2.0744 | 0.5219 | 310 | 2.0886 |
81
+ | 2.0744 | 0.5387 | 320 | 2.0894 |
82
+ | 2.0744 | 0.5556 | 330 | 2.0908 |
83
+ | 2.0744 | 0.5724 | 340 | 2.0841 |
84
+ | 2.0744 | 0.5892 | 350 | 2.0799 |
85
+ | 2.0744 | 0.6061 | 360 | 2.0799 |
86
+ | 2.0744 | 0.6229 | 370 | 2.0755 |
87
+ | 2.0744 | 0.6397 | 380 | 2.0753 |
88
+ | 2.0744 | 0.6566 | 390 | 2.0713 |
89
+ | 2.054 | 0.6734 | 400 | 2.0713 |
90
+ | 2.054 | 0.6902 | 410 | 2.0704 |
91
+ | 2.054 | 0.7071 | 420 | 2.0678 |
92
+ | 2.054 | 0.7239 | 430 | 2.0664 |
93
+ | 2.054 | 0.7407 | 440 | 2.0700 |
94
+ | 2.054 | 0.7576 | 450 | 2.0672 |
95
+ | 2.054 | 0.7744 | 460 | 2.0639 |
96
+ | 2.054 | 0.7912 | 470 | 2.0624 |
97
+ | 2.054 | 0.8081 | 480 | 2.0630 |
98
+ | 2.054 | 0.8249 | 490 | 2.0579 |
99
+ | 2.0228 | 0.8418 | 500 | 2.0548 |
100
+ | 2.0228 | 0.8586 | 510 | 2.0517 |
101
+ | 2.0228 | 0.8754 | 520 | 2.0490 |
102
+ | 2.0228 | 0.8923 | 530 | 2.0509 |
103
+ | 2.0228 | 0.9091 | 540 | 2.0488 |
104
+ | 2.0228 | 0.9259 | 550 | 2.0482 |
105
+ | 2.0228 | 0.9428 | 560 | 2.0446 |
106
+ | 2.0228 | 0.9596 | 570 | 2.0407 |
107
+ | 2.0228 | 0.9764 | 580 | 2.0445 |
108
+ | 2.0228 | 0.9933 | 590 | 2.0410 |
109
+ | 2.0186 | 1.0101 | 600 | 2.0426 |
110
+ | 2.0186 | 1.0269 | 610 | 2.0408 |
111
+ | 2.0186 | 1.0438 | 620 | 2.0407 |
112
+ | 2.0186 | 1.0606 | 630 | 2.0404 |
113
+ | 2.0186 | 1.0774 | 640 | 2.0363 |
114
+ | 2.0186 | 1.0943 | 650 | 2.0358 |
115
+ | 2.0186 | 1.1111 | 660 | 2.0365 |
116
+ | 2.0186 | 1.1279 | 670 | 2.0348 |
117
+ | 2.0186 | 1.1448 | 680 | 2.0343 |
118
+ | 2.0186 | 1.1616 | 690 | 2.0319 |
119
+ | 1.9341 | 1.1785 | 700 | 2.0268 |
120
+ | 1.9341 | 1.1953 | 710 | 2.0287 |
121
+ | 1.9341 | 1.2121 | 720 | 2.0302 |
122
+ | 1.9341 | 1.2290 | 730 | 2.0298 |
123
+ | 1.9341 | 1.2458 | 740 | 2.0307 |
124
+ | 1.9341 | 1.2626 | 750 | 2.0282 |
125
+ | 1.9341 | 1.2795 | 760 | 2.0305 |
126
+ | 1.9341 | 1.2963 | 770 | 2.0240 |
127
+ | 1.9341 | 1.3131 | 780 | 2.0245 |
128
+ | 1.9341 | 1.3300 | 790 | 2.0204 |
129
+ | 1.9309 | 1.3468 | 800 | 2.0208 |
130
+ | 1.9309 | 1.3636 | 810 | 2.0189 |
131
+ | 1.9309 | 1.3805 | 820 | 2.0179 |
132
+ | 1.9309 | 1.3973 | 830 | 2.0185 |
133
+ | 1.9309 | 1.4141 | 840 | 2.0187 |
134
+ | 1.9309 | 1.4310 | 850 | 2.0191 |
135
+ | 1.9309 | 1.4478 | 860 | 2.0218 |
136
