Hugging Face's logo

mtzig
/
reverse_add_replicate_eval17_corruptedfull

Transformers
Safetensors
nanogpt
Generated from Trainer
Model card Files
xet
Community
mtzig commited on
Commit
b94a819
·
verified ·
1 Parent(s): f3195f5

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_corruptedfull
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_corruptedfull
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: 0.5300
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 | 2.7197 | 0.0 |
53
+ | 2.2508 | 0.0064 | 100 | 2.3854 | 0.0 |
54
+ | 2.1734 | 0.0128 | 200 | 2.2516 | 0.0 |
55
+ | 2.0 | 0.0192 | 300 | 2.2224 | 0.0 |
56
+ | 2.042 | 0.0256 | 400 | 2.1754 | 0.0 |
57
+ | 1.9312 | 0.032 | 500 | 2.1393 | 0.0 |
58
+ | 1.6389 | 0.0384 | 600 | 1.9024 | 0.0 |
59
+ | 1.6857 | 0.0448 | 700 | 1.7966 | 0.0 |
60
+ | 1.3667 | 0.0512 | 800 | 1.6226 | 0.0 |
61
+ | 1.5327 | 0.0576 | 900 | 1.5372 | 0.0 |
62
+ | 1.4855 | 0.064 | 1000 | 1.5815 | 0.001 |
63
+ | 1.5424 | 0.0704 | 1100 | 1.7777 | 0.0 |
64
+ | 1.23 | 0.0768 | 1200 | 1.4737 | 0.001 |
65
+ | 1.1634 | 0.0832 | 1300 | 1.4714 | 0.0 |
66
+ | 1.2363 | 0.0896 | 1400 | 1.3542 | 0.0 |
67
+ | 1.4037 | 0.096 | 1500 | 1.5225 | 0.0 |
68
+ | 1.3053 | 0.1024 | 1600 | 1.6180 | 0.0 |
69
+ | 1.1767 | 0.1088 | 1700 | 1.3083 | 0.0 |
70
+ | 1.1297 | 0.1152 | 1800 | 1.2672 | 0.0 |
71
+ | 1.1554 | 0.1216 | 1900 | 1.2852 | 0.0 |
72
+ | 1.0743 | 0.128 | 2000 | 1.2583 | 0.0 |
73
+ | 1.0619 | 0.1344 | 2100 | 1.2129 | 0.001 |
74
+ | 1.1048 | 0.1408 | 2200 | 1.2669 | 0.001 |
75
+ | 1.1799 | 0.1472 | 2300 | 1.2783 | 0.001 |
76
+ | 1.195 | 0.1536 | 2400 | 1.3627 | 0.0 |
77
+ | 1.1809 | 0.16 | 2500 | 1.2085 | 0.001 |
78
+ | 1.1969 | 0.1664 | 2600 | 1.4069 | 0.0 |
79
+ | 1.1118 | 0.1728 | 2700 | 1.2797 | 0.0 |
80
+ | 1.171 | 0.1792 | 2800 | 1.2713 | 0.0 |
81
+ | 1.1446 | 0.1856 | 2900 | 1.5193 | 0.0 |
82
+ | 1.2357 | 0.192 | 3000 | 1.2437 | 0.0 |
83
+ | 1.1157 | 0.1984 | 3100 | 1.2369 | 0.003 |
84
+ | 1.0299 | 0.2048 | 3200 | 1.2956 | 0.0 |
85
+ | 0.9853 | 0.2112 | 3300 | 1.2215 | 0.0 |
86
+ | 1.013 | 0.2176 | 3400 | 1.1521 | 0.002 |
87
+ | 1.0245 | 0.224 | 3500 | 1.2305 | 0.001 |
88
+ | 1.0655 | 0.2304 | 3600 | 1.2626 | 0.0 |
89
+ | 1.0799 | 0.2368 | 3700 | 1.2363 | 0.0 |
90
+ | 1.0102 | 0.2432 | 3800 | 1.1814 | 0.003 |
91
+ | 0.9486 | 0.2496 | 3900 | 1.1798 | 0.001 |
92
+ | 0.9528 | 0.256 | 4000 | 1.1197 | 0.0 |
93
+ | 0.9053 | 0.2624 | 4100 | 1.1351 | 0.001 |
94
+ | 0.7067 | 0.2688 | 4200 | 0.8761 | 0.0 |
95
+ | 0.6589 | 0.2752 | 4300 | 0.8723 | 0.007 |
96
+ | 0.4399 | 0.2816 | 4400 | 0.5698 | 0.001 |
97
+ | 0.3902 | 0.288 | 4500 | 0.4925 | 0.003 |
98
+ | 0.8062 | 0.2944 | 4600 | 1.4631 | 0.021 |
99
+ | 0.4406 | 0.3008 | 4700 | 0.6817 | 0.123 |
100
+ | 0.2309 | 0.3072 | 4800 | 0.8043 | 0.151 |
101
