Hugging Face's logo

PawelNarcos
/
calculator_model_test

Text2Text Generation
Transformers
TensorBoard
Safetensors
encoder-decoder
Generated from Trainer
Model card Files Metrics Community
PawelNarcos commited on
Commit
91f4a29
·
verified ·
1 Parent(s): 1a7d730

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_14-08-28_7eccf1ba7969/events.out.tfevents.1709561308.7eccf1ba7969.331.2 +3 -0
  5. tokenizer.json +15 -51
  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: 0.4321
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
- | 1.6407 | 1.0 | 6 | 1.4441 |
48
- | 1.3434 | 2.0 | 12 | 1.1708 |
49
- | 1.1389 | 3.0 | 18 | 1.0341 |
50
- | 1.0368 | 4.0 | 24 | 0.9642 |
51
- | 0.9908 | 5.0 | 30 | 0.9415 |
52
- | 0.9337 | 6.0 | 36 | 0.8563 |
53
- | 0.8645 | 7.0 | 42 | 0.8316 |
54
- | 0.8712 | 8.0 | 48 | 0.7734 |
55
- | 0.8167 | 9.0 | 54 | 0.7830 |
56
- | 0.8066 | 10.0 | 60 | 0.8592 |
57
- | 0.8427 | 11.0 | 66 | 0.8967 |
58
- | 0.8576 | 12.0 | 72 | 0.7355 |
59
- | 0.768 | 13.0 | 78 | 0.7169 |
60
- | 0.7285 | 14.0 | 84 | 0.7622 |
61
- | 0.7499 | 15.0 | 90 | 0.7064 |
62
- | 0.745 | 16.0 | 96 | 0.6762 |
63
- | 0.7111 | 17.0 | 102 | 0.6568 |
64
- | 0.6875 | 18.0 | 108 | 0.6555 |
65
- | 0.6578 | 19.0 | 114 | 0.6345 |
66
- | 0.6575 | 20.0 | 120 | 0.6218 |
67
- | 0.6395 | 21.0 | 126 | 0.5968 |
68
- | 0.6334 | 22.0 | 132 | 0.6121 |
69
- | 0.6152 | 23.0 | 138 | 0.5598 |
70
- | 0.6004 | 24.0 | 144 | 0.5747 |
71
- | 0.6055 | 25.0 | 150 | 0.5442 |
72
- | 0.5802 | 26.0 | 156 | 0.5698 |
73
- | 0.569 | 27.0 | 162 | 0.5516 |
74
- | 0.59 | 28.0 | 168 | 0.5207 |
75
- | 0.5726 | 29.0 | 174 | 0.5025 |
76
- | 0.5501 | 30.0 | 180 | 0.4908 |
77
- | 0.5348 | 31.0 | 186 | 0.4861 |
78
- | 0.5264 | 32.0 | 192 | 0.4948 |
79
- | 0.5247 | 33.0 | 198 | 0.4665 |
80
- | 0.5225 | 34.0 | 204 | 0.4615 |
81
- | 0.5074 | 35.0 | 210 | 0.4552 |
82
- | 0.5044 | 36.0 | 216 | 0.4687 |
83
- | 0.4931 | 37.0 | 222 | 0.4478 |
84
- | 0.5002 | 38.0 | 228 | 0.4479 |
85
- | 0.5039 | 39.0 | 234 | 0.4330 |
86
- | 0.4774 | 40.0 | 240 | 0.4321 |
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: 0.0045
17
 