+ | 1.9309 | 1.4646 | 870 | 2.0131 |
137
+ | 1.9309 | 1.4815 | 880 | 2.0096 |
138
+ | 1.9309 | 1.4983 | 890 | 2.0092 |
139
+ | 1.919 | 1.5152 | 900 | 2.0070 |
140
+ | 1.919 | 1.5320 | 910 | 2.0060 |
141
+ | 1.919 | 1.5488 | 920 | 2.0070 |
142
+ | 1.919 | 1.5657 | 930 | 2.0094 |
143
+ | 1.919 | 1.5825 | 940 | 2.0137 |
144
+ | 1.919 | 1.5993 | 950 | 2.0092 |
145
+ | 1.919 | 1.6162 | 960 | 2.0033 |
146
+ | 1.919 | 1.6330 | 970 | 2.0045 |
147
+ | 1.919 | 1.6498 | 980 | 2.0053 |
148
+ | 1.919 | 1.6667 | 990 | 2.0043 |
149
+ | 1.9546 | 1.6835 | 1000 | 2.0028 |
150
+ | 1.9546 | 1.7003 | 1010 | 2.0018 |
151
+ | 1.9546 | 1.7172 | 1020 | 2.0005 |
152
+ | 1.9546 | 1.7340 | 1030 | 1.9999 |
153
+ | 1.9546 | 1.7508 | 1040 | 1.9983 |
154
+ | 1.9546 | 1.7677 | 1050 | 1.9974 |
155
+ | 1.9546 | 1.7845 | 1060 | 1.9971 |
156
+ | 1.9546 | 1.8013 | 1070 | 1.9961 |
157
+ | 1.9546 | 1.8182 | 1080 | 1.9943 |
158
+ | 1.9546 | 1.8350 | 1090 | 1.9938 |
159
+ | 1.9247 | 1.8519 | 1100 | 1.9949 |
160
+ | 1.9247 | 1.8687 | 1110 | 1.9949 |
161
+ | 1.9247 | 1.8855 | 1120 | 1.9926 |
162
+ | 1.9247 | 1.9024 | 1130 | 1.9888 |
163
+ | 1.9247 | 1.9192 | 1140 | 1.9894 |
164
+ | 1.9247 | 1.9360 | 1150 | 1.9893 |
165
+ | 1.9247 | 1.9529 | 1160 | 1.9912 |
166
+ | 1.9247 | 1.9697 | 1170 | 1.9896 |
167
+ | 1.9247 | 1.9865 | 1180 | 1.9896 |
168
+ | 1.9247 | 2.0034 | 1190 | 1.9900 |
169
+ | 1.8978 | 2.0202 | 1200 | 1.9886 |
170
+ | 1.8978 | 2.0370 | 1210 | 1.9898 |
171
+ | 1.8978 | 2.0539 | 1220 | 1.9883 |
172
+ | 1.8978 | 2.0707 | 1230 | 1.9869 |
173
+ | 1.8978 | 2.0875 | 1240 | 1.9876 |
174
+ | 1.8978 | 2.1044 | 1250 | 1.9873 |
175
+ | 1.8978 | 2.1212 | 1260 | 1.9893 |
176
+ | 1.8978 | 2.1380 | 1270 | 1.9879 |
177
+ | 1.8978 | 2.1549 | 1280 | 1.9880 |
178
+ | 1.8978 | 2.1717 | 1290 | 1.9882 |
179
+ | 1.8637 | 2.1886 | 1300 | 1.9869 |
180
+ | 1.8637 | 2.2054 | 1310 | 1.9879 |
181
+ | 1.8637 | 2.2222 | 1320 | 1.9881 |
182
+ | 1.8637 | 2.2391 | 1330 | 1.9901 |
183
+ | 1.8637 | 2.2559 | 1340 | 1.9874 |
184
+ | 1.8637 | 2.2727 | 1350 | 1.9855 |
185
+ | 1.8637 | 2.2896 | 1360 | 1.9871 |
186
+ | 1.8637 | 2.3064 | 1370 | 1.9871 |
187
+ | 1.8637 | 2.3232 | 1380 | 1.9849 |
188
+ | 1.8637 | 2.3401 | 1390 | 1.9837 |
189
+ | 1.8206 | 2.3569 | 1400 | 1.9841 |
190
+ | 1.8206 | 2.3737 | 1410 | 1.9828 |
