Hugging Face's logo

Toflamus
/
GPT-2_para3M_2epoch_256

Text Generation
Transformers
PyTorch
gpt2
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
1
Toflamus commited on
Commit
ab03083
·
1 Parent(s): 2c1649f

Toflamus/GPT-2_para3M_256

Browse files
Files changed (10) hide show
  1. README.md +228 -0
  2. config.json +39 -0
  3. generation_config.json +6 -0
  4. merges.txt +0 -0
  5. pytorch_model.bin +3 -0
  6. special_tokens_map.json +6 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +9 -0
  9. training_args.bin +3 -0
  10. vocab.json +0 -0
README.md ADDED
@@ -0,0 +1,228 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: gpt2
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: GPT-2_para3M_512
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # GPT-2_para3M_512
15
+
16
+ This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 2.1100
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 0.0005
38
+ - train_batch_size: 8
39
+ - eval_batch_size: 8
40
+ - seed: 42
41
+ - gradient_accumulation_steps: 8
42
+ - total_train_batch_size: 64
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: cosine
45
+ - lr_scheduler_warmup_steps: 100
46
+ - num_epochs: 2
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss |
51
+ |:-------------:|:-----:|:-----:|:---------------:|
52
+ | 4.1873 | 0.01 | 500 | 4.0187 |
53
+ | 3.5461 | 0.02 | 1000 | 3.4287 |
54
+ | 3.2706 | 0.04 | 1500 | 3.1495 |
55
+ | 3.105 | 0.05 | 2000 | 2.9773 |
56
+ | 2.9885 | 0.06 | 2500 | 2.8566 |
57
+ | 2.8931 | 0.07 | 3000 | 2.7720 |
58
+ | 2.8307 | 0.08 | 3500 | 2.7016 |
59
+ | 2.7912 | 0.09 | 4000 | 2.6474 |
60
+ | 2.7295 | 0.11 | 4500 | 2.5972 |
61
+ | 2.6927 | 0.12 | 5000 | 2.5641 |
62
+ | 2.6756 | 0.13 | 5500 | 2.5248 |
63
+ | 2.6536 | 0.14 | 6000 | 2.4972 |
64
+ | 2.6186 | 0.15 | 6500 | 2.4730 |
65
+ | 2.5947 | 0.17 | 7000 | 2.4492 |
66
+ | 2.591 | 0.18 | 7500 | 2.4313 |
67
+ | 2.5706 | 0.19 | 8000 | 2.4172 |
68
+ | 2.5441 | 0.2 | 8500 | 2.3991 |
69
+ | 2.5266 | 0.21 | 9000 | 2.3838 |
70
+ | 2.5259 | 0.22 | 9500 | 2.3740 |
71
+ | 2.5173 | 0.24 | 10000 | 2.3629 |
72
+ | 2.5122 | 0.25 | 10500 | 2.3549 |
73
+ | 2.5004 | 0.26 | 11000 | 2.3409 |
74
+ | 2.4902 | 0.27 | 11500 | 2.3364 |
75
+ | 2.4735 | 0.28 | 12000 | 2.3242 |
76
+ | 2.4784 | 0.29 | 12500 | 2.3193 |
77
+ | 2.4754 | 0.31 | 13000 | 2.3126 |
78
+ | 2.4587 | 0.32 | 13500 | 2.3077 |
