Vichentito commited on
Commit
d5a17b1
1 Parent(s): ed3cf26

End of training

Browse files
README.md CHANGED
@@ -1,6 +1,4 @@
1
  ---
2
- license: apache-2.0
3
- base_model: google/flan-t5-base
4
  tags:
5
  - generated_from_trainer
6
  metrics:
@@ -15,11 +13,11 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # Nahuatl_Espanol_v1
17
 
18
- This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 1.5154
21
- - Bleu: 2.2653
22
- - Gen Len: 17.1333
23
 
24
  ## Model description
25
 
@@ -50,192 +48,192 @@ The following hyperparameters were used during training:
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
52
  |:-------------:|:-------:|:-----:|:---------------:|:------:|:-------:|
53
- | No log | 0.1610 | 100 | 2.3179 | 0.7638 | 18.0099 |
54
- | No log | 0.3221 | 200 | 2.2215 | 0.7642 | 17.7826 |
55
- | No log | 0.4831 | 300 | 2.1423 | 0.8569 | 17.6048 |
56
- | No log | 0.6441 | 400 | 2.0711 | 0.9499 | 17.6088 |
57
- | 2.2828 | 0.8052 | 500 | 2.0262 | 1.0213 | 17.4291 |
58
- | 2.2828 | 0.9662 | 600 | 1.9769 | 1.0255 | 17.5774 |
59
- | 2.2828 | 1.1272 | 700 | 1.9424 | 1.0666 | 17.4301 |
60
- | 2.2828 | 1.2882 | 800 | 1.9020 | 1.1141 | 17.5849 |
61
- | 2.2828 | 1.4493 | 900 | 1.8767 | 1.2416 | 17.2931 |
62
- | 2.0671 | 1.6103 | 1000 | 1.8469 | 1.3325 | 17.4264 |
63
- | 2.0671 | 1.7713 | 1100 | 1.8227 | 1.3589 | 17.4095 |
64
- | 2.0671 | 1.9324 | 1200 | 1.7893 | 1.1997 | 17.4643 |
65
- | 2.0671 | 2.0934 | 1300 | 1.7792 | 1.3348 | 17.4205 |
66
- | 2.0671 | 2.2544 | 1400 | 1.7578 | 1.3012 | 17.4621 |
67
- | 1.8797 | 2.4155 | 1500 | 1.7341 | 1.353 | 17.4318 |
68
- | 1.8797 | 2.5765 | 1600 | 1.7179 | 1.3681 | 17.3912 |
69
- | 1.8797 | 2.7375 | 1700 | 1.7002 | 1.3002 | 17.3364 |
70
- | 1.8797 | 2.8986 | 1800 | 1.6853 | 1.3557 | 17.3415 |
71
- | 1.8797 | 3.0596 | 1900 | 1.6827 | 1.4801 | 17.331 |
72
- | 1.7661 | 3.2206 | 2000 | 1.6606 | 1.5884 | 17.3165 |
73
- | 1.7661 | 3.3816 | 2100 | 1.6442 | 1.5312 | 17.3538 |
74
- | 1.7661 | 3.5427 | 2200 | 1.6340 | 1.533 | 17.3455 |
75
- | 1.7661 | 3.7037 | 2300 | 1.6182 | 1.5647 | 17.2491 |
76
- | 1.7661 | 3.8647 | 2400 | 1.6061 | 1.4782 | 17.2389 |
77
- | 1.6576 | 4.0258 | 2500 | 1.6168 | 1.6584 | 17.2174 |
78
- | 1.6576 | 4.1868 | 2600 | 1.6077 | 1.678 | 17.31 |
79
- | 1.6576 | 4.3478 | 2700 | 1.5914 | 1.597 | 17.3068 |
80
- | 1.6576 | 4.5089 | 2800 | 1.5727 | 1.6485 | 17.3987 |
81
- | 1.6576 | 4.6699 | 2900 | 1.5647 | 1.6079 | 17.3391 |
82
- | 1.56 | 4.8309 | 3000 | 1.5531 | 1.6307 | 17.274 |
83
- | 1.56 | 4.9919 | 3100 | 1.5456 | 1.6314 | 17.3845 |
84
- | 1.56 | 5.1530 | 3200 | 1.5585 | 1.6671 | 17.2402 |
85
- | 1.56 | 5.3140 | 3300 | 1.5398 | 1.6264 | 17.2601 |
86
- | 1.56 | 5.4750 | 3400 | 1.5351 | 1.6673 | 17.3141 |
87
- | 1.4881 | 5.6361 | 3500 | 1.5244 | 1.6951 | 17.3184 |
88
- | 1.4881 | 5.7971 | 3600 | 1.5114 | 1.7094 | 17.2786 |
89
- | 1.4881 | 5.9581 | 3700 | 1.5153 | 1.785 | 17.2622 |
90
- | 1.4881 | 6.1192 | 3800 | 1.5128 | 1.7629 | 17.2539 |
91
- | 1.4881 | 6.2802 | 3900 | 1.5041 | 1.8124 | 17.2536 |
92
