Model save
Browse files- README.md +218 -0
- config.json +18 -0
- generation_config.json +4 -0
- model.safetensors +3 -0
- 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_eval30
|
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_eval30
|
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: 4.2069
|
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: 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 | 2.7824 | 0.0 |
|
55 |
+
| 4.4924 | 0.0064 | 100 | 2.3666 | 0.0 |
|
56 |
+
| 4.4303 | 0.0128 | 200 | 2.3891 | 0.0 |
|
57 |
+
| 4.2696 | 0.0192 | 300 | 2.3886 | 0.0 |
|
58 |
+
| 4.1579 | 0.0256 | 400 | 2.3007 | 0.0 |
|
59 |
+
| 3.9553 | 0.032 | 500 | 2.2664 | 0.0 |
|
60 |
+
| 3.443 | 0.0384 | 600 | 2.1687 | 0.0 |
|
61 |
+
| 2.9354 | 0.0448 | 700 | 2.2864 | 0.0 |
|
62 |
+
| 3.1202 | 0.0512 | 800 | 2.3458 | 0.0 |
|
63 |
+
| 2.6519 | 0.0576 | 900 | 2.2538 | 0.0 |
|
64 |
+
| 2.8012 | 0.064 | 1000 | 1.9890 | 0.0 |
|
65 |
+
| 2.6125 | 0.0704 | 1100 | 2.0957 | 0.0 |
|
66 |
+
| 2.4014 | 0.0768 | 1200 | 2.2698 | 0.0 |
|
67 |
+
| 2.6731 | 0.0832 | 1300 | 2.4123 | 0.0 |
|
68 |
+
| 2.6851 | 0.0896 | 1400 | 2.5450 | 0.0 |
|
69 |
+
| 2.5736 | 0.096 | 1500 | 1.9995 | 0.0 |
|
70 |
+
| 2.3324 | 0.1024 | 1600 | 2.1640 | 0.0 |
|
71 |
+
| 2.4952 | 0.1088 | 1700 | 2.3585 | 0.0 |
|
72 |
+
| 2.2542 | 0.1152 | 1800 | 2.3618 | 0.0 |
|
73 |
+
| 2.3456 | 0.1216 | 1900 | 2.2109 | 0.0 |
|
74 |
+
| 2.386 | 0.128 | 2000 | 2.3208 | 0.0 |
|
75 |
+
| 2.528 | 0.1344 | 2100 | 2.2732 | 0.0 |
|
76 |
+
| 2.5489 | 0.1408 | 2200 | 2.0203 | 0.0 |
|
77 |
+
| 2.4391 | 0.1472 | 2300 | 2.2699 | 0.0 |
|
78 |
+
| 2.4452 | 0.1536 | 2400 | 2.2424 | 0.0 |
|
79 |
+
| 2.3189 | 0.16 | 2500 | 2.1381 | 0.0 |
|
80 |
+
| 4.4429 | 0.1664 | 2600 | 2.2751 | 0.0 |
|
81 |
+
| 2.2243 | 0.1728 | 2700 | 2.5335 | 0.0 |
|
82 |
+
| 2.3893 | 0.1792 | 2800 | 2.6115 | 0.0 |
|
83 |
+
| 2.3394 | 0.1856 | 2900 | 2.6899 | 0.0 |
|
84 |
+
| 2.6173 | 0.192 | 3000 | 2.4414 | 0.0 |
|
85 |
+
| 2.3326 | 0.1984 | 3100 | 2.6462 | 0.0 |
|
86 |
+
| 2.1011 | 0.2048 | 3200 | 2.6349 | 0.0 |
|
87 |
+
| 2.5971 | 0.2112 | 3300 | 2.2816 | 0.0 |
|
88 |
+
| 2.1758 | 0.2176 | 3400 | 2.9367 | 0.0 |
|
89 |
+
