Hugging Face's logo

mtzig
/
bm_train1-8_eval21-25_lr1e-5

Transformers
Safetensors
nanogpt
Generated from Trainer
Model card Files Community
mtzig commited on
Commit
b09646a
·
verified ·
1 Parent(s): 05d4a36

Model save

Browse files
Files changed (5) hide show
  1. README.md +216 -0
  2. config.json +19 -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: bm_train1-8_eval21-25_lr1e-5
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
+ # bm_train1-8_eval21-25_lr1e-5
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: 1.2406
20
+ - Accuracy: 0.513
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: 1e-05
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 | 2.6121 | 0.513 |
53
+ | 2.6112 | 0.0064 | 100 | 2.6106 | 0.513 |
54
+ | 2.6041 | 0.0128 | 200 | 2.6060 | 0.513 |
55
+ | 2.6038 | 0.0192 | 300 | 2.5985 | 0.513 |
56
+ | 2.5946 | 0.0256 | 400 | 2.5880 | 0.513 |
57
+ | 2.5777 | 0.032 | 500 | 2.5744 | 0.513 |
58
+ | 2.5551 | 0.0384 | 600 | 2.5577 | 0.513 |
59
+ | 2.5353 | 0.0448 | 700 | 2.5376 | 0.513 |
60
+ | 2.5162 | 0.0512 | 800 | 2.5138 | 0.513 |
61
+ | 2.5064 | 0.0576 | 900 | 2.4879 | 0.513 |
62
+ | 2.4682 | 0.064 | 1000 | 2.4630 | 0.513 |
63
+ | 2.4466 | 0.0704 | 1100 | 2.4403 | 0.513 |
64
+ | 2.4171 | 0.0768 | 1200 | 2.4196 | 0.545 |
65
+ | 2.4006 | 0.0832 | 1300 | 2.4007 | 0.711 |
66
+ | 2.3823 | 0.0896 | 1400 | 2.3824 | 0.745 |
67
+ | 2.3681 | 0.096 | 1500 | 2.3638 | 0.77 |
68
+ | 2.3479 | 0.1024 | 1600 | 2.3443 | 0.779 |
69
+ | 2.3234 | 0.1088 | 1700 | 2.3247 | 0.775 |
70
+ | 2.3101 | 0.1152 | 1800 | 2.3053 | 0.775 |
71
+ | 2.2805 | 0.1216 | 1900 | 2.2862 | 0.764 |
72
+ | 2.265 | 0.128 | 2000 | 2.2673 | 0.764 |
73
+ | 2.2465 | 0.1344 | 2100 | 2.2486 | 0.745 |
74
+ | 2.2279 | 0.1408 | 2200 | 2.2300 | 0.74 |
75
+ | 2.2072 | 0.1472 | 2300 | 2.2115 | 0.727 |
76
+ | 2.1912 | 0.1536 | 2400 | 2.1931 | 0.719 |
77
+ | 2.1756 | 0.16 | 2500 | 2.1749 | 0.696 |
78
+ | 2.1615 | 0.1664 | 2600 | 2.1568 | 0.69 |
79
+ | 2.1327 | 0.1728 | 2700 | 2.1388 | 0.661 |
80
+ | 2.1242 | 0.1792 | 2800 | 2.1210 | 0.654 |
81
+ | 2.1052 | 0.1856 | 2900 | 2.1033 | 0.62 |
82
+ | 2.0912 | 0.192 | 3000 | 2.0857 | 0.585 |
83
+ | 2.0776 | 0.1984 | 3100 | 2.0683 | 0.576 |
84
+ | 2.0488 | 0.2048 | 3200 | 2.0510 | 0.513 |
85
