Hugging Face's logo

mtzig
/
reverseadd_lr5e-4_batch128_train1-16_eval17

Transformers
Safetensors
nanogpt
Generated from Trainer
Model card Files
xet
Community
mtzig commited on
Commit
48d39a1
·
verified ·
1 Parent(s): 27ef97b

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_eval17
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_eval17
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: 0.0001
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: 0.0005
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 | 2.8155 | 0.0 |
53
+ | 2.2946 | 0.0064 | 100 | 2.3351 | 0.0 |
54
+ | 2.1902 | 0.0128 | 200 | 2.2386 | 0.0 |
55
+ | 2.1098 | 0.0192 | 300 | 2.1977 | 0.0 |
56
+ | 2.0555 | 0.0256 | 400 | 2.1978 | 0.0 |
57
+ | 2.0039 | 0.032 | 500 | 2.1589 | 0.0 |
58
+ | 1.8206 | 0.0384 | 600 | 1.9316 | 0.0 |
59
+ | 1.7494 | 0.0448 | 700 | 1.8544 | 0.0 |
60
+ | 1.6857 | 0.0512 | 800 | 1.8468 | 0.0 |
61
+ | 1.4657 | 0.0576 | 900 | 1.6150 | 0.0 |
62
+ | 1.4123 | 0.064 | 1000 | 1.6095 | 0.0 |
63
+ | 1.4308 | 0.0704 | 1100 | 1.4342 | 0.0 |
64
+ | 1.4203 | 0.0768 | 1200 | 1.4498 | 0.0014 |
65
+ | 1.2564 | 0.0832 | 1300 | 1.3778 | 0.0 |
66
+ | 1.4974 | 0.0896 | 1400 | 1.4512 | 0.0 |
67
+ | 1.2751 | 0.096 | 1500 | 1.3121 | 0.0008 |
68
+ | 1.3045 | 0.1024 | 1600 | 1.3020 | 0.0004 |
69
+ | 1.4441 | 0.1088 | 1700 | 1.2960 | 0.0019 |
70
+ | 1.2986 | 0.1152 | 1800 | 1.3620 | 0.0023 |
71
+ | 1.202 | 0.1216 | 1900 | 1.3917 | 0.0 |
72
+ | 1.0536 | 0.128 | 2000 | 1.2194 | 0.003 |
73
+ | 1.1365 | 0.1344 | 2100 | 1.2133 | 0.002 |
74
+ | 1.1016 | 0.1408 | 2200 | 1.3385 | 0.0012 |
75
+ | 1.0749 | 0.1472 | 2300 | 1.2830 | 0.0002 |
76
+ | 1.1077 | 0.1536 | 2400 | 1.2144 | 0.0018 |
77
+ | 1.2018 | 0.16 | 2500 | 1.3076 | 0.0001 |
78
+ | 1.0792 | 0.1664 | 2600 | 1.1722 | 0.0035 |
79
+ | 1.1767 | 0.1728 | 2700 | 1.4412 | 0.0006 |
80
+ | 1.1921 | 0.1792 | 2800 | 1.4885 | 0.0009 |
81
+ | 1.1296 | 0.1856 | 2900 | 1.1856 | 0.0044 |
82
+ | 1.1497 | 0.192 | 3000 | 1.2461 | 0.0003 |
83
+ | 1.1368 | 0.1984 | 3100 | 1.2033 | 0.0019 |
84
+ | 1.0723 | 0.2048 | 3200 | 1.1648 | 0.0044 |
85
+ | 1.2805 | 0.2112 | 3300 | 1.3671 | 0.0012 |