| 2.0391 | 0.224 | 3500 | 2.5660 | 0.0 |
|
90 |
+
| 2.683 | 0.2304 | 3600 | 2.2197 | 0.0 |
|
91 |
+
| 2.1331 | 0.2368 | 3700 | 1.9519 | 0.0 |
|
92 |
+
| 2.5328 | 0.2432 | 3800 | 2.8043 | 0.0 |
|
93 |
+
| 2.307 | 0.2496 | 3900 | 3.1588 | 0.0 |
|
94 |
+
| 2.4706 | 0.256 | 4000 | 1.7832 | 0.0 |
|
95 |
+
| 2.2706 | 0.2624 | 4100 | 2.3912 | 0.0 |
|
96 |
+
| 2.0165 | 0.2688 | 4200 | 3.3943 | 0.0 |
|
97 |
+
| 2.1406 | 0.2752 | 4300 | 2.8255 | 0.0 |
|
98 |
+
| 2.1749 | 0.2816 | 4400 | 1.9678 | 0.0 |
|
99 |
+
| 2.3053 | 0.288 | 4500 | 2.1989 | 0.0 |
|
100 |
+
| 2.1815 | 0.2944 | 4600 | 2.5911 | 0.0 |
|
101 |
+
| 2.1675 | 0.3008 | 4700 | 2.7480 | 0.0 |
|
102 |
+
| 2.0463 | 0.3072 | 4800 | 2.0872 | 0.0 |
|
103 |
+
| 2.2269 | 0.3136 | 4900 | 2.5325 | 0.0 |
|
104 |
+
| 1.9049 | 0.32 | 5000 | 2.7470 | 0.0 |
|
105 |
+
| 2.0929 | 0.3264 | 5100 | 2.2618 | 0.0 |
|
106 |
+
| 1.8538 | 0.3328 | 5200 | 2.0825 | 0.0 |
|
107 |
+
| 1.4804 | 0.3392 | 5300 | 2.0630 | 0.0 |
|
108 |
+
| 1.3704 | 0.3456 | 5400 | 1.7688 | 0.0 |
|
109 |
+
| 1.2029 | 0.352 | 5500 | 2.7977 | 0.0 |
|
110 |
+
| 0.6455 | 0.3584 | 5600 | 2.7000 | 0.0 |
|
111 |
+
| 0.9013 | 0.3648 | 5700 | 2.7678 | 0.0 |
|
112 |
+
| 0.4867 | 0.3712 | 5800 | 2.7487 | 0.0 |
|
113 |
+
| 1.4135 | 0.3776 | 5900 | 2.3163 | 0.0 |
|
114 |
+
| 0.1742 | 0.384 | 6000 | 2.7119 | 0.0 |
|
115 |
+
| 0.5932 | 0.3904 | 6100 | 2.8409 | 0.0 |
|
116 |
+
| 0.3346 | 0.3968 | 6200 | 2.4202 | 0.0 |
|
117 |
+
| 0.7908 | 0.4032 | 6300 | 3.1410 | 0.0 |
|
118 |
+
| 0.4932 | 0.4096 | 6400 | 3.6802 | 0.0 |
|
119 |
+
| 0.3316 | 0.416 | 6500 | 2.2771 | 0.0 |
|
120 |
+
| 0.3097 | 0.4224 | 6600 | 2.5632 | 0.0 |
|
121 |
+
| 0.3322 | 0.4288 | 6700 | 2.7335 | 0.0 |
|
122 |
+
| 0.2749 | 0.4352 | 6800 | 3.1795 | 0.0 |
|
123 |
+
| 0.3139 | 0.4416 | 6900 | 3.6155 | 0.0 |
|
124 |
+
| 0.2414 | 0.448 | 7000 | 3.1201 | 0.0 |
|
125 |
+
| 2.3029 | 0.4544 | 7100 | 3.7881 | 0.0 |
|
126 |
+
| 0.4029 | 0.4608 | 7200 | 3.7932 | 0.0 |
|
127 |
+
| 0.1374 | 0.4672 | 7300 | 2.8160 | 0.0 |
|
128 |
+
| 0.2741 | 0.4736 | 7400 | 2.4926 | 0.0 |
|
129 |
+
| 0.2765 | 0.48 | 7500 | 3.0036 | 0.0 |
|
130 |
+
| 0.022 | 0.4864 | 7600 | 3.4260 | 0.0 |
|
131 |
+
