Hugging Face's logo

mtzig
/
reverse_add_replicate_eval17_small

Transformers
Safetensors
nanogpt
Generated from Trainer
Model card Files
xet
Community
mtzig commited on
Commit
c91062f
·
verified ·
1 Parent(s): 8248943

Model save

Browse files
Files changed (5) hide show
  1. README.md +216 -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 +1,216 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - accuracy
7
+ model-index:
8
+ - name: reverse_add_replicate_eval17_small
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_eval17_small
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: 2.0642
20
+ - Accuracy: 0.0
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: 128
41
+ - eval_batch_size: 128
42
+ - seed: 7658372
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 | 2.6455 | 0.0 |
53
+ | 2.5992 | 0.0064 | 100 | 2.5954 | 0.0 |
54
+ | 2.5397 | 0.0128 | 200 | 2.5367 | 0.0 |
55
+ | 2.4878 | 0.0192 | 300 | 2.4854 | 0.0 |
56
+ | 2.45 | 0.0256 | 400 | 2.4480 | 0.0 |
57
+ | 2.4249 | 0.032 | 500 | 2.4242 | 0.0 |
58
+ | 2.3934 | 0.0384 | 600 | 2.4032 | 0.0 |
59
+ | 2.2979 | 0.0448 | 700 | 2.3667 | 0.0 |
60
+ | 2.2776 | 0.0512 | 800 | 2.3317 | 0.0 |
61
+ | 2.2734 | 0.0576 | 900 | 2.3736 | 0.0 |
62
+ | 2.2659 | 0.064 | 1000 | 2.2899 | 0.0 |
63
+ | 2.2418 | 0.0704 | 1100 | 2.3116 | 0.0 |
64
+ | 2.2429 | 0.0768 | 1200 | 2.2717 | 0.0 |
65
+ | 2.2383 | 0.0832 | 1300 | 2.3187 | 0.0 |
66
+ | 2.2103 | 0.0896 | 1400 | 2.2793 | 0.0 |
67
+ | 2.1697 | 0.096 | 1500 | 2.2506 | 0.0 |
68
+ | 2.1416 | 0.1024 | 1600 | 2.1943 | 0.0 |
69
+ | 2.1466 | 0.1088 | 1700 | 2.1995 | 0.0 |
70
+ | 2.101 | 0.1152 | 1800 | 2.1803 | 0.0 |
71
+ | 2.1117 | 0.1216 | 1900 | 2.2038 | 0.0 |
72
+ | 2.0812 | 0.128 | 2000 | 2.1659 | 0.0 |
73
+ | 2.0913 | 0.1344 | 2100 | 2.1778 | 0.0 |
74
+ | 2.079 | 0.1408 | 2200 | 2.1600 | 0.0 |
75
+ | 2.0759 | 0.1472 | 2300 | 2.1603 | 0.0 |
76
+ | 2.0763 | 0.1536 | 2400 | 2.1515 | 0.0 |
77
+ | 2.0837 | 0.16 | 2500 | 2.1415 | 0.0 |
78
+ | 2.08 | 0.1664 | 2600 | 2.1521 | 0.0 |
79
+ | 2.0647 | 0.1728 | 2700 | 2.1527 | 0.0 |
80
+ | 2.0523 | 0.1792 | 2800 | 2.1468 | 0.0 |
81
+ | 2.0452 | 0.1856 | 2900 | 2.1353 | 0.0 |
82
+ | 2.0478 | 0.192 | 3000 | 2.1522 | 0.0 |
