Anish13 commited on
Commit
83f0f75
·
verified ·
1 Parent(s): 584a424

Model save

Browse files
Files changed (3) hide show
  1. README.md +90 -90
  2. best/model.safetensors +1 -1
  3. model.safetensors +1 -1
README.md CHANGED
@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
13
 
14
  This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
15
  It achieves the following results on the evaluation set:
16
- - Loss: 230.4205
17
 
18
  ## Model description
19
 
@@ -46,95 +46,95 @@ The following hyperparameters were used during training:
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-------:|:------:|:---------------:|
49
- | 7.2107 | 0.5570 | 10000 | 7.1334 |
50
- | 6.855 | 1.1141 | 20000 | 6.8933 |
51
- | 6.7223 | 1.6711 | 30000 | 6.8169 |
52
- | 6.5948 | 2.2282 | 40000 | 6.8059 |
53
- | 6.5197 | 2.7852 | 50000 | 6.8322 |
54
- | 6.3908 | 3.3422 | 60000 | 6.6924 |
55
- | 6.3202 | 3.8993 | 70000 | 6.8986 |
56
- | 6.2023 | 4.4563 | 80000 | 6.7110 |
57
- | 6.1197 | 5.0134 | 90000 | 6.5662 |
58
- | 6.1291 | 5.5704 | 100000 | 6.7865 |
59
- | 6.0831 | 6.1275 | 110000 | 6.4560 |
60
- | 6.0572 | 6.6845 | 120000 | 6.6910 |
61
- | 5.9835 | 7.2415 | 130000 | 6.5923 |
62
- | 5.9799 | 7.7986 | 140000 | 6.6270 |
63
- | 5.889 | 8.3556 | 150000 | 6.5736 |
64
- | 5.9385 | 8.9127 | 160000 | 6.5225 |
65
- | 5.9399 | 9.4697 | 170000 | 6.4342 |
66
- | 5.8455 | 10.0267 | 180000 | 6.7230 |
67
- | 5.8304 | 10.5838 | 190000 | 6.6909 |
68
- | 5.8024 | 11.1408 | 200000 | 6.5837 |
69
- | 5.7549 | 11.6979 | 210000 | 6.6577 |
70
- | 5.7796 | 12.2549 | 220000 | 6.4482 |
71
- | 5.7656 | 12.8119 | 230000 | 6.4355 |
72
- | 5.7265 | 13.3690 | 240000 | 6.8308 |
73
- | 5.7496 | 13.9260 | 250000 | 6.5874 |
74
- | 5.6837 | 14.4831 | 260000 | 6.4602 |
75
- | 5.6449 | 15.0401 | 270000 | 6.8683 |
76
- | 5.6522 | 15.5971 | 280000 | 6.7332 |
77
- | 5.5971 | 16.1542 | 290000 | 7.0091 |
78
- | 5.6177 | 16.7112 | 300000 | 6.9452 |
79
- | 5.5726 | 17.2683 | 310000 | 7.1216 |
80
- | 5.6119 | 17.8253 | 320000 | 7.3758 |
81
- | 5.5656 | 18.3824 | 330000 | 6.7465 |
82
- | 5.5463 | 18.9394 | 340000 | 6.4133 |
83
- | 5.5375 | 19.4964 | 350000 | 6.7948 |
84
- | 5.4745 | 20.0535 | 360000 | 7.1663 |
85
- | 5.5345 | 20.6105 | 370000 | 6.9830 |
86
- | 5.5127 | 21.1676 | 380000 | 7.1736 |
87
- | 5.5163 | 21.7246 | 390000 | 6.9526 |
88
- | 5.5085 | 22.2816 | 400000 | 7.1294 |
89
- | 5.4868 | 22.8387 | 410000 | 7.2336 |
