Hugging Face's logo

mtzig
/
reverse_add_replicate

Transformers
Safetensors
nanogpt
Generated from Trainer
Model card Files Community
mtzig commited on
Commit
3ff333a
·
verified ·
1 Parent(s): bcdd155

Model save

Browse files
Files changed (5) hide show
  1. README.md +218 -0
  2. config.json +18 -0
  3. generation_config.json +4 -0
  4. model.safetensors +3 -0
  5. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,218 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - accuracy
7
+ model-index:
8
+ - name: reverse_add_replicate
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # reverse_add_replicate
16
+
17
+ This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.0000
20
+ - Accuracy: 1.0
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 0.001
40
+ - train_batch_size: 64
41
+ - eval_batch_size: 64
42
+ - seed: 42
43
+ - gradient_accumulation_steps: 2
44
+ - total_train_batch_size: 128
45
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
46
+ - lr_scheduler_type: cosine
47
+ - lr_scheduler_warmup_ratio: 0.1
48
+ - num_epochs: 1
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
+ |:-------------:|:------:|:-----:|:---------------:|:--------:|
54
+ | No log | 0 | 0 | 2.6817 | 0.0 |
55
+ | 4.4613 | 0.0064 | 100 | 2.3109 | 0.0 |
56
+ | 4.335 | 0.0128 | 200 | 2.2529 | 0.0 |
57
+ | 4.2668 | 0.0192 | 300 | 2.1999 | 0.0 |
58
+ | 4.1908 | 0.0256 | 400 | 2.2754 | 0.0 |
59
+ | 4.2314 | 0.032 | 500 | 2.2359 | 0.0 |
60
+ | 3.6347 | 0.0384 | 600 | 1.8769 | 0.0 |
61
+ | 3.4763 | 0.0448 | 700 | 1.9187 | 0.0 |
62
+ | 3.1229 | 0.0512 | 800 | 1.9776 | 0.0 |
63
+ | 2.8398 | 0.0576 | 900 | 1.6601 | 0.0 |
64
+ | 3.0181 | 0.064 | 1000 | 1.6472 | 0.0 |
65
+ | 3.0209 | 0.0704 | 1100 | 1.6118 | 0.0 |
66
+ | 2.5603 | 0.0768 | 1200 | 1.3266 | 0.002 |
67
+ | 2.6247 | 0.0832 | 1300 | 1.4725 | 0.0 |
68
+ | 2.502 | 0.0896 | 1400 | 1.4013 | 0.0 |
69
+ | 2.6392 | 0.096 | 1500 | 1.6963 | 0.0 |
70
+ | 2.3297 | 0.1024 | 1600 | 1.5349 | 0.001 |
71
+ | 2.4639 | 0.1088 | 1700 | 1.3084 | 0.001 |
72
+ | 2.4555 | 0.1152 | 1800 | 1.3022 | 0.0 |
73
+ | 2.1326 | 0.1216 | 1900 | 1.2985 | 0.002 |
74
+ | 2.2766 | 0.128 | 2000 | 1.2175 | 0.0 |
75
+ | 2.5442 | 0.1344 | 2100 | 1.2973 | 0.0 |
76
+ | 2.3005 | 0.1408 | 2200 | 1.4224 | 0.0 |
77
+ | 2.4872 | 0.1472 | 2300 | 1.3877 | 0.001 |
78
+ | 2.3095 | 0.1536 | 2400 | 1.2081 | 0.002 |
79
+ | 2.3245 | 0.16 | 2500 | 1.2708 | 0.001 |
80
+ | 2.6165 | 0.1664 | 2600 | 1.5453 | 0.001 |