83
+ | 2.0539 | 0.1984 | 3100 | 2.1394 | 0.0 |
84
+ | 2.0356 | 0.2048 | 3200 | 2.1435 | 0.0 |
85
+ | 2.0306 | 0.2112 | 3300 | 2.1406 | 0.0 |
86
+ | 2.0416 | 0.2176 | 3400 | 2.1326 | 0.0 |
87
+ | 2.0264 | 0.224 | 3500 | 2.1493 | 0.0 |
88
+ | 2.0666 | 0.2304 | 3600 | 2.1384 | 0.0 |
89
+ | 2.0356 | 0.2368 | 3700 | 2.1295 | 0.0 |
90
+ | 2.0383 | 0.2432 | 3800 | 2.1317 | 0.0 |
91
+ | 2.0507 | 0.2496 | 3900 | 2.1199 | 0.0 |
92
+ | 2.0189 | 0.256 | 4000 | 2.1245 | 0.0 |
93
+ | 2.0345 | 0.2624 | 4100 | 2.1259 | 0.0 |
94
+ | 2.0192 | 0.2688 | 4200 | 2.1747 | 0.0 |
95
+ | 2.0017 | 0.2752 | 4300 | 2.1250 | 0.0 |
96
+ | 2.0266 | 0.2816 | 4400 | 2.1157 | 0.0 |
97
+ | 1.9993 | 0.288 | 4500 | 2.1181 | 0.0 |
98
+ | 2.0285 | 0.2944 | 4600 | 2.1301 | 0.0 |
99
+ | 2.0196 | 0.3008 | 4700 | 2.1156 | 0.0 |
100
+ | 2.0204 | 0.3072 | 4800 | 2.1273 | 0.0 |
101
+ | 2.0276 | 0.3136 | 4900 | 2.1141 | 0.0 |
102
+ | 2.004 | 0.32 | 5000 | 2.1263 | 0.0 |
103
+ | 2.0176 | 0.3264 | 5100 | 2.1243 | 0.0 |
104
+ | 2.0072 | 0.3328 | 5200 | 2.1198 | 0.0 |
105
+ | 2.0043 | 0.3392 | 5300 | 2.1166 | 0.0 |
106
+ | 2.0202 | 0.3456 | 5400 | 2.1138 | 0.0 |
107
+ | 2.0212 | 0.352 | 5500 | 2.1248 | 0.0 |
108
+ | 1.9996 | 0.3584 | 5600 | 2.1102 | 0.0 |
109
+ | 1.9932 | 0.3648 | 5700 | 2.1000 | 0.0 |
110
+ | 1.9864 | 0.3712 | 5800 | 2.1031 | 0.0 |
111
+ | 1.9929 | 0.3776 | 5900 | 2.1047 | 0.0 |
112
+ | 2.0075 | 0.384 | 6000 | 2.1167 | 0.0 |
113
+ | 1.9849 | 0.3904 | 6100 | 2.1348 | 0.0 |
114
+ | 2.0021 | 0.3968 | 6200 | 2.0987 | 0.0 |
115
+ | 1.9998 | 0.4032 | 6300 | 2.1118 | 0.0 |
116
+ | 1.9872 | 0.4096 | 6400 | 2.1183 | 0.0 |
117
+ | 2.0153 | 0.416 | 6500 | 2.1257 | 0.0 |
118
+ | 1.9726 | 0.4224 | 6600 | 2.1016 | 0.0 |
119
+ | 1.9761 | 0.4288 | 6700 | 2.0957 | 0.0 |
120
+ | 1.9979 | 0.4352 | 6800 | 2.1133 | 0.0 |
121
+ | 2.0006 | 0.4416 | 6900 | 2.1083 | 0.0 |
122
+ | 2.0004 | 0.448 | 7000 | 2.0941 | 0.0 |
123
+ | 1.9712 | 0.4544 | 7100 | 2.1035 | 0.0 |
124
+ | 1.9965 | 0.4608 | 7200 | 2.1026 | 0.0 |
125
+ | 1.9795 | 0.4672 | 7300 | 2.0913 | 0.0 |
126
+ | 1.9739 | 0.4736 | 7400 | 2.1003 | 0.0 |
127
+ | 1.9915 | 0.48 | 7500 | 2.0937 | 0.0 |
128
+ | 1.9658 | 0.4864 | 7600 | 2.1355 | 0.0 |
