Hugging Face's logo

TrLOX
/
gpt2-tdk

Text Generation
Transformers
PyTorch
gpt2
generated_from_trainer
Inference Endpoints
text-generation-inference
Model card Files Community
1
TrLOX commited on
Commit
ff265b2
•
1 Parent(s): 1f48e15

Update from

Browse files
Files changed (12) hide show
  1. README.md +57 -0
  2. all_results.json +8 -0
  3. config.json +46 -0
  4. merges.txt +0 -0
  5. pytorch_model.bin +3 -0
  6. special_tokens_map.json +1 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +1 -0
  9. train_results.json +8 -0
  10. trainer_state.json +403 -0
  11. training_args.bin +3 -0
  12. vocab.json +0 -0
README.md ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: dgpt
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # dgpt
14
+
15
+ This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset.
16
+
17
+ ## Model description
18
+
19
+ More information needed
20
+
21
+ ## Intended uses & limitations
22
+
23
+ More information needed
24
+
25
+ ## Training and evaluation data
26
+
27
+ More information needed
28
+
29
+ ## Training procedure
30
+
31
+ ### Training hyperparameters
32
+
33
+ The following hyperparameters were used during training:
34
+ - learning_rate: 5e-05
35
+ - train_batch_size: 2
36
+ - eval_batch_size: 8
37
+ - seed: 42
38
+ - distributed_type: tpu
39
+ - num_devices: 8
40
+ - total_train_batch_size: 16
41
+ - total_eval_batch_size: 64
42
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
+ - lr_scheduler_type: linear
44
+ - num_epochs: 10.0
45
+
46
+ ### Training results
47
+
48
+
49
+
50
+ ### Framework versions
51
+
52
+ - Transformers 4.14.0.dev0
53
+ - Pytorch 1.9.0+cu102
54
+ - Datasets 1.16.2.dev0
55
+ - Tokenizers 0.10.3
56
+ hello
57
+ hello
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "train_loss": 2.2214493739870194,
4
+ "train_runtime": 13454.7366,
5
+ "train_samples": 51053,
6
+ "train_samples_per_second": 37.944,
7
+ "train_steps_per_second": 2.372
8
+ }
config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilgpt2",
3
+ "_num_labels": 1,
4
+ "activation_function": "gelu_new",
5
+ "architectures": [
6
+ "GPT2LMHeadModel"
7
+ ],
8
+ "attn_pdrop": 0.1,
9
+ "bos_token_id": 50256,
10
+ "embd_pdrop": 0.1,
11
+ "eos_token_id": 50256,
12
+ "id2label": {
13
+ "0": "LABEL_0"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "label2id": {
17
+ "LABEL_0": 0
18
+ },
19
+ "layer_norm_epsilon": 1e-05,
20
+ "model_type": "gpt2",
21
+ "n_ctx": 1024,
22
+ "n_embd": 768,
23
+ "n_head": 12,
24
+ "n_inner": null,
25
+ "n_layer": 6,
26
+ "n_positions": 1024,
27
+ "reorder_and_upcast_attn": false,
28
+ "resid_pdrop": 0.1,
29
+ "scale_attn_by_inverse_layer_idx": false,
30
+ "scale_attn_weights": true,
31
+ "summary_activation": null,
32
+ "summary_first_dropout": 0.1,
33
+ "summary_proj_to_labels": true,
34
+ "summary_type": "cls_index",
35
+ "summary_use_proj": true,
36
+ "task_specific_params": {
37
+ "text-generation": {
38
+ "do_sample": true,
39
+ "max_length": 50
40
+ }
41
+ },
42
+ "torch_dtype": "float32",
43
+ "transformers_version": "4.14.0.dev0",
44
+ "use_cache": true,