- | 1.4276 | 6.4412 | 4000 | 1.5071 | 1.7952 | 17.2219 |
93
- | 1.4276 | 6.6023 | 4100 | 1.4941 | 1.7619 | 17.238 |
94
- | 1.4276 | 6.7633 | 4200 | 1.4918 | 1.8064 | 17.3213 |
95
- | 1.4276 | 6.9243 | 4300 | 1.4807 | 1.8163 | 17.2918 |
96
- | 1.4276 | 7.0853 | 4400 | 1.4925 | 1.7995 | 17.1738 |
97
- | 1.374 | 7.2464 | 4500 | 1.4904 | 1.7981 | 17.3036 |
98
- | 1.374 | 7.4074 | 4600 | 1.4710 | 1.8179 | 17.1642 |
99
- | 1.374 | 7.5684 | 4700 | 1.4761 | 1.8369 | 17.2208 |
100
- | 1.374 | 7.7295 | 4800 | 1.4654 | 1.8904 | 17.2673 |
101
- | 1.374 | 7.8905 | 4900 | 1.4639 | 1.8355 | 17.2329 |
102
- | 1.3276 | 8.0515 | 5000 | 1.4702 | 1.8657 | 17.3017 |
103
- | 1.3276 | 8.2126 | 5100 | 1.4709 | 1.8587 | 17.1985 |
104
- | 1.3276 | 8.3736 | 5200 | 1.4581 | 1.8356 | 17.2383 |
105
- | 1.3276 | 8.5346 | 5300 | 1.4506 | 1.7963 | 17.3127 |
106
- | 1.3276 | 8.6957 | 5400 | 1.4508 | 1.8119 | 17.2227 |
107
- | 1.2675 | 8.8567 | 5500 | 1.4470 | 1.8833 | 17.2303 |
108
- | 1.2675 | 9.0177 | 5600 | 1.4635 | 1.9121 | 17.2491 |
109
- | 1.2675 | 9.1787 | 5700 | 1.4545 | 1.9176 | 17.2305 |
110
- | 1.2675 | 9.3398 | 5800 | 1.4513 | 1.9372 | 17.2383 |
111
- | 1.2675 | 9.5008 | 5900 | 1.4537 | 1.8879 | 17.2423 |
112
- | 1.2169 | 9.6618 | 6000 | 1.4395 | 1.8688 | 17.2281 |
113
- | 1.2169 | 9.8229 | 6100 | 1.4383 | 1.9686 | 17.1642 |
114
- | 1.2169 | 9.9839 | 6200 | 1.4384 | 1.8888 | 17.1733 |
115
- | 1.2169 | 10.1449 | 6300 | 1.4493 | 1.9693 | 17.2278 |
116
- | 1.2169 | 10.3060 | 6400 | 1.4482 | 1.9316 | 17.2053 |
117
- | 1.1713 | 10.4670 | 6500 | 1.4417 | 1.9584 | 17.1991 |
118
- | 1.1713 | 10.6280 | 6600 | 1.4265 | 1.9343 | 17.2071 |
119
- | 1.1713 | 10.7890 | 6700 | 1.4257 | 1.9549 | 17.1685 |
120
- | 1.1713 | 10.9501 | 6800 | 1.4166 | 2.0275 | 17.158 |
121
- | 1.1713 | 11.1111 | 6900 | 1.4429 | 1.9878 | 17.2093 |
122
- | 1.1472 | 11.2721 | 7000 | 1.4376 | 1.9507 | 17.209 |
123
- | 1.1472 | 11.4332 | 7100 | 1.4353 | 2.0378 | 17.1873 |
124
- | 1.1472 | 11.5942 | 7200 | 1.4301 | 1.981 | 17.1497 |
125
- | 1.1472 | 11.7552 | 7300 | 1.4194 | 1.949 | 17.1548 |
126
- | 1.1472 | 11.9163 | 7400 | 1.4262 | 1.9815 | 17.1795 |
127
- | 1.1085 | 12.0773 | 7500 | 1.4416 | 2.0402 | 17.1601 |
128
- | 1.1085 | 12.2383 | 7600 | 1.4343 | 2.0161 | 17.1518 |
129
- | 1.1085 | 12.3994 | 7700 | 1.4268 | 2.0063 | 17.1921 |
130
- | 1.1085 | 12.5604 | 7800 | 1.4187 | 1.9984 | 17.2061 |
131
- | 1.1085 | 12.7214 | 7900 | 1.4294 | 2.0133 | 17.1574 |
132
- | 1.0705 | 12.8824 | 8000 | 1.4317 | 2.0277 | 17.1679 |
133
- | 1.0705 | 13.0435 | 8100 | 1.4358 | 2.0857 | 17.1437 |
134
- | 1.0705 | 13.2045 | 8200 | 1.4320 | 2.0843 | 17.1695 |
135
- | 1.0705 | 13.3655 | 8300 | 1.4205 | 2.0842 | 17.2276 |
136
- | 1.0705 | 13.5266 | 8400 | 1.4246 | 2.0441 | 17.1488 |
137
- | 1.0359 | 13.6876 | 8500 | 1.4246 | 2.0807 | 17.2569 |
138
- | 1.0359 | 13.8486 | 8600 | 1.4178 | 2.0278 | 17.1647 |
139
- | 1.0359 | 14.0097 | 8700 | 1.4265 | 2.0627 | 17.1711 |
140
- | 1.0359 | 14.1707 | 8800 | 1.4427 | 2.1085 | 17.1295 |
141
- | 1.0359 | 14.3317 | 8900 | 1.4283 | 2.0871 | 17.1738 |
142