191
+ | 1.8206 | 2.3906 | 1420 | 1.9809 |
192
+ | 1.8206 | 2.4074 | 1430 | 1.9774 |
193
+ | 1.8206 | 2.4242 | 1440 | 1.9770 |
194
+ | 1.8206 | 2.4411 | 1450 | 1.9779 |
195
+ | 1.8206 | 2.4579 | 1460 | 1.9779 |
196
+ | 1.8206 | 2.4747 | 1470 | 1.9783 |
197
+ | 1.8206 | 2.4916 | 1480 | 1.9763 |
198
+ | 1.8206 | 2.5084 | 1490 | 1.9766 |
199
+ | 1.8587 | 2.5253 | 1500 | 1.9762 |
200
+ | 1.8587 | 2.5421 | 1510 | 1.9768 |
201
+ | 1.8587 | 2.5589 | 1520 | 1.9782 |
202
+ | 1.8587 | 2.5758 | 1530 | 1.9787 |
203
+ | 1.8587 | 2.5926 | 1540 | 1.9770 |
204
+ | 1.8587 | 2.6094 | 1550 | 1.9755 |
205
+ | 1.8587 | 2.6263 | 1560 | 1.9753 |
206
+ | 1.8587 | 2.6431 | 1570 | 1.9753 |
207
+ | 1.8587 | 2.6599 | 1580 | 1.9747 |
208
+ | 1.8587 | 2.6768 | 1590 | 1.9742 |
209
+ | 1.8226 | 2.6936 | 1600 | 1.9743 |
210
+ | 1.8226 | 2.7104 | 1610 | 1.9729 |
211
+ | 1.8226 | 2.7273 | 1620 | 1.9735 |
212
+ | 1.8226 | 2.7441 | 1630 | 1.9749 |
213
+ | 1.8226 | 2.7609 | 1640 | 1.9737 |
214
+ | 1.8226 | 2.7778 | 1650 | 1.9731 |
215
+ | 1.8226 | 2.7946 | 1660 | 1.9723 |
216
+ | 1.8226 | 2.8114 | 1670 | 1.9721 |
217
+ | 1.8226 | 2.8283 | 1680 | 1.9713 |
218
+ | 1.8226 | 2.8451 | 1690 | 1.9698 |
219
+ | 1.8331 | 2.8620 | 1700 | 1.9695 |
220
+ | 1.8331 | 2.8788 | 1710 | 1.9688 |
221
+ | 1.8331 | 2.8956 | 1720 | 1.9689 |
222
+ | 1.8331 | 2.9125 | 1730 | 1.9686 |
223
+ | 1.8331 | 2.9293 | 1740 | 1.9685 |
224
+ | 1.8331 | 2.9461 | 1750 | 1.9681 |
225
+ | 1.8331 | 2.9630 | 1760 | 1.9675 |
226
+ | 1.8331 | 2.9798 | 1770 | 1.9669 |
227
+ | 1.8331 | 2.9966 | 1780 | 1.9671 |
228
+ | 1.8331 | 3.0135 | 1790 | 1.9680 |
229
+ | 1.8251 | 3.0303 | 1800 | 1.9696 |
230
+ | 1.8251 | 3.0471 | 1810 | 1.9705 |
231
+ | 1.8251 | 3.0640 | 1820 | 1.9695 |
232
+ | 1.8251 | 3.0808 | 1830 | 1.9700 |
233
+ | 1.8251 | 3.0976 | 1840 | 1.9701 |
234
+ | 1.8251 | 3.1145 | 1850 | 1.9701 |
235
+ | 1.8251 | 3.1313 | 1860 | 1.9705 |
236
+ | 1.8251 | 3.1481 | 1870 | 1.9707 |
237
+ | 1.8251 | 3.1650 | 1880 | 1.9709 |
238
+ | 1.8251 | 3.1818 | 1890 | 1.9712 |
239
+ | 1.7809 | 3.1987 | 1900 | 1.9713 |
240
+ | 1.7809 | 3.2155 | 1910 | 1.9718 |
241
+ | 1.7809 | 3.2323 | 1920 | 1.9720 |
242
+ | 1.7809 | 3.2492 | 1930 | 1.9714 |
243
+ | 1.7809 | 3.2660 | 1940 | 1.9704 |
244