79
+ | 2.4613 | 0.33 | 14000 | 2.3050 |
80
+ | 2.4562 | 0.34 | 14500 | 2.2968 |
81
+ | 2.4422 | 0.35 | 15000 | 2.2913 |
82
+ | 2.4307 | 0.37 | 15500 | 2.2870 |
83
+ | 2.4339 | 0.38 | 16000 | 2.2814 |
84
+ | 2.445 | 0.39 | 16500 | 2.2801 |
85
+ | 2.4257 | 0.4 | 17000 | 2.2747 |
86
+ | 2.425 | 0.41 | 17500 | 2.2709 |
87
+ | 2.4095 | 0.42 | 18000 | 2.2672 |
88
+ | 2.4137 | 0.44 | 18500 | 2.2632 |
89
+ | 2.4284 | 0.45 | 19000 | 2.2601 |
90
+ | 2.419 | 0.46 | 19500 | 2.2569 |
91
+ | 2.4221 | 0.47 | 20000 | 2.2504 |
92
+ | 2.3951 | 0.48 | 20500 | 2.2507 |
93
+ | 2.4054 | 0.5 | 21000 | 2.2515 |
94
+ | 2.3977 | 0.51 | 21500 | 2.2442 |
95
+ | 2.4009 | 0.52 | 22000 | 2.2422 |
96
+ | 2.3941 | 0.53 | 22500 | 2.2388 |
97
+ | 2.3909 | 0.54 | 23000 | 2.2349 |
98
+ | 2.4016 | 0.55 | 23500 | 2.2380 |
99
+ | 2.389 | 0.57 | 24000 | 2.2326 |
100
+ | 2.3864 | 0.58 | 24500 | 2.2287 |
101
+ | 2.3795 | 0.59 | 25000 | 2.2285 |
102
+ | 2.3817 | 0.6 | 25500 | 2.2266 |
103
+ | 2.3789 | 0.61 | 26000 | 2.2256 |
104
+ | 2.3801 | 0.62 | 26500 | 2.2210 |
105
+ | 2.3687 | 0.64 | 27000 | 2.2189 |
106
+ | 2.378 | 0.65 | 27500 | 2.2194 |
107
+ | 2.3735 | 0.66 | 28000 | 2.2157 |
108
+ | 2.3758 | 0.67 | 28500 | 2.2142 |
109
+ | 2.3616 | 0.68 | 29000 | 2.2133 |
110
+ | 2.3731 | 0.7 | 29500 | 2.2085 |
111
+ | 2.3606 | 0.71 | 30000 | 2.2115 |
112
+ | 2.3516 | 0.72 | 30500 | 2.2072 |
113
+ | 2.3551 | 0.73 | 31000 | 2.2067 |
114
+ | 2.3626 | 0.74 | 31500 | 2.2033 |
115
+ | 2.3516 | 0.75 | 32000 | 2.2031 |
116
+ | 2.3658 | 0.77 | 32500 | 2.2008 |
117
+ | 2.3554 | 0.78 | 33000 | 2.1992 |
118
+ | 2.3524 | 0.79 | 33500 | 2.1988 |
119
+ | 2.3509 | 0.8 | 34000 | 2.1996 |
120
+ | 2.3474 | 0.81 | 34500 | 2.1949 |
121
+ | 2.3431 | 0.83 | 35000 | 2.1943 |
122
+ | 2.3413 | 0.84 | 35500 | 2.1907 |
123
+ | 2.3592 | 0.85 | 36000 | 2.1917 |
124
+ | 2.3636 | 0.86 | 36500 | 2.1919 |
125
+ | 2.3529 | 0.87 | 37000 | 2.1881 |
126
+ | 2.3371 | 0.88 | 37500 | 2.1875 |
127
+ | 2.3413 | 0.9 | 38000 | 2.1856 |
128
+ | 2.3463 | 0.91 | 38500 | 2.1839 |
129
+ | 2.3303 | 0.92 | 39000 | 2.1859 |
130
+ | 2.3432 | 0.93 | 39500 | 2.1790 |
131
+ | 2.3455 | 0.94 | 40000 | 2.1801 |
132
+ | 2.344 | 0.95 | 40500 | 2.1761 |
133
+ | 2.3442 | 0.97 | 41000 | 2.1759 |
134
+ | 2.3331 | 0.98 | 41500 | 2.1760 |
135
+ | 2.3391 | 0.99 | 42000 | 2.1748 |
136
+ | 2.3275 | 1.0 | 42500 | 2.1760 |
137