86
+ | 1.1424 | 0.2176 | 3400 | 1.2261 | 0.0034 |
87
+ | 1.0507 | 0.224 | 3500 | 1.6901 | 0.0012 |
88
+ | 1.1209 | 0.2304 | 3600 | 1.1904 | 0.0037 |
89
+ | 1.0004 | 0.2368 | 3700 | 1.1728 | 0.0052 |
90
+ | 1.0119 | 0.2432 | 3800 | 1.3097 | 0.0014 |
91
+ | 0.8694 | 0.2496 | 3900 | 1.2167 | 0.0021 |
92
+ | 0.7671 | 0.256 | 4000 | 0.9645 | 0.0063 |
93
+ | 0.6854 | 0.2624 | 4100 | 0.8259 | 0.0103 |
94
+ | 0.6831 | 0.2688 | 4200 | 1.8649 | 0.0052 |
95
+ | 0.7282 | 0.2752 | 4300 | 1.0701 | 0.0129 |
96
+ | 0.5102 | 0.2816 | 4400 | 0.7336 | 0.0177 |
97
+ | 0.504 | 0.288 | 4500 | 0.9905 | 0.0037 |
98
+ | 0.6358 | 0.2944 | 4600 | 0.9810 | 0.0056 |
99
+ | 0.4155 | 0.3008 | 4700 | 0.7320 | 0.0203 |
100
+ | 0.5209 | 0.3072 | 4800 | 0.7939 | 0.0143 |
101
+ | 0.4059 | 0.3136 | 4900 | 0.7709 | 0.0224 |
102
+ | 1.1919 | 0.32 | 5000 | 1.2763 | 0.0095 |
103
+ | 0.4233 | 0.3264 | 5100 | 0.9546 | 0.0332 |
104
+ | 0.4587 | 0.3328 | 5200 | 0.5571 | 0.024 |
105
+ | 0.357 | 0.3392 | 5300 | 0.6538 | 0.0319 |
106
+ | 0.1951 | 0.3456 | 5400 | 0.7499 | 0.0794 |
107
+ | 0.0627 | 0.352 | 5500 | 0.1778 | 0.4928 |
108
+ | 0.1673 | 0.3584 | 5600 | 0.4276 | 0.3864 |
109
+ | 0.108 | 0.3648 | 5700 | 0.2546 | 0.475 |
110
+ | 0.303 | 0.3712 | 5800 | 0.8399 | 0.1792 |
111
+ | 0.0955 | 0.3776 | 5900 | 0.1259 | 0.6165 |
112
+ | 0.3565 | 0.384 | 6000 | 0.4181 | 0.2727 |
113
+ | 0.1023 | 0.3904 | 6100 | 0.3169 | 0.2621 |
114
+ | 0.088 | 0.3968 | 6200 | 0.5066 | 0.4139 |
115
+ | 0.1426 | 0.4032 | 6300 | 0.2009 | 0.4383 |
116
+ | 0.0982 | 0.4096 | 6400 | 0.3973 | 0.4288 |
117
+ | 0.0761 | 0.416 | 6500 | 0.1796 | 0.5228 |
118
+ | 0.0535 | 0.4224 | 6600 | 0.1319 | 0.554 |
119
+ | 0.067 | 0.4288 | 6700 | 0.1653 | 0.5779 |
120
+ | 0.0809 | 0.4352 | 6800 | 0.2924 | 0.3632 |
121
+ | 0.0287 | 0.4416 | 6900 | 0.2800 | 0.4756 |
122
+ | 0.2862 | 0.448 | 7000 | 0.4914 | 0.4814 |
123
+ | 0.1426 | 0.4544 | 7100 | 0.1894 | 0.4845 |
124
+ | 0.5235 | 0.4608 | 7200 | 0.4767 | 0.3179 |
125
+ | 0.1059 | 0.4672 | 7300 | 0.0758 | 0.7329 |
126
+ | 0.0569 | 0.4736 | 7400 | 0.0930 | 0.6479 |
127
+ | 0.2759 | 0.48 | 7500 | 0.6940 | 0.2162 |
