Hugging Face's logo

mtzig
/
reverseadd_lr5e-4_batch128_train1-16_eval19

Transformers
Safetensors
nanogpt
Generated from Trainer
Model card Files
xet
Community
mtzig commited on
Commit
b3f97ea
·
verified ·
1 Parent(s): 74b1e99

Model save

Browse files
Files changed (4) hide show
  1. README.md +215 -0
  2. config.json +19 -0
  3. model.safetensors +3 -0
  4. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,215 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - accuracy
7
+ model-index:
8
+ - name: reverseadd_lr5e-4_batch128_train1-16_eval19
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
+ # reverseadd_lr5e-4_batch128_train1-16_eval19
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: 0.0282
20
+ - Accuracy: 0.9071
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: 0.0005
40
+ - train_batch_size: 128
41
+ - eval_batch_size: 512
42
+ - seed: 23452399
43
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
44
+ - lr_scheduler_type: cosine
45
+ - lr_scheduler_warmup_ratio: 0.1
46
+ - num_epochs: 1
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
+ |:-------------:|:------:|:-----:|:---------------:|:--------:|
52
+ | No log | 0 | 0 | 2.6749 | 0.0 |
53
+ | 2.2847 | 0.0064 | 100 | 2.3390 | 0.0 |
54
+ | 2.2888 | 0.0128 | 200 | 2.2967 | 0.0 |
55
+ | 2.1023 | 0.0192 | 300 | 2.2337 | 0.0 |
56
+ | 2.2718 | 0.0256 | 400 | 2.2355 | 0.0 |
57
+ | 2.0874 | 0.032 | 500 | 2.2691 | 0.0 |
58
+ | 1.9163 | 0.0384 | 600 | 2.1325 | 0.0 |
59
+ | 1.862 | 0.0448 | 700 | 2.2135 | 0.0 |
60
+ | 1.6661 | 0.0512 | 800 | 2.0404 | 0.0 |
61
+ | 1.5156 | 0.0576 | 900 | 2.4042 | 0.0 |
62
+ | 1.4395 | 0.064 | 1000 | 1.5664 | 0.0 |
63
+ | 1.8082 | 0.0704 | 1100 | 1.8056 | 0.0 |
64
+ | 1.4478 | 0.0768 | 1200 | 1.4878 | 0.0003 |
65
+ | 1.328 | 0.0832 | 1300 | 1.4281 | 0.0 |
66
+ | 1.4386 | 0.0896 | 1400 | 1.5305 | 0.0 |
67
+ | 1.2565 | 0.096 | 1500 | 1.4687 | 0.0 |
68
+ | 1.3237 | 0.1024 | 1600 | 1.4644 | 0.0 |
69
+ | 1.398 | 0.1088 | 1700 | 1.4478 | 0.0 |
70
+ | 1.2262 | 0.1152 | 1800 | 1.3935 | 0.0 |
71
+ | 1.1314 | 0.1216 | 1900 | 1.3781 | 0.0 |
72
+ | 1.1959 | 0.128 | 2000 | 1.6554 | 0.0 |
73
+ | 1.1514 | 0.1344 | 2100 | 1.6594 | 0.0 |
74
+ | 1.0965 | 0.1408 | 2200 | 1.4454 | 0.0 |
75
+ | 1.0504 | 0.1472 | 2300 | 1.2525 | 0.0 |
76
+ | 1.1241 | 0.1536 | 2400 | 1.2877 | 0.0002 |
77
+ | 1.0926 | 0.16 | 2500 | 1.2335 | 0.0031 |
78
+ | 1.0979 | 0.1664 | 2600 | 1.2177 | 0.0013 |
79
