Hugging Face's logo

Taeyeun72
/
GPT2_V2

Text Generation
Transformers
Safetensors
Korean
gpt2
Generated from Trainer
text-generation-inference
Model card Files
xet
Community
Taeyeun72 commited on
Commit
b4cfd19
·
1 Parent(s): 79d9804

End of training

Browse files
Files changed (5) hide show
  1. README.md +188 -0
  2. config.json +39 -0
  3. generation_config.json +6 -0
  4. model.safetensors +3 -0
  5. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,188 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - ko
4
+ license: mit
5
+ base_model: gpt2
6
+ tags:
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: gpt2-cs00
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # gpt2-cs00
17
+
18
+ This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the gpt2-cs00 dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 1.3143
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: 5e-05
40
+ - train_batch_size: 4
41
+ - eval_batch_size: 4
42
+ - seed: 42
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - lr_scheduler_warmup_steps: 1000
46
+ - num_epochs: 3
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss |
51
+ |:-------------:|:-----:|:-----:|:---------------:|
52
+ | 11.0601 | 0.02 | 200 | 1.8848 |
53
+ | 1.8408 | 0.05 | 400 | 1.7685 |
54
+ | 1.7219 | 0.07 | 600 | 1.6998 |
55
+ | 1.7133 | 0.09 | 800 | 1.6720 |
56
+ | 1.6776 | 0.12 | 1000 | 1.6420 |
57
+ | 1.6309 | 0.14 | 1200 | 1.7187 |
58
+ | 1.6157 | 0.16 | 1400 | 1.6025 |
59
+ | 1.5546 | 0.18 | 1600 | 1.5661 |
60
+ | 1.4834 | 0.21 | 1800 | 1.5589 |
61
+ | 1.5641 | 0.23 | 2000 | 1.5451 |
62
+ | 1.5133 | 0.25 | 2200 | 1.5195 |
63
+ | 1.5373 | 0.28 | 2400 | 1.5099 |
64
+ | 1.498 | 0.3 | 2600 | 1.5026 |
65
+ | 1.4382 | 0.32 | 2800 | 1.4915 |
66
+ | 1.4585 | 0.35 | 3000 | 1.4937 |
67
+ | 1.4493 | 0.37 | 3200 | 1.4737 |
68
+ | 1.403 | 0.39 | 3400 | 1.4713 |
69
+ | 1.4216 | 0.42 | 3600 | 1.4573 |
70
+ | 1.4204 | 0.44 | 3800 | 1.4684 |
71
+ | 1.5143 | 0.46 | 4000 | 1.4458 |
72
+ | 1.5003 | 0.48 | 4200 | 1.4115 |
73
+ | 1.4828 | 0.51 | 4400 | 1.4446 |
74
+ | 1.4098 | 0.53 | 4600 | 1.4133 |
75
+ | 1.4208 | 0.55 | 4800 | 1.4178 |
76
+ | 1.401 | 0.58 | 5000 | 1.3915 |
77
+ | 1.3639 | 0.6 | 5200 | 1.4326 |
78
+ | 1.3752 | 0.62 | 5400 | 1.3989 |
79
+ | 1.4016 | 0.65 | 5600 | 1.3873 |
80
+ | 1.4157 | 0.67 | 5800 | 1.3792 |
81
+ | 1.4421 | 0.69 | 6000 | 1.3809 |
82
