ludziej commited on
Commit
1790df3
1 Parent(s): 1b91e58

End of training

Browse files
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: 0.0868
17
 
18
  ## Model description
19
 
@@ -44,51 +44,51 @@ The following hyperparameters were used during training:
44
 
45
  | Training Loss | Epoch | Step | Validation Loss |
46
  |:-------------:|:-----:|:----:|:---------------:|
47
- | 2.9639 | 1.0 | 6 | 2.2327 |
48
- | 2.0112 | 2.0 | 12 | 1.7195 |
49
- | 1.5448 | 3.0 | 18 | 1.3346 |
50
- | 1.2344 | 4.0 | 24 | 1.1502 |
51
- | 1.0961 | 5.0 | 30 | 1.0083 |
52
- | 0.9938 | 6.0 | 36 | 0.9712 |
53
- | 0.9205 | 7.0 | 42 | 0.8846 |
54
- | 0.8293 | 8.0 | 48 | 0.7529 |
55
- | 0.7735 | 9.0 | 54 | 0.7236 |
56
- | 0.7284 | 10.0 | 60 | 0.7006 |
57
- | 0.673 | 11.0 | 66 | 0.6580 |
58
- | 0.6238 | 12.0 | 72 | 0.5931 |
59
- | 0.5871 | 13.0 | 78 | 0.5475 |
60
- | 0.548 | 14.0 | 84 | 0.4944 |
61
- | 0.5 | 15.0 | 90 | 0.4888 |
62
- | 0.4772 | 16.0 | 96 | 0.4259 |
63
- | 0.4605 | 17.0 | 102 | 0.4471 |
64
- | 0.4191 | 18.0 | 108 | 0.3692 |
65
- | 0.3724 | 19.0 | 114 | 0.3329 |
66
- | 0.3483 | 20.0 | 120 | 0.3270 |
67
- | 0.3268 | 21.0 | 126 | 0.2739 |
68
- | 0.2884 | 22.0 | 132 | 0.2396 |
69
- | 0.2567 | 23.0 | 138 | 0.2038 |
70
- | 0.2415 | 24.0 | 144 | 0.2121 |
71
- | 0.2322 | 25.0 | 150 | 0.1778 |
72
- | 0.1971 | 26.0 | 156 | 0.1631 |
73
- | 0.2065 | 27.0 | 162 | 0.1592 |
74
- | 0.1918 | 28.0 | 168 | 0.1422 |
75
- | 0.1854 | 29.0 | 174 | 0.1359 |
76
- | 0.1691 | 30.0 | 180 | 0.1291 |
77
- | 0.1645 | 31.0 | 186 | 0.1201 |
78
- | 0.1614 | 32.0 | 192 | 0.1138 |
79
- | 0.1435 | 33.0 | 198 | 0.1082 |
80
- | 0.1354 | 34.0 | 204 | 0.1014 |
81
- | 0.129 | 35.0 | 210 | 0.0956 |
82
- | 0.1298 | 36.0 | 216 | 0.0971 |
83
- | 0.1266 | 37.0 | 222 | 0.0916 |
84
- | 0.1374 | 38.0 | 228 | 0.0919 |
85
- | 0.1217 | 39.0 | 234 | 0.0882 |
86
- | 0.1341 | 40.0 | 240 | 0.0868 |
87
 
88
 
89
  ### Framework versions
90
 
91
  - Transformers 4.38.1
92
  - Pytorch 2.1.0+cu121
93
- - Datasets 2.17.1
94
  - Tokenizers 0.15.2
 
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: 0.1268
17
 
18
  ## Model description
19
 
 
44
 
45
  | Training Loss | Epoch | Step | Validation Loss |
46
  |:-------------:|:-----:|:----:|:---------------:|
47
+ | 2.9786 | 1.0 | 6 | 2.2468 |
48
+ | 2.0116 | 2.0 | 12 | 1.7255 |
49
+ | 1.5628 | 3.0 | 18 | 1.3183 |
50
+ | 1.2273 | 4.0 | 24 | 1.0790 |
51
+ | 1.0219 | 5.0 | 30 | 0.9549 |
52
+ | 0.9147 | 6.0 | 36 | 0.8300 |
53
+ | 0.7993 | 7.0 | 42 | 0.7326 |
54
+ | 0.7256 | 8.0 | 48 | 0.7028 |
55
+ | 0.6677 | 9.0 | 54 | 0.6345 |
56
+ | 0.6369 | 10.0 | 60 | 0.5926 |
57
+ | 0.5883 | 11.0 | 66 | 0.5722 |
58
+ | 0.5506 | 12.0 | 72 | 0.5835 |
59
+ | 0.5504 | 13.0 | 78 | 0.5491 |
60
+ | 0.5232 | 14.0 | 84 | 0.5165 |
61
+ | 0.4977 | 15.0 | 90 | 0.4719 |
62
+ | 0.4754 | 16.0 | 96 | 0.4910 |
63
+ | 0.4706 | 17.0 | 102 | 0.4623 |
64
+ | 0.4659 | 18.0 | 108 | 0.4202 |
65
+ | 0.4186 | 19.0 | 114 | 0.3720 |
66
+ | 0.385 | 20.0 | 120 | 0.3768 |
67
+ | 0.3692 | 21.0 | 126 | 0.3751 |
68
+ | 0.3775 | 22.0 | 132 | 0.3508 |
69
+ | 0.3359 | 23.0 | 138 | 0.3427 |
70
+ | 0.3412 | 24.0 | 144 | 0.3015 |
71
+ | 0.3128 | 25.0 | 150 | 0.2826 |
72
+ | 0.2892 | 26.0 | 156 | 0.2688 |
73
+ | 0.28 | 27.0 | 162 | 0.2512 |
74
+ | 0.2653 | 28.0 | 168 | 0.2385 |
75
+ | 0.255 | 29.0 | 174 | 0.2275 |
76
+ | 0.249 | 30.0 | 180 | 0.2108 |
77
+ | 0.2316 | 31.0 | 186 | 0.1894 |
78
+ | 0.2184 | 32.0 | 192 | 0.1777 |
79
+ | 0.2057 | 33.0 | 198 | 0.1644 |
80
+ | 0.186 | 34.0 | 204 | 0.1527 |
81
+ | 0.1853 | 35.0 | 210 | 0.1484 |
82
+ | 0.1721 | 36.0 | 216 | 0.1380 |
83
+ | 0.165 | 37.0 | 222 | 0.1336 |
84
+ | 0.1544 | 38.0 | 228 | 0.1299 |
85
+ | 0.153 | 39.0 | 234 | 0.1288 |
86
+ | 0.158 | 40.0 | 240 | 0.1268 |
87
 
