BartekSadlej commited on
Commit
6b0ae77
1 Parent(s): 5147f9d

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: 0.6779
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
- | 3.4465 | 1.0 | 6 | 2.8008 |
48
- | 2.4324 | 2.0 | 12 | 2.0258 |
49
- | 1.8717 | 3.0 | 18 | 1.7217 |
50
- | 1.6802 | 4.0 | 24 | 1.6377 |
51
- | 1.5784 | 5.0 | 30 | 1.5571 |
52
- | 1.5182 | 6.0 | 36 | 1.5249 |
53
- | 1.4891 | 7.0 | 42 | 1.5271 |
54
- | 1.491 | 8.0 | 48 | 1.5028 |
55
- | 1.4957 | 9.0 | 54 | 1.4941 |
56
- | 1.4419 | 10.0 | 60 | 1.4593 |
57
- | 1.4233 | 11.0 | 66 | 1.4681 |
58
- | 1.4452 | 12.0 | 72 | 1.3954 |
59
- | 1.3414 | 13.0 | 78 | 1.3100 |
60
- | 1.2882 | 14.0 | 84 | 1.2658 |
61
- | 1.2233 | 15.0 | 90 | 1.1740 |
62
- | 1.1812 | 16.0 | 96 | 1.1963 |
63
- | 1.1567 | 17.0 | 102 | 1.3220 |
64
- | 1.1566 | 18.0 | 108 | 1.1536 |
65
- | 1.0904 | 19.0 | 114 | 1.1253 |
66
- | 1.0811 | 20.0 | 120 | 1.0386 |
67
- | 1.0245 | 21.0 | 126 | 1.0415 |
68
- | 1.0028 | 22.0 | 132 | 0.9741 |
69
- | 0.9561 | 23.0 | 138 | 0.9236 |
70
- | 0.9204 | 24.0 | 144 | 0.9070 |
71
- | 0.9064 | 25.0 | 150 | 0.8667 |
72
- | 0.8868 | 26.0 | 156 | 0.8357 |
73
- | 0.8513 | 27.0 | 162 | 0.8124 |
74
- | 0.8199 | 28.0 | 168 | 0.8041 |
75
- | 0.7951 | 29.0 | 174 | 0.7810 |
76
- | 0.8079 | 30.0 | 180 | 0.7692 |
77
- | 0.7769 | 31.0 | 186 | 0.7839 |
78
- | 0.782 | 32.0 | 192 | 0.7484 |
79
- | 0.7378 | 33.0 | 198 | 0.7386 |
80
- | 0.7591 | 34.0 | 204 | 0.7165 |
81
- | 0.7269 | 35.0 | 210 | 0.7015 |
82
- | 0.7163 | 36.0 | 216 | 0.7006 |
83
- | 0.7231 | 37.0 | 222 | 0.6897 |
84
- | 0.7088 | 38.0 | 228 | 0.6824 |
85
- | 0.7067 | 39.0 | 234 | 0.6795 |
86
- | 0.7004 | 40.0 | 240 | 0.6779 |
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: 0.0923
17
 
