Hugging Face's logo

Adamas23
/
calculator_model_test

Transformers
TensorBoard
Safetensors
encoder-decoder
text2text-generation
Generated from Trainer
Model card Files
xet
Metrics Community
Adamas23 commited on
Commit
1b76fe1
·
verified ·
1 Parent(s): c76b5a1

End of training

Browse files
Files changed (7) hide show
  1. README.md +43 -43
  2. config.json +1 -1
  3. generation_config.json +1 -1
  4. model.safetensors +1 -1
  5. runs/Mar20_18-03-49_84f0f3a57a0c/events.out.tfevents.1710957830.84f0f3a57a0c.853.0 +3 -0
  6. tokenizer.json +6 -6
  7. 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: 0.0162
17
 
18
  ## Model description
19
 
@@ -44,51 +44,51 @@ The following hyperparameters were used during training:
44
 
45
  | Training Loss | Epoch | Step | Validation Loss |
46
  |:-------------:|:-----:|:----:|:---------------:|
47
- | 2.7671 | 1.0 | 6 | 2.1243 |
48
- | 1.8409 | 2.0 | 12 | 1.5234 |
49
- | 1.3096 | 3.0 | 18 | 1.0612 |
50
- | 0.9557 | 4.0 | 24 | 0.8622 |
51
- | 0.8499 | 5.0 | 30 | 0.7836 |
52
- | 0.7285 | 6.0 | 36 | 0.6873 |
53
- | 0.6464 | 7.0 | 42 | 0.5698 |
54
- | 0.5513 | 8.0 | 48 | 0.5230 |
55
- | 0.4906 | 9.0 | 54 | 0.4933 |
56
- | 0.4817 | 10.0 | 60 | 0.4228 |
57
- | 0.388 | 11.0 | 66 | 0.3776 |
58
- | 0.3697 | 12.0 | 72 | 0.3796 |
59
- | 0.3994 | 13.0 | 78 | 0.3245 |
60
- | 0.3127 | 14.0 | 84 | 0.3145 |
61
- | 0.3215 | 15.0 | 90 | 0.2752 |
62
- | 0.2758 | 16.0 | 96 | 0.2400 |
63
- | 0.2507 | 17.0 | 102 | 0.2158 |
64
- | 0.217 | 18.0 | 108 | 0.2150 |
65
- | 0.2223 | 19.0 | 114 | 0.1940 |
66
- | 0.1746 | 20.0 | 120 | 0.1826 |
67
- | 0.1625 | 21.0 | 126 | 0.1445 |
68
- | 0.1386 | 22.0 | 132 | 0.1421 |
69
- | 0.1432 | 23.0 | 138 | 0.1241 |
70
- | 0.1329 | 24.0 | 144 | 0.1104 |
71
- | 0.1413 | 25.0 | 150 | 0.0889 |
72
- | 0.1093 | 26.0 | 156 | 0.0765 |
73
- | 0.0869 | 27.0 | 162 | 0.0596 |
74
- | 0.0677 | 28.0 | 168 | 0.0495 |
75
- | 0.0646 | 29.0 | 174 | 0.0397 |
76
- | 0.0539 | 30.0 | 180 | 0.0359 |
77
- | 0.0502 | 31.0 | 186 | 0.0339 |
78
- | 0.0399 | 32.0 | 192 | 0.0285 |
79
- | 0.0453 | 33.0 | 198 | 0.0239 |
80
- | 0.0351 | 34.0 | 204 | 0.0223 |
81
- | 0.039 | 35.0 | 210 | 0.0199 |
82
- | 0.0255 | 36.0 | 216 | 0.0195 |
83
- | 0.0259 | 37.0 | 222 | 0.0177 |
84
- | 0.0241 | 38.0 | 228 | 0.0168 |
85
- | 0.0251 | 39.0 | 234 | 0.0163 |
86
- | 0.0239 | 40.0 | 240 | 0.0162 |
87
 
88
 
89
  ### Framework versions
90
 
91
- - Transformers 4.38.1
92
- - Pytorch 2.1.0+cu121
93
  - Datasets 2.18.0
94
  - Tokenizers 0.15.2
 