90
- | 5.4954 | 23.3957 | 420000 | 7.3882 |
91
- | 5.4534 | 23.9528 | 430000 | 7.4660 |
92
- | 5.4636 | 24.5098 | 440000 | 7.7570 |
93
- | 5.4572 | 25.0668 | 450000 | 7.2802 |
94
- | 5.4501 | 25.6239 | 460000 | 7.0237 |
95
- | 5.4259 | 26.1809 | 470000 | 7.2043 |
96
- | 5.4205 | 26.7380 | 480000 | 7.4920 |
97
- | 5.4388 | 27.2950 | 490000 | 7.6919 |
98
- | 5.4461 | 27.8520 | 500000 | 7.2496 |
99
- | 5.4505 | 28.4091 | 510000 | 8.0927 |
100
- | 5.3868 | 28.9661 | 520000 | 7.9013 |
101
- | 5.3955 | 29.5232 | 530000 | 7.3911 |
102
- | 5.3767 | 30.0802 | 540000 | 7.5686 |
103
- | 5.4033 | 30.6373 | 550000 | 7.6312 |
104
- | 5.4766 | 31.1943 | 560000 | 7.4374 |
105
- | 5.4446 | 31.7513 | 570000 | 8.5821 |
106
- | 5.3709 | 32.3084 | 580000 | 8.1120 |
107
- | 5.3984 | 32.8654 | 590000 | 7.8773 |
108
- | 5.3645 | 33.4225 | 600000 | 7.4649 |
109
- | 5.4198 | 33.9795 | 610000 | 8.5657 |
110
- | 5.3058 | 34.5365 | 620000 | 7.8521 |
111
- | 5.3206 | 35.0936 | 630000 | 7.7948 |
112
- | 5.3565 | 35.6506 | 640000 | 8.0000 |
113
- | 5.2853 | 36.2077 | 650000 | 7.2801 |
114
- | 5.354 | 36.7647 | 660000 | 7.6050 |
115
- | 5.3187 | 37.3217 | 670000 | 7.9883 |
116
- | 5.3183 | 37.8788 | 680000 | 7.8469 |
117
- | 5.4273 | 38.4358 | 690000 | 6.9470 |
118
- | 5.5932 | 38.9929 | 700000 | 6.4775 |
119
- | 6.8168 | 39.5499 | 710000 | 7.6621 |
120
- | 7.9333 | 40.1070 | 720000 | 8.5982 |
121
- | 10.8308 | 40.6640 | 730000 | 11.0965 |
122
- | 25.3974 | 41.2210 | 740000 | 25.4061 |
123
- | 13.526 | 41.7781 | 750000 | 13.1423 |
124
- | 11.8513 | 42.3351 | 760000 | 11.7643 |
125
- | 10.1776 | 42.8922 | 770000 | 9.8905 |
126
- | 96.1114 | 43.4492 | 780000 | 97.4525 |
127
- | 196.2914 | 44.0062 | 790000 | 199.1897 |
128
- | 227.9711 | 44.5633 | 800000 | 230.4205 |
129
- | 226.7711 | 45.1203 | 810000 | 230.4205 |
130
- | 225.694 | 45.6774 | 820000 | 230.4205 |
131
- | 226.7237 | 46.2344 | 830000 | 230.4205 |
132
- | 226.6388 | 46.7914 | 840000 | 230.4205 |
133
- | 225.8023 | 47.3485 | 850000 | 230.4205 |
134
- | 226.7597 | 47.9055 | 860000 | 230.4205 |
135
- | 226.232 | 48.4626 | 870000 | 230.4205 |
136
- | 226.6263 | 49.0196 | 880000 | 230.4205 |
137
- | 226.0536 | 49.5766 | 890000 | 230.4205 |
138
 
139
 
140
  ### Framework versions
 
13
 
14
  This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
15
  It achieves the following results on the evaluation set:
16
+ - Loss: 7.6601
17
 
