Hugging Face's logo

mtzig
/
reverse_add_replicate_eval18

Transformers
Safetensors
nanogpt
Generated from Trainer
Model card Files Community
mtzig commited on
Commit
051a5ce
·
verified ·
1 Parent(s): 8e7b027

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_eval18
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_eval18
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: 0.0462
20
+ - Accuracy: 0.822
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 | 2.6252 | 0.0 |
55
+ | 4.5838 | 0.0064 | 100 | 2.3366 | 0.0 |
56
+ | 4.431 | 0.0128 | 200 | 2.2655 | 0.0 |
57
+ | 4.337 | 0.0192 | 300 | 2.3128 | 0.0 |
58
+ | 4.2999 | 0.0256 | 400 | 2.1857 | 0.0 |
59
+ | 4.3044 | 0.032 | 500 | 2.2308 | 0.0 |
60
+ | 3.9499 | 0.0384 | 600 | 2.0985 | 0.0 |
61
+ | 3.778 | 0.0448 | 700 | 2.0666 | 0.0 |
62
+ | 3.3655 | 0.0512 | 800 | 1.7091 | 0.0 |
63
+ | 3.1301 | 0.0576 | 900 | 2.0713 | 0.0 |
64
+ | 3.3799 | 0.064 | 1000 | 1.7607 | 0.0 |
65
+ | 2.7031 | 0.0704 | 1100 | 1.4787 | 0.0 |
66
+ | 2.4529 | 0.0768 | 1200 | 1.4061 | 0.0 |
67
+ | 3.1457 | 0.0832 | 1300 | 1.5655 | 0.0 |
68
+ | 2.7466 | 0.0896 | 1400 | 1.5409 | 0.0 |
69
+ | 2.545 | 0.096 | 1500 | 1.6788 | 0.0 |
70
+ | 2.215 | 0.1024 | 1600 | 1.4968 | 0.0 |
71
+ | 2.4219 | 0.1088 | 1700 | 1.7860 | 0.0 |
72
+ | 2.3565 | 0.1152 | 1800 | 1.3797 | 0.0 |
73
+ | 2.5352 | 0.1216 | 1900 | 1.4154 | 0.0 |
74
+ | 2.4223 | 0.128 | 2000 | 1.3751 | 0.0 |
75
+ | 2.3618 | 0.1344 | 2100 | 1.2539 | 0.002 |
76
+ | 2.7171 | 0.1408 | 2200 | 1.4281 | 0.0 |
77
+ | 2.3209 | 0.1472 | 2300 | 1.2035 | 0.002 |
78
+ | 2.6747 | 0.1536 | 2400 | 1.9148 | 0.0 |
79
+ | 2.3485 | 0.16 | 2500 | 1.4721 | 0.0 |
80
+ | 3.1889 | 0.1664 | 2600 | 1.3520 | 0.0 |
81
+ | 2.2109 | 0.1728 | 2700 | 1.1634 | 0.001 |
82
+ | 2.2771 | 0.1792 | 2800 | 1.2053 | 0.003 |
83
+ | 2.4756 | 0.1856 | 2900 | 1.2916 | 0.0 |
84
+ | 2.085 | 0.192 | 3000 | 1.2781 | 0.001 |
85
+ | 2.496 | 0.1984 | 3100 | 1.2191 | 0.001 |
86
+ | 2.1021 | 0.2048 | 3200 | 1.2496 | 0.001 |
87
+ | 2.5637 | 0.2112 | 3300 | 1.4160 | 0.001 |
88
+ | 2.2194 | 0.2176 | 3400 | 1.2784 | 0.006 |
89
+ | 1.9931 | 0.224 | 3500 | 1.3809 | 0.001 |
90
+ | 2.2398 | 0.2304 | 3600 | 1.2137 | 0.001 |
91
+ | 2.2651 | 0.2368 | 3700 | 1.2654 | 0.001 |
92
+ | 2.3313 | 0.2432 | 3800 | 1.1569 | 0.007 |
93
+ | 2.3756 | 0.2496 | 3900 | 1.2921 | 0.004 |
94
+ | 2.5309 | 0.256 | 4000 | 1.3908 | 0.0 |
95
+ | 2.2903 | 0.2624 | 4100 | 1.2230 | 0.001 |
96
+ | 2.0149 | 0.2688 | 4200 | 1.1809 | 0.002 |
97
+ | 2.2713 | 0.2752 | 4300 | 1.4983 | 0.001 |
98
+ | 2.2298 | 0.2816 | 4400 | 1.2858 | 0.004 |
99
+ | 2.4944 | 0.288 | 4500 | 1.4696 | 0.0 |
100
+ | 2.2138 | 0.2944 | 4600 | 1.2601 | 0.001 |
101
+ | 2.1888 | 0.3008 | 4700 | 1.2084 | 0.008 |
102
+ | 2.6511 | 0.3072 | 4800 | 1.3996 | 0.003 |
103
+ | 2.0815 | 0.3136 | 4900 | 1.1967 | 0.003 |