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: 0.0086
17
 
18
  ## Model description
19
 
 
44
 
45
  | Training Loss | Epoch | Step | Validation Loss |
46
  |:-------------:|:-----:|:----:|:---------------:|
47
+ | 2.7015 | 1.0 | 6 | 2.0207 |
48
+ | 1.7126 | 2.0 | 12 | 1.2868 |
49
+ | 1.1107 | 3.0 | 18 | 0.9127 |
50
+ | 0.8465 | 4.0 | 24 | 0.7797 |
51
+ | 0.749 | 5.0 | 30 | 0.7586 |
52
+ | 0.71 | 6.0 | 36 | 0.6566 |
53
+ | 0.6332 | 7.0 | 42 | 0.6026 |
54
+ | 0.5757 | 8.0 | 48 | 0.5232 |
55
+ | 0.5054 | 9.0 | 54 | 0.4744 |
56
+ | 0.4469 | 10.0 | 60 | 0.3915 |
57
+ | 0.3736 | 11.0 | 66 | 0.3214 |
58
+ | 0.314 | 12.0 | 72 | 0.2855 |
59
+ | 0.282 | 13.0 | 78 | 0.2260 |
60
+ | 0.2234 | 14.0 | 84 | 0.2077 |
61
+ | 0.2157 | 15.0 | 90 | 0.1623 |
62
+ | 0.1647 | 16.0 | 96 | 0.1344 |
63
+ | 0.1505 | 17.0 | 102 | 0.1246 |
64
+ | 0.1342 | 18.0 | 108 | 0.1086 |
65
+ | 0.1104 | 19.0 | 114 | 0.0998 |
66
+ | 0.098 | 20.0 | 120 | 0.0788 |
67
+ | 0.0829 | 21.0 | 126 | 0.0575 |
68
+ | 0.0706 | 22.0 | 132 | 0.0496 |
69
+ | 0.0639 | 23.0 | 138 | 0.0425 |
70
+ | 0.0544 | 24.0 | 144 | 0.0352 |
71
+ | 0.0478 | 25.0 | 150 | 0.0316 |
72
+ | 0.0435 | 26.0 | 156 | 0.0255 |
73
+ | 0.0368 | 27.0 | 162 | 0.0237 |
74
+ | 0.0314 | 28.0 | 168 | 0.0215 |
75
+ | 0.0313 | 29.0 | 174 | 0.0175 |
76
+ | 0.0281 | 30.0 | 180 | 0.0157 |
77
+ | 0.0319 | 31.0 | 186 | 0.0132 |
78
+ | 0.0235 | 32.0 | 192 | 0.0117 |
79
+ | 0.0207 | 33.0 | 198 | 0.0112 |
80
+ | 0.0178 | 34.0 | 204 | 0.0104 |
81
+ | 0.0184 | 35.0 | 210 | 0.0098 |
82
+ | 0.0176 | 36.0 | 216 | 0.0092 |
83
+ | 0.0161 | 37.0 | 222 | 0.0092 |
84
+ | 0.0167 | 38.0 | 228 | 0.0090 |
85
+ | 0.0154 | 39.0 | 234 | 0.0087 |
86
+ | 0.0155 | 40.0 | 240 | 0.0086 |
87
 
88
 
89
  ### Framework versions
90
 
91
+ - Transformers 4.38.2
92
+ - Pytorch 2.2.1+cu121
93
  - Datasets 2.18.0
94
  - Tokenizers 0.15.2
config.json CHANGED
@@ -164,6 +164,6 @@
164
  "model_type": "encoder-decoder",
165
  "pad_token_id": 3,
166
  "torch_dtype": "float32",
167
- "transformers_version": "4.38.1",
168
  "unk_token_id": null
169
  }
 
164
  "model_type": "encoder-decoder",
165
  "pad_token_id": 3,
166
  "torch_dtype": "float32",
167
+ "transformers_version": "4.38.2",
168
  "unk_token_id": null
169
  }
generation_config.json CHANGED
@@ -3,5 +3,5 @@
3
  "decoder_start_token_id": 2,
4
  "eos_token_id": 0,
5
  "pad_token_id": 3,
6
- "transformers_version": "4.38.1"
7
  }
 
3
  "decoder_start_token_id": 2,
4
  "eos_token_id": 0,
5
  "pad_token_id": 3,
6
+ "transformers_version": "4.38.2"
7
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3d8b3effa605654cc97228060a9f386e0549bc6153a1a73b1e30c69d69467952
3
  size 31168616
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55134369b1e8fe1e2d405f391294eb4f469b550209ca9ce1b99d173cb60760e6
3
  size 31168616
runs/Mar20_18-03-49_84f0f3a57a0c/events.out.tfevents.1710957830.84f0f3a57a0c.853.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:077d4c012ce69c5bea1a606609db0279794ab0754d432db2c531e5716cde7bbd
3
+ size 27997
tokenizer.json CHANGED
@@ -114,8 +114,8 @@
114
  "9": 15,
115
  "99": 16,
116
  "10": 17,
117
- "98": 18,
118
- "11": 19,
119
  "12": 20,
120
  "97": 21,
121
  "13": 22,
@@ -126,16 +126,16 @@
126
  "15": 27,
127
  "93": 28,
128
  "16": 29,
129
- "92": 30,
130
- "17": 31,
131
  "91": 32,
132
  "18": 33
133
  },
134
  "merges": [
135
  "9 9",
136
  "1 0",
137
- "9 8",
138
  "1 1",
 
139
  "1 2",
140
  "9 7",
141
  "1 3",
@@ -146,8 +146,8 @@
146
  "1 5",
147
  "9 3",
148
  "1 6",
149
- "9 2",
150
  "1 7",
 
151
  "9 1",
152
  "1 8"
153
  ]
 
114
  "9": 15,
115
  "99": 16,
116
  "10": 17,
117
+ "11": 18,
118
+ "98": 19,
119
  "12": 20,
120
  "97": 21,
121
  "13": 22,
 
126
  "15": 27,
127
  "93": 28,
128
  "16": 29,
129
+ "17": 30,
130
+ "92": 31,
131
  "91": 32,
132
  "18": 33
133
  },
134
  "merges": [
135
  "9 9",
136
  "1 0",
 
137
  "1 1",
138
+ "9 8",
139
  "1 2",
140
  "9 7",
141
  "1 3",
 
146
  "1 5",
147
  "9 3",
148
  "1 6",
 
149
  "1 7",
150
+ "9 2",
151
  "9 1",
152
  "1 8"
153
  ]
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2927464d0a68791dc1fc35a7ce36cd8aa776a70ecf01c86a319312356a440785
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3ef6394f7d7f9ab5741d70af66cd8b4dc30df6f269be664e4563b0803947ec5
3
  size 5112