128
+ | 0.0365 | 0.4864 | 7600 | 0.1118 | 0.7336 |
129
+ | 0.1459 | 0.4928 | 7700 | 0.3021 | 0.5704 |
130
+ | 0.0642 | 0.4992 | 7800 | 0.3398 | 0.3859 |
131
+ | 0.0475 | 0.5056 | 7900 | 0.1293 | 0.6375 |
132
+ | 0.2529 | 0.512 | 8000 | 0.1974 | 0.5196 |
133
+ | 0.0545 | 0.5184 | 8100 | 0.5865 | 0.0885 |
134
+ | 0.023 | 0.5248 | 8200 | 0.2984 | 0.5018 |
135
+ | 0.1067 | 0.5312 | 8300 | 0.1996 | 0.419 |
136
+ | 0.0251 | 0.5376 | 8400 | 0.0553 | 0.7663 |
137
+ | 0.0202 | 0.544 | 8500 | 0.0368 | 0.8618 |
138
+ | 0.0487 | 0.5504 | 8600 | 0.3866 | 0.4186 |
139
+ | 0.0637 | 0.5568 | 8700 | 0.1638 | 0.681 |
140
+ | 0.0237 | 0.5632 | 8800 | 0.0808 | 0.6553 |
141
+ | 0.0278 | 0.5696 | 8900 | 0.0793 | 0.6923 |
142
+ | 0.0181 | 0.576 | 9000 | 0.0814 | 0.7107 |
143
+ | 0.0385 | 0.5824 | 9100 | 0.0419 | 0.8253 |
144
+ | 0.1081 | 0.5888 | 9200 | 0.2834 | 0.4629 |
145
+ | 0.0539 | 0.5952 | 9300 | 0.1097 | 0.6756 |
146
+ | 0.0059 | 0.6016 | 9400 | 0.0250 | 0.8896 |
147
+ | 0.0109 | 0.608 | 9500 | 0.2312 | 0.4467 |
148
+ | 0.0091 | 0.6144 | 9600 | 0.0257 | 0.9123 |
149
+ | 0.0158 | 0.6208 | 9700 | 0.0657 | 0.7171 |
150
+ | 0.0093 | 0.6272 | 9800 | 0.0579 | 0.7496 |
151
+ | 0.0046 | 0.6336 | 9900 | 0.0079 | 0.9606 |
152
+ | 0.0006 | 0.64 | 10000 | 0.3415 | 0.5193 |
153
+ | 0.0284 | 0.6464 | 10100 | 0.1142 | 0.7089 |
154
+ | 0.0011 | 0.6528 | 10200 | 0.0064 | 0.9759 |
155
+ | 0.0035 | 0.6592 | 10300 | 0.1225 | 0.7545 |
156
+ | 0.0081 | 0.6656 | 10400 | 0.0127 | 0.9453 |
157
+ | 0.0003 | 0.672 | 10500 | 0.0052 | 0.9788 |
158
+ | 0.0015 | 0.6784 | 10600 | 0.0175 | 0.9311 |
159
+ | 0.0001 | 0.6848 | 10700 | 0.0066 | 0.9688 |
160
+ | 0.0012 | 0.6912 | 10800 | 0.0459 | 0.877 |
161
+ | 0.0002 | 0.6976 | 10900 | 0.0725 | 0.7628 |
162
+ | 0.0002 | 0.704 | 11000 | 0.3270 | 0.4999 |
163
+ | 0.0003 | 0.7104 | 11100 | 0.0195 | 0.8962 |
164
+ | 0.0001 | 0.7168 | 11200 | 0.0041 | 0.9819 |
165
+ | 0.0 | 0.7232 | 11300 | 0.0029 | 0.9864 |
166
+ | 0.0 | 0.7296 | 11400 | 0.0010 | 0.9952 |
167
+ | 0.0 | 0.736 | 11500 | 0.0017 | 0.9913 |
168
+ | 0.0 | 0.7424 | 11600 | 0.0015 | 0.992 |
169