+ | 1.1338 | 0.1728 | 2700 | 1.3293 | 0.0 |
80
+ | 1.0675 | 0.1792 | 2800 | 1.3052 | 0.0012 |
81
+ | 1.1648 | 0.1856 | 2900 | 1.3016 | 0.0 |
82
+ | 1.23 | 0.192 | 3000 | 1.4616 | 0.0001 |
83
+ | 1.0822 | 0.1984 | 3100 | 1.2298 | 0.0006 |
84
+ | 1.0924 | 0.2048 | 3200 | 1.2667 | 0.0023 |
85
+ | 1.2845 | 0.2112 | 3300 | 2.0913 | 0.0 |
86
+ | 0.9362 | 0.2176 | 3400 | 1.1774 | 0.0009 |
87
+ | 0.7342 | 0.224 | 3500 | 1.0416 | 0.0101 |
88
+ | 0.4629 | 0.2304 | 3600 | 1.1162 | 0.0029 |
89
+ | 0.2339 | 0.2368 | 3700 | 1.0761 | 0.0113 |
90
+ | 0.3522 | 0.2432 | 3800 | 0.9133 | 0.021 |
91
+ | 0.1289 | 0.2496 | 3900 | 0.7999 | 0.0334 |
92
+ | 0.2369 | 0.256 | 4000 | 1.2702 | 0.0273 |
93
+ | 0.2972 | 0.2624 | 4100 | 0.8842 | 0.0024 |
94
+ | 0.328 | 0.2688 | 4200 | 1.4525 | 0.0038 |
95
+ | 0.1071 | 0.2752 | 4300 | 0.4093 | 0.1764 |
96
+ | 0.2717 | 0.2816 | 4400 | 0.4844 | 0.1486 |
97
+ | 0.1862 | 0.288 | 4500 | 0.7234 | 0.1626 |
98
+ | 0.1448 | 0.2944 | 4600 | 0.6820 | 0.0589 |
99
+ | 0.1097 | 0.3008 | 4700 | 0.5829 | 0.1356 |
100
+ | 0.8399 | 0.3072 | 4800 | 1.1572 | 0.0952 |
101
+ | 0.0855 | 0.3136 | 4900 | 0.6682 | 0.1126 |
102
+ | 0.3689 | 0.32 | 5000 | 0.6060 | 0.1014 |
103
+ | 0.0803 | 0.3264 | 5100 | 0.5115 | 0.1708 |
104
+ | 0.1108 | 0.3328 | 5200 | 0.6770 | 0.2847 |
105
+ | 0.1968 | 0.3392 | 5300 | 0.7723 | 0.066 |
106
+ | 0.0271 | 0.3456 | 5400 | 0.3863 | 0.2103 |
107
+ | 0.249 | 0.352 | 5500 | 1.0287 | 0.2347 |
108
+ | 0.4778 | 0.3584 | 5600 | 0.8103 | 0.0657 |
109
+ | 0.1905 | 0.3648 | 5700 | 0.9973 | 0.0024 |
110
+ | 0.0915 | 0.3712 | 5800 | 0.3592 | 0.2475 |
111
+ | 0.4359 | 0.3776 | 5900 | 0.7012 | 0.0446 |
112
+ | 0.2581 | 0.384 | 6000 | 1.0053 | 0.016 |
113
+ | 0.0725 | 0.3904 | 6100 | 0.9440 | 0.1805 |
114
+ | 0.0314 | 0.3968 | 6200 | 0.8534 | 0.0391 |
115
+ | 0.1078 | 0.4032 | 6300 | 0.8485 | 0.0766 |
116
+ | 0.1192 | 0.4096 | 6400 | 0.7595 | 0.081 |
117
+ | 0.0313 | 0.416 | 6500 | 0.7632 | 0.1392 |
118
+ | 0.0913 | 0.4224 | 6600 | 0.9090 | 0.0457 |
119
+ | 0.0698 | 0.4288 | 6700 | 0.6446 | 0.1377 |
120
+ | 0.0634 | 0.4352 | 6800 | 0.5044 | 0.1722 |
121
+ | 0.0206 | 0.4416 | 6900 | 0.4350 | 0.1596 |
122
+ | 0.0541 | 0.448 | 7000 | 0.5126 | 0.1993 |
123
+ | 0.0309 | 0.4544 | 7100 | 0.3665 | 0.2323 |
124
+ | 0.014 | 0.4608 | 7200 | 0.2903 | 0.3326 |
125
+ | 0.6508 | 0.4672 | 7300 | 1.3151 | 0.0301 |
126
+ | 0.2519 | 0.4736 | 7400 | 0.8930 | 0.0963 |
127
+ | 0.0093 | 0.48 | 7500 | 0.8081 | 0.2188 |
