ludziej commited on
Commit
32d4c7f
1 Parent(s): 8736aaf

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: 0.7400
17
 
18
  ## Model description
19
 
@@ -44,16 +44,16 @@ The following hyperparameters were used during training:
44
 
45
  | Training Loss | Epoch | Step | Validation Loss |
46
  |:-------------:|:-----:|:----:|:---------------:|
47
- | 2.966 | 1.0 | 6 | 2.2765 |
48
- | 2.0606 | 2.0 | 12 | 1.7855 |
49
- | 1.6303 | 3.0 | 18 | 1.4249 |
50
- | 1.2968 | 4.0 | 24 | 1.1742 |
51
- | 1.1342 | 5.0 | 30 | 1.0421 |
52
- | 0.9916 | 6.0 | 36 | 0.9159 |
53
- | 0.8864 | 7.0 | 42 | 0.8410 |
54
- | 0.8119 | 8.0 | 48 | 0.7857 |
55
- | 0.7691 | 9.0 | 54 | 0.7509 |
56
- | 0.7515 | 10.0 | 60 | 0.7400 |
57
 
58
 
59
  ### 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: 0.8293
17
 
18
  ## Model description
19
 
 
44
 
45
  | Training Loss | Epoch | Step | Validation Loss |
46
  |:-------------:|:-----:|:----:|:---------------:|
47
+ | 3.1137 | 1.0 | 5 | 2.4084 |
48
+ | 2.2183 | 2.0 | 10 | 1.9525 |
49
+ | 1.8245 | 3.0 | 15 | 1.6233 |
50
+ | 1.4964 | 4.0 | 20 | 1.3035 |
51
+ | 1.2386 | 5.0 | 25 | 1.1278 |
52
+ | 1.1028 | 6.0 | 30 | 1.0257 |
53
+ | 1.0138 | 7.0 | 35 | 0.9629 |
54
+ | 0.9489 | 8.0 | 40 | 0.8972 |
55
+ | 0.8914 | 9.0 | 45 | 0.8501 |
56
+ | 0.8541 | 10.0 | 50 | 0.8293 |
57
 
58
 
59
  ### Framework versions
config.json CHANGED
@@ -78,9 +78,9 @@
78
  "typical_p": 1.0,
79
  "use_bfloat16": false,
80
  "use_cache": true,
81
- "vocab_size": 56
82
  },
83
- "decoder_start_token_id": 1,
84
  "encoder": {
85
  "_name_or_path": "",
86
  "add_cross_attention": false,
@@ -157,9 +157,9 @@
157
  "typical_p": 1.0,
158
  "use_bfloat16": false,
159
  "use_cache": true,
160
- "vocab_size": 56
161
  },
162
- "eos_token_id": 6,
163
  "is_encoder_decoder": true,
164
  "model_type": "encoder-decoder",
165
  "pad_token_id": 3,
 
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": {
85
  "_name_or_path": "",
86
  "add_cross_attention": false,
 
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,
164
  "model_type": "encoder-decoder",
165
  "pad_token_id": 3,
generation_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "_from_model_config": true,
3
- "decoder_start_token_id": 1,
4
- "eos_token_id": 6,
5
  "pad_token_id": 3,
6
  "transformers_version": "4.37.2"
7
  }
 