- | 1.0029 | 14.4928 | 9000 | 1.4273 | 2.1009 | 17.223 |
143
- | 1.0029 | 14.6538 | 9100 | 1.4322 | 2.0663 | 17.1392 |
144
- | 1.0029 | 14.8148 | 9200 | 1.4225 | 2.1163 | 17.1236 |
145
- | 1.0029 | 14.9758 | 9300 | 1.4247 | 2.1017 | 17.147 |
146
- | 1.0029 | 15.1369 | 9400 | 1.4374 | 2.0509 | 17.133 |
147
- | 0.9794 | 15.2979 | 9500 | 1.4342 | 2.0897 | 17.1959 |
148
- | 0.9794 | 15.4589 | 9600 | 1.4252 | 2.1142 | 17.1459 |
149
- | 0.9794 | 15.6200 | 9700 | 1.4250 | 2.1114 | 17.1865 |
150
- | 0.9794 | 15.7810 | 9800 | 1.4271 | 2.1773 | 17.1131 |
151
- | 0.9794 | 15.9420 | 9900 | 1.4300 | 2.1037 | 17.1824 |
152
- | 0.9574 | 16.1031 | 10000 | 1.4499 | 2.1544 | 17.1582 |
153
- | 0.9574 | 16.2641 | 10100 | 1.4446 | 2.1116 | 17.1515 |
154
- | 0.9574 | 16.4251 | 10200 | 1.4338 | 2.116 | 17.1542 |
155
- | 0.9574 | 16.5862 | 10300 | 1.4429 | 2.0679 | 17.1507 |
156
- | 0.9574 | 16.7472 | 10400 | 1.4366 | 2.1286 | 17.1448 |
157
- | 0.9228 | 16.9082 | 10500 | 1.4317 | 2.1217 | 17.1744 |
158
- | 0.9228 | 17.0692 | 10600 | 1.4419 | 2.0927 | 17.1494 |
159
- | 0.9228 | 17.2303 | 10700 | 1.4500 | 2.1305 | 17.151 |
160
- | 0.9228 | 17.3913 | 10800 | 1.4499 | 2.1222 | 17.1789 |
161
- | 0.9228 | 17.5523 | 10900 | 1.4406 | 2.1485 | 17.1381 |
162
- | 0.904 | 17.7134 | 11000 | 1.4384 | 2.1156 | 17.1687 |
163
- | 0.904 | 17.8744 | 11100 | 1.4336 | 2.1636 | 17.1811 |
164
- | 0.904 | 18.0354 | 11200 | 1.4567 | 2.1351 | 17.1741 |
165
- | 0.904 | 18.1965 | 11300 | 1.4486 | 2.0972 | 17.1628 |
166
- | 0.904 | 18.3575 | 11400 | 1.4456 | 2.0998 | 17.1596 |
167
- | 0.8687 | 18.5185 | 11500 | 1.4507 | 2.1431 | 17.1411 |
168
- | 0.8687 | 18.6795 | 11600 | 1.4506 | 2.0942 | 17.1505 |
169
- | 0.8687 | 18.8406 | 11700 | 1.4354 | 2.1521 | 17.1263 |
170
- | 0.8687 | 19.0016 | 11800 | 1.4343 | 2.1521 | 17.1475 |
171
- | 0.8687 | 19.1626 | 11900 | 1.4657 | 2.177 | 17.1666 |
172
- | 0.8607 | 19.3237 | 12000 | 1.4569 | 2.1509 | 17.1814 |
173
- | 0.8607 | 19.4847 | 12100 | 1.4499 | 2.1553 | 17.1217 |
174
- | 0.8607 | 19.6457 | 12200 | 1.4438 | 2.1261 | 17.1467 |
175
- | 0.8607 | 19.8068 | 12300 | 1.4429 | 2.1572 | 17.1381 |
176
- | 0.8607 | 19.9678 | 12400 | 1.4459 | 2.1982 | 17.1599 |
177
- | 0.8445 | 20.1288 | 12500 | 1.4669 | 2.2097 | 17.1749 |
178
- | 0.8445 | 20.2899 | 12600 | 1.4637 | 2.1451 | 17.1335 |
179
- | 0.8445 | 20.4509 | 12700 | 1.4568 | 2.1697 | 17.1467 |
180
- | 0.8445 | 20.6119 | 12800 | 1.4526 | 2.2072 | 17.1709 |
181
- | 0.8445 | 20.7729 | 12900 | 1.4678 | 2.1904 | 17.1421 |
182
- | 0.8226 | 20.9340 | 13000 | 1.4546 | 2.1783 | 17.1411 |
183
- | 0.8226 | 21.0950 | 13100 | 1.4760 | 2.2183 | 17.1338 |
184
- | 0.8226 | 21.2560 | 13200 | 1.4686 | 2.1857 | 17.1222 |
185
- | 0.8226 | 21.4171 | 13300 | 1.4689 | 2.2066 | 17.2028 |
186
- | 0.8226 | 21.5781 | 13400 | 1.4700 | 2.2407 | 17.1163 |
187
- | 0.8057 | 21.7391 | 13500 | 1.4764 | 2.2428 | 17.13 |
188
- | 0.8057 | 21.9002 | 13600 | 1.4671 | 2.1992 | 17.1196 |
189
- | 0.8057 | 22.0612 | 13700 | 1.4714 | 2.2272 | 17.111 |
190
- | 0.8057 | 22.2222 | 13800 | 1.4839 | 2.209 | 17.1163 |