128
+ | 0.0184 | 0.4864 | 7600 | 0.4988 | 0.1794 |
129
+ | 0.037 | 0.4928 | 7700 | 0.7907 | 0.0773 |
130
+ | 0.0141 | 0.4992 | 7800 | 0.5505 | 0.1646 |
131
+ | 0.0076 | 0.5056 | 7900 | 0.2600 | 0.3208 |
132
+ | 0.0111 | 0.512 | 8000 | 0.4490 | 0.2233 |
133
+ | 0.0167 | 0.5184 | 8100 | 1.8546 | 0.0175 |
134
+ | 0.0054 | 0.5248 | 8200 | 0.7066 | 0.0855 |
135
+ | 0.0023 | 0.5312 | 8300 | 0.3227 | 0.194 |
136
+ | 0.0027 | 0.5376 | 8400 | 0.3176 | 0.3663 |
137
+ | 0.0019 | 0.544 | 8500 | 0.3129 | 0.2532 |
138
+ | 0.0095 | 0.5504 | 8600 | 0.4997 | 0.3292 |
139
+ | 0.0042 | 0.5568 | 8700 | 0.5050 | 0.3324 |
140
+ | 0.0507 | 0.5632 | 8800 | 0.2728 | 0.432 |
141
+ | 0.0021 | 0.5696 | 8900 | 0.1853 | 0.4227 |
142
+ | 0.0098 | 0.576 | 9000 | 0.1531 | 0.4567 |
143
+ | 0.0021 | 0.5824 | 9100 | 0.1294 | 0.563 |
144
+ | 0.0003 | 0.5888 | 9200 | 0.1399 | 0.6031 |
145
+ | 0.0027 | 0.5952 | 9300 | 0.5910 | 0.0974 |
146
+ | 0.0019 | 0.6016 | 9400 | 0.3085 | 0.3276 |
147
+ | 0.0001 | 0.608 | 9500 | 0.1920 | 0.5483 |
148
+ | 0.0073 | 0.6144 | 9600 | 0.3350 | 0.1231 |
149
+ | 0.0011 | 0.6208 | 9700 | 0.1745 | 0.6341 |
150
+ | 0.0006 | 0.6272 | 9800 | 0.2882 | 0.3489 |
151
+ | 0.0017 | 0.6336 | 9900 | 0.3170 | 0.2057 |
152
+ | 0.0007 | 0.64 | 10000 | 0.2683 | 0.3683 |
153
+ | 0.0006 | 0.6464 | 10100 | 0.0489 | 0.8182 |
154
+ | 0.036 | 0.6528 | 10200 | 0.0854 | 0.5987 |
155
+ | 0.0001 | 0.6592 | 10300 | 0.5204 | 0.3131 |
156
+ | 0.0003 | 0.6656 | 10400 | 0.4601 | 0.154 |
157
+ | 0.0001 | 0.672 | 10500 | 0.0270 | 0.8961 |
158
+ | 0.0 | 0.6784 | 10600 | 0.1030 | 0.5611 |
159
+ | 0.0 | 0.6848 | 10700 | 0.0703 | 0.6982 |
160
+ | 0.0 | 0.6912 | 10800 | 0.0639 | 0.763 |
161
+ | 0.0 | 0.6976 | 10900 | 0.0443 | 0.8296 |
162
+ | 0.0 | 0.704 | 11000 | 0.0430 | 0.8349 |
163
+ | 0.0 | 0.7104 | 11100 | 0.0416 | 0.843 |
164
+ | 0.0 | 0.7168 | 11200 | 0.0432 | 0.8373 |
165
+ | 0.0 | 0.7232 | 11300 | 0.0436 | 0.8393 |
166
+ | 0.0 | 0.7296 | 11400 | 0.0473 | 0.8207 |
167
+ | 0.0 | 0.736 | 11500 | 0.0453 | 0.8337 |
168
+ | 0.0 | 0.7424 | 11600 | 0.0434 | 0.8434 |
169
+ | 0.0 | 0.7488 | 11700 | 0.0379 | 0.8742 |
170
+ | 0.0 | 0.7552 | 11800 | 0.0386 | 0.8712 |
171
+ | 0.0 | 0.7616 | 11900 | 0.0375 | 0.8765 |
172
+ | 0.0 | 0.768 | 12000 | 0.0424 | 0.8793 |
173
+ | 0.0 | 0.7744 | 12100 | 0.0409 | 0.8846 |
174
+ | 0.0 | 0.7808 | 12200 | 0.0384 | 0.8901 |
175
+ | 0.0 | 0.7872 | 12300 | 0.0374 | 0.8927 |