+ | 2.3308 | 1.01 | 43000 | 2.1712 |
138
+ | 2.3191 | 1.03 | 43500 | 2.1727 |
139
+ | 2.3182 | 1.04 | 44000 | 2.1682 |
140
+ | 2.3184 | 1.05 | 44500 | 2.1683 |
141
+ | 2.3177 | 1.06 | 45000 | 2.1668 |
142
+ | 2.3163 | 1.07 | 45500 | 2.1643 |
143
+ | 2.321 | 1.08 | 46000 | 2.1631 |
144
+ | 2.3164 | 1.1 | 46500 | 2.1655 |
145
+ | 2.3231 | 1.11 | 47000 | 2.1631 |
146
+ | 2.3139 | 1.12 | 47500 | 2.1591 |
147
+ | 2.3223 | 1.13 | 48000 | 2.1588 |
148
+ | 2.3133 | 1.14 | 48500 | 2.1588 |
149
+ | 2.2995 | 1.16 | 49000 | 2.1569 |
150
+ | 2.308 | 1.17 | 49500 | 2.1578 |
151
+ | 2.3062 | 1.18 | 50000 | 2.1539 |
152
+ | 2.3203 | 1.19 | 50500 | 2.1538 |
153
+ | 2.3116 | 1.2 | 51000 | 2.1526 |
154
+ | 2.294 | 1.21 | 51500 | 2.1520 |
155
+ | 2.2941 | 1.23 | 52000 | 2.1499 |
156
+ | 2.3053 | 1.24 | 52500 | 2.1502 |
157
+ | 2.3154 | 1.25 | 53000 | 2.1507 |
158
+ | 2.3057 | 1.26 | 53500 | 2.1485 |
159
+ | 2.3106 | 1.27 | 54000 | 2.1464 |
160
+ | 2.3035 | 1.28 | 54500 | 2.1457 |
161
+ | 2.304 | 1.3 | 55000 | 2.1445 |
162
+ | 2.2985 | 1.31 | 55500 | 2.1439 |
163
+ | 2.296 | 1.32 | 56000 | 2.1421 |
164
+ | 2.2917 | 1.33 | 56500 | 2.1411 |
165
+ | 2.2936 | 1.34 | 57000 | 2.1406 |
166
+ | 2.2866 | 1.36 | 57500 | 2.1383 |
167
+ | 2.2973 | 1.37 | 58000 | 2.1396 |
168
+ | 2.2865 | 1.38 | 58500 | 2.1378 |
169
+ | 2.2929 | 1.39 | 59000 | 2.1370 |
170
+ | 2.2858 | 1.4 | 59500 | 2.1351 |
171
+ | 2.2857 | 1.41 | 60000 | 2.1350 |
172
+ | 2.3019 | 1.43 | 60500 | 2.1338 |
173
+ | 2.289 | 1.44 | 61000 | 2.1330 |
174
+ | 2.2874 | 1.45 | 61500 | 2.1318 |
175
+ | 2.2858 | 1.46 | 62000 | 2.1305 |
176
+ | 2.2875 | 1.47 | 62500 | 2.1298 |
177
+ | 2.2859 | 1.49 | 63000 | 2.1294 |
178
+ | 2.28 | 1.5 | 63500 | 2.1275 |
179
+ | 2.2866 | 1.51 | 64000 | 2.1277 |
180
+ | 2.2851 | 1.52 | 64500 | 2.1281 |
181
+ | 2.2806 | 1.53 | 65000 | 2.1258 |
182
+ | 2.2889 | 1.54 | 65500 | 2.1245 |
183
+ | 2.2745 | 1.56 | 66000 | 2.1249 |
184
+ | 2.2739 | 1.57 | 66500 | 2.1230 |
185
+ | 2.2853 | 1.58 | 67000 | 2.1226 |
186
+ | 2.2773 | 1.59 | 67500 | 2.1228 |
187
+ | 2.2742 | 1.6 | 68000 | 2.1214 |
188
+ | 2.2656 | 1.61 | 68500 | 2.1200 |
189
+ | 2.2756 | 1.63 | 69000 | 2.1194 |
190
+ | 2.2806 | 1.64 | 69500 | 2.1193 |
191
+ | 2.271 | 1.65 | 70000 | 2.1186 |
192
+ | 2.2671 | 1.66 | 70500 | 2.1185 |
193
+ | 2.2718 | 1.67 | 71000 | 2.1168 |
194
+ | 2.2781 | 1.69 | 71500 | 2.1172 |
195