191
- | 0.8057 | 22.3833 | 13900 | 1.4752 | 2.2453 | 17.1319 |
192
- | 0.7809 | 22.5443 | 14000 | 1.4628 | 2.1897 | 17.1462 |
193
- | 0.7809 | 22.7053 | 14100 | 1.4635 | 2.2228 | 17.1472 |
194
- | 0.7809 | 22.8663 | 14200 | 1.4712 | 2.243 | 17.1282 |
195
- | 0.7809 | 23.0274 | 14300 | 1.4791 | 2.2124 | 17.1419 |
196
- | 0.7809 | 23.1884 | 14400 | 1.4872 | 2.2557 | 17.1204 |
197
- | 0.7719 | 23.3494 | 14500 | 1.4927 | 2.2347 | 17.1241 |
198
- | 0.7719 | 23.5105 | 14600 | 1.4746 | 2.2433 | 17.1206 |
199
- | 0.7719 | 23.6715 | 14700 | 1.4932 | 2.2536 | 17.1193 |
200
- | 0.7719 | 23.8325 | 14800 | 1.4854 | 2.2668 | 17.1523 |
201
- | 0.7719 | 23.9936 | 14900 | 1.4895 | 2.2108 | 17.0879 |
202
- | 0.7588 | 24.1546 | 15000 | 1.5019 | 2.2456 | 17.1241 |
203
- | 0.7588 | 24.3156 | 15100 | 1.4935 | 2.2128 | 17.137 |
204
- | 0.7588 | 24.4767 | 15200 | 1.4953 | 2.2573 | 17.1338 |
205
- | 0.7588 | 24.6377 | 15300 | 1.4921 | 2.3069 | 17.1212 |
206
- | 0.7588 | 24.7987 | 15400 | 1.4913 | 2.2572 | 17.1185 |
207
- | 0.7466 | 24.9597 | 15500 | 1.4861 | 2.281 | 17.1429 |
208
- | 0.7466 | 25.1208 | 15600 | 1.5026 | 2.2549 | 17.1155 |
209
- | 0.7466 | 25.2818 | 15700 | 1.5035 | 2.2658 | 17.13 |
210
- | 0.7466 | 25.4428 | 15800 | 1.5062 | 2.2296 | 17.1179 |
211
- | 0.7466 | 25.6039 | 15900 | 1.5009 | 2.2533 | 17.1222 |
212
- | 0.7317 | 25.7649 | 16000 | 1.4860 | 2.2324 | 17.133 |
213
- | 0.7317 | 25.9259 | 16100 | 1.4926 | 2.2392 | 17.1284 |
214
- | 0.7317 | 26.0870 | 16200 | 1.5146 | 2.2788 | 17.1276 |
215
- | 0.7317 | 26.2480 | 16300 | 1.5021 | 2.2681 | 17.1338 |
216
- | 0.7317 | 26.4090 | 16400 | 1.4959 | 2.2617 | 17.1357 |
217
- | 0.7265 | 26.5700 | 16500 | 1.5047 | 2.2686 | 17.133 |
218
- | 0.7265 | 26.7311 | 16600 | 1.5070 | 2.2427 | 17.1193 |
219
- | 0.7265 | 26.8921 | 16700 | 1.5046 | 2.2522 | 17.1042 |
220
- | 0.7265 | 27.0531 | 16800 | 1.5086 | 2.2463 | 17.1282 |
221
- | 0.7265 | 27.2142 | 16900 | 1.5095 | 2.2689 | 17.1274 |
222
- | 0.7166 | 27.3752 | 17000 | 1.5105 | 2.2589 | 17.1188 |
223
- | 0.7166 | 27.5362 | 17100 | 1.5042 | 2.2538 | 17.1123 |
224
- | 0.7166 | 27.6973 | 17200 | 1.5077 | 2.2606 | 17.1257 |
225
- | 0.7166 | 27.8583 | 17300 | 1.5023 | 2.2879 | 17.1333 |
226
- | 0.7166 | 28.0193 | 17400 | 1.5078 | 2.2703 | 17.1231 |
227
- | 0.7132 | 28.1804 | 17500 | 1.5126 | 2.2849 | 17.1091 |
228
- | 0.7132 | 28.3414 | 17600 | 1.5092 | 2.2641 | 17.1265 |
229
- | 0.7132 | 28.5024 | 17700 | 1.5136 | 2.2667 | 17.1206 |
230
- | 0.7132 | 28.6634 | 17800 | 1.5114 | 2.2698 | 17.1314 |
231
- | 0.7132 | 28.8245 | 17900 | 1.5069 | 2.2702 | 17.1397 |
232
- | 0.7012 | 28.9855 | 18000 | 1.5095 | 2.2596 | 17.1327 |
233
- | 0.7012 | 29.1465 | 18100 | 1.5150 | 2.26 | 17.137 |
234
- | 0.7012 | 29.3076 | 18200 | 1.5120 | 2.26 | 17.1303 |
235
- | 0.7012 | 29.4686 | 18300 | 1.5135 | 2.2713 | 17.1346 |
236
- | 0.7012 | 29.6296 | 18400 | 1.5139 | 2.2483 | 17.1276 |
237
- | 0.6987 | 29.7907 | 18500 | 1.5148 | 2.2528 | 17.13 |
238
- | 0.6987 | 29.9517 | 18600 | 1.5154 | 2.2653 | 17.1333 |
239
 