+ | 0.0 | 0.7488 | 11700 | 0.0011 | 0.9941 |
170
+ | 0.0002 | 0.7552 | 11800 | 0.0091 | 0.9548 |
171
+ | 0.0 | 0.7616 | 11900 | 0.0002 | 0.9994 |
172
+ | 0.0 | 0.768 | 12000 | 0.0003 | 0.9993 |
173
+ | 0.0 | 0.7744 | 12100 | 0.0001 | 0.9997 |
174
+ | 0.0 | 0.7808 | 12200 | 0.0005 | 0.9981 |
175
+ | 0.0 | 0.7872 | 12300 | 0.0002 | 0.9995 |
176
+ | 0.0 | 0.7936 | 12400 | 0.0002 | 0.9995 |
177
+ | 0.0 | 0.8 | 12500 | 0.0001 | 0.9999 |
178
+ | 0.0 | 0.8064 | 12600 | 0.0000 | 1.0 |
179
+ | 0.0 | 0.8128 | 12700 | 0.0000 | 1.0 |
180
+ | 0.0 | 0.8192 | 12800 | 0.0000 | 1.0 |
181
+ | 0.0 | 0.8256 | 12900 | 0.0000 | 1.0 |
182
+ | 0.0 | 0.832 | 13000 | 0.0000 | 1.0 |
183
+ | 0.0 | 0.8384 | 13100 | 0.0000 | 1.0 |
184
+ | 0.0 | 0.8448 | 13200 | 0.0000 | 1.0 |
185
+ | 0.0 | 0.8512 | 13300 | 0.0000 | 1.0 |
186
+ | 0.0 | 0.8576 | 13400 | 0.0000 | 1.0 |
187
+ | 0.0 | 0.864 | 13500 | 0.0000 | 1.0 |
188
+ | 0.0 | 0.8704 | 13600 | 0.0000 | 1.0 |
189
+ | 0.0 | 0.8768 | 13700 | 0.0000 | 1.0 |
190
+ | 0.0 | 0.8832 | 13800 | 0.0000 | 1.0 |
191
+ | 0.0 | 0.8896 | 13900 | 0.0000 | 1.0 |
192
+ | 0.0 | 0.896 | 14000 | 0.0000 | 1.0 |
193
+ | 0.0 | 0.9024 | 14100 | 0.0000 | 1.0 |
194
+ | 0.0 | 0.9088 | 14200 | 0.0000 | 1.0 |
195
+ | 0.0 | 0.9152 | 14300 | 0.0001 | 0.9998 |
196
+ | 0.0 | 0.9216 | 14400 | 0.0000 | 0.9999 |
197
+ | 0.0 | 0.928 | 14500 | 0.0001 | 1.0 |
198
+ | 0.0 | 0.9344 | 14600 | 0.0001 | 1.0 |
199
+ | 0.0 | 0.9408 | 14700 | 0.0001 | 1.0 |
200
+ | 0.0 | 0.9472 | 14800 | 0.0001 | 1.0 |
201
+ | 0.0 | 0.9536 | 14900 | 0.0001 | 1.0 |
202
+ | 0.0 | 0.96 | 15000 | 0.0001 | 1.0 |
203
+ | 0.0 | 0.9664 | 15100 | 0.0001 | 1.0 |
204
+ | 0.0 | 0.9728 | 15200 | 0.0001 | 1.0 |
205
+ | 0.0 | 0.9792 | 15300 | 0.0001 | 1.0 |
206
+ | 0.0 | 0.9856 | 15400 | 0.0001 | 1.0 |
207
+ | 0.0 | 0.992 | 15500 | 0.0001 | 1.0 |
208
+ | 0.0 | 0.9984 | 15600 | 0.0001 | 1.0 |
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:b91c22f10a97ddc01172f18430123188f70ff048930fe9182dead1fb8b5c32d3
3
+ size 42640744
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c61c8a26dc92f0ab4088af36a6234e5861944bbfeaafc8c8fb74517eb6391c81
3
+ size 5368