88
 
89
  ### Framework versions
90
 
91
  - Transformers 4.38.1
92
  - Pytorch 2.1.0+cu121
93
+ - Datasets 2.18.0
94
  - Tokenizers 0.15.2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4cfbcc16fa186e80c1f30f878cd3491ee3c5e85053511e9589b369a081ced43d
3
  size 31207604
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d909ff86e2efa4695738c107a45410f68e077eeb366d2aabac8780d7ccef7fb7
3
  size 31207604
runs/Mar04_14-22-00_dd5a9353f29e/events.out.tfevents.1709562121.dd5a9353f29e.390.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7e61d195923d2ee30420fd83e13a699a6d99b8d418a36407773d038842188d5
3
+ size 27997
tokenizer.json CHANGED
@@ -113,34 +113,34 @@
113
  "8": 14,
114
  "9": 15,
115
  "=": 16,
116
- "99": 17,
117
- "10": 18,
118
- "98": 19,
119
- "11": 20,
120
- "97": 21,
121
- "12": 22,
122
- "96": 23,
123
- "13": 24,
124
- "95": 25,
125
- "14": 26,
126
  "15": 27,
127
  "94": 28,
128
- "93": 29,
129
- "16": 30,
130
  "92": 31,
131
  "17": 32,
132
- "18": 33,
133
- "91": 34,
134
- "90": 35,
135
- "19": 36,
136
- "89": 37,
137
- "20": 38,
138
  "21": 39,
139
  "88": 40,
140
  "87": 41,
141
  "22": 42,
142
- "23": 43,
143
- "86": 44,
144
  "24": 45,
145
  "85": 46,
146
  "25": 47,
@@ -151,34 +151,34 @@
151
  "82": 52
152
  },
153
  "merges": [
154
- "9 9",
155
  "1 0",
156
- "9 8",
157
  "1 1",
158
- "9 7",
159
  "1 2",
160
- "9 6",
161
  "1 3",
162
- "9 5",
163
  "1 4",
 
164
  "1 5",
165
  "9 4",
166
- "9 3",
167
  "1 6",
 
168
  "9 2",
169
  "1 7",
170
- "1 8",
171
  "9 1",
172
- "9 0",
173
  "1 9",
174
- "8 9",
175
  "2 0",
 
176
  "2 1",
177
  "8 8",
178
  "8 7",
179
  "2 2",
180
- "2 3",
181
  "8 6",
 
182
  "2 4",
183
  "8 5",
184
  "2 5",
 
113
  "8": 14,
114
  "9": 15,
115
  "=": 16,
116
+ "10": 17,
117
+ "99": 18,
118
+ "11": 19,
119
+ "98": 20,
120
+ "12": 21,
121
+ "97": 22,
122
+ "13": 23,
123
+ "96": 24,
124
+ "14": 25,
125
+ "95": 26,
126
  "15": 27,
127
  "94": 28,
128
+ "16": 29,
129
+ "93": 30,
130
  "92": 31,
131
  "17": 32,
132
+ "91": 33,
133
+ "18": 34,
134
+ "19": 35,
135
+ "90": 36,
136
+ "20": 37,
137
+ "89": 38,
138
  "21": 39,
139
  "88": 40,
140
  "87": 41,
141
  "22": 42,
142
+ "86": 43,
143
+ "23": 44,
144
  "24": 45,
145
  "85": 46,
146
  "25": 47,
 
151
  "82": 52
152
  },
153
  "merges": [
 
154
  "1 0",
155
+ "9 9",
156
  "1 1",
157
+ "9 8",
158
  "1 2",
159
+ "9 7",
160
  "1 3",
161
+ "9 6",
162
  "1 4",
163
+ "9 5",
164
  "1 5",
165
  "9 4",
 
166
  "1 6",
167
+ "9 3",
168
  "9 2",
169
  "1 7",
 
170
  "9 1",
171
+ "1 8",
172
  "1 9",
173
+ "9 0",
174
  "2 0",
175
+ "8 9",
176
  "2 1",
177
  "8 8",
178
  "8 7",
179
  "2 2",
 
180
  "8 6",
181
+ "2 3",
182
  "2 4",
183
  "8 5",
184
  "2 5",
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d8d78e70a07f179c1153d41b5f956272edf46055c23441c484f26204c26026f5
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64d1328e59c0d1a44beb0f9d39d3a780e9714faf81159b142113fff9fdd60958
3
  size 5112