45
+ "vocab_size": 50257
46
+ }
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:a2f92bdf3010a5e3398bf312885bd63fe9ca50024e29baecc03fbd055ef2e4ea
3
+ size 488357594
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "distilgpt2", "tokenizer_class": "GPT2Tokenizer"}
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "train_loss": 2.2214493739870194,
4
+ "train_runtime": 13454.7366,
5
+ "train_samples": 51053,
6
+ "train_samples_per_second": 37.944,
7
+ "train_steps_per_second": 2.372
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,403 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 10.0,
5
+ "global_step": 31910,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.16,
12
+ "learning_rate": 4.9216546537135696e-05,
13
+ "loss": 3.1564,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.31,
18
+ "learning_rate": 4.843309307427139e-05,
19
+ "loss": 2.8629,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.47,
24
+ "learning_rate": 4.764963961140708e-05,
25
+ "loss": 2.7321,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.63,
30
+ "learning_rate": 4.6866186148542776e-05,
31
+ "loss": 2.657,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.78,
36
+ "learning_rate": 4.608273268567847e-05,
37
+ "loss": 2.6045,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.94,
42
+ "learning_rate": 4.529927922281417e-05,
43
+ "loss": 2.5492,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 1.1,
48
+ "learning_rate": 4.4515825759949856e-05,
49
+ "loss": 2.5043,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 1.25,
54
+ "learning_rate": 4.3732372297085556e-05,
55
+ "loss": 2.4617,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 1.41,
60
+ "learning_rate": 4.294891883422125e-05,
61
+ "loss": 2.4395,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 1.57,
66
+ "learning_rate": 4.216546537135694e-05,
67
+ "loss": 2.4319,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 1.72,
72
+ "learning_rate": 4.1382011908492636e-05,
73
+ "loss": 2.3865,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 1.88,
78
+ "learning_rate": 4.059855844562833e-05,
79
+ "loss": 2.3805,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 2.04,
84
+ "learning_rate": 3.981510498276402e-05,
85
+ "loss": 2.3441,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 2.19,
90
+ "learning_rate": 3.903165151989972e-05,
91
+ "loss": 2.3244,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 2.35,
96
+ "learning_rate": 3.824819805703541e-05,
97
+ "loss": 2.3225,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 2.51,
102
+ "learning_rate": 3.746474459417111e-05,
103
+ "loss": 2.2977,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 2.66,
108
+ "learning_rate": 3.66812911313068e-05,
109
+ "loss": 2.2783,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 2.82,
114
+ "learning_rate": 3.5897837668442496e-05,
115
+ "loss": 2.2706,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 2.98,
120
+ "learning_rate": 3.511438420557819e-05,
121
+ "loss": 2.26,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 3.13,
126