| 0.1145 | 0.4928 | 7700 | 3.2066 | 0.0 |
|
132 |
+
| 0.2077 | 0.4992 | 7800 | 2.9937 | 0.0 |
|
133 |
+
| 0.086 | 0.5056 | 7900 | 2.7413 | 0.0 |
|
134 |
+
| 0.0884 | 0.512 | 8000 | 3.2411 | 0.0 |
|
135 |
+
| 0.158 | 0.5184 | 8100 | 3.4493 | 0.0 |
|
136 |
+
| 0.1484 | 0.5248 | 8200 | 2.4997 | 0.0 |
|
137 |
+
| 0.0335 | 0.5312 | 8300 | 3.4125 | 0.0 |
|
138 |
+
| 0.0128 | 0.5376 | 8400 | 2.4688 | 0.0 |
|
139 |
+
| 0.0317 | 0.544 | 8500 | 2.9963 | 0.0 |
|
140 |
+
| 0.092 | 0.5504 | 8600 | 3.6333 | 0.0 |
|
141 |
+
| 0.028 | 0.5568 | 8700 | 2.9518 | 0.0 |
|
142 |
+
| 0.0442 | 0.5632 | 8800 | 3.4326 | 0.0 |
|
143 |
+
| 0.0901 | 0.5696 | 8900 | 3.9253 | 0.0 |
|
144 |
+
| 0.1999 | 0.576 | 9000 | 3.9988 | 0.0 |
|
145 |
+
| 0.0344 | 0.5824 | 9100 | 3.8048 | 0.0 |
|
146 |
+
| 0.0015 | 0.5888 | 9200 | 3.7488 | 0.0 |
|
147 |
+
| 0.0846 | 0.5952 | 9300 | 4.5372 | 0.0 |
|
148 |
+
| 0.0147 | 0.6016 | 9400 | 4.1808 | 0.0 |
|
149 |
+
| 0.0282 | 0.608 | 9500 | 3.3729 | 0.0 |
|
150 |
+
| 0.0273 | 0.6144 | 9600 | 2.6182 | 0.0 |
|
151 |
+
| 0.0229 | 0.6208 | 9700 | 3.7613 | 0.0 |
|
152 |
+
| 0.0005 | 0.6272 | 9800 | 4.1924 | 0.0 |
|
153 |
+
| 0.0023 | 0.6336 | 9900 | 3.0110 | 0.0 |
|
154 |
+
| 0.002 | 0.64 | 10000 | 3.1986 | 0.0 |
|
155 |
+
| 0.0018 | 0.6464 | 10100 | 2.8814 | 0.0 |
|
156 |
+
| 0.0006 | 0.6528 | 10200 | 3.2804 | 0.0 |
|
157 |
+
| 0.0002 | 0.6592 | 10300 | 4.5229 | 0.0 |
|
158 |
+
| 0.007 | 0.6656 | 10400 | 4.0220 | 0.0 |
|
159 |
+
| 0.0 | 0.672 | 10500 | 4.3269 | 0.0 |
|
160 |
+
| 0.0012 | 0.6784 | 10600 | 4.4005 | 0.0 |
|
161 |
+
| 0.0 | 0.6848 | 10700 | 4.0689 | 0.0 |
|
162 |
+
| 0.0003 | 0.6912 | 10800 | 3.0147 | 0.0 |
|
163 |
+
| 0.0023 | 0.6976 | 10900 | 5.2716 | 0.0 |
|
164 |
+
| 0.0004 | 0.704 | 11000 | 3.3269 | 0.0 |
|
165 |
+
| 0.0006 | 0.7104 | 11100 | 3.6125 | 0.0 |
|
166 |
+
| 0.0002 | 0.7168 | 11200 | 2.9193 | 0.0 |
|
167 |
+
| 0.0002 | 0.7232 | 11300 | 4.0888 | 0.0 |
|
168 |
+
| 0.0002 | 0.7296 | 11400 | 3.3349 | 0.0 |
|
169 |
+
| 0.0 | 0.736 | 11500 | 3.4065 | 0.0 |
|
170 |
+
| 0.0 | 0.7424 | 11600 | 3.5861 | 0.0 |
|
171 |
+
| 0.0 | 0.7488 | 11700 | 3.6467 | 0.0 |
|
172 |
+
| 0.0 | 0.7552 | 11800 | 3.6487 | 0.0 |
|
173 |
+