240
 
241
  ### Framework versions
 
1
  ---
 
 
2
  tags:
3
  - generated_from_trainer
4
  metrics:
 
13
 
14
  # Nahuatl_Espanol_v1
15
 
16
+ This model was trained from scratch on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 1.7731
19
+ - Bleu: 2.855
20
+ - Gen Len: 16.4731
21
 
22
  ## Model description
23
 
 
48
 
49
  | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
50
  |:-------------:|:-------:|:-----:|:---------------:|:------:|:-------:|
51
+ | No log | 0.1610 | 100 | 2.5463 | 0.3374 | 17.6013 |
52
+ | No log | 0.3221 | 200 | 2.3620 | 0.5422 | 17.5578 |
53
+ | No log | 0.4831 | 300 | 2.2535 | 0.5657 | 17.2797 |
54
+ | No log | 0.6441 | 400 | 2.1754 | 0.7341 | 17.2977 |
55
+ | 2.6455 | 0.8052 | 500 | 2.1126 | 0.8894 | 16.9874 |
56
+ | 2.6455 | 0.9662 | 600 | 2.0582 | 0.9524 | 17.036 |
57
+ | 2.6455 | 1.1272 | 700 | 2.0159 | 1.0109 | 16.9672 |
58
+ | 2.6455 | 1.2882 | 800 | 1.9775 | 1.1543 | 16.8598 |
59
+ | 2.6455 | 1.4493 | 900 | 1.9452 | 1.1861 | 16.8724 |
60
+ | 2.1536 | 1.6103 | 1000 | 1.9148 | 1.2127 | 16.9035 |
61
+ | 2.1536 | 1.7713 | 1100 | 1.8855 | 1.3266 | 16.9366 |
62
+ | 2.1536 | 1.9324 | 1200 | 1.8609 | 1.3655 | 16.878 |
63
+ | 2.1536 | 2.0934 | 1300 | 1.8449 | 1.4542 | 16.7461 |
64
+ | 2.1536 | 2.2544 | 1400 | 1.8221 | 1.4619 | 16.6625 |
65
+ | 1.9509 | 2.4155 | 1500 | 1.8114 | 1.5078 | 16.8248 |
66
+ | 1.9509 | 2.5765 | 1600 | 1.7913 | 1.6021 | 16.756 |
67
+ | 1.9509 | 2.7375 | 1700 | 1.7632 | 1.5406 | 16.8348 |
68
+ | 1.9509 | 2.8986 | 1800 | 1.7524 | 1.6257 | 16.7233 |
69
+ | 1.9509 | 3.0596 | 1900 | 1.7450 | 1.6093 | 16.7668 |
70
+ | 1.8086 | 3.2206 | 2000 | 1.7397 | 1.6759 | 16.7077 |
71
+ | 1.8086 | 3.3816 | 2100 | 1.7152 | 1.7204 | 16.7182 |
72
+ | 1.8086 | 3.5427 | 2200 | 1.7080 | 1.6942 | 16.6916 |
73
+ | 1.8086 | 3.7037 | 2300 | 1.7020 | 1.7501 | 16.5768 |
74
+ | 1.8086 | 3.8647 | 2400 | 1.6805 | 1.7556 | 16.7566 |
75
+ | 1.6943 | 4.0258 | 2500 | 1.6866 | 1.795 | 16.586 |
76
+ | 1.6943 | 4.1868 | 2600 | 1.6717 | 1.835 | 16.6588 |
77
+ | 1.6943 | 4.3478 | 2700 | 1.6658 | 1.824 | 16.5852 |
78
+ | 1.6943 | 4.5089 | 2800 | 1.6573 | 1.8731 | 16.6032 |
79
+ | 1.6943 | 4.6699 | 2900 | 1.6483 | 1.8997 | 16.6628 |
80
+ | 1.5847 | 4.8309 | 3000 | 1.6405 | 1.86 | 16.6362 |
81
+ | 1.5847 | 4.9919 | 3100 | 1.6217 | 1.9496 | 16.7004 |
82
+ | 1.5847 | 5.1530 | 3200 | 1.6342 | 1.9594 | 16.6405 |
83
+ | 1.5847 | 5.3140 | 3300 | 1.6340 | 1.9784 | 16.6155 |
84
+ | 1.5847 | 5.4750 | 3400 | 1.6271 | 2.0696 | 16.5838 |
85
+ | 1.5035 | 5.6361 | 3500 | 1.6177 | 1.9757 | 16.5895 |
86
+ | 1.5035 | 5.7971 | 3600 | 1.6119 | 2.0183 | 16.5551 |
87
+ | 1.5035 | 5.9581 | 3700 | 1.6002 | 2.0347 | 16.5473 |
88
+ | 1.5035 | 6.1192 | 3800 | 1.6029 | 2.0596 | 16.5951 |
89
+ | 1.5035 | 6.2802 | 3900 | 1.6064 | 2.0672 | 16.5529 |
90
+ | 1.4234 | 6.4412 | 4000 | 1.6070 | 2.2163 | 16.6067 |
91
+ | 1.4234 | 6.6023 | 4100 | 1.5889 | 2.1004 | 16.6212 |
92
+ | 1.4234 | 6.7633 | 4200 | 1.5925 | 2.1498 | 16.5591 |
93
+ | 1.4234 | 6.9243 | 4300 | 1.5911 | 2.1569 | 16.6832 |
94
+ | 1.4234 | 7.0853 | 4400 | 1.5902 | 2.1138 | 16.5618 |
95
+ | 1.3688 | 7.2464 | 4500 | 1.5970 | 2.151 | 16.5849 |