1
  {
2
  "_from_model_config": true,
3
+ "decoder_start_token_id": 2,
4
+ "eos_token_id": 0,
5
  "pad_token_id": 3,
6
  "transformers_version": "4.37.2"
7
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:52242b7293996d19398d1cb5904e713f5bce9bdcddfa61064c3e552d21d77ae3
3
- size 31213760
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81fc7b57152471f3a7e91ddb5748cb31d364cdf1231993b9b2e9a2e4935eacc2
3
+ size 31207604
runs/Feb28_16-17-19_3897ec21fae5/events.out.tfevents.1709137040.3897ec21fae5.58973.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05368d123af3b649195433823c9c8dff918427372036ad24af5306e61e5c1043
3
+ size 12864
tokenizer.json CHANGED
@@ -5,7 +5,7 @@
5
  "added_tokens": [
6
  {
7
  "id": 0,
8
- "content": "[UNK]",
9
  "single_word": false,
10
  "lstrip": false,
11
  "rstrip": false,
@@ -14,7 +14,7 @@
14
  },
15
  {
16
  "id": 1,
17
- "content": "[CLS]",
18
  "single_word": false,
19
  "lstrip": false,
20
  "rstrip": false,
@@ -23,7 +23,7 @@
23
  },
24
  {
25
  "id": 2,
26
- "content": "[SEP]",
27
  "single_word": false,
28
  "lstrip": false,
29
  "rstrip": false,
@@ -38,33 +38,6 @@
38
  "rstrip": false,
39
  "normalized": false,
40
  "special": true
41
- },
42
- {
43
- "id": 4,
44
- "content": "[MASK]",
45
- "single_word": false,
46
- "lstrip": false,
47
- "rstrip": false,
48
- "normalized": false,
49
- "special": true
50
- },
51
- {
52
- "id": 5,
53
- "content": "[BOS]",
54
- "single_word": false,
55
- "lstrip": false,
56
- "rstrip": false,
57
- "normalized": false,
58
- "special": true
59
- },
60
- {
61
- "id": 6,
62
- "content": "[EOS]",
63
- "single_word": false,
64
- "lstrip": false,
65
- "rstrip": false,
66
- "normalized": false,
67
- "special": true
68
  }
69
  ],
70
  "normalizer": null,
@@ -82,7 +55,7 @@
82
  },
83
  {
84
  "SpecialToken": {
85
- "id": "[CLS]",
86
  "type_id": 0
87
  }
88
  }
@@ -94,39 +67,18 @@
94
  "type_id": 0
95
  }
96
  },
97
- {
98
- "SpecialToken": {
99
- "id": "[CLS]",
100
- "type_id": 0
101
- }
102
- },
103
  {
104
  "Sequence": {
105
  "id": "B",
106
  "type_id": 1
107
  }
108
- },
109
- {
110
- "SpecialToken": {
111
- "id": "[EOS]",
112
- "type_id": 1
113
- }
114
  }
115
  ],
116
  "special_tokens": {
117
- "[CLS]": {
118
- "id": "[CLS]",
119
- "ids": [
120
- 0
121
- ],
122
- "tokens": [
123
- "[CLS]"
124
- ]
125
- },
126
  "[EOS]": {
127
  "id": "[EOS]",
128
  "ids": [
129
- 1
130
  ],
131
  "tokens": [
132
  "[EOS]"
@@ -144,80 +96,77 @@
144
  "fuse_unk": false,
145
  "byte_fallback": false,
146
  "vocab": {
147
- "[UNK]": 0,
148
- "[CLS]": 1,
149
- "[SEP]": 2,
150
  "[PAD]": 3,
151
- "[MASK]": 4,
152
- "[BOS]": 5,
153
- "[EOS]": 6,
154
- "+": 7,
155
- "-": 8,
156
- "0": 9,
157
- "1": 10,
158
- "2": 11,
159
- "3": 12,
160
- "4": 13,
161
- "5": 14,
162
- "6": 15,
163
- "7": 16,
164
- "8": 17,
165
- "9": 18,
166
- "=": 19,
167
- "99": 20,
168
- "10": 21,
169
- "98": 22,
170
- "11": 23,
171
- "97": 24,
172
- "12": 25,
173
- "96": 26,
174
- "13": 27,
175
- "95": 28,
176
- "14": 29,
177
- "94": 30,
178
- "15": 31,
179
- "93": 32,
180
- "16": 33,
181
- "92": 34,
182
- "17": 35,
183
- "91": 36,
184
- "18": 37,
185
- "19": 38,
186
- "90": 39,
187
- "20": 40,
188
- "89": 41,
189
- "21": 42,
190
- "88": 43,
191
- "22": 44,
192
- "87": 45,
193
- "23": 46,
194
- "86": 47,
195
- "85": 48,
196
- "24": 49,
197
- "25": 50,
198
- "84": 51,
199
- "26": 52,
200
- "83": 53,
201
- "27": 54,
202
- "82": 55
203
  },
204
  "merges": [
205
- "9 9",
206
  "1 0",
207
- "9 8",
208
  "1 1",
209
- "9 7",
210
  "1 2",
211
- "9 6",
212
  "1 3",
213
- "9 5",
214
  "1 4",
 
215
  "9 4",
216
  "1 5",
217
  "9 3",
218
  "1 6",
219
- "9 2",
220
  "1 7",
 
221
  "9 1",
222
  "1 8",
223
  "1 9",
@@ -228,10 +177,10 @@
228
  "8 8",
229
  "2 2",
230
  "8 7",
231
- "2 3",
232
  "8 6",
233
- "8 5",
234
  "2 4",
 