+ | 1.4024 | 0.72 | 6200 | 1.3780 |
83
+ | 1.4031 | 0.74 | 6400 | 1.4014 |
84
+ | 1.4033 | 0.76 | 6600 | 1.4148 |
85
+ | 1.4009 | 0.78 | 6800 | 1.3824 |
86
+ | 1.4519 | 0.81 | 7000 | 1.3795 |
87
+ | 1.377 | 0.83 | 7200 | 1.3762 |
88
+ | 1.4153 | 0.85 | 7400 | 1.3608 |
89
+ | 1.4112 | 0.88 | 7600 | 1.3853 |
90
+ | 1.409 | 0.9 | 7800 | 1.3728 |
91
+ | 1.4125 | 0.92 | 8000 | 1.3661 |
92
+ | 1.3637 | 0.95 | 8200 | 1.3609 |
93
+ | 1.3902 | 0.97 | 8400 | 1.3591 |
94
+ | 1.4463 | 0.99 | 8600 | 1.3665 |
95
+ | 1.3782 | 1.02 | 8800 | 1.3634 |
96
+ | 1.3468 | 1.04 | 9000 | 1.3728 |
97
+ | 1.3339 | 1.06 | 9200 | 1.3712 |
98
+ | 1.3171 | 1.09 | 9400 | 1.3557 |
99
+ | 1.357 | 1.11 | 9600 | 1.3723 |
100
+ | 1.3791 | 1.13 | 9800 | 1.3617 |
101
+ | 1.3888 | 1.15 | 10000 | 1.3477 |
102
+ | 1.3923 | 1.18 | 10200 | 1.3512 |
103
+ | 1.342 | 1.2 | 10400 | 1.3538 |
104
+ | 1.3485 | 1.22 | 10600 | 1.3595 |
105
+ | 1.3523 | 1.25 | 10800 | 1.3623 |
106
+ | 1.3881 | 1.27 | 11000 | 1.3416 |
107
+ | 1.3741 | 1.29 | 11200 | 1.3523 |
108
+ | 1.3869 | 1.32 | 11400 | 1.3442 |
109
+ | 1.3545 | 1.34 | 11600 | 1.3490 |
110
+ | 1.3571 | 1.36 | 11800 | 1.3491 |
111
+ | 1.3396 | 1.39 | 12000 | 1.3510 |
112
+ | 1.3713 | 1.41 | 12200 | 1.3341 |
113
+ | 1.3165 | 1.43 | 12400 | 1.3376 |
114
+ | 1.3236 | 1.45 | 12600 | 1.3364 |
115
+ | 1.3028 | 1.48 | 12800 | 1.3322 |
116
+ | 1.3671 | 1.5 | 13000 | 1.3403 |
117
+ | 1.3295 | 1.52 | 13200 | 1.3377 |
118
+ | 1.3807 | 1.55 | 13400 | 1.3264 |
119
+ | 1.3714 | 1.57 | 13600 | 1.3271 |
120
+ | 1.3249 | 1.59 | 13800 | 1.3388 |
121
+ | 1.3656 | 1.62 | 14000 | 1.3319 |
122
+ | 1.2864 | 1.64 | 14200 | 1.3321 |
123
+ | 1.352 | 1.66 | 14400 | 1.3497 |
124
+ | 1.3599 | 1.69 | 14600 | 1.3268 |
125
+ | 1.3191 | 1.71 | 14800 | 1.3339 |
126
+ | 1.3136 | 1.73 | 15000 | 1.3336 |
127
+ | 1.3338 | 1.75 | 15200 | 1.3265 |
128
+ | 1.3528 | 1.78 | 15400 | 1.3363 |
129
+ | 1.3538 | 1.8 | 15600 | 1.3196 |
130
+ | 1.2879 | 1.82 | 15800 | 1.3335 |
131
+ | 1.3217 | 1.85 | 16000 | 1.3376 |
132
+ | 1.3657 | 1.87 | 16200 | 1.3257 |
133
+ | 1.3351 | 1.89 | 16400 | 1.3262 |
134
+ | 1.3469 | 1.92 | 16600 | 1.3299 |
135
+ | 1.3053 | 1.94 | 16800 | 1.3329 |
136
+ | 1.3332 | 1.96 | 17000 | 1.3212 |
137
+ | 1.3466 | 1.99 | 17200 | 1.3317 |
138
+ | 1.3743 | 2.01 | 17400 | 1.3302 |
139
+ | 1.3227 | 2.03 | 17600 | 1.3332 |
140
+ | 1.2728 | 2.05 | 17800 | 1.3450 |
