Hugging Face's logo

AaRaBiNoZa
/
calculator_model_test

Text2Text Generation
Transformers
TensorBoard
Safetensors
encoder-decoder
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
AaRaBiNoZa commited on
Commit
5dde924
•
1 Parent(s): e73c489

End of training

Browse files
Files changed (6) hide show
  1. README.md +41 -41
  2. config.json +2 -2
  3. model.safetensors +2 -2
  4. runs/Mar04_10-14-38_4aecdba70411/events.out.tfevents.1709547278.4aecdba70411.306.1 +3 -0
  5. tokenizer.json +17 -53
  6. training_args.bin +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: 0.8108
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
- | 3.3648 | 1.0 | 6 | 2.7465 |
48
- | 2.3708 | 2.0 | 12 | 2.0172 |
49
- | 1.8554 | 3.0 | 18 | 1.7507 |
50
- | 1.6599 | 4.0 | 24 | 1.6101 |
51
- | 1.5513 | 5.0 | 30 | 1.6004 |
52
- | 1.5494 | 6.0 | 36 | 1.5314 |
53
- | 1.5147 | 7.0 | 42 | 1.6012 |
54
- | 1.5361 | 8.0 | 48 | 1.9344 |
55
- | 1.5928 | 9.0 | 54 | 1.5257 |
56
- | 1.5114 | 10.0 | 60 | 1.5045 |
57
- | 1.457 | 11.0 | 66 | 1.4829 |
58
- | 1.4053 | 12.0 | 72 | 1.4635 |
59
- | 1.4049 | 13.0 | 78 | 1.4393 |
60
- | 1.4052 | 14.0 | 84 | 1.3878 |
61
- | 1.3437 | 15.0 | 90 | 1.3503 |
62
- | 1.3226 | 16.0 | 96 | 1.3059 |
63
- | 1.2817 | 17.0 | 102 | 1.2379 |
64
- | 1.2255 | 18.0 | 108 | 1.1771 |
65
- | 1.1717 | 19.0 | 114 | 1.2811 |
66
- | 1.2039 | 20.0 | 120 | 1.3512 |
67
- | 1.2312 | 21.0 | 126 | 1.2075 |
68
- | 1.1481 | 22.0 | 132 | 1.0787 |
69
- | 1.091 | 23.0 | 138 | 1.0809 |
70
- | 1.0598 | 24.0 | 144 | 1.0479 |
71
- | 1.0649 | 25.0 | 150 | 1.0148 |
72
- | 1.0172 | 26.0 | 156 | 1.0194 |
73
- | 1.0004 | 27.0 | 162 | 0.9618 |
74
- | 0.9639 | 28.0 | 168 | 0.9565 |
75
- | 0.9461 | 29.0 | 174 | 0.9197 |
76
- | 0.9112 | 30.0 | 180 | 0.9280 |
77
- | 0.9397 | 31.0 | 186 | 0.8850 |
78
- | 0.8829 | 32.0 | 192 | 0.8936 |
79
- | 0.8869 | 33.0 | 198 | 0.9086 |
80
- | 0.8956 | 34.0 | 204 | 0.8656 |
81
- | 0.8672 | 35.0 | 210 | 0.8579 |
82
- | 0.8427 | 36.0 | 216 | 0.8305 |
83
- | 0.8538 | 37.0 | 222 | 0.8312 |
84
- | 0.83 | 38.0 | 228 | 0.8179 |
85
- | 0.8411 | 39.0 | 234 | 0.8124 |
86
- | 0.8238 | 40.0 | 240 | 0.8108 |
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: 0.0047
17
 