96
+ | 1.3688 | 7.4074 | 4600 | 1.5906 | 2.1259 | 16.5553 |
97
+ | 1.3688 | 7.5684 | 4700 | 1.5857 | 2.2305 | 16.5443 |
98
+ | 1.3688 | 7.7295 | 4800 | 1.5672 | 2.2411 | 16.547 |
99
+ | 1.3688 | 7.8905 | 4900 | 1.5596 | 2.2849 | 16.5562 |
100
+ | 1.3144 | 8.0515 | 5000 | 1.5777 | 2.256 | 16.5828 |
101
+ | 1.3144 | 8.2126 | 5100 | 1.5855 | 2.2882 | 16.5489 |
102
+ | 1.3144 | 8.3736 | 5200 | 1.5834 | 2.2823 | 16.5682 |
103
+ | 1.3144 | 8.5346 | 5300 | 1.5723 | 2.2694 | 16.5328 |
104
+ | 1.3144 | 8.6957 | 5400 | 1.5713 | 2.2923 | 16.5478 |
105
+ | 1.244 | 8.8567 | 5500 | 1.5638 | 2.3811 | 16.5425 |
106
+ | 1.244 | 9.0177 | 5600 | 1.5842 | 2.3126 | 16.5776 |
107
+ | 1.244 | 9.1787 | 5700 | 1.5777 | 2.357 | 16.5226 |
108
+ | 1.244 | 9.3398 | 5800 | 1.5618 | 2.3822 | 16.4809 |
109
+ | 1.244 | 9.5008 | 5900 | 1.5710 | 2.3494 | 16.5038 |
110
+ | 1.1933 | 9.6618 | 6000 | 1.5728 | 2.3299 | 16.5287 |
111
+ | 1.1933 | 9.8229 | 6100 | 1.5520 | 2.4029 | 16.5317 |
112
+ | 1.1933 | 9.9839 | 6200 | 1.5572 | 2.3852 | 16.5411 |
113
+ | 1.1933 | 10.1449 | 6300 | 1.5791 | 2.3908 | 16.4973 |
114
+ | 1.1933 | 10.3060 | 6400 | 1.5676 | 2.4364 | 16.5336 |
115
+ | 1.1507 | 10.4670 | 6500 | 1.5796 | 2.4361 | 16.4925 |
116
+ | 1.1507 | 10.6280 | 6600 | 1.5560 | 2.4666 | 16.5239 |
117
+ | 1.1507 | 10.7890 | 6700 | 1.5596 | 2.4446 | 16.55 |
118
+ | 1.1507 | 10.9501 | 6800 | 1.5521 | 2.4664 | 16.5459 |
119
+ | 1.1507 | 11.1111 | 6900 | 1.5784 | 2.5296 | 16.5196 |
120
+ | 1.1065 | 11.2721 | 7000 | 1.5680 | 2.4907 | 16.5454 |
121
+ | 1.1065 | 11.4332 | 7100 | 1.5717 | 2.4572 | 16.449 |
122
+ | 1.1065 | 11.5942 | 7200 | 1.5628 | 2.4754 | 16.4715 |
123
+ | 1.1065 | 11.7552 | 7300 | 1.5531 | 2.5194 | 16.5411 |
124
+ | 1.1065 | 11.9163 | 7400 | 1.5634 | 2.536 | 16.5247 |
125
+ | 1.0746 | 12.0773 | 7500 | 1.5911 | 2.5297 | 16.5271 |
126
+ | 1.0746 | 12.2383 | 7600 | 1.5856 | 2.5618 | 16.514 |
127
+ | 1.0746 | 12.3994 | 7700 | 1.5821 | 2.5151 | 16.5024 |
128
+ | 1.0746 | 12.5604 | 7800 | 1.5799 | 2.5401 | 16.4895 |
129
+ | 1.0746 | 12.7214 | 7900 | 1.5702 | 2.5466 | 16.4798 |
130
+ | 1.0266 | 12.8824 | 8000 | 1.5721 | 2.584 | 16.4952 |
131
+ | 1.0266 | 13.0435 | 8100 | 1.5895 | 2.6024 | 16.5406 |
132
+ | 1.0266 | 13.2045 | 8200 | 1.5863 | 2.5719 | 16.5395 |
133
+ | 1.0266 | 13.3655 | 8300 | 1.5887 | 2.5903 | 16.4742 |
134
+ | 1.0266 | 13.5266 | 8400 | 1.6005 | 2.5751 | 16.5457 |
135
+ | 0.9806 | 13.6876 | 8500 | 1.5757 | 2.6075 | 16.4782 |
136
+ | 0.9806 | 13.8486 | 8600 | 1.5767 | 2.6331 | 16.4887 |
137
+ | 0.9806 | 14.0097 | 8700 | 1.5863 | 2.5818 | 16.4785 |
138
+ | 0.9806 | 14.1707 | 8800 | 1.6043 | 2.6117 | 16.5408 |
139
+ | 0.9806 | 14.3317 | 8900 | 1.5829 | 2.5749 | 16.45 |
140
+ | 0.9577 | 14.4928 | 9000 | 1.6059 | 2.5734 | 16.5019 |
141
+ | 0.9577 | 14.6538 | 9100 | 1.5926 | 2.6662 | 16.4831 |
142
+ | 0.9577 | 14.8148 | 9200 | 1.5854 | 2.6131 | 16.5116 |
143
+ | 0.9577 | 14.9758 | 9300 | 1.5714 | 2.6157 | 16.4954 |
144
+ | 0.9577 | 15.1369 | 9400 | 1.6011 | 2.6916 | 16.442 |
145
+ | 0.9266 | 15.2979 | 9500 | 1.6128 | 2.6445 | 16.5242 |
146
+ | 0.9266 | 15.4589 | 9600 | 1.6070 | 2.6538 | 16.4847 |
147