81
+ | 2.2608 | 0.1728 | 2700 | 1.2128 | 0.002 |
82
+ | 2.3363 | 0.1792 | 2800 | 1.2837 | 0.002 |
83
+ | 2.262 | 0.1856 | 2900 | 1.2287 | 0.007 |
84
+ | 2.1686 | 0.192 | 3000 | 1.3750 | 0.0 |
85
+ | 2.3021 | 0.1984 | 3100 | 1.1819 | 0.005 |
86
+ | 1.8808 | 0.2048 | 3200 | 1.1540 | 0.003 |
87
+ | 2.5449 | 0.2112 | 3300 | 1.1970 | 0.0 |
88
+ | 2.1555 | 0.2176 | 3400 | 1.1703 | 0.001 |
89
+ | 1.8908 | 0.224 | 3500 | 1.2023 | 0.003 |
90
+ | 2.074 | 0.2304 | 3600 | 1.3576 | 0.002 |
91
+ | 2.2279 | 0.2368 | 3700 | 1.7341 | 0.0 |
92
+ | 2.4889 | 0.2432 | 3800 | 1.2299 | 0.003 |
93
+ | 2.0978 | 0.2496 | 3900 | 1.2305 | 0.0 |
94
+ | 2.6161 | 0.256 | 4000 | 1.8482 | 0.002 |
95
+ | 1.937 | 0.2624 | 4100 | 1.1050 | 0.005 |
96
+ | 1.9751 | 0.2688 | 4200 | 1.2011 | 0.003 |
97
+ | 2.1199 | 0.2752 | 4300 | 1.2652 | 0.004 |
98
+ | 1.3263 | 0.2816 | 4400 | 0.7553 | 0.018 |
99
+ | 1.6805 | 0.288 | 4500 | 1.2216 | 0.005 |
100
+ | 1.1079 | 0.2944 | 4600 | 0.8702 | 0.012 |
101
+ | 1.4584 | 0.3008 | 4700 | 1.0929 | 0.0 |
102
+ | 1.1793 | 0.3072 | 4800 | 0.8990 | 0.005 |
103
+ | 0.7387 | 0.3136 | 4900 | 0.5412 | 0.031 |
104
+ | 1.4369 | 0.32 | 5000 | 1.4076 | 0.057 |
105
+ | 0.4073 | 0.3264 | 5100 | 0.4967 | 0.384 |
106
+ | 0.4319 | 0.3328 | 5200 | 0.4954 | 0.22 |
107
+ | 0.4177 | 0.3392 | 5300 | 0.5079 | 0.461 |
108
+ | 0.3973 | 0.3456 | 5400 | 0.4415 | 0.377 |
109
+ | 0.7054 | 0.352 | 5500 | 0.6503 | 0.1 |
110
+ | 0.5802 | 0.3584 | 5600 | 0.8201 | 0.063 |
111
+ | 0.1897 | 0.3648 | 5700 | 0.2479 | 0.462 |
112
+ | 0.3982 | 0.3712 | 5800 | 1.3623 | 0.186 |
113
+ | 0.6079 | 0.3776 | 5900 | 0.9248 | 0.195 |
114
+ | 0.2099 | 0.384 | 6000 | 0.4132 | 0.308 |
115
+ | 0.1991 | 0.3904 | 6100 | 0.1490 | 0.605 |
116
+ | 0.4226 | 0.3968 | 6200 | 0.5506 | 0.284 |
117
+ | 1.0515 | 0.4032 | 6300 | 1.1107 | 0.129 |
118
+ | 0.1014 | 0.4096 | 6400 | 0.2367 | 0.447 |
119
+ | 0.2219 | 0.416 | 6500 | 0.4163 | 0.347 |
120
+ | 2.1345 | 0.4224 | 6600 | 1.4566 | 0.0 |
121
+ | 0.5009 | 0.4288 | 6700 | 0.5398 | 0.158 |
122
+ | 0.1368 | 0.4352 | 6800 | 0.3955 | 0.17 |
123
+ | 0.0253 | 0.4416 | 6900 | 0.1468 | 0.629 |
124
+ | 0.1325 | 0.448 | 7000 | 0.3457 | 0.467 |
125
+ | 0.1866 | 0.4544 | 7100 | 0.4352 | 0.313 |
126
+ | 0.6098 | 0.4608 | 7200 | 0.8387 | 0.16 |
127
+ | 0.1887 | 0.4672 | 7300 | 0.2170 | 0.453 |
128
+ | 0.058 | 0.4736 | 7400 | 0.0872 | 0.731 |
129
+ | 0.2518 | 0.48 | 7500 | 0.3798 | 0.267 |
130