18
  ## Model description
19
 
 
44
 
45
  | Training Loss | Epoch | Step | Validation Loss |
46
  |:-------------:|:-----:|:----:|:---------------:|
47
+ | 3.0524 | 1.0 | 6 | 2.3364 |
48
+ | 2.0601 | 2.0 | 12 | 1.7532 |
49
+ | 1.5868 | 3.0 | 18 | 1.3439 |
50
+ | 1.2198 | 4.0 | 24 | 1.0697 |
51
+ | 1.0324 | 5.0 | 30 | 0.9496 |
52
+ | 0.8954 | 6.0 | 36 | 0.8209 |
53
+ | 0.7853 | 7.0 | 42 | 0.7529 |
54
+ | 0.7118 | 8.0 | 48 | 0.6709 |
55
+ | 0.6574 | 9.0 | 54 | 0.6452 |
56
+ | 0.6368 | 10.0 | 60 | 0.5870 |
57
+ | 0.5746 | 11.0 | 66 | 0.5092 |
58
+ | 0.5092 | 12.0 | 72 | 0.4923 |
59
+ | 0.4829 | 13.0 | 78 | 0.4596 |
60
+ | 0.4542 | 14.0 | 84 | 0.4221 |
61
+ | 0.4286 | 15.0 | 90 | 0.3805 |
62
+ | 0.3987 | 16.0 | 96 | 0.3707 |
63
+ | 0.3704 | 17.0 | 102 | 0.3424 |
64
+ | 0.3639 | 18.0 | 108 | 0.3204 |
65
+ | 0.3297 | 19.0 | 114 | 0.2918 |
66
+ | 0.3085 | 20.0 | 120 | 0.2683 |
67
+ | 0.2814 | 21.0 | 126 | 0.2524 |
68
+ | 0.2667 | 22.0 | 132 | 0.2489 |
69
+ | 0.2593 | 23.0 | 138 | 0.2238 |
70
+ | 0.2427 | 24.0 | 144 | 0.2168 |
71
+ | 0.2318 | 25.0 | 150 | 0.2048 |
72
+ | 0.226 | 26.0 | 156 | 0.2018 |
73
+ | 0.2085 | 27.0 | 162 | 0.1860 |
74
+ | 0.1976 | 28.0 | 168 | 0.1800 |
75
+ | 0.1928 | 29.0 | 174 | 0.1621 |
76
+ | 0.1814 | 30.0 | 180 | 0.1551 |
77
+ | 0.1758 | 31.0 | 186 | 0.1398 |
78
+ | 0.1598 | 32.0 | 192 | 0.1291 |
79
+ | 0.1541 | 33.0 | 198 | 0.1206 |
80
+ | 0.1411 | 34.0 | 204 | 0.1097 |
81
+ | 0.1371 | 35.0 | 210 | 0.1042 |
82
+ | 0.1299 | 36.0 | 216 | 0.1015 |
83
+ | 0.1273 | 37.0 | 222 | 0.0955 |
84
+ | 0.1214 | 38.0 | 228 | 0.0944 |
85
+ | 0.1161 | 39.0 | 234 | 0.0935 |
86
+ | 0.1188 | 40.0 | 240 | 0.0923 |
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 sha256:6725a75dc79b2917a840667d5428b4249d91fd36502cfc5e7aa3a967383da036
3
- size 31205552
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea68d63e33c6aa4e3963c65007072dd91138022c527fb9911e38f90037f0ea1a
3
+ size 31207604
runs/Mar04_10-05-24_f9b5e148b874/events.out.tfevents.1709546724.f9b5e148b874.318.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1856cb68386e1447ff2eaeb1f817adb39e9e7042877f3c566383d0f3a1f8d47
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
  "11": 18,
118
- "98": 19,
119
- "12": 20,
120
- "97": 21,
121
- "96": 22,
122
- "13": 23,
123
- "95": 24,
124
- "14": 25,
125
- "15": 26,
126
- "94": 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
- "89": 36,
136
  "20": 37,
137
- "88": 38,
138
  "21": 39,
139
- "22": 40,
140
  "87": 41,
141
- "23": 42,
142
- "86": 43,
143
- "24": 44,
144
  "85": 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
  "1 1",
156
- "9 8",
157
  "1 2",
158
- "9 7",
159
- "9 6",
160
  "1 3",
161
- "9 5",
162
  "1 4",
163
  "1 5",
164
- "9 4",
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
- "8 9",
174
  "2 0",
175
- "8 8",
176
  "2 1",
177
- "2 2",
178
  "8 7",
 
179
  "2 3",
180
  "8 6",
181
- "2 4",
182
  "8 5",
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
+ "16": 24,
124
+ "98": 25,
125
+ "97": 26,
126
+ "96": 27,
127
+ "17": 28,
128
+ "95": 29,
129
+ "94": 30,
130
+ "93": 31,
131
  "18": 32,
132
+ "92": 33,
133
+ "91": 34,
134
  "90": 35,
135
+ "19": 36,
136
  "20": 37,
137
+ "89": 38,
138
  "21": 39,
139
+ "88": 40,
140
  "87": 41,
141
+ "22": 42,
142
+ "23": 43,
143
+ "86": 44,
144
  "85": 45,
145
+ "24": 46,
146
  "25": 47,
147
+ "84": 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
  "1 6",
162
+ "9 8",
163
+ "9 7",
164
+ "9 6",
165
  "1 7",
166
+ "9 5",
167
+ "9 4",
168
+ "9 3",
169
  "1 8",
170
+ "9 2",
171
  "9 1",
 
172
  "9 0",
173
+ "1 9",
174
  "2 0",
175
+ "8 9",
176
  "2 1",
177
+ "8 8",
178
  "8 7",
179
+ "2 2",
180
  "2 3",
181
  "8 6",
 
182
  "8 5",
183
+ "2 4",
184
  "2 5",
185
+ "8 4",
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 sha256:65bd80821cc36b408de2a8706ddb6762183801d3bf3910bb268eb7f7e7c2de7c
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4365175f4bd43cb181ceb471649e3c191725217a9b6655f6c931ccfc1f9c9098
3
  size 5112