+ | 1.7809 | 3.2828 | 1950 | 1.9694 |
245
+ | 1.7809 | 3.2997 | 1960 | 1.9694 |
246
+ | 1.7809 | 3.3165 | 1970 | 1.9692 |
247
+ | 1.7809 | 3.3333 | 1980 | 1.9690 |
248
+ | 1.7809 | 3.3502 | 1990 | 1.9689 |
249
+ | 1.7957 | 3.3670 | 2000 | 1.9687 |
250
+ | 1.7957 | 3.3838 | 2010 | 1.9685 |
251
+ | 1.7957 | 3.4007 | 2020 | 1.9682 |
252
+ | 1.7957 | 3.4175 | 2030 | 1.9684 |
253
+ | 1.7957 | 3.4343 | 2040 | 1.9688 |
254
+ | 1.7957 | 3.4512 | 2050 | 1.9689 |
255
+ | 1.7957 | 3.4680 | 2060 | 1.9685 |
256
+ | 1.7957 | 3.4848 | 2070 | 1.9683 |
257
+ | 1.7957 | 3.5017 | 2080 | 1.9685 |
258
+ | 1.7957 | 3.5185 | 2090 | 1.9686 |
259
+ | 1.7859 | 3.5354 | 2100 | 1.9688 |
260
+ | 1.7859 | 3.5522 | 2110 | 1.9691 |
261
+ | 1.7859 | 3.5690 | 2120 | 1.9692 |
262
+ | 1.7859 | 3.5859 | 2130 | 1.9693 |
263
+ | 1.7859 | 3.6027 | 2140 | 1.9694 |
264
+ | 1.7859 | 3.6195 | 2150 | 1.9692 |
265
+ | 1.7859 | 3.6364 | 2160 | 1.9690 |
266
+ | 1.7859 | 3.6532 | 2170 | 1.9689 |
267
+ | 1.7859 | 3.6700 | 2180 | 1.9689 |
268
+ | 1.7859 | 3.6869 | 2190 | 1.9689 |
269
+ | 1.7794 | 3.7037 | 2200 | 1.9687 |
270
+ | 1.7794 | 3.7205 | 2210 | 1.9686 |
271
+ | 1.7794 | 3.7374 | 2220 | 1.9685 |
272
+ | 1.7794 | 3.7542 | 2230 | 1.9685 |
273
+ | 1.7794 | 3.7710 | 2240 | 1.9684 |
274
+ | 1.7794 | 3.7879 | 2250 | 1.9684 |
275
+ | 1.7794 | 3.8047 | 2260 | 1.9683 |
276
+ | 1.7794 | 3.8215 | 2270 | 1.9683 |
277
+ | 1.7794 | 3.8384 | 2280 | 1.9682 |
278
+ | 1.7794 | 3.8552 | 2290 | 1.9682 |
279
+ | 1.7766 | 3.8721 | 2300 | 1.9682 |
280
+ | 1.7766 | 3.8889 | 2310 | 1.9682 |
281
+ | 1.7766 | 3.9057 | 2320 | 1.9682 |
282
+ | 1.7766 | 3.9226 | 2330 | 1.9682 |
283
+ | 1.7766 | 3.9394 | 2340 | 1.9682 |
284
+ | 1.7766 | 3.9562 | 2350 | 1.9682 |
285
+ | 1.7766 | 3.9731 | 2360 | 1.9682 |
286
+ | 1.7766 | 3.9899 | 2370 | 1.9682 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
287
 
288
 
289
  ### Framework versions
runs/Jul22_02-07-44_cmle-training-9882793803855143298/events.out.tfevents.1721614065.cmle-training-9882793803855143298 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:77601a4e34a3a937a6d68f8a16e684d577be68677d91cce35cd015a644f1ea85
3
- size 73673
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1904db57a6dce127c8d0321d20ed2c545fc3fc32a097c4b7d2940951f1fba207
3
+ size 74298