cvzx commited on
Commit
f6ef304
1 Parent(s): fe79f73

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: 0.6928
17
 
18
  ## Model description
19
 
@@ -44,46 +44,46 @@ The following hyperparameters were used during training:
44
 
45
  | Training Loss | Epoch | Step | Validation Loss |
46
  |:-------------:|:-----:|:----:|:---------------:|
47
- | 3.3995 | 1.0 | 6 | 2.7654 |
48
- | 2.3627 | 2.0 | 12 | 2.0026 |
49
- | 1.8401 | 3.0 | 18 | 1.6902 |
50
- | 1.662 | 4.0 | 24 | 1.6234 |
51
- | 1.5803 | 5.0 | 30 | 1.5471 |
52
- | 1.526 | 6.0 | 36 | 1.5404 |
53
- | 1.5392 | 7.0 | 42 | 1.5229 |
54
- | 1.488 | 8.0 | 48 | 1.4944 |
55
- | 1.492 | 9.0 | 54 | 1.4652 |
56
- | 1.4448 | 10.0 | 60 | 1.4098 |
57
- | 1.3673 | 11.0 | 66 | 1.3128 |
58
- | 1.3264 | 12.0 | 72 | 1.2688 |
59
- | 1.2517 | 13.0 | 78 | 1.1730 |
60
- | 1.1956 | 14.0 | 84 | 1.1706 |
61
- | 1.1611 | 15.0 | 90 | 1.1054 |
62
- | 1.1071 | 16.0 | 96 | 1.0976 |
63
- | 1.0902 | 17.0 | 102 | 1.0297 |
64
- | 1.0608 | 18.0 | 108 | 1.0287 |
65
- | 1.0572 | 19.0 | 114 | 1.0717 |
66
- | 1.0308 | 20.0 | 120 | 0.9988 |
67
- | 0.993 | 21.0 | 126 | 0.9327 |
68
- | 0.9265 | 22.0 | 132 | 0.9105 |
69
- | 0.9157 | 23.0 | 138 | 0.8810 |
70
- | 0.9134 | 24.0 | 144 | 0.9195 |
71
- | 0.9301 | 25.0 | 150 | 1.0128 |
72
- | 0.9529 | 26.0 | 156 | 0.9117 |
73
- | 0.9287 | 27.0 | 162 | 0.9456 |
74
- | 0.9075 | 28.0 | 168 | 0.8443 |
75
- | 0.8507 | 29.0 | 174 | 0.8308 |
76
- | 0.8232 | 30.0 | 180 | 0.7894 |
77
- | 0.8086 | 31.0 | 186 | 0.7883 |
78
- | 0.7955 | 32.0 | 192 | 0.7545 |
79
- | 0.7791 | 33.0 | 198 | 0.7381 |
80
- | 0.7835 | 34.0 | 204 | 0.7364 |
81
- | 0.7744 | 35.0 | 210 | 0.7281 |
82
- | 0.7675 | 36.0 | 216 | 0.7230 |
83
- | 0.7549 | 37.0 | 222 | 0.7100 |
84
- | 0.7459 | 38.0 | 228 | 0.6969 |
85
- | 0.7449 | 39.0 | 234 | 0.6945 |
86
- | 0.7257 | 40.0 | 240 | 0.6928 |
87
 