129
+ | 1.989 | 0.4928 | 7700 | 2.1041 | 0.0 |
130
+ | 1.9852 | 0.4992 | 7800 | 2.0973 | 0.0 |
131
+ | 1.9804 | 0.5056 | 7900 | 2.0937 | 0.0 |
132
+ | 1.987 | 0.512 | 8000 | 2.1065 | 0.0 |
133
+ | 1.9963 | 0.5184 | 8100 | 2.1002 | 0.0 |
134
+ | 1.9752 | 0.5248 | 8200 | 2.0926 | 0.0 |
135
+ | 1.9815 | 0.5312 | 8300 | 2.0841 | 0.0 |
136
+ | 1.9916 | 0.5376 | 8400 | 2.0887 | 0.0 |
137
+ | 1.9708 | 0.544 | 8500 | 2.0884 | 0.0 |
138
+ | 1.9574 | 0.5504 | 8600 | 2.1067 | 0.0 |
139
+ | 1.9828 | 0.5568 | 8700 | 2.0994 | 0.0 |
140
+ | 1.9666 | 0.5632 | 8800 | 2.0842 | 0.0 |
141
+ | 1.9789 | 0.5696 | 8900 | 2.0817 | 0.0 |
142
+ | 1.9755 | 0.576 | 9000 | 2.0937 | 0.0 |
143
+ | 1.9562 | 0.5824 | 9100 | 2.0935 | 0.0 |
144
+ | 1.9897 | 0.5888 | 9200 | 2.1065 | 0.0 |
145
+ | 1.9863 | 0.5952 | 9300 | 2.0792 | 0.0 |
146
+ | 1.9701 | 0.6016 | 9400 | 2.0892 | 0.0 |
147
+ | 1.9688 | 0.608 | 9500 | 2.0818 | 0.0 |
148
+ | 1.9487 | 0.6144 | 9600 | 2.0787 | 0.0 |
149
+ | 1.9649 | 0.6208 | 9700 | 2.0826 | 0.0 |
150
+ | 1.9834 | 0.6272 | 9800 | 2.0864 | 0.0 |
151
+ | 1.9524 | 0.6336 | 9900 | 2.0829 | 0.0 |
152
+ | 1.9572 | 0.64 | 10000 | 2.0865 | 0.0 |
153
+ | 1.9637 | 0.6464 | 10100 | 2.0831 | 0.0 |
154
+ | 1.9617 | 0.6528 | 10200 | 2.0695 | 0.0 |
155
+ | 1.9454 | 0.6592 | 10300 | 2.0951 | 0.0 |
156
+ | 1.9825 | 0.6656 | 10400 | 2.0845 | 0.0 |
157
+ | 1.95 | 0.672 | 10500 | 2.0899 | 0.0 |
158
+ | 1.9685 | 0.6784 | 10600 | 2.0865 | 0.0 |
159
+ | 1.9748 | 0.6848 | 10700 | 2.0884 | 0.0 |
160
+ | 1.9482 | 0.6912 | 10800 | 2.1084 | 0.0 |
161
+ | 1.9614 | 0.6976 | 10900 | 2.0775 | 0.0 |
162
+ | 1.9419 | 0.704 | 11000 | 2.0829 | 0.0 |
163
+ | 1.9229 | 0.7104 | 11100 | 2.0846 | 0.0 |
164
+ | 1.9595 | 0.7168 | 11200 | 2.0788 | 0.0 |
165
+ | 1.9362 | 0.7232 | 11300 | 2.0749 | 0.0 |
166
+ | 1.9752 | 0.7296 | 11400 | 2.0699 | 0.0 |
167
+ | 1.9623 | 0.736 | 11500 | 2.0761 | 0.0 |
168
+ | 1.9628 | 0.7424 | 11600 | 2.0778 | 0.0 |
169
+ | 1.9276 | 0.7488 | 11700 | 2.0760 | 0.0 |
170
+ | 1.956 | 0.7552 | 11800 | 2.0704 | 0.0 |
171
+ | 1.9599 | 0.7616 | 11900 | 2.0770 | 0.0 |
172
+ | 1.9725 | 0.768 | 12000 | 2.0735 | 0.0 |
173
+ | 1.9662 | 0.7744 | 12100 | 2.0695 | 0.0 |
174