+ | 0.9266 | 15.6200 | 9700 | 1.6060 | 2.5989 | 16.5059 |
148
+ | 0.9266 | 15.7810 | 9800 | 1.6178 | 2.5933 | 16.5266 |
149
+ | 0.9266 | 15.9420 | 9900 | 1.6260 | 2.6454 | 16.4979 |
150
+ | 0.8936 | 16.1031 | 10000 | 1.6296 | 2.6559 | 16.461 |
151
+ | 0.8936 | 16.2641 | 10100 | 1.6290 | 2.6873 | 16.4997 |
152
+ | 0.8936 | 16.4251 | 10200 | 1.6076 | 2.6861 | 16.4694 |
153
+ | 0.8936 | 16.5862 | 10300 | 1.6201 | 2.6822 | 16.4524 |
154
+ | 0.8936 | 16.7472 | 10400 | 1.6161 | 2.7133 | 16.4833 |
155
+ | 0.8613 | 16.9082 | 10500 | 1.6229 | 2.686 | 16.4554 |
156
+ | 0.8613 | 17.0692 | 10600 | 1.6395 | 2.7024 | 16.4213 |
157
+ | 0.8613 | 17.2303 | 10700 | 1.6463 | 2.6706 | 16.4331 |
158
+ | 0.8613 | 17.3913 | 10800 | 1.6549 | 2.6859 | 16.4484 |
159
+ | 0.8613 | 17.5523 | 10900 | 1.6331 | 2.6857 | 16.4863 |
160
+ | 0.8385 | 17.7134 | 11000 | 1.6305 | 2.6936 | 16.4441 |
161
+ | 0.8385 | 17.8744 | 11100 | 1.6322 | 2.6882 | 16.4503 |
162
+ | 0.8385 | 18.0354 | 11200 | 1.6516 | 2.7029 | 16.4175 |
163
+ | 0.8385 | 18.1965 | 11300 | 1.6568 | 2.6676 | 16.4602 |
164
+ | 0.8385 | 18.3575 | 11400 | 1.6554 | 2.6773 | 16.4954 |
165
+ | 0.8034 | 18.5185 | 11500 | 1.6494 | 2.7066 | 16.4213 |
166
+ | 0.8034 | 18.6795 | 11600 | 1.6497 | 2.6936 | 16.4436 |
167
+ | 0.8034 | 18.8406 | 11700 | 1.6394 | 2.7009 | 16.4833 |
168
+ | 0.8034 | 19.0016 | 11800 | 1.6493 | 2.7471 | 16.4549 |
169
+ | 0.8034 | 19.1626 | 11900 | 1.6696 | 2.6889 | 16.417 |
170
+ | 0.7883 | 19.3237 | 12000 | 1.6540 | 2.6753 | 16.4382 |
171
+ | 0.7883 | 19.4847 | 12100 | 1.6597 | 2.7349 | 16.4557 |
172
+ | 0.7883 | 19.6457 | 12200 | 1.6558 | 2.7191 | 16.4393 |
173
+ | 0.7883 | 19.8068 | 12300 | 1.6557 | 2.7646 | 16.4484 |
174
+ | 0.7883 | 19.9678 | 12400 | 1.6599 | 2.7076 | 16.4444 |
175
+ | 0.7761 | 20.1288 | 12500 | 1.6873 | 2.7427 | 16.4653 |
176
+ | 0.7761 | 20.2899 | 12600 | 1.6976 | 2.7498 | 16.4704 |
177
+ | 0.7761 | 20.4509 | 12700 | 1.6969 | 2.7683 | 16.4331 |
178
+ | 0.7761 | 20.6119 | 12800 | 1.6710 | 2.7009 | 16.4347 |
179
+ | 0.7761 | 20.7729 | 12900 | 1.6614 | 2.7105 | 16.4038 |
180
+ | 0.7438 | 20.9340 | 13000 | 1.6864 | 2.7188 | 16.425 |
181
+ | 0.7438 | 21.0950 | 13100 | 1.6923 | 2.7656 | 16.4909 |
182
+ | 0.7438 | 21.2560 | 13200 | 1.7034 | 2.745 | 16.4675 |
183
+ | 0.7438 | 21.4171 | 13300 | 1.6972 | 2.7237 | 16.428 |
184
+ | 0.7438 | 21.5781 | 13400 | 1.6992 | 2.7556 | 16.4242 |
185
+ | 0.7251 | 21.7391 | 13500 | 1.6785 | 2.8106 | 16.45 |
186
+ | 0.7251 | 21.9002 | 13600 | 1.6830 | 2.7098 | 16.4108 |
187
+ | 0.7251 | 22.0612 | 13700 | 1.7122 | 2.733 | 16.4656 |
188
+ | 0.7251 | 22.2222 | 13800 | 1.7046 | 2.7216 | 16.4331 |
189
+ | 0.7251 | 22.3833 | 13900 | 1.6968 | 2.7373 | 16.4326 |
190
+ | 0.7049 | 22.5443 | 14000 | 1.7202 | 2.7242 | 16.4777 |
191
+ | 0.7049 | 22.7053 | 14100 | 1.6988 | 2.7873 | 16.4804 |
192
+ | 0.7049 | 22.8663 | 14200 | 1.6913 | 2.7961 | 16.446 |
193
+ | 0.7049 | 23.0274 | 14300 | 1.7020 | 2.7455 | 16.4575 |
194
+ | 0.7049 | 23.1884 | 14400 | 1.7156 | 2.7819 | 16.4436 |
195
+ | 0.6917 | 23.3494 | 14500 | 1.7248 | 2.7571 | 16.4436 |
196
+ | 0.6917 | 23.5105 | 14600 | 1.7131 | 2.7771 | 16.4573 |
197