88
 
89
  ### 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: 0.1142
17
 
18
  ## Model description
19
 
 
44
 
45
  | Training Loss | Epoch | Step | Validation Loss |
46
  |:-------------:|:-----:|:----:|:---------------:|
47
+ | 2.9994 | 1.0 | 6 | 2.3829 |
48
+ | 2.1071 | 2.0 | 12 | 1.8146 |
49
+ | 1.6604 | 3.0 | 18 | 1.4548 |
50
+ | 1.3344 | 4.0 | 24 | 1.2129 |
51
+ | 1.1057 | 5.0 | 30 | 1.1267 |
52
+ | 0.9979 | 6.0 | 36 | 0.9518 |
53
+ | 0.8972 | 7.0 | 42 | 0.8461 |
54
+ | 0.7958 | 8.0 | 48 | 0.7534 |
55
+ | 0.7312 | 9.0 | 54 | 0.7009 |
56
+ | 0.6649 | 10.0 | 60 | 0.6680 |
57
+ | 0.6393 | 11.0 | 66 | 0.7051 |
58
+ | 0.6601 | 12.0 | 72 | 0.6567 |
59
+ | 0.6068 | 13.0 | 78 | 0.5767 |
60
+ | 0.5647 | 14.0 | 84 | 0.5255 |
61
+ | 0.4983 | 15.0 | 90 | 0.4750 |
62
+ | 0.5041 | 16.0 | 96 | 0.4331 |
63
+ | 0.4763 | 17.0 | 102 | 0.4182 |
64
+ | 0.4353 | 18.0 | 108 | 0.3774 |
65
+ | 0.3764 | 19.0 | 114 | 0.3496 |
66
+ | 0.3449 | 20.0 | 120 | 0.3113 |
67
+ | 0.3256 | 21.0 | 126 | 0.2987 |
68
+ | 0.2946 | 22.0 | 132 | 0.2670 |
69
+ | 0.3009 | 23.0 | 138 | 0.2560 |
70
+ | 0.2382 | 24.0 | 144 | 0.2373 |
71
+ | 0.2447 | 25.0 | 150 | 0.2340 |
72
+ | 0.2641 | 26.0 | 156 | 0.3113 |
73
+ | 0.2926 | 27.0 | 162 | 0.1925 |
74
+ | 0.2231 | 28.0 | 168 | 0.1932 |
75
+ | 0.2826 | 29.0 | 174 | 0.1867 |
76
+ | 0.1928 | 30.0 | 180 | 0.1672 |
77
+ | 0.1924 | 31.0 | 186 | 0.1577 |
78
+ | 0.1727 | 32.0 | 192 | 0.1451 |
79
+ | 0.1715 | 33.0 | 198 | 0.1365 |
80
+ | 0.1582 | 34.0 | 204 | 0.1334 |
81
+ | 0.1606 | 35.0 | 210 | 0.1278 |
82
+ | 0.1556 | 36.0 | 216 | 0.1282 |
83
+ | 0.1355 | 37.0 | 222 | 0.1226 |
84
+ | 0.1305 | 38.0 | 228 | 0.1184 |
85
+ | 0.1494 | 39.0 | 234 | 0.1148 |
86
+ | 0.1392 | 40.0 | 240 | 0.1142 |
87
 
88
 
89
  ### Framework versions
config.json CHANGED
@@ -78,7 +78,7 @@
78
  "typical_p": 1.0,
79
  "use_bfloat16": false,
80
  "use_cache": true,
81
- "vocab_size": 52
82
  },
83
  "decoder_start_token_id": 2,
84
  "encoder": {
@@ -157,7 +157,7 @@
157
  "typical_p": 1.0,
158
  "use_bfloat16": false,
159
  "use_cache": true,
160
- "vocab_size": 52
161
  },
162
  "eos_token_id": 0,
163
  "is_encoder_decoder": true,
 
78
  "typical_p": 1.0,
79
  "use_bfloat16": false,
80
  "use_cache": true,
81
+ "vocab_size": 53
82
  },
83
  "decoder_start_token_id": 2,
84
  "encoder": {
 