+ | 2.2744 | 1.7 | 72000 | 2.1164 |
196
+ | 2.2744 | 1.71 | 72500 | 2.1156 |
197
+ | 2.2603 | 1.72 | 73000 | 2.1154 |
198
+ | 2.2703 | 1.73 | 73500 | 2.1141 |
199
+ | 2.267 | 1.74 | 74000 | 2.1141 |
200
+ | 2.2614 | 1.76 | 74500 | 2.1141 |
201
+ | 2.263 | 1.77 | 75000 | 2.1133 |
202
+ | 2.2668 | 1.78 | 75500 | 2.1128 |
203
+ | 2.2642 | 1.79 | 76000 | 2.1128 |
204
+ | 2.2637 | 1.8 | 76500 | 2.1128 |
205
+ | 2.2692 | 1.82 | 77000 | 2.1118 |
206
+ | 2.2631 | 1.83 | 77500 | 2.1117 |
207
+ | 2.2567 | 1.84 | 78000 | 2.1116 |
208
+ | 2.2707 | 1.85 | 78500 | 2.1112 |
209
+ | 2.2707 | 1.86 | 79000 | 2.1109 |
210
+ | 2.2664 | 1.87 | 79500 | 2.1114 |
211
+ | 2.266 | 1.89 | 80000 | 2.1113 |
212
+ | 2.2645 | 1.9 | 80500 | 2.1108 |
213
+ | 2.2767 | 1.91 | 81000 | 2.1106 |
214
+ | 2.274 | 1.92 | 81500 | 2.1102 |
215
+ | 2.2587 | 1.93 | 82000 | 2.1102 |
216
+ | 2.2736 | 1.94 | 82500 | 2.1100 |
217
+ | 2.2633 | 1.96 | 83000 | 2.1102 |
218
+ | 2.2652 | 1.97 | 83500 | 2.1100 |
219
+ | 2.2655 | 1.98 | 84000 | 2.1101 |
220
+ | 2.2683 | 1.99 | 84500 | 2.1100 |
221
+
222
+
223
+ ### Framework versions
224
+
225
+ - Transformers 4.32.0
226
+ - Pytorch 2.0.1+cu117
227
+ - Datasets 2.14.4
228
+ - Tokenizers 0.13.2
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 256,
15
+ "n_embd": 64,
16
+ "n_head": 8,
17
+ "n_inner": null,
18
+ "n_layer": 6,
19
+ "n_positions": 1024,
20
+ "reorder_and_upcast_attn": false,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_by_inverse_layer_idx": false,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "task_specific_params": {
30
+ "text-generation": {
31
+ "do_sample": true,
32
+ "max_length": 50
33
+ }
34
+ },
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.32.0",
37
+ "use_cache": true,
38
+ "vocab_size": 50257
39
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.32.0"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7eb5e077ed85648365991e05f202e7b200cee30d76fe05a25b438ef9d38da578
3
+ size 14352341
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "eos_token": "<|endoftext|>",
6
+ "model_max_length": 1024,
7
+ "tokenizer_class": "GPT2Tokenizer",
8
+ "unk_token": "<|endoftext|>"
9
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:178283ad030dc217fe4ba290350184c1c391a77c96388bdee74eed15231ae63c
3
+ size 4027
vocab.json ADDED
The diff for this file is too large to render. See raw diff