176
+ | 0.0 | 0.7936 | 12400 | 0.0369 | 0.8938 |
177
+ | 0.0 | 0.8 | 12500 | 0.0366 | 0.8945 |
178
+ | 0.0 | 0.8064 | 12600 | 0.0363 | 0.8956 |
179
+ | 0.0 | 0.8128 | 12700 | 0.0358 | 0.8975 |
180
+ | 0.0 | 0.8192 | 12800 | 0.0362 | 0.897 |
181
+ | 0.0 | 0.8256 | 12900 | 0.0355 | 0.8991 |
182
+ | 0.0 | 0.832 | 13000 | 0.0346 | 0.9008 |
183
+ | 0.0 | 0.8384 | 13100 | 0.0343 | 0.9016 |
184
+ | 0.0 | 0.8448 | 13200 | 0.0314 | 0.8925 |
185
+ | 0.0 | 0.8512 | 13300 | 0.0316 | 0.8908 |
186
+ | 0.0 | 0.8576 | 13400 | 0.0318 | 0.8912 |
187
+ | 0.0 | 0.864 | 13500 | 0.0315 | 0.892 |
188
+ | 0.0 | 0.8704 | 13600 | 0.0312 | 0.8937 |
189
+ | 0.0 | 0.8768 | 13700 | 0.0296 | 0.9001 |
190
+ | 0.0 | 0.8832 | 13800 | 0.0292 | 0.9017 |
191
+ | 0.0 | 0.8896 | 13900 | 0.0290 | 0.9026 |
192
+ | 0.0 | 0.896 | 14000 | 0.0292 | 0.9018 |
193
+ | 0.0 | 0.9024 | 14100 | 0.0290 | 0.9027 |
194
+ | 0.0 | 0.9088 | 14200 | 0.0295 | 0.8995 |
195
+ | 0.0 | 0.9152 | 14300 | 0.0294 | 0.9002 |
196
+ | 0.0 | 0.9216 | 14400 | 0.0293 | 0.9006 |
197
+ | 0.0 | 0.928 | 14500 | 0.0292 | 0.9009 |
198
+ | 0.0 | 0.9344 | 14600 | 0.0291 | 0.9013 |
199
+ | 0.0 | 0.9408 | 14700 | 0.0288 | 0.9031 |
200
+ | 0.0 | 0.9472 | 14800 | 0.0287 | 0.9032 |
201
+ | 0.0 | 0.9536 | 14900 | 0.0286 | 0.9035 |
202
+ | 0.0 | 0.96 | 15000 | 0.0286 | 0.9037 |
203
+ | 0.0 | 0.9664 | 15100 | 0.0285 | 0.9044 |
204
+ | 0.0 | 0.9728 | 15200 | 0.0285 | 0.9047 |
205
+ | 0.0 | 0.9792 | 15300 | 0.0285 | 0.9047 |
206
+ | 0.0 | 0.9856 | 15400 | 0.0282 | 0.9072 |
207
+ | 0.0 | 0.992 | 15500 | 0.0282 | 0.9071 |
208
+ | 0.0 | 0.9984 | 15600 | 0.0282 | 0.9071 |
209
+
210
+
211
+ ### Framework versions
212
+
213
+ - Transformers 4.50.3
214
+ - Pytorch 2.6.0+cu124
215
+ - Tokenizers 0.21.1
config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "NanoGPT"
4
+ ],
5
+ "bias": true,
6
+ "block_size": 256,
7
+ "dropout": 0.0,
8
+ "mlp_dim": 4,
9
+ "model_type": "nanogpt",
10
+ "n_embd": 384,
11
+ "n_head": 6,
12
+ "n_layer": 6,
13
+ "nonlinearity": "RELU",
14
+ "torch_dtype": "float32",
15
+ "transformers_version": "4.50.3",
16
+ "use_NoPE": true,
17
+ "use_layernorm": true,
18
+ "vocab_size": 14
19
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d617b9e6f20f2ff74a32eb29afd1bcffd8e83e1ff367fea6b7ca390ea5bf078
3
+ size 42640744
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c8235c7d025b4a366f5621754f6f0e226cebb9921555e8d379361dd404967e1
3
+ size 5368