157
  "typical_p": 1.0,
158
  "use_bfloat16": false,
159
  "use_cache": true,
160
+ "vocab_size": 53
161
  },
162
  "eos_token_id": 0,
163
  "is_encoder_decoder": true,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a145ff9ebf9cb627a777a9a18ed169d88476f9abf4752cfe35e888b5b69abb3
3
- size 31205552
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c42cb91277d22ed8d3b996c4a0bcd18d710e0c99e81b92739765eff35e217f21
3
+ size 31207604
runs/Mar04_14-28-09_af6ff0e52cb3/events.out.tfevents.1709562490.af6ff0e52cb3.543.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c04f34608326da58f6ac8b8fa6736fb11a04e991f25cd2c75aa3ddb858ffdefc
3
+ size 27997
tokenizer.json CHANGED
@@ -112,78 +112,79 @@
112
  "7": 13,
113
  "8": 14,
114
  "9": 15,
115
- "10": 16,
116
- "99": 17,
117
- "98": 18,
118
- "11": 19,
119
- "12": 20,
120
- "97": 21,
121
- "13": 22,
122
- "96": 23,
123
- "95": 24,
124
- "14": 25,
125
- "94": 26,
126
- "15": 27,
127
- "16": 28,
128
- "93": 29,
129
- "92": 30,
130
- "17": 31,
131
- "18": 32,
132
- "91": 33,
133
- "19": 34,
134
- "90": 35,
135
- "20": 36,
136
- "89": 37,
137
- "88": 38,
138
  "21": 39,
139
- "22": 40,
140
- "87": 41,
141
- "23": 42,
142
  "86": 43,
143
- "85": 44,
144
  "24": 45,
145
- "84": 46,
146
- "25": 47,
147
- "26": 48,
148
  "83": 49,
149
- "27": 50,
150
- "82": 51
 
151
  },
152
  "merges": [
153
  "1 0",
154
- "9 9",
155
- "9 8",
156
  "1 1",
157
  "1 2",
158
- "9 7",
159
  "1 3",
160
- "9 6",
161
- "9 5",
162
  "1 4",
163
- "9 4",
164
  "1 5",
 
 
165
  "1 6",
166
- "9 3",
167
- "9 2",
168
  "1 7",
 
 
169
  "1 8",
 
 
170
  "9 1",
171
  "1 9",
172
  "9 0",
173
  "2 0",
174
  "8 9",
175
- "8 8",
176
  "2 1",
 
177
  "2 2",
178
  "8 7",
179
- "2 3",
180
  "8 6",
181
- "8 5",
182
  "2 4",
 
183
  "8 4",
184
  "2 5",
185
- "2 6",
186
  "8 3",
 
187
  "2 7",
188
  "8 2"
189
  ]
 
112
  "7": 13,
113
  "8": 14,
114
  "9": 15,
115
+ "=": 16,
116
+ "10": 17,
117
+ "11": 18,
118
+ "12": 19,
119
+ "13": 20,
120
+ "14": 21,
121
+ "15": 22,
122
+ "99": 23,
123
+ "98": 24,
124
+ "16": 25,
125
+ "97": 26,
126
+ "96": 27,
127
+ "17": 28,
128
+ "95": 29,
129
+ "94": 30,
130
+ "18": 31,
131
+ "93": 32,
132
+ "92": 33,
133
+ "91": 34,
134
+ "19": 35,
135
+ "90": 36,
136
+ "20": 37,
137
+ "89": 38,
138
  "21": 39,
139
+ "88": 40,
140
+ "22": 41,
141
+ "87": 42,
142
  "86": 43,
143
+ "23": 44,
144
  "24": 45,
145
+ "85": 46,
146
+ "84": 47,
147
+ "25": 48,
148
  "83": 49,
149
+ "26": 50,
150
+ "27": 51,
151
+ "82": 52
152
  },
153
  "merges": [
154
  "1 0",
 
 
155
  "1 1",
156
  "1 2",
 
157
  "1 3",
 
 
158
  "1 4",
 
159
  "1 5",
160
+ "9 9",
161
+ "9 8",
162
  "1 6",
163
+ "9 7",
164
+ "9 6",
165
  "1 7",
166
+ "9 5",
167
+ "9 4",
168
  "1 8",
169
+ "9 3",
170
+ "9 2",
171
  "9 1",
172
  "1 9",
173
  "9 0",
174
  "2 0",
175
  "8 9",
 
176
  "2 1",
177
+ "8 8",
178
  "2 2",
179
  "8 7",
 
180
  "8 6",
181
+ "2 3",
182
  "2 4",
183
+ "8 5",
184
  "8 4",
185
  "2 5",
 
186
  "8 3",
187
+ "2 6",
188
  "2 7",
189
  "8 2"
190
  ]
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ff1c739f49f1d5e41ec51ab373535b8a764a50d8baebabfa83575e1ac23c1259
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73f1fc7c92e5da9ab6501822b5f2d2a56bd159953c98e128e16c9e34ef8bc6a4
3
  size 5112