+ | 2.0294 | 0.2112 | 3300 | 2.0339 | 0.513 |
86
+ | 2.0182 | 0.2176 | 3400 | 2.0169 | 0.513 |
87
+ | 1.9955 | 0.224 | 3500 | 2.0001 | 0.513 |
88
+ | 1.9809 | 0.2304 | 3600 | 1.9835 | 0.513 |
89
+ | 1.9622 | 0.2368 | 3700 | 1.9670 | 0.513 |
90
+ | 1.9481 | 0.2432 | 3800 | 1.9507 | 0.513 |
91
+ | 1.936 | 0.2496 | 3900 | 1.9346 | 0.513 |
92
+ | 1.9149 | 0.256 | 4000 | 1.9186 | 0.513 |
93
+ | 1.9005 | 0.2624 | 4100 | 1.9029 | 0.513 |
94
+ | 1.8887 | 0.2688 | 4200 | 1.8873 | 0.513 |
95
+ | 1.8716 | 0.2752 | 4300 | 1.8719 | 0.513 |
96
+ | 1.8538 | 0.2816 | 4400 | 1.8567 | 0.513 |
97
+ | 1.8476 | 0.288 | 4500 | 1.8417 | 0.513 |
98
+ | 1.821 | 0.2944 | 4600 | 1.8268 | 0.513 |
99
+ | 1.8118 | 0.3008 | 4700 | 1.8122 | 0.513 |
100
+ | 1.7986 | 0.3072 | 4800 | 1.7977 | 0.513 |
101
+ | 1.7861 | 0.3136 | 4900 | 1.7835 | 0.513 |
102
+ | 1.758 | 0.32 | 5000 | 1.7694 | 0.513 |
103
+ | 1.7454 | 0.3264 | 5100 | 1.7555 | 0.513 |
104
+ | 1.7431 | 0.3328 | 5200 | 1.7419 | 0.513 |
105
+ | 1.7347 | 0.3392 | 5300 | 1.7284 | 0.513 |
106
+ | 1.7122 | 0.3456 | 5400 | 1.7152 | 0.513 |
107
+ | 1.6946 | 0.352 | 5500 | 1.7021 | 0.513 |
108
+ | 1.6928 | 0.3584 | 5600 | 1.6893 | 0.513 |
109
+ | 1.6679 | 0.3648 | 5700 | 1.6767 | 0.513 |
110
+ | 1.6727 | 0.3712 | 5800 | 1.6642 | 0.513 |
111
+ | 1.6564 | 0.3776 | 5900 | 1.6520 | 0.513 |
112
+ | 1.6501 | 0.384 | 6000 | 1.6400 | 0.513 |
113
+ | 1.6266 | 0.3904 | 6100 | 1.6281 | 0.513 |
114
+ | 1.6133 | 0.3968 | 6200 | 1.6166 | 0.513 |
115
+ | 1.599 | 0.4032 | 6300 | 1.6052 | 0.513 |
116
+ | 1.5986 | 0.4096 | 6400 | 1.5940 | 0.513 |
117
+ | 1.592 | 0.416 | 6500 | 1.5831 | 0.513 |
118
+ | 1.5756 | 0.4224 | 6600 | 1.5723 | 0.513 |
119
+ | 1.5644 | 0.4288 | 6700 | 1.5618 | 0.513 |
120
+ | 1.548 | 0.4352 | 6800 | 1.5515 | 0.513 |
121
+ | 1.5408 | 0.4416 | 6900 | 1.5413 | 0.513 |
122
+ | 1.531 | 0.448 | 7000 | 1.5314 | 0.513 |
123
+ | 1.5157 | 0.4544 | 7100 | 1.5216 | 0.513 |
124
+ | 1.503 | 0.4608 | 7200 | 1.5121 | 0.513 |
125
+ | 1.4966 | 0.4672 | 7300 | 1.5028 | 0.513 |
126
+ | 1.4902 | 0.4736 | 7400 | 1.4937 | 0.513 |
127
+ | 1.4874 | 0.48 | 7500 | 1.4848 | 0.513 |
128
+ | 1.4795 | 0.4864 | 7600 | 1.4761 | 0.513 |
129
+ | 1.4701 | 0.4928 | 7700 | 1.4676 | 0.513 |
130
+ | 1.4607 | 0.4992 | 7800 | 1.4593 | 0.513 |
131