+ | 0.0314 | 0.4864 | 7600 | 0.3710 | 0.311 |
131
+ | 0.5078 | 0.4928 | 7700 | 0.5315 | 0.18 |
132
+ | 0.0894 | 0.4992 | 7800 | 0.2551 | 0.366 |
133
+ | 0.0788 | 0.5056 | 7900 | 0.1619 | 0.468 |
134
+ | 0.6913 | 0.512 | 8000 | 0.5418 | 0.198 |
135
+ | 0.2068 | 0.5184 | 8100 | 0.3154 | 0.323 |
136
+ | 0.8031 | 0.5248 | 8200 | 0.6006 | 0.149 |
137
+ | 0.0841 | 0.5312 | 8300 | 0.1740 | 0.74 |
138
+ | 0.1649 | 0.5376 | 8400 | 0.1316 | 0.592 |
139
+ | 0.4631 | 0.544 | 8500 | 0.5998 | 0.226 |
140
+ | 0.2732 | 0.5504 | 8600 | 0.7268 | 0.168 |
141
+ | 0.2153 | 0.5568 | 8700 | 0.2141 | 0.4 |
142
+ | 0.6022 | 0.5632 | 8800 | 0.3403 | 0.412 |
143
+ | 0.115 | 0.5696 | 8900 | 0.0905 | 0.712 |
144
+ | 0.1791 | 0.576 | 9000 | 0.1527 | 0.554 |
145
+ | 0.2843 | 0.5824 | 9100 | 0.3514 | 0.319 |
146
+ | 0.0359 | 0.5888 | 9200 | 0.0447 | 0.829 |
147
+ | 0.018 | 0.5952 | 9300 | 0.0565 | 0.781 |
148
+ | 0.0363 | 0.6016 | 9400 | 0.1747 | 0.507 |
149
+ | 0.1352 | 0.608 | 9500 | 0.3075 | 0.498 |
150
+ | 0.0642 | 0.6144 | 9600 | 0.2735 | 0.475 |
151
+ | 0.0619 | 0.6208 | 9700 | 0.0728 | 0.773 |
152
+ | 0.0305 | 0.6272 | 9800 | 0.2225 | 0.694 |
153
+ | 0.1128 | 0.6336 | 9900 | 0.1043 | 0.649 |
154
+ | 0.1403 | 0.64 | 10000 | 0.0730 | 0.692 |
155
+ | 0.1471 | 0.6464 | 10100 | 0.1880 | 0.497 |
156
+ | 0.0632 | 0.6528 | 10200 | 0.1933 | 0.657 |
157
+ | 0.0757 | 0.6592 | 10300 | 0.0467 | 0.806 |
158
+ | 0.0969 | 0.6656 | 10400 | 0.3012 | 0.546 |
159
+ | 0.0552 | 0.672 | 10500 | 0.2214 | 0.37 |
160
+ | 0.0821 | 0.6784 | 10600 | 0.2411 | 0.504 |
161
+ | 0.0254 | 0.6848 | 10700 | 0.1192 | 0.619 |
162
+ | 0.0058 | 0.6912 | 10800 | 0.0409 | 0.901 |
163
+ | 0.0343 | 0.6976 | 10900 | 0.1508 | 0.671 |
164
+ | 0.0357 | 0.704 | 11000 | 0.0646 | 0.766 |
165
+ | 0.1314 | 0.7104 | 11100 | 0.1610 | 0.558 |
166
+ | 0.3291 | 0.7168 | 11200 | 1.1259 | 0.282 |
167
+ | 0.0217 | 0.7232 | 11300 | 0.0448 | 0.855 |
168
+ | 0.0486 | 0.7296 | 11400 | 0.1727 | 0.719 |
169
+ | 0.0055 | 0.736 | 11500 | 0.0911 | 0.715 |
170
+ | 0.028 | 0.7424 | 11600 | 0.0281 | 0.904 |
171
+ | 0.0518 | 0.7488 | 11700 | 0.2969 | 0.421 |
172
+ | 0.0049 | 0.7552 | 11800 | 0.0311 | 0.871 |
173
+ | 0.0044 | 0.7616 | 11900 | 0.0091 | 0.955 |
174
+ | 0.0158 | 0.768 | 12000 | 0.0036 | 0.979 |
175
+ | 0.0015 | 0.7744 | 12100 | 0.0169 | 0.919 |
176
+ | 0.0099 | 0.7808 | 12200 | 0.0078 | 0.961 |
177
+ | 0.0098 | 0.7872 | 12300 | 0.0123 | 0.952 |
178
+ | 0.0006 | 0.7936 | 12400 | 0.0065 | 0.966 |
179