| 0.0 | 0.7616 | 11900 | 3.6888 | 0.0 |
|
174 |
+
| 0.0 | 0.768 | 12000 | 3.7449 | 0.0 |
|
175 |
+
| 0.0 | 0.7744 | 12100 | 3.8121 | 0.0 |
|
176 |
+
| 0.0 | 0.7808 | 12200 | 3.8735 | 0.0 |
|
177 |
+
| 0.0 | 0.7872 | 12300 | 3.9032 | 0.0 |
|
178 |
+
| 0.0 | 0.7936 | 12400 | 3.9248 | 0.0 |
|
179 |
+
| 0.0 | 0.8 | 12500 | 3.9542 | 0.0 |
|
180 |
+
| 0.0 | 0.8064 | 12600 | 3.9486 | 0.0 |
|
181 |
+
| 0.0 | 0.8128 | 12700 | 3.9630 | 0.0 |
|
182 |
+
| 0.0 | 0.8192 | 12800 | 3.9758 | 0.0 |
|
183 |
+
| 0.0 | 0.8256 | 12900 | 3.9721 | 0.0 |
|
184 |
+
| 0.0 | 0.832 | 13000 | 3.9492 | 0.0 |
|
185 |
+
| 0.0 | 0.8384 | 13100 | 3.9657 | 0.0 |
|
186 |
+
| 0.0 | 0.8448 | 13200 | 3.9868 | 0.0 |
|
187 |
+
| 0.0 | 0.8512 | 13300 | 4.0069 | 0.0 |
|
188 |
+
| 0.0 | 0.8576 | 13400 | 4.0213 | 0.0 |
|
189 |
+
| 0.0 | 0.864 | 13500 | 4.0300 | 0.0 |
|
190 |
+
| 0.0 | 0.8704 | 13600 | 4.0330 | 0.0 |
|
191 |
+
| 0.0 | 0.8768 | 13700 | 4.0619 | 0.0 |
|
192 |
+
| 0.0 | 0.8832 | 13800 | 4.2990 | 0.0 |
|
193 |
+
| 0.0 | 0.8896 | 13900 | 4.2865 | 0.0 |
|
194 |
+
| 0.0 | 0.896 | 14000 | 4.2903 | 0.0 |
|
195 |
+
| 0.0 | 0.9024 | 14100 | 4.2958 | 0.0 |
|
196 |
+
| 0.0 | 0.9088 | 14200 | 4.2725 | 0.0 |
|
197 |
+
| 0.0 | 0.9152 | 14300 | 4.2739 | 0.0 |
|
198 |
+
| 0.0 | 0.9216 | 14400 | 4.2878 | 0.0 |
|
199 |
+
| 0.0 | 0.928 | 14500 | 4.2924 | 0.0 |
|
200 |
+
| 0.0 | 0.9344 | 14600 | 4.2934 | 0.0 |
|
201 |
+
| 0.0 | 0.9408 | 14700 | 4.2081 | 0.0 |
|
202 |
+
| 0.0 | 0.9472 | 14800 | 4.2132 | 0.0 |
|
203 |
+
| 0.0 | 0.9536 | 14900 | 4.2024 | 0.0 |
|
204 |
+
| 0.0 | 0.96 | 15000 | 4.2036 | 0.0 |
|
205 |
+
| 0.0 | 0.9664 | 15100 | 4.2049 | 0.0 |
|
206 |
+
| 0.0 | 0.9728 | 15200 | 4.2054 | 0.0 |
|
207 |
+
| 0.0 | 0.9792 | 15300 | 4.2064 | 0.0 |
|
208 |
+
| 0.0 | 0.9856 | 15400 | 4.2069 | 0.0 |
|
209 |
+
| 0.0 | 0.992 | 15500 | 4.2069 | 0.0 |
|
210 |
+
| 0.0 | 0.9984 | 15600 | 4.2069 | 0.0 |
|
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 sha256:5617b31ad24eb7b1e71540f13748b7d894f8471282f0d79d98cba399b2bc7f4d
|
3 |
+
size 42640744
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e17ee82b634fd4df3f5751ec12f577a5d53ee3ba3d70f23dc089aedaab70fb10
|
3 |
+
size 5240
|