104
+ | 2.296 | 0.32 | 5000 | 1.2770 | 0.001 |
105
+ | 2.3372 | 0.3264 | 5100 | 1.2541 | 0.0 |
106
+ | 2.0872 | 0.3328 | 5200 | 1.1923 | 0.001 |
107
+ | 2.1522 | 0.3392 | 5300 | 1.2390 | 0.005 |
108
+ | 1.9354 | 0.3456 | 5400 | 1.1832 | 0.005 |
109
+ | 2.5261 | 0.352 | 5500 | 1.5203 | 0.001 |
110
+ | 2.134 | 0.3584 | 5600 | 1.1531 | 0.004 |
111
+ | 1.7733 | 0.3648 | 5700 | 1.2219 | 0.015 |
112
+ | 1.8473 | 0.3712 | 5800 | 1.1778 | 0.018 |
113
+ | 2.1981 | 0.3776 | 5900 | 1.3320 | 0.001 |
114
+ | 2.0556 | 0.384 | 6000 | 1.5240 | 0.01 |
115
+ | 1.9013 | 0.3904 | 6100 | 1.3080 | 0.008 |
116
+ | 1.9382 | 0.3968 | 6200 | 1.0881 | 0.017 |
117
+ | 1.9539 | 0.4032 | 6300 | 1.1345 | 0.025 |
118
+ | 1.9041 | 0.4096 | 6400 | 1.5530 | 0.005 |
119
+ | 2.0314 | 0.416 | 6500 | 1.1389 | 0.023 |
120
+ | 1.9645 | 0.4224 | 6600 | 1.1751 | 0.018 |
121
+ | 1.9642 | 0.4288 | 6700 | 1.1277 | 0.03 |
122
+ | 1.8727 | 0.4352 | 6800 | 1.2153 | 0.001 |
123
+ | 1.6457 | 0.4416 | 6900 | 1.5273 | 0.059 |
124
+ | 1.3439 | 0.448 | 7000 | 0.8178 | 0.055 |
125
+ | 0.6969 | 0.4544 | 7100 | 0.6332 | 0.092 |
126
+ | 0.9132 | 0.4608 | 7200 | 0.9930 | 0.032 |
127
+ | 0.5933 | 0.4672 | 7300 | 0.5563 | 0.292 |
128
+ | 0.4775 | 0.4736 | 7400 | 0.6892 | 0.275 |
129
+ | 0.8709 | 0.48 | 7500 | 1.1903 | 0.074 |
130
+ | 0.6346 | 0.4864 | 7600 | 0.8924 | 0.159 |
131
+ | 0.756 | 0.4928 | 7700 | 1.1650 | 0.135 |
132
+ | 0.283 | 0.4992 | 7800 | 0.7111 | 0.105 |
133
+ | 0.2729 | 0.5056 | 7900 | 0.3804 | 0.135 |
134
+ | 1.1775 | 0.512 | 8000 | 1.3814 | 0.122 |
135
+ | 0.1442 | 0.5184 | 8100 | 0.3274 | 0.491 |
136
+ | 0.9447 | 0.5248 | 8200 | 0.7572 | 0.203 |
137
+ | 0.5056 | 0.5312 | 8300 | 0.4948 | 0.166 |
138
+ | 0.5298 | 0.5376 | 8400 | 0.5869 | 0.279 |
139
+ | 0.1373 | 0.544 | 8500 | 0.7485 | 0.2 |
140
+ | 0.0449 | 0.5504 | 8600 | 0.2730 | 0.375 |
141
+ | 0.1203 | 0.5568 | 8700 | 0.3131 | 0.258 |
142
+ | 0.0388 | 0.5632 | 8800 | 0.1571 | 0.477 |
143
+ | 0.0707 | 0.5696 | 8900 | 0.1798 | 0.459 |
144
+ | 0.8594 | 0.576 | 9000 | 0.7271 | 0.156 |
145
+ | 0.1756 | 0.5824 | 9100 | 0.3364 | 0.307 |
146
+ | 0.4308 | 0.5888 | 9200 | 0.3278 | 0.334 |
147
+ | 0.2429 | 0.5952 | 9300 | 0.6799 | 0.068 |
148
+ | 0.008 | 0.6016 | 9400 | 0.1588 | 0.443 |
149
+ | 0.0404 | 0.608 | 9500 | 0.2014 | 0.43 |
150
+ | 0.0879 | 0.6144 | 9600 | 0.5365 | 0.136 |
151
+ | 0.6424 | 0.6208 | 9700 | 0.6502 | 0.228 |
152
+ | 0.1784 | 0.6272 | 9800 | 0.5427 | 0.088 |
153
+ | 0.0782 | 0.6336 | 9900 | 1.0986 | 0.211 |
154
+ | 0.0053 | 0.64 | 10000 | 0.1458 | 0.632 |
155
+ | 0.0158 | 0.6464 | 10100 | 0.1768 | 0.456 |
156
+ | 0.0506 | 0.6528 | 10200 | 0.1966 | 0.409 |
157
+ | 0.017 | 0.6592 | 10300 | 0.2878 | 0.195 |
158
+ | 0.0401 | 0.6656 | 10400 | 0.3751 | 0.246 |
159
+ | 0.0371 | 0.672 | 10500 | 0.2150 | 0.389 |
160