141
+ | 1.3239 | 2.08 | 18000 | 1.3414 |
142
+ | 1.3661 | 2.1 | 18200 | 1.3243 |
143
+ | 1.298 | 2.12 | 18400 | 1.3315 |
144
+ | 1.2974 | 2.15 | 18600 | 1.3310 |
145
+ | 1.3174 | 2.17 | 18800 | 1.3224 |
146
+ | 1.3121 | 2.19 | 19000 | 1.3233 |
147
+ | 1.3527 | 2.22 | 19200 | 1.3211 |
148
+ | 1.3712 | 2.24 | 19400 | 1.3143 |
149
+ | 1.2873 | 2.26 | 19600 | 1.3302 |
150
+ | 1.306 | 2.29 | 19800 | 1.3211 |
151
+ | 1.3161 | 2.31 | 20000 | 1.3242 |
152
+ | 1.308 | 2.33 | 20200 | 1.3176 |
153
+ | 1.3403 | 2.35 | 20400 | 1.3143 |
154
+ | 1.3688 | 2.38 | 20600 | 1.3195 |
155
+ | 1.2743 | 2.4 | 20800 | 1.3230 |
156
+ | 1.2892 | 2.42 | 21000 | 1.3287 |
157
+ | 1.3782 | 2.45 | 21200 | 1.3137 |
158
+ | 1.3331 | 2.47 | 21400 | 1.3148 |
159
+ | 1.3182 | 2.49 | 21600 | 1.3220 |
160
+ | 1.2542 | 2.52 | 21800 | 1.3332 |
161
+ | 1.2879 | 2.54 | 22000 | 1.3229 |
162
+ | 1.316 | 2.56 | 22200 | 1.3181 |
163
+ | 1.2989 | 2.59 | 22400 | 1.3155 |
164
+ | 1.3095 | 2.61 | 22600 | 1.3218 |
165
+ | 1.2457 | 2.63 | 22800 | 1.3185 |
166
+ | 1.3053 | 2.65 | 23000 | 1.3168 |
167
+ | 1.3036 | 2.68 | 23200 | 1.3180 |
168
+ | 1.2861 | 2.7 | 23400 | 1.3117 |
169
+ | 1.3 | 2.72 | 23600 | 1.3208 |
170
+ | 1.3026 | 2.75 | 23800 | 1.3147 |
171
+ | 1.3006 | 2.77 | 24000 | 1.3211 |
172
+ | 1.3477 | 2.79 | 24200 | 1.3140 |
173
+ | 1.2851 | 2.82 | 24400 | 1.3208 |
174
+ | 1.2859 | 2.84 | 24600 | 1.3172 |
175
+ | 1.3286 | 2.86 | 24800 | 1.3151 |
176
+ | 1.3237 | 2.89 | 25000 | 1.3148 |
177
+ | 1.3503 | 2.91 | 25200 | 1.3133 |
178
+ | 1.27 | 2.93 | 25400 | 1.3138 |
179
+ | 1.2998 | 2.96 | 25600 | 1.3151 |
180
+ | 1.3461 | 2.98 | 25800 | 1.3143 |
181
+
182
+
183
+ ### Framework versions
184
+
185
+ - Transformers 4.35.2
186
+ - Pytorch 2.1.1+cu118
187
+ - Datasets 2.15.0
188
+ - Tokenizers 0.15.0
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": 1024,
15
+ "n_embd": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
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": "4.35.2",
37
+ "use_cache": true,
38
+ "vocab_size": 50258
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": "4.35.2"
6
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc0efc639a6bb004591e06e379574f4f68678efc62435e09aa694e9aee2c5d7
3
+ size 497777280
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:458eb23722a24431097ea85aadf859e46a533366f3b0899d80e4db9759b5e85a
3
+ size 4536