235
  "2 5",
236
  "8 4",
237
  "2 6",
 
5
  "added_tokens": [
6
  {
7
  "id": 0,
8
+ "content": "[EOS]",
9
  "single_word": false,
10
  "lstrip": false,
11
  "rstrip": false,
 
14
  },
15
  {
16
  "id": 1,
17
+ "content": "[UNK]",
18
  "single_word": false,
19
  "lstrip": false,
20
  "rstrip": false,
 
23
  },
24
  {
25
  "id": 2,
26
+ "content": "[CLS]",
27
  "single_word": false,
28
  "lstrip": false,
29
  "rstrip": false,
 
38
  "rstrip": false,
39
  "normalized": false,
40
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
41
  }
42
  ],
43
  "normalizer": null,
 
55
  },
56
  {
57
  "SpecialToken": {
58
+ "id": "[EOS]",
59
  "type_id": 0
60
  }
61
  }
 
67
  "type_id": 0
68
  }
69
  },
 
 
 
 
 
 
70
  {
71
  "Sequence": {
72
  "id": "B",
73
  "type_id": 1
74
  }
 
 
 
 
 
 
75
  }
76
  ],
77
  "special_tokens": {
 
 
 
 
 
 
 
 
 
78
  "[EOS]": {
79
  "id": "[EOS]",
80
  "ids": [
81
+ 0
82
  ],
83
  "tokens": [
84
  "[EOS]"
 
96
  "fuse_unk": false,
97
  "byte_fallback": false,
98
  "vocab": {
99
+ "[EOS]": 0,
100
+ "[UNK]": 1,
101
+ "[CLS]": 2,
102
  "[PAD]": 3,
103
+ "+": 4,
104
+ "-": 5,
105
+ "0": 6,
106
+ "1": 7,
107
+ "2": 8,
108
+ "3": 9,
109
+ "4": 10,
110
+ "5": 11,
111
+ "6": 12,
112
+ "7": 13,
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
+ "94": 27,
127
+ "15": 28,
128
+ "93": 29,
129
+ "16": 30,
130
+ "17": 31,
131
+ "92": 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
+ "22": 41,
141
+ "87": 42,
142
+ "86": 43,
143
+ "23": 44,
144
+ "24": 45,
145
+ "85": 46,
146
+ "25": 47,
147
+ "84": 48,
148
+ "26": 49,
149
+ "83": 50,
150
+ "27": 51,
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
  "9 4",
165
  "1 5",
166
  "9 3",
167
  "1 6",
 
168
  "1 7",
169
+ "9 2",
170
  "9 1",
171
  "1 8",
172
  "1 9",
 
177
  "8 8",
178
  "2 2",
179
  "8 7",
 
180
  "8 6",
181
+ "2 3",
182
  "2 4",
183
+ "8 5",
184
  "2 5",
185
  "8 4",
186
  "2 6",
tokenizer_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "added_tokens_decoder": {
3
  "0": {
4
- "content": "[UNK]",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
@@ -9,7 +9,7 @@
9
  "special": true
10
  },
11
  "1": {
12
- "content": "[CLS]",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
@@ -17,7 +17,7 @@
17
  "special": true
18
  },
19
  "2": {
20
- "content": "[SEP]",
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
@@ -31,30 +31,6 @@
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
34
- },
35
- "4": {
36
- "content": "[MASK]",
37
- "lstrip": false,
38
- "normalized": false,
39
- "rstrip": false,
40
- "single_word": false,
41
- "special": true
42
- },
43
- "5": {
44
- "content": "[BOS]",
45
- "lstrip": false,
46
- "normalized": false,
47
- "rstrip": false,
48
- "single_word": false,
49
- "special": true
50
- },
51
- "6": {
52
- "content": "[EOS]",
53
- "lstrip": false,
54
- "normalized": false,
55
- "rstrip": false,
56
- "single_word": false,
57
- "special": true
58
  }
59
  },
60
  "clean_up_tokenization_spaces": true,
 
1
  {
2
  "added_tokens_decoder": {
3
  "0": {
4
+ "content": "[EOS]",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
 
9
  "special": true
10
  },
11
  "1": {
12
+ "content": "[UNK]",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
 
17
  "special": true
18
  },
19
  "2": {
20
+ "content": "[CLS]",
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
 
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
34
  }
35
  },
36
  "clean_up_tokenization_spaces": true,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e54a33d2f290f85e42924b5f98306a6bedf48ced4afa93e90600479ea6cfd23f
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e46815b331bc7909d4a5070fdf40bbc45cf7721c8d9b964c3fe72a560bdecce
3
  size 4920