+ | 0.0237 | 0.6784 | 10600 | 0.0889 | 0.567 |
161
+ | 0.0158 | 0.6848 | 10700 | 0.0455 | 0.787 |
162
+ | 0.0112 | 0.6912 | 10800 | 0.2969 | 0.454 |
163
+ | 0.0105 | 0.6976 | 10900 | 0.4749 | 0.454 |
164
+ | 0.0051 | 0.704 | 11000 | 0.0889 | 0.732 |
165
+ | 0.0072 | 0.7104 | 11100 | 0.1155 | 0.723 |
166
+ | 0.0009 | 0.7168 | 11200 | 0.1212 | 0.701 |
167
+ | 0.0012 | 0.7232 | 11300 | 0.1257 | 0.574 |
168
+ | 0.0071 | 0.7296 | 11400 | 0.1758 | 0.618 |
169
+ | 0.0006 | 0.736 | 11500 | 0.0439 | 0.867 |
170
+ | 0.0008 | 0.7424 | 11600 | 0.2523 | 0.511 |
171
+ | 0.0129 | 0.7488 | 11700 | 0.1786 | 0.612 |
172
+ | 0.0001 | 0.7552 | 11800 | 0.0333 | 0.838 |
173
+ | 0.0017 | 0.7616 | 11900 | 0.1826 | 0.524 |
174
+ | 0.0002 | 0.768 | 12000 | 0.1427 | 0.499 |
175
+ | 0.0001 | 0.7744 | 12100 | 0.0132 | 0.952 |
176
+ | 0.0003 | 0.7808 | 12200 | 0.0720 | 0.692 |
177
+ | 0.0001 | 0.7872 | 12300 | 0.0181 | 0.935 |
178
+ | 0.0004 | 0.7936 | 12400 | 0.0166 | 0.926 |
179
+ | 0.0062 | 0.8 | 12500 | 0.0919 | 0.642 |
180
+ | 0.0003 | 0.8064 | 12600 | 0.0160 | 0.915 |
181
+ | 0.0 | 0.8128 | 12700 | 0.0232 | 0.911 |
182
+ | 0.0001 | 0.8192 | 12800 | 0.0177 | 0.921 |
183
+ | 0.0001 | 0.8256 | 12900 | 0.0448 | 0.812 |
184
+ | 0.0001 | 0.832 | 13000 | 0.0027 | 0.984 |
185
+ | 0.0001 | 0.8384 | 13100 | 0.0877 | 0.717 |
186
+ | 0.028 | 0.8448 | 13200 | 0.0960 | 0.804 |
187
+ | 0.0078 | 0.8512 | 13300 | 0.0969 | 0.66 |
188
+ | 0.0 | 0.8576 | 13400 | 0.0824 | 0.736 |
189
+ | 0.0001 | 0.864 | 13500 | 0.0756 | 0.718 |
190
+ | 0.0 | 0.8704 | 13600 | 0.0649 | 0.778 |
191
+ | 0.0 | 0.8768 | 13700 | 0.0152 | 0.927 |
192
+ | 0.0002 | 0.8832 | 13800 | 0.0610 | 0.813 |
193
+ | 0.0 | 0.8896 | 13900 | 0.0067 | 0.968 |
194
+ | 0.0015 | 0.896 | 14000 | 0.0314 | 0.867 |
195
+ | 0.0005 | 0.9024 | 14100 | 0.0174 | 0.92 |
196
+ | 0.0 | 0.9088 | 14200 | 0.0864 | 0.716 |
197
+ | 0.0001 | 0.9152 | 14300 | 0.0513 | 0.807 |
198
+ | 0.0006 | 0.9216 | 14400 | 0.0106 | 0.95 |
199
+ | 0.0009 | 0.928 | 14500 | 0.0238 | 0.905 |
200
+ | 0.0001 | 0.9344 | 14600 | 0.0335 | 0.856 |
201
+ | 0.0 | 0.9408 | 14700 | 0.0411 | 0.829 |
202
+ | 0.0 | 0.9472 | 14800 | 0.0456 | 0.822 |
203
+ | 0.0 | 0.9536 | 14900 | 0.0425 | 0.833 |
204
+ | 0.0 | 0.96 | 15000 | 0.0460 | 0.821 |
205
+ | 0.0 | 0.9664 | 15100 | 0.0457 | 0.821 |
206
+ | 0.0 | 0.9728 | 15200 | 0.0460 | 0.823 |
207
+ | 0.0 | 0.9792 | 15300 | 0.0477 | 0.821 |
208
+ | 0.0023 | 0.9856 | 15400 | 0.0474 | 0.821 |
209
+ | 0.0 | 0.992 | 15500 | 0.0464 | 0.822 |
210
+ | 0.0 | 0.9984 | 15600 | 0.0462 | 0.822 |
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:d4f893dc72d887fc9d48104abfce7b616975e4955477a35833d02c20c77f98e5
3
+ size 42640744
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:837a743ebcf1e835c6bc1584f401590db21b635ceba27b24736e397a64f31e42
3
+ size 5240