+ "learning_rate": 3.433093074271388e-05,
127
+ "loss": 2.2494,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 3.29,
132
+ "learning_rate": 3.3547477279849576e-05,
133
+ "loss": 2.2223,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 3.45,
138
+ "learning_rate": 3.2764023816985276e-05,
139
+ "loss": 2.2247,
140
+ "step": 11000
141
+ },
142
+ {
143
+ "epoch": 3.6,
144
+ "learning_rate": 3.198057035412096e-05,
145
+ "loss": 2.223,
146
+ "step": 11500
147
+ },
148
+ {
149
+ "epoch": 3.76,
150
+ "learning_rate": 3.119711689125666e-05,
151
+ "loss": 2.1946,
152
+ "step": 12000
153
+ },
154
+ {
155
+ "epoch": 3.92,
156
+ "learning_rate": 3.0413663428392353e-05,
157
+ "loss": 2.2036,
158
+ "step": 12500
159
+ },
160
+ {
161
+ "epoch": 4.07,
162
+ "learning_rate": 2.963020996552805e-05,
163
+ "loss": 2.1822,
164
+ "step": 13000
165
+ },
166
+ {
167
+ "epoch": 4.23,
168
+ "learning_rate": 2.884675650266374e-05,
169
+ "loss": 2.1706,
170
+ "step": 13500
171
+ },
172
+ {
173
+ "epoch": 4.39,
174
+ "learning_rate": 2.8063303039799436e-05,
175
+ "loss": 2.1655,
176
+ "step": 14000
177
+ },
178
+ {
179
+ "epoch": 4.54,
180
+ "learning_rate": 2.727984957693513e-05,
181
+ "loss": 2.1517,
182
+ "step": 14500
183
+ },
184
+ {
185
+ "epoch": 4.7,
186
+ "learning_rate": 2.6496396114070827e-05,
187
+ "loss": 2.1619,
188
+ "step": 15000
189
+ },
190
+ {
191
+ "epoch": 4.86,
192
+ "learning_rate": 2.5712942651206517e-05,
193
+ "loss": 2.1518,
194
+ "step": 15500
195
+ },
196
+ {
197
+ "epoch": 5.01,
198
+ "learning_rate": 2.4929489188342213e-05,
199
+ "loss": 2.1542,
200
+ "step": 16000
201
+ },
202
+ {
203
+ "epoch": 5.17,
204
+ "learning_rate": 2.414603572547791e-05,
205
+ "loss": 2.1407,
206
+ "step": 16500
207
+ },
208
+ {
209
+ "epoch": 5.33,
210
+ "learning_rate": 2.3362582262613603e-05,
211
+ "loss": 2.1297,
212
+ "step": 17000
213
+ },
214
+ {
215
+ "epoch": 5.48,
216
+ "learning_rate": 2.2579128799749297e-05,
217
+ "loss": 2.1235,
218
+ "step": 17500
219
+ },
220
+ {
221
+ "epoch": 5.64,
222
+ "learning_rate": 2.179567533688499e-05,
223
+ "loss": 2.1185,
224
+ "step": 18000
225
+ },
226
+ {
227
+ "epoch": 5.8,
228
+ "learning_rate": 2.1012221874020683e-05,
229
+ "loss": 2.1085,
230
+ "step": 18500
231
+ },
232
+ {
233
+ "epoch": 5.95,
234
+ "learning_rate": 2.022876841115638e-05,
235
+ "loss": 2.1073,
236
+ "step": 19000
237
+ },
238
+ {
239
+ "epoch": 6.11,
240
+ "learning_rate": 1.9445314948292073e-05,
241
+ "loss": 2.0961,
242
+ "step": 19500
243
+ },
244
+ {
245
+ "epoch": 6.27,
246
+ "learning_rate": 1.8661861485427767e-05,
247
+ "loss": 2.0912,
248
+ "step": 20000
249
+ },
250
+ {
251
+ "epoch": 6.42,
252
+ "learning_rate": 1.787840802256346e-05,
253
+ "loss": 2.0957,
254
+ "step": 20500
255
+ },
256
+ {
257
+ "epoch": 6.58,
258
+ "learning_rate": 1.7094954559699157e-05,
259
+ "loss": 2.0874,
260
+ "step": 21000
261
+ },
262
+ {
263
+ "epoch": 6.74,
264
+ "learning_rate": 1.631150109683485e-05,
265
+ "loss": 2.0912,
266
+ "step": 21500
267
+ },
268
+ {
269
+ "epoch": 6.89,
270
+ "learning_rate": 1.5528047633970544e-05,
271