+ | 1.4516 | 0.5056 | 7900 | 1.4512 | 0.513 |
132
+ | 1.4381 | 0.512 | 8000 | 1.4432 | 0.513 |
133
+ | 1.4321 | 0.5184 | 8100 | 1.4355 | 0.513 |
134
+ | 1.4237 | 0.5248 | 8200 | 1.4280 | 0.513 |
135
+ | 1.4284 | 0.5312 | 8300 | 1.4207 | 0.513 |
136
+ | 1.4128 | 0.5376 | 8400 | 1.4135 | 0.513 |
137
+ | 1.405 | 0.544 | 8500 | 1.4065 | 0.513 |
138
+ | 1.3974 | 0.5504 | 8600 | 1.3998 | 0.513 |
139
+ | 1.3868 | 0.5568 | 8700 | 1.3932 | 0.513 |
140
+ | 1.3763 | 0.5632 | 8800 | 1.3867 | 0.513 |
141
+ | 1.3702 | 0.5696 | 8900 | 1.3805 | 0.513 |
142
+ | 1.3652 | 0.576 | 9000 | 1.3745 | 0.513 |
143
+ | 1.3633 | 0.5824 | 9100 | 1.3686 | 0.513 |
144
+ | 1.3576 | 0.5888 | 9200 | 1.3629 | 0.513 |
145
+ | 1.351 | 0.5952 | 9300 | 1.3574 | 0.513 |
146
+ | 1.3476 | 0.6016 | 9400 | 1.3520 | 0.513 |
147
+ | 1.3433 | 0.608 | 9500 | 1.3468 | 0.513 |
148
+ | 1.3373 | 0.6144 | 9600 | 1.3418 | 0.513 |
149
+ | 1.3383 | 0.6208 | 9700 | 1.3369 | 0.513 |
150
+ | 1.3327 | 0.6272 | 9800 | 1.3322 | 0.513 |
151
+ | 1.3282 | 0.6336 | 9900 | 1.3276 | 0.513 |
152
+ | 1.3127 | 0.64 | 10000 | 1.3232 | 0.513 |
153
+ | 1.3115 | 0.6464 | 10100 | 1.3190 | 0.513 |
154
+ | 1.3143 | 0.6528 | 10200 | 1.3149 | 0.513 |
155
+ | 1.3124 | 0.6592 | 10300 | 1.3109 | 0.513 |
156
+ | 1.3056 | 0.6656 | 10400 | 1.3071 | 0.513 |
157
+ | 1.3009 | 0.672 | 10500 | 1.3034 | 0.513 |
158
+ | 1.2924 | 0.6784 | 10600 | 1.2999 | 0.513 |
159
+ | 1.292 | 0.6848 | 10700 | 1.2964 | 0.513 |
160
+ | 1.2946 | 0.6912 | 10800 | 1.2931 | 0.513 |
161
+ | 1.2754 | 0.6976 | 10900 | 1.2900 | 0.513 |
162
+ | 1.2892 | 0.704 | 11000 | 1.2870 | 0.513 |
163
+ | 1.2786 | 0.7104 | 11100 | 1.2840 | 0.513 |
164
+ | 1.274 | 0.7168 | 11200 | 1.2813 | 0.513 |
165
+ | 1.2811 | 0.7232 | 11300 | 1.2786 | 0.513 |
166
+ | 1.2727 | 0.7296 | 11400 | 1.2761 | 0.513 |
167
+ | 1.267 | 0.736 | 11500 | 1.2736 | 0.513 |
168
+ | 1.2739 | 0.7424 | 11600 | 1.2713 | 0.513 |
169
+ | 1.2594 | 0.7488 | 11700 | 1.2691 | 0.513 |
170
+ | 1.2624 | 0.7552 | 11800 | 1.2670 | 0.513 |
171
+ | 1.2656 | 0.7616 | 11900 | 1.2650 | 0.513 |
172
+ | 1.2635 | 0.768 | 12000 | 1.2631 | 0.513 |
173
+ | 1.2567 | 0.7744 | 12100 | 1.2613 | 0.513 |
174
+ | 1.247 | 0.7808 | 12200 | 1.2596 | 0.513 |
175
+ | 1.2583 | 0.7872 | 12300 | 1.2580 | 0.513 |
176