+ | 0.3159 | 0.3136 | 4900 | 0.7227 | 0.148 |
102
+ | 0.1867 | 0.32 | 5000 | 0.3206 | 0.346 |
103
+ | 0.6064 | 0.3264 | 5100 | 0.8217 | 0.088 |
104
+ | 0.1587 | 0.3328 | 5200 | 0.2855 | 0.182 |
105
+ | 0.4183 | 0.3392 | 5300 | 0.5310 | 0.133 |
106
+ | 0.0808 | 0.3456 | 5400 | 0.7348 | 0.072 |
107
+ | 0.2543 | 0.352 | 5500 | 1.0533 | 0.127 |
108
+ | 0.1427 | 0.3584 | 5600 | 0.5136 | 0.418 |
109
+ | 0.2765 | 0.3648 | 5700 | 0.4418 | 0.17 |
110
+ | 0.1488 | 0.3712 | 5800 | 0.3970 | 0.315 |
111
+ | 0.1357 | 0.3776 | 5900 | 0.6474 | 0.275 |
112
+ | 0.1526 | 0.384 | 6000 | 0.5895 | 0.076 |
113
+ | 0.206 | 0.3904 | 6100 | 1.2247 | 0.077 |
114
+ | 0.1029 | 0.3968 | 6200 | 0.8231 | 0.097 |
115
+ | 0.1207 | 0.4032 | 6300 | 0.3404 | 0.51 |
116
+ | 0.0677 | 0.4096 | 6400 | 0.2952 | 0.247 |
117
+ | 0.2954 | 0.416 | 6500 | 0.5292 | 0.052 |
118
+ | 0.134 | 0.4224 | 6600 | 0.3610 | 0.224 |
119
+ | 0.0762 | 0.4288 | 6700 | 0.3354 | 0.407 |
120
+ | 0.1286 | 0.4352 | 6800 | 0.3923 | 0.293 |
121
+ | 0.1515 | 0.4416 | 6900 | 0.1537 | 0.513 |
122
+ | 0.0624 | 0.448 | 7000 | 0.1791 | 0.443 |
123
+ | 0.0776 | 0.4544 | 7100 | 0.2687 | 0.413 |
124
+ | 0.0677 | 0.4608 | 7200 | 0.2416 | 0.315 |
125
+ | 0.0422 | 0.4672 | 7300 | 0.1709 | 0.433 |
126
+ | 0.0441 | 0.4736 | 7400 | 0.1300 | 0.434 |
127
+ | 0.0734 | 0.48 | 7500 | 0.1390 | 0.498 |
128
+ | 0.0214 | 0.4864 | 7600 | 0.3181 | 0.353 |
129
+ | 0.6083 | 0.4928 | 7700 | 1.0202 | 0.08 |
130
+ | 0.0599 | 0.4992 | 7800 | 0.2724 | 0.342 |
131
+ | 0.051 | 0.5056 | 7900 | 0.1759 | 0.362 |
132
+ | 0.1857 | 0.512 | 8000 | 0.7223 | 0.21 |
133
+ | 0.1543 | 0.5184 | 8100 | 0.7703 | 0.039 |
134
+ | 0.0614 | 0.5248 | 8200 | 0.1059 | 0.513 |
135
+ | 0.0342 | 0.5312 | 8300 | 0.1070 | 0.661 |
136
+ | 0.054 | 0.5376 | 8400 | 0.2630 | 0.337 |
137
+ | 0.0325 | 0.544 | 8500 | 0.2198 | 0.327 |
138
+ | 0.0092 | 0.5504 | 8600 | 0.0922 | 0.698 |
139
+ | 0.0156 | 0.5568 | 8700 | 0.1876 | 0.439 |
140
+ | 0.0129 | 0.5632 | 8800 | 0.2162 | 0.29 |
141
+ | 0.0169 | 0.5696 | 8900 | 0.1118 | 0.325 |
142
+ | 0.0512 | 0.576 | 9000 | 0.0743 | 0.718 |
143
+ | 0.1005 | 0.5824 | 9100 | 0.3120 | 0.161 |
144
+ | 0.0101 | 0.5888 | 9200 | 0.0649 | 0.603 |
145
+ | 0.0441 | 0.5952 | 9300 | 0.0737 | 0.745 |
146
+ | 0.082 | 0.6016 | 9400 | 0.2053 | 0.376 |
147
+ | 0.0219 | 0.608 | 9500 | 0.1205 | 0.619 |
148
+ | 0.0243 | 0.6144 | 9600 | 0.0675 | 0.662 |
149
+ | 0.0148 | 0.6208 | 9700 | 0.6656 | 0.272 |
150
+ | 0.0082 | 0.6272 | 9800 | 0.0833 | 0.395 |
151
+ | 0.005 | 0.6336 | 9900 | 0.0921 | 0.518 |
152
+ | 0.0096 | 0.64 | 10000 | 0.6033 | 0.348 |
153
+ | 0.0074 | 0.6464 | 10100 | 0.1524 | 0.097 |
154
+ | 0.0022 | 0.6528 | 10200 | 0.1999 | 0.071 |
155
+ | 0.0024 | 0.6592 | 10300 | 0.1307 | 0.292 |
156
+ | 0.0003 | 0.6656 | 10400 | 0.1261 | 0.244 |
157
+ | 0.0102 | 0.672 | 10500 | 0.1265 | 0.312 |