18
  ## Model description
19
 
 
44
 
45
  | Training Loss | Epoch | Step | Validation Loss |
46
  |:-------------:|:-----:|:----:|:---------------:|
47
+ | 2.7292 | 1.0 | 6 | 2.1173 |
48
+ | 1.7871 | 2.0 | 12 | 1.3767 |
49
+ | 1.1487 | 3.0 | 18 | 0.9345 |
50
+ | 0.8396 | 4.0 | 24 | 0.8010 |
51
+ | 0.741 | 5.0 | 30 | 0.6938 |
52
+ | 0.617 | 6.0 | 36 | 0.6118 |
53
+ | 0.5495 | 7.0 | 42 | 0.5396 |
54
+ | 0.4991 | 8.0 | 48 | 0.4896 |
55
+ | 0.4526 | 9.0 | 54 | 0.4333 |
56
+ | 0.3899 | 10.0 | 60 | 0.3730 |
57
+ | 0.331 | 11.0 | 66 | 0.3093 |
58
+ | 0.2617 | 12.0 | 72 | 0.2348 |
59
+ | 0.2112 | 13.0 | 78 | 0.1729 |
60
+ | 0.1642 | 14.0 | 84 | 0.1352 |
61
+ | 0.1285 | 15.0 | 90 | 0.1043 |
62
+ | 0.1063 | 16.0 | 96 | 0.0811 |
63
+ | 0.0806 | 17.0 | 102 | 0.0593 |
64
+ | 0.0617 | 18.0 | 108 | 0.0429 |
65
+ | 0.0519 | 19.0 | 114 | 0.0305 |
66
+ | 0.0372 | 20.0 | 120 | 0.0230 |
67
+ | 0.0323 | 21.0 | 126 | 0.0191 |
68
+ | 0.0255 | 22.0 | 132 | 0.0152 |
69
+ | 0.0219 | 23.0 | 138 | 0.0134 |
70
+ | 0.0202 | 24.0 | 144 | 0.0118 |
71
+ | 0.0161 | 25.0 | 150 | 0.0105 |
72
+ | 0.0154 | 26.0 | 156 | 0.0087 |
73
+ | 0.0126 | 27.0 | 162 | 0.0077 |
74
+ | 0.0115 | 28.0 | 168 | 0.0069 |
75
+ | 0.0104 | 29.0 | 174 | 0.0064 |
76
+ | 0.0121 | 30.0 | 180 | 0.0061 |
77
+ | 0.0113 | 31.0 | 186 | 0.0062 |
78
+ | 0.0105 | 32.0 | 192 | 0.0059 |
79
+ | 0.0103 | 33.0 | 198 | 0.0057 |
80
+ | 0.0097 | 34.0 | 204 | 0.0052 |
81
+ | 0.0088 | 35.0 | 210 | 0.0052 |
82
+ | 0.0083 | 36.0 | 216 | 0.0050 |
83
+ | 0.0086 | 37.0 | 222 | 0.0048 |
84
+ | 0.0075 | 38.0 | 228 | 0.0048 |
85
+ | 0.0075 | 39.0 | 234 | 0.0047 |
86
+ | 0.0073 | 40.0 | 240 | 0.0047 |
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": 34
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": 34
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 sha256:39ba38daef0694e4ee3d5f5eef9162864c41b88cf1ecd98994d9cf8d87ac4c77
3
- size 31205552
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91f0aad8570d108895a8690688662c0eb6282ec67aec2acd1ffb139eb660ab3c
3
+ size 31168616
runs/Mar04_10-14-38_4aecdba70411/events.out.tfevents.1709547278.4aecdba70411.306.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4afeb7803097b9155009aad5867713813a97bf9e549969bf21eaf7ef6f415ff5
3
+ size 27997
tokenizer.json CHANGED
@@ -116,76 +116,40 @@
116
  "99": 17,
117
  "98": 18,
118
  "11": 19,
119
- "12": 20,
120
- "97": 21,
121
- "13": 22,
122
- "96": 23,
123
  "14": 24,
124
- "94": 25,
125
- "95": 26,
126
  "15": 27,
127
- "16": 28,
128
- "93": 29,
129
- "17": 30,
130
- "92": 31,
131
  "18": 32,
132
- "91": 33,
133
- "90": 34,
134
- "19": 35,
135
- "89": 36,
136
- "20": 37,
137
- "21": 38,
138
- "88": 39,
139
- "87": 40,
140
- "22": 41,
141
- "23": 42,
142
- "86": 43,
143
- "85": 44,
144
- "24": 45,
145
- "25": 46,
146
- "84": 47,
147
- "83": 48,
148
- "26": 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
  "1 4",
162
- "9 4",
163
  "9 5",
 
164
  "1 5",
165
- "1 6",
166
  "9 3",
167
- "1 7",
168
  "9 2",
 
169
  "1 8",
170
- "9 1",
171
- "9 0",
172
- "1 9",
173
- "8 9",
174
- "2 0",
175
- "2 1",
176
- "8 8",
177
- "8 7",
178
- "2 2",
179
- "2 3",
180
- "8 6",
181
- "8 5",
182
- "2 4",
183
- "2 5",
184
- "8 4",
185
- "8 3",
186
- "2 6",
187
- "2 7",
188
- "8 2"
189
  ]
190
  }
191
  }
 
116
  "99": 17,
117
  "98": 18,
118
  "11": 19,
119
+ "97": 20,
120
+ "12": 21,
121
+ "96": 22,
122
+ "13": 23,
123
  "14": 24,
124
+ "95": 25,
125
+ "94": 26,
126
  "15": 27,
127
+ "93": 28,
128
+ "16": 29,
129
+ "92": 30,
130
+ "17": 31,
131
  "18": 32,
132
+ "91": 33
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
133
  },
134
  "merges": [
135
  "1 0",
136
  "9 9",
137
  "9 8",
138
  "1 1",
 
139
  "9 7",
140
+ "1 2",
141
  "9 6",
142
+ "1 3",
143
  "1 4",
 
144
  "9 5",
145
+ "9 4",
146
  "1 5",
 
147
  "9 3",
148
+ "1 6",
149
  "9 2",
150
+ "1 7",
151
  "1 8",
152
+ "9 1"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
153
  ]
154
  }
155
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c82b96d19238c510597b546ba69be7fcb3344cc82e22d34d4a2bc8153fdf4ad2
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcfbe883afc6dc2fd20c64e1776f58f3ea875a7100e49d1f84ecf94198ca77cb
3
  size 5112