+ "loss": 2.0849,
272
+ "step": 22000
273
+ },
274
+ {
275
+ "epoch": 7.05,
276
+ "learning_rate": 1.4744594171106239e-05,
277
+ "loss": 2.0867,
278
+ "step": 22500
279
+ },
280
+ {
281
+ "epoch": 7.21,
282
+ "learning_rate": 1.3961140708241932e-05,
283
+ "loss": 2.0729,
284
+ "step": 23000
285
+ },
286
+ {
287
+ "epoch": 7.36,
288
+ "learning_rate": 1.3177687245377627e-05,
289
+ "loss": 2.0824,
290
+ "step": 23500
291
+ },
292
+ {
293
+ "epoch": 7.52,
294
+ "learning_rate": 1.2394233782513319e-05,
295
+ "loss": 2.0678,
296
+ "step": 24000
297
+ },
298
+ {
299
+ "epoch": 7.68,
300
+ "learning_rate": 1.1610780319649014e-05,
301
+ "loss": 2.0553,
302
+ "step": 24500
303
+ },
304
+ {
305
+ "epoch": 7.83,
306
+ "learning_rate": 1.0827326856784707e-05,
307
+ "loss": 2.0678,
308
+ "step": 25000
309
+ },
310
+ {
311
+ "epoch": 7.99,
312
+ "learning_rate": 1.0043873393920402e-05,
313
+ "loss": 2.0624,
314
+ "step": 25500
315
+ },
316
+ {
317
+ "epoch": 8.15,
318
+ "learning_rate": 9.260419931056095e-06,
319
+ "loss": 2.0681,
320
+ "step": 26000
321
+ },
322
+ {
323
+ "epoch": 8.3,
324
+ "learning_rate": 8.476966468191789e-06,
325
+ "loss": 2.0587,
326
+ "step": 26500
327
+ },
328
+ {
329
+ "epoch": 8.46,
330
+ "learning_rate": 7.693513005327484e-06,
331
+ "loss": 2.0504,
332
+ "step": 27000
333
+ },
334
+ {
335
+ "epoch": 8.62,
336
+ "learning_rate": 6.910059542463178e-06,
337
+ "loss": 2.0483,
338
+ "step": 27500
339
+ },
340
+ {
341
+ "epoch": 8.77,
342
+ "learning_rate": 6.126606079598872e-06,
343
+ "loss": 2.0504,
344
+ "step": 28000
345
+ },
346
+ {
347
+ "epoch": 8.93,
348
+ "learning_rate": 5.3431526167345665e-06,
349
+ "loss": 2.0539,
350
+ "step": 28500
351
+ },
352
+ {
353
+ "epoch": 9.09,
354
+ "learning_rate": 4.55969915387026e-06,
355
+ "loss": 2.0507,
356
+ "step": 29000
357
+ },
358
+ {
359
+ "epoch": 9.24,
360
+ "learning_rate": 3.7762456910059544e-06,
361
+ "loss": 2.0396,
362
+ "step": 29500
363
+ },
364
+ {
365
+ "epoch": 9.4,
366
+ "learning_rate": 2.9927922281416486e-06,
367
+ "loss": 2.0538,
368
+ "step": 30000
369
+ },
370
+ {
371
+ "epoch": 9.56,
372
+ "learning_rate": 2.2093387652773424e-06,
373
+ "loss": 2.0514,
374
+ "step": 30500
375
+ },
376
+ {
377
+ "epoch": 9.71,
378
+ "learning_rate": 1.4258853024130368e-06,
379
+ "loss": 2.0394,
380
+ "step": 31000
381
+ },
382
+ {
383
+ "epoch": 9.87,
384
+ "learning_rate": 6.424318395487308e-07,
385
+ "loss": 2.048,
386
+ "step": 31500
387
+ },
388
+ {
389
+ "epoch": 10.0,
390
+ "step": 31910,
391
+ "total_flos": 1.667595862278144e+16,
392
+ "train_loss": 2.2214493739870194,
393
+ "train_runtime": 13454.7366,
394
+ "train_samples_per_second": 37.944,
395
+ "train_steps_per_second": 2.372
396
+ }
397
+ ],
398
+ "max_steps": 31910,
399
+ "num_train_epochs": 10,
400
+ "total_flos": 1.667595862278144e+16,
401
+ "trial_name": null,
402
+ "trial_params": null
403
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b87a29ffa77ca1907fdf31adb35ec651d000a8e4650b6f59edce992c6a028b06
3
+ size 2927
vocab.json ADDED
The diff for this file is too large to render. See raw diff