18
  ## Model description
19
 
 
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-------:|:------:|:---------------:|
49
+ | 7.2381 | 0.5570 | 10000 | 7.1552 |
50
+ | 6.9121 | 1.1141 | 20000 | 6.8341 |
51
+ | 6.7123 | 1.6711 | 30000 | 6.6405 |
52
+ | 6.4926 | 2.2282 | 40000 | 6.4267 |
53
+ | 6.3666 | 2.7852 | 50000 | 6.3720 |
54
+ | 6.2655 | 3.3422 | 60000 | 6.3113 |
55
+ | 6.1958 | 3.8993 | 70000 | 6.2503 |
56
+ | 6.0908 | 4.4563 | 80000 | 6.2392 |
57
+ | 6.0127 | 5.0134 | 90000 | 6.2291 |
58
+ | 6.0189 | 5.5704 | 100000 | 6.2311 |
59
+ | 5.9728 | 6.1275 | 110000 | 6.1985 |
60
+ | 5.9594 | 6.6845 | 120000 | 6.2354 |
61
+ | 5.873 | 7.2415 | 130000 | 6.2018 |
62
+ | 5.8756 | 7.7986 | 140000 | 6.2386 |
63
+ | 5.7656 | 8.3556 | 150000 | 6.2222 |
64
+ | 5.813 | 8.9127 | 160000 | 6.2550 |
65
+ | 5.8192 | 9.4697 | 170000 | 6.2894 |
66
+ | 5.7091 | 10.0267 | 180000 | 6.3533 |
67
+ | 5.703 | 10.5838 | 190000 | 6.3356 |
68
+ | 5.6674 | 11.1408 | 200000 | 6.4957 |
69
+ | 5.6302 | 11.6979 | 210000 | 6.4069 |
70
+ | 5.6517 | 12.2549 | 220000 | 6.5459 |
71
+ | 5.6388 | 12.8119 | 230000 | 6.5383 |
72
+ | 5.5918 | 13.3690 | 240000 | 6.5509 |
73
+ | 5.622 | 13.9260 | 250000 | 6.4959 |
74
+ | 5.5546 | 14.4831 | 260000 | 6.5783 |
75
+ | 5.5205 | 15.0401 | 270000 | 6.5076 |
76
+ | 5.5209 | 15.5971 | 280000 | 6.5128 |
77
+ | 5.4692 | 16.1542 | 290000 | 6.3658 |
78
+ | 5.4871 | 16.7112 | 300000 | 6.3450 |
79
+ | 5.444 | 17.2683 | 310000 | 6.3261 |
80
+ | 5.4781 | 17.8253 | 320000 | 6.3246 |
81
+ | 5.4131 | 18.3824 | 330000 | 6.3904 |
82
+ | 5.4128 | 18.9394 | 340000 | 6.5145 |
83
+ | 5.4063 | 19.4964 | 350000 | 6.4409 |
84
+ | 5.3473 | 20.0535 | 360000 | 6.6570 |
85
+ | 5.4103 | 20.6105 | 370000 | 6.5708 |
86
+ | 5.3782 | 21.1676 | 380000 | 6.7661 |
87
+ | 5.4002 | 21.7246 | 390000 | 6.7968 |
88
+ | 5.3759 | 22.2816 | 400000 | 6.7145 |
89
+ | 5.3636 | 22.8387 | 410000 | 6.8896 |
90
+ | 5.3629 | 23.3957 | 420000 | 6.7899 |
91
+ | 5.3251 | 23.9528 | 430000 | 6.7925 |
92
+ | 5.3415 | 24.5098 | 440000 | 6.5798 |
93
+ | 5.3247 | 25.0668 | 450000 | 6.7255 |
94
+ | 5.3172 | 25.6239 | 460000 | 6.7998 |
95
+ | 5.2915 | 26.1809 | 470000 | 6.9089 |
96
+ | 5.2899 | 26.7380 | 480000 | 6.7261 |
97
+ | 5.3112 | 27.2950 | 490000 | 6.7184 |
98
+ | 5.3173 | 27.8520 | 500000 | 6.8470 |
99
+ | 5.325 | 28.4091 | 510000 | 6.9112 |