158
+ | 0.0005 | 0.6784 | 10600 | 0.2220 | 0.036 |
159
+ | 0.0113 | 0.6848 | 10700 | 0.1430 | 0.186 |
160
+ | 0.0005 | 0.6912 | 10800 | 0.2842 | 0.007 |
161
+ | 0.0095 | 0.6976 | 10900 | 0.1886 | 0.109 |
162
+ | 0.0006 | 0.704 | 11000 | 0.2308 | 0.042 |
163
+ | 0.0032 | 0.7104 | 11100 | 0.3134 | 0.105 |
164
+ | 0.0028 | 0.7168 | 11200 | 0.1602 | 0.12 |
165
+ | 0.0003 | 0.7232 | 11300 | 0.2925 | 0.001 |
166
+ | 0.0138 | 0.7296 | 11400 | 0.2362 | 0.047 |
167
+ | 0.0006 | 0.736 | 11500 | 0.3262 | 0.0 |
168
+ | 0.002 | 0.7424 | 11600 | 0.1361 | 0.213 |
169
+ | 0.0001 | 0.7488 | 11700 | 0.1560 | 0.37 |
170
+ | 0.0005 | 0.7552 | 11800 | 0.3111 | 0.007 |
171
+ | 0.0001 | 0.7616 | 11900 | 0.3441 | 0.002 |
172
+ | 0.0004 | 0.768 | 12000 | 0.3842 | 0.0 |
173
+ | 0.0001 | 0.7744 | 12100 | 0.4115 | 0.0 |
174
+ | 0.0007 | 0.7808 | 12200 | 0.3541 | 0.02 |
175
+ | 0.0 | 0.7872 | 12300 | 0.3537 | 0.002 |
176
+ | 0.0046 | 0.7936 | 12400 | 0.3153 | 0.015 |
177
+ | 0.0004 | 0.8 | 12500 | 0.4039 | 0.003 |
178
+ | 0.0 | 0.8064 | 12600 | 0.4155 | 0.003 |
179
+ | 0.0001 | 0.8128 | 12700 | 0.3909 | 0.001 |
180
+ | 0.0004 | 0.8192 | 12800 | 0.4673 | 0.0 |
181
+ | 0.0 | 0.8256 | 12900 | 0.3996 | 0.0 |
182
+ | 0.0 | 0.832 | 13000 | 0.3360 | 0.004 |
183
+ | 0.0 | 0.8384 | 13100 | 0.3118 | 0.011 |
184
+ | 0.0 | 0.8448 | 13200 | 0.4214 | 0.0 |
185
+ | 0.0 | 0.8512 | 13300 | 0.4547 | 0.0 |
186
+ | 0.0 | 0.8576 | 13400 | 0.4271 | 0.0 |
187
+ | 0.0004 | 0.864 | 13500 | 0.4966 | 0.0 |
188
+ | 0.0 | 0.8704 | 13600 | 0.5133 | 0.0 |
189
+ | 0.0 | 0.8768 | 13700 | 0.5046 | 0.0 |
190
+ | 0.0 | 0.8832 | 13800 | 0.5605 | 0.0 |
191
+ | 0.0 | 0.8896 | 13900 | 0.5063 | 0.0 |
192
+ | 0.0 | 0.896 | 14000 | 0.5144 | 0.0 |
193
+ | 0.0 | 0.9024 | 14100 | 0.5037 | 0.0 |
194
+ | 0.0 | 0.9088 | 14200 | 0.5242 | 0.0 |
195
+ | 0.0 | 0.9152 | 14300 | 0.5054 | 0.0 |
196
+ | 0.0 | 0.9216 | 14400 | 0.5186 | 0.0 |
197
+ | 0.0 | 0.928 | 14500 | 0.5487 | 0.0 |
198
+ | 0.0 | 0.9344 | 14600 | 0.5526 | 0.0 |
199
+ | 0.0 | 0.9408 | 14700 | 0.5597 | 0.0 |
200
+ | 0.0 | 0.9472 | 14800 | 0.5461 | 0.0 |
201
+ | 0.0 | 0.9536 | 14900 | 0.5410 | 0.0 |
202
+ | 0.0 | 0.96 | 15000 | 0.5398 | 0.0 |
203
+ | 0.0 | 0.9664 | 15100 | 0.5367 | 0.0 |
204
+ | 0.0003 | 0.9728 | 15200 | 0.5336 | 0.0 |
205
+ | 0.0 | 0.9792 | 15300 | 0.5342 | 0.0 |
206
+ | 0.0 | 0.9856 | 15400 | 0.5308 | 0.0 |
207
+ | 0.0 | 0.992 | 15500 | 0.5296 | 0.0 |
208
+ | 0.0 | 0.9984 | 15600 | 0.5300 | 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": 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 sha256:7a9e23db6246d5cc3d176c0a5173c485b03063846b585c879829de78623ddee0
3
+ size 42640744
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acf613225c6f8597ae53536c21106cbd9ad7c1e6e6b61dbb320d314ee3119b3b
3
+ size 5240