+ | 0.0015 | 0.8 | 12500 | 0.0058 | 0.971 |
180
+ | 0.0 | 0.8064 | 12600 | 0.0031 | 0.984 |
181
+ | 0.0002 | 0.8128 | 12700 | 0.0124 | 0.961 |
182
+ | 0.0002 | 0.8192 | 12800 | 0.0024 | 0.988 |
183
+ | 0.0 | 0.8256 | 12900 | 0.0034 | 0.987 |
184
+ | 0.0 | 0.832 | 13000 | 0.0055 | 0.98 |
185
+ | 0.0 | 0.8384 | 13100 | 0.0063 | 0.979 |
186
+ | 0.0063 | 0.8448 | 13200 | 0.0082 | 0.958 |
187
+ | 0.0003 | 0.8512 | 13300 | 0.0016 | 0.993 |
188
+ | 0.0001 | 0.8576 | 13400 | 0.0007 | 0.996 |
189
+ | 0.0002 | 0.864 | 13500 | 0.0009 | 0.996 |
190
+ | 0.0 | 0.8704 | 13600 | 0.0004 | 0.997 |
191
+ | 0.0 | 0.8768 | 13700 | 0.0072 | 0.971 |
192
+ | 0.0012 | 0.8832 | 13800 | 0.0011 | 0.995 |
193
+ | 0.0 | 0.8896 | 13900 | 0.0059 | 0.986 |
194
+ | 0.0 | 0.896 | 14000 | 0.0091 | 0.981 |
195
+ | 0.0 | 0.9024 | 14100 | 0.0081 | 0.984 |
196
+ | 0.0 | 0.9088 | 14200 | 0.0023 | 0.991 |
197
+ | 0.0 | 0.9152 | 14300 | 0.0031 | 0.991 |
198
+ | 0.0 | 0.9216 | 14400 | 0.0001 | 0.999 |
199
+ | 0.0 | 0.928 | 14500 | 0.0001 | 1.0 |
200
+ | 0.0 | 0.9344 | 14600 | 0.0001 | 1.0 |
201
+ | 0.0 | 0.9408 | 14700 | 0.0001 | 1.0 |
202
+ | 0.0 | 0.9472 | 14800 | 0.0000 | 1.0 |
203
+ | 0.0 | 0.9536 | 14900 | 0.0001 | 1.0 |
204
+ | 0.0 | 0.96 | 15000 | 0.0000 | 1.0 |
205
+ | 0.0001 | 0.9664 | 15100 | 0.0000 | 1.0 |
206
+ | 0.0 | 0.9728 | 15200 | 0.0000 | 1.0 |
207
+ | 0.0 | 0.9792 | 15300 | 0.0000 | 1.0 |
208
+ | 0.0 | 0.9856 | 15400 | 0.0000 | 1.0 |
209
+ | 0.0 | 0.992 | 15500 | 0.0000 | 1.0 |
210
+ | 0.0 | 0.9984 | 15600 | 0.0000 | 1.0 |
211
+
212
+
213
+ ### Framework versions
214
+
215
+ - Transformers 4.46.0
216
+ - Pytorch 2.5.1
217
+ - Datasets 3.1.0
218
+ - Tokenizers 0.20.1
config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "NanoGPT"
4
+ ],
5
+ "bias": true,
6
+ "block_size": 256,
7
+ "dropout": 0.0,
8
+ "model_type": "nanogpt",
9
+ "n_embd": 384,
10
+ "n_head": 6,
11
+ "n_layer": 6,
12
+ "nonlinearity": "RELU",
13
+ "torch_dtype": "float32",
14
+ "transformers_version": "4.46.0",
15
+ "use_NoPE": true,
16
+ "use_layernorm": true,
17
+ "vocab_size": 14
18
+ }
generation_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "transformers_version": "4.46.0"
4
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e690fbbbc9ca587e0419aa902d1bcbf5f20545ed219a9a32e047b1caa1b7915
3
+ size 42640744
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa0fdf48f20c59e3d6da245ddade0ec393ed2bdef608d2fb69b015c1077fe2e6
3
+ size 5240