100
+ | 5.2632 | 28.9661 | 520000 | 6.7319 |
101
+ | 5.2486 | 29.5232 | 530000 | 6.9459 |
102
+ | 5.2513 | 30.0802 | 540000 | 6.9476 |
103
+ | 5.2666 | 30.6373 | 550000 | 7.1228 |
104
+ | 5.2209 | 31.1943 | 560000 | 7.1333 |
105
+ | 5.2951 | 31.7513 | 570000 | 7.0138 |
106
+ | 5.2281 | 32.3084 | 580000 | 7.1338 |
107
+ | 5.275 | 32.8654 | 590000 | 7.0661 |
108
+ | 5.2248 | 33.4225 | 600000 | 7.1180 |
109
+ | 5.243 | 33.9795 | 610000 | 7.2631 |
110
+ | 5.1808 | 34.5365 | 620000 | 7.2399 |
111
+ | 5.2124 | 35.0936 | 630000 | 7.3326 |
112
+ | 5.2298 | 35.6506 | 640000 | 7.3016 |
113
+ | 5.1622 | 36.2077 | 650000 | 7.2848 |
114
+ | 5.1914 | 36.7647 | 660000 | 7.2105 |
115
+ | 5.2101 | 37.3217 | 670000 | 7.3469 |
116
+ | 5.2145 | 37.8788 | 680000 | 7.2929 |
117
+ | 5.1965 | 38.4358 | 690000 | 7.4581 |
118
+ | 5.1829 | 38.9929 | 700000 | 7.3079 |
119
+ | 5.1948 | 39.5499 | 710000 | 7.4294 |
120
+ | 5.1887 | 40.1070 | 720000 | 7.4563 |
121
+ | 5.1636 | 40.6640 | 730000 | 7.3479 |
122
+ | 5.1674 | 41.2210 | 740000 | 7.4878 |
123
+ | 5.2115 | 41.7781 | 750000 | 7.5378 |
124
+ | 5.1818 | 42.3351 | 760000 | 7.6372 |
125
+ | 5.1997 | 42.8922 | 770000 | 7.6155 |
126
+ | 5.1652 | 43.4492 | 780000 | 7.5538 |
127
+ | 5.1446 | 44.0062 | 790000 | 7.5399 |
128
+ | 5.1693 | 44.5633 | 800000 | 7.6295 |
129
+ | 5.1336 | 45.1203 | 810000 | 7.6689 |
130
+ | 5.1358 | 45.6774 | 820000 | 7.5853 |
131
+ | 5.1233 | 46.2344 | 830000 | 7.6833 |
132
+ | 5.1395 | 46.7914 | 840000 | 7.6448 |
133
+ | 5.125 | 47.3485 | 850000 | 7.6463 |
134
+ | 5.161 | 47.9055 | 860000 | 7.6284 |
135
+ | 5.1301 | 48.4626 | 870000 | 7.6313 |
136
+ | 5.1448 | 49.0196 | 880000 | 7.6512 |
137
+ | 5.1284 | 49.5766 | 890000 | 7.6601 |
138
 
139
 
140
  ### Framework versions
best/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fdd7befb72b4a43439725b565c62c562c31e15a1a3e27aab34f8bb4523f27417
3
  size 251300560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9826e1d0bc174ea18ecdc6f5ae1123810ce4f63407bf720e822e273490a90aef
3
  size 251300560
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:77005d4c5b56ab6a83a38c09d389c407aad0af353bfd7d21ab14f9367aabb2ed
3
  size 251300560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9826e1d0bc174ea18ecdc6f5ae1123810ce4f63407bf720e822e273490a90aef
3
  size 251300560