+ | 0.6917 | 23.6715 | 14700 | 1.7140 | 2.7973 | 16.4495 |
198
+ | 0.6917 | 23.8325 | 14800 | 1.7135 | 2.8346 | 16.4672 |
199
+ | 0.6917 | 23.9936 | 14900 | 1.7135 | 2.8071 | 16.4471 |
200
+ | 0.6802 | 24.1546 | 15000 | 1.7296 | 2.8281 | 16.4433 |
201
+ | 0.6802 | 24.3156 | 15100 | 1.7336 | 2.8261 | 16.479 |
202
+ | 0.6802 | 24.4767 | 15200 | 1.7373 | 2.8372 | 16.4567 |
203
+ | 0.6802 | 24.6377 | 15300 | 1.7263 | 2.8396 | 16.4938 |
204
+ | 0.6802 | 24.7987 | 15400 | 1.7388 | 2.8184 | 16.4498 |
205
+ | 0.6645 | 24.9597 | 15500 | 1.7182 | 2.8107 | 16.4398 |
206
+ | 0.6645 | 25.1208 | 15600 | 1.7427 | 2.7916 | 16.4207 |
207
+ | 0.6645 | 25.2818 | 15700 | 1.7491 | 2.824 | 16.4242 |
208
+ | 0.6645 | 25.4428 | 15800 | 1.7390 | 2.8197 | 16.4132 |
209
+ | 0.6645 | 25.6039 | 15900 | 1.7498 | 2.8252 | 16.449 |
210
+ | 0.651 | 25.7649 | 16000 | 1.7379 | 2.8417 | 16.4895 |
211
+ | 0.651 | 25.9259 | 16100 | 1.7447 | 2.8191 | 16.4637 |
212
+ | 0.651 | 26.0870 | 16200 | 1.7522 | 2.8645 | 16.4554 |
213
+ | 0.651 | 26.2480 | 16300 | 1.7513 | 2.8656 | 16.4672 |
214
+ | 0.651 | 26.4090 | 16400 | 1.7593 | 2.8727 | 16.478 |
215
+ | 0.6385 | 26.5700 | 16500 | 1.7589 | 2.8586 | 16.4514 |
216
+ | 0.6385 | 26.7311 | 16600 | 1.7620 | 2.8671 | 16.4731 |
217
+ | 0.6385 | 26.8921 | 16700 | 1.7587 | 2.8518 | 16.4691 |
218
+ | 0.6385 | 27.0531 | 16800 | 1.7714 | 2.8843 | 16.4527 |
219
+ | 0.6385 | 27.2142 | 16900 | 1.7713 | 2.8654 | 16.45 |
220
+ | 0.6317 | 27.3752 | 17000 | 1.7681 | 2.8745 | 16.4785 |
221
+ | 0.6317 | 27.5362 | 17100 | 1.7579 | 2.831 | 16.4621 |
222
+ | 0.6317 | 27.6973 | 17200 | 1.7668 | 2.8836 | 16.4672 |
223
+ | 0.6317 | 27.8583 | 17300 | 1.7606 | 2.8513 | 16.4817 |
224
+ | 0.6317 | 28.0193 | 17400 | 1.7564 | 2.8436 | 16.4782 |
225
+ | 0.6276 | 28.1804 | 17500 | 1.7735 | 2.8623 | 16.4592 |
226
+ | 0.6276 | 28.3414 | 17600 | 1.7751 | 2.8616 | 16.4597 |
227
+ | 0.6276 | 28.5024 | 17700 | 1.7665 | 2.8474 | 16.4592 |
228
+ | 0.6276 | 28.6634 | 17800 | 1.7666 | 2.8633 | 16.4707 |
229
+ | 0.6276 | 28.8245 | 17900 | 1.7733 | 2.8409 | 16.4694 |
230
+ | 0.6169 | 28.9855 | 18000 | 1.7709 | 2.8444 | 16.4557 |
231
+ | 0.6169 | 29.1465 | 18100 | 1.7766 | 2.8485 | 16.4527 |
232
+ | 0.6169 | 29.3076 | 18200 | 1.7745 | 2.8587 | 16.4661 |
233
+ | 0.6169 | 29.4686 | 18300 | 1.7751 | 2.8552 | 16.4688 |
234
+ | 0.6169 | 29.6296 | 18400 | 1.7755 | 2.8574 | 16.4699 |
235
+ | 0.6112 | 29.7907 | 18500 | 1.7737 | 2.8521 | 16.4694 |
236
+ | 0.6112 | 29.9517 | 18600 | 1.7731 | 2.855 | 16.4731 |
237
 
238
 
239
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a5247a68091b21ddc726ba562fcd896a07ff0d058da1c00919372809ef3b3142
3
  size 990345064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a5b35c5b789a4baaa7329f2ab5a677fffb9c9fc518240bbbf867ee0f2fd5809
3
  size 990345064
runs/Apr26_05-25-41_23f4811e55ec/events.out.tfevents.1714109143.23f4811e55ec.399.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:29dcf470f3d9111abba92bc5dfe549b018bfaab647eb85dee77fcf729edea282
3
- size 82210
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e599c2f7fc2c4850d385b6b42f18e94a3c10a589d7df7f4c748949b0981ce5e9
3
+ size 82947