+ | 1.9455 | 0.7808 | 12200 | 2.0709 | 0.0 |
175
+ | 1.9406 | 0.7872 | 12300 | 2.0709 | 0.0 |
176
+ | 1.944 | 0.7936 | 12400 | 2.0775 | 0.0 |
177
+ | 1.9296 | 0.8 | 12500 | 2.0734 | 0.0 |
178
+ | 1.9271 | 0.8064 | 12600 | 2.0713 | 0.0 |
179
+ | 1.9476 | 0.8128 | 12700 | 2.0712 | 0.0 |
180
+ | 1.9769 | 0.8192 | 12800 | 2.0735 | 0.0 |
181
+ | 1.9475 | 0.8256 | 12900 | 2.0667 | 0.0 |
182
+ | 1.9576 | 0.832 | 13000 | 2.0697 | 0.0 |
183
+ | 1.9468 | 0.8384 | 13100 | 2.0694 | 0.0 |
184
+ | 1.9497 | 0.8448 | 13200 | 2.0659 | 0.0 |
185
+ | 1.9437 | 0.8512 | 13300 | 2.0674 | 0.0 |
186
+ | 1.9662 | 0.8576 | 13400 | 2.0691 | 0.0 |
187
+ | 1.931 | 0.864 | 13500 | 2.0714 | 0.0 |
188
+ | 1.9409 | 0.8704 | 13600 | 2.0702 | 0.0 |
189
+ | 1.9169 | 0.8768 | 13700 | 2.0701 | 0.0 |
190
+ | 1.9532 | 0.8832 | 13800 | 2.0696 | 0.0 |
191
+ | 1.9505 | 0.8896 | 13900 | 2.0676 | 0.0 |
192
+ | 1.9438 | 0.896 | 14000 | 2.0661 | 0.0 |
193
+ | 1.9492 | 0.9024 | 14100 | 2.0656 | 0.0 |
194
+ | 1.9463 | 0.9088 | 14200 | 2.0663 | 0.0 |
195
+ | 1.9331 | 0.9152 | 14300 | 2.0656 | 0.0 |
196
+ | 1.9095 | 0.9216 | 14400 | 2.0654 | 0.0 |
197
+ | 1.9287 | 0.928 | 14500 | 2.0667 | 0.0 |
198
+ | 1.9244 | 0.9344 | 14600 | 2.0666 | 0.0 |
199
+ | 1.9246 | 0.9408 | 14700 | 2.0653 | 0.0 |
200
+ | 1.9227 | 0.9472 | 14800 | 2.0662 | 0.0 |
201
+ | 1.9324 | 0.9536 | 14900 | 2.0664 | 0.0 |
202
+ | 1.9343 | 0.96 | 15000 | 2.0650 | 0.0 |
203
+ | 1.9552 | 0.9664 | 15100 | 2.0649 | 0.0 |
204
+ | 1.9389 | 0.9728 | 15200 | 2.0645 | 0.0 |
205
+ | 1.9556 | 0.9792 | 15300 | 2.0644 | 0.0 |
206
+ | 1.9616 | 0.9856 | 15400 | 2.0644 | 0.0 |
207
+ | 1.9526 | 0.992 | 15500 | 2.0643 | 0.0 |
208
+ | 1.9387 | 0.9984 | 15600 | 2.0642 | 0.0 |
209
+
210
+
211
+ ### Framework versions
212
+
213
+ - Transformers 4.46.0
214
+ - Pytorch 2.5.1
215
+ - Datasets 3.1.0
216
+ - 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": 16,
10
+ "n_head": 1,
11
+ "n_layer": 2,
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 sha256:56b350f38ebdb21df05f385ccbec4aeb7b027e4d9b101137a2ac9f8f5677fac4
3
+ size 30712
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a97fa4b7b478b75c42a8a2798c02dcdd9729cd25bc103d5aad7f6ccea300b99e
3
+ size 5240