18
  ## Model description
19
 
 
44
 
45
  | Training Loss | Epoch | Step | Validation Loss |
46
  |:-------------:|:-----:|:----:|:---------------:|
47
+ | 2.7184 | 1.0 | 6 | 2.0589 |
48
+ | 1.7718 | 2.0 | 12 | 1.3610 |
49
+ | 1.1599 | 3.0 | 18 | 0.9216 |
50
+ | 0.8588 | 4.0 | 24 | 0.8028 |
51
+ | 0.7576 | 5.0 | 30 | 0.6973 |
52
+ | 0.6641 | 6.0 | 36 | 0.6219 |
53
+ | 0.5964 | 7.0 | 42 | 0.5578 |
54
+ | 0.5248 | 8.0 | 48 | 0.4840 |
55
+ | 0.4463 | 9.0 | 54 | 0.4088 |
56
+ | 0.3832 | 10.0 | 60 | 0.3579 |
57
+ | 0.3398 | 11.0 | 66 | 0.2951 |
58
+ | 0.2834 | 12.0 | 72 | 0.2701 |
59
+ | 0.2533 | 13.0 | 78 | 0.2033 |
60
+ | 0.2001 | 14.0 | 84 | 0.1558 |
61
+ | 0.1609 | 15.0 | 90 | 0.1252 |
62
+ | 0.1303 | 16.0 | 96 | 0.0917 |
63
+ | 0.1075 | 17.0 | 102 | 0.0676 |
64
+ | 0.0833 | 18.0 | 108 | 0.0490 |
65
+ | 0.0646 | 19.0 | 114 | 0.0408 |
66
+ | 0.0584 | 20.0 | 120 | 0.0320 |
67
+ | 0.0458 | 21.0 | 126 | 0.0233 |
68
+ | 0.0369 | 22.0 | 132 | 0.0167 |
69
+ | 0.0269 | 23.0 | 138 | 0.0137 |
70
+ | 0.0224 | 24.0 | 144 | 0.0119 |
71
+ | 0.0206 | 25.0 | 150 | 0.0097 |
72
+ | 0.0175 | 26.0 | 156 | 0.0094 |
73
+ | 0.0159 | 27.0 | 162 | 0.0073 |
74
+ | 0.0132 | 28.0 | 168 | 0.0069 |
75
+ | 0.0123 | 29.0 | 174 | 0.0064 |
76
+ | 0.0112 | 30.0 | 180 | 0.0058 |
77
+ | 0.0101 | 31.0 | 186 | 0.0056 |
78
+ | 0.0105 | 32.0 | 192 | 0.0053 |
79
+ | 0.0091 | 33.0 | 198 | 0.0050 |
80
+ | 0.01 | 34.0 | 204 | 0.0047 |
81
+ | 0.0093 | 35.0 | 210 | 0.0056 |
82
+ | 0.0102 | 36.0 | 216 | 0.0047 |
83
+ | 0.0092 | 37.0 | 222 | 0.0046 |
84
+ | 0.0086 | 38.0 | 228 | 0.0046 |
85
+ | 0.0091 | 39.0 | 234 | 0.0045 |
86
+ | 0.0088 | 40.0 | 240 | 0.0045 |
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:a8d99f725e716a42f4fc000c24f15c4496c7b9cbd638e5196036c8e4d5082d15
3
- size 31205552
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20043c6fa90bf082bae70b6d662ed56b58fadab68cb8e17c6bfcc1b1a611c365
3
+ size 31168616
runs/Mar04_14-08-28_7eccf1ba7969/events.out.tfevents.1709561308.7eccf1ba7969.331.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89f8db1a3da11a59172493fadd027646b66122372dca1f0bad8ad1e50865055b
3
+ size 27997
tokenizer.json CHANGED
@@ -112,8 +112,8 @@
112
  "7": 13,
113
  "8": 14,
114
  "9": 15,
115
- "10": 16,
116
- "99": 17,
117
  "98": 18,
118
  "11": 19,
119
  "97": 20,
@@ -122,36 +122,18 @@
122
  "13": 23,
123
  "14": 24,
124
  "95": 25,
125
- "15": 26,
126
- "94": 27,
127
- "16": 28,
128
- "93": 29,
129
- "17": 30,
130
- "92": 31,
131
- "91": 32,
132
- "18": 33,
133
- "19": 34,
134
- "90": 35,
135
- "89": 36,
136
- "20": 37,
137
- "88": 38,
138
- "21": 39,
139
- "87": 40,
140
- "22": 41,
141
- "23": 42,
142
- "86": 43,
143
- "24": 44,
144
- "85": 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
  "9 7",
@@ -160,32 +142,14 @@
160
  "1 3",
161
  "1 4",
162
  "9 5",
163
- "1 5",
164
  "9 4",
165
- "1 6",
166
  "9 3",
167
- "1 7",
168
  "9 2",
169
- "9 1",
170
  "1 8",
171
- "1 9",
172
- "9 0",
173
- "8 9",
174
- "2 0",
175
- "8 8",
176
- "2 1",
177
- "8 7",
178
- "2 2",
179
- "2 3",
180
- "8 6",
181
- "2 4",
182
- "8 5",
183
- "2 5",
184
- "8 4",
185
- "8 3",
186
- "2 6",
187
- "2 7",
188
- "8 2"
189
  ]
190
  }
191
  }
 
112
  "7": 13,
113
  "8": 14,
114
  "9": 15,
115
+ "99": 16,
116
+ "10": 17,
117
  "98": 18,
118
  "11": 19,
119
  "97": 20,
 
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
  "9 9",
136
+ "1 0",
137
  "9 8",
138
  "1 1",
139
  "9 7",
 
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:e48c1d8fa27c48211840a852e57d6071bb08a3240f84a0bbf6daf6c9dd45c69e
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2073aa3d0f54e113b4b4ae75748e771a17ca3862e58cb54d4c3a9a41ec41ea28
3
  size 5112