+ | 1.2502 | 0.7936 | 12400 | 1.2565 | 0.513 |
177
+ | 1.2497 | 0.8 | 12500 | 1.2551 | 0.513 |
178
+ | 1.2532 | 0.8064 | 12600 | 1.2537 | 0.513 |
179
+ | 1.2491 | 0.8128 | 12700 | 1.2525 | 0.513 |
180
+ | 1.2609 | 0.8192 | 12800 | 1.2513 | 0.513 |
181
+ | 1.2456 | 0.8256 | 12900 | 1.2502 | 0.513 |
182
+ | 1.2458 | 0.832 | 13000 | 1.2492 | 0.513 |
183
+ | 1.2437 | 0.8384 | 13100 | 1.2482 | 0.513 |
184
+ | 1.2409 | 0.8448 | 13200 | 1.2474 | 0.513 |
185
+ | 1.2471 | 0.8512 | 13300 | 1.2466 | 0.513 |
186
+ | 1.2442 | 0.8576 | 13400 | 1.2458 | 0.513 |
187
+ | 1.2416 | 0.864 | 13500 | 1.2452 | 0.513 |
188
+ | 1.2482 | 0.8704 | 13600 | 1.2445 | 0.513 |
189
+ | 1.2495 | 0.8768 | 13700 | 1.2440 | 0.513 |
190
+ | 1.248 | 0.8832 | 13800 | 1.2435 | 0.513 |
191
+ | 1.2353 | 0.8896 | 13900 | 1.2430 | 0.513 |
192
+ | 1.2311 | 0.896 | 14000 | 1.2426 | 0.513 |
193
+ | 1.2339 | 0.9024 | 14100 | 1.2423 | 0.513 |
194
+ | 1.2386 | 0.9088 | 14200 | 1.2419 | 0.513 |
195
+ | 1.231 | 0.9152 | 14300 | 1.2417 | 0.513 |
196
+ | 1.2398 | 0.9216 | 14400 | 1.2414 | 0.513 |
197
+ | 1.2386 | 0.928 | 14500 | 1.2412 | 0.513 |
198
+ | 1.2354 | 0.9344 | 14600 | 1.2411 | 0.513 |
199
+ | 1.2393 | 0.9408 | 14700 | 1.2409 | 0.513 |
200
+ | 1.2423 | 0.9472 | 14800 | 1.2408 | 0.513 |
201
+ | 1.2333 | 0.9536 | 14900 | 1.2407 | 0.513 |
202
+ | 1.2352 | 0.96 | 15000 | 1.2407 | 0.513 |
203
+ | 1.2411 | 0.9664 | 15100 | 1.2406 | 0.513 |
204
+ | 1.2309 | 0.9728 | 15200 | 1.2406 | 0.513 |
205
+ | 1.2392 | 0.9792 | 15300 | 1.2406 | 0.513 |
206
+ | 1.2381 | 0.9856 | 15400 | 1.2406 | 0.513 |
207
+ | 1.2289 | 0.992 | 15500 | 1.2406 | 0.513 |
208
+ | 1.222 | 0.9984 | 15600 | 1.2406 | 0.513 |
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 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 10,
11
+ "n_head": 1,
12
+ "n_layer": 1,
13
+ "nonlinearity": "RELU",
14
+ "torch_dtype": "float32",
15
+ "transformers_version": "4.46.0",
16
+ "use_NoPE": true,
17
+ "use_layernorm": true,
18
+ "vocab_size": 14
19
+ }
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 sha256:1cc60e1d095fb763e926ddea3de951f0a562f95dbac57385a97023006d32e26d
3
+ size 7960
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:884d122de7688161a7010bff0d99c3caf382edf815b1093470391917f5d2ffb3
3
+ size 5240