Hugging Face's logo

etmckinley
/
BOTHALTEROUT

Text Generation Transformers PyTorch TensorBoard gpt2 Inference Endpoints text-generation-inference
Model card Files Metrics Community
1
etmckinley commited on
Commit
ae415b9
•
1 Parent(s): 8d44cbb

Training in progress, step 500

Browse files
Files changed (23) hide show
  1. .gitignore +1 -0
  2. config.json +43 -0
  3. last-checkpoint/config.json +43 -0
  4. last-checkpoint/merges.txt +0 -0
  5. last-checkpoint/optimizer.pt +3 -0
  6. last-checkpoint/pytorch_model.bin +3 -0
  7. last-checkpoint/rng_state.pth +3 -0
  8. last-checkpoint/scheduler.pt +3 -0
  9. last-checkpoint/special_tokens_map.json +1 -0
  10. last-checkpoint/tokenizer.json +0 -0
  11. last-checkpoint/tokenizer_config.json +1 -0
  12. last-checkpoint/trainer_state.json +616 -0
  13. last-checkpoint/training_args.bin +3 -0
  14. last-checkpoint/vocab.json +0 -0
  15. merges.txt +0 -0
  16. pytorch_model.bin +3 -0
  17. runs/Jun02_18-32-12_0076a51e6274/1654194775.362782/events.out.tfevents.1654194775.0076a51e6274.73.4 +3 -0
  18. runs/Jun02_18-32-12_0076a51e6274/events.out.tfevents.1654194775.0076a51e6274.73.3 +3 -0
  19. special_tokens_map.json +1 -0
  20. tokenizer.json +0 -0
  21. tokenizer_config.json +1 -0
  22. training_args.bin +3 -0
  23. vocab.json +0 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 160,
33
+ "min_length": 10,
34
+ "prefix": "<|endoftext|>",
35
+ "temperature": 1.0,
36
+ "top_p": 0.95
37
+ }
38
+ },
39
+ "torch_dtype": "float32",
40
+ "transformers_version": "4.19.2",
41
+ "use_cache": true,
42
+ "vocab_size": 50257
43
+ }
last-checkpoint/config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 160,
33
+ "min_length": 10,
34
+ "prefix": "<|endoftext|>",
35
+ "temperature": 1.0,
36
+ "top_p": 0.95
37
+ }
38
+ },
39
+ "torch_dtype": "float32",
40
+ "transformers_version": "4.19.2",
41
+ "use_cache": true,
42
+ "vocab_size": 50257
43
+ }
last-checkpoint/merges.txt ADDED
The diff for this file is too large to render. See raw diff
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f4e148e89bf9e7f10b4d83f050549d08743c5d0e3a959a248848f7f8f1a7ea7
3
+ size 995604017
last-checkpoint/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49c391befd6890f902bb453609f9bf21692247faccf132ff190c2d68e4e38d5c
3
+ size 510396521
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4614a7bdbd7606e79d95b5d778da9fdec49f736f92446714a188482d1eb4ae1f
3
+ size 14503
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a68ae7ef7105b6b5b211c27ebcdb59f6c1620607e320f3ae8a96d70afbb3dfa4
3
+ size 623
last-checkpoint/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}
last-checkpoint/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
last-checkpoint/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": "gpt2", "tokenizer_class": "GPT2Tokenizer"}
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,616 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.07046223224351747,
5
+ "global_step": 500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.0,
12
+ "learning_rate": 0.0001371033258173619,
13
+ "loss": 5.0827,
14
+ "step": 5
15
+ },
16
+ {
17
+ "epoch": 0.0,
18
+ "learning_rate": 0.00013700665163472378,
19
+ "loss": 4.5803,
20
+ "step": 10
21
+ },
22
+ {
23
+ "epoch": 0.0,
24
+ "learning_rate": 0.0001369099774520857,
25
+ "loss": 4.4629,
26
+ "step": 15
27
+ },
28
+ {
29
+ "epoch": 0.0,
30
+ "learning_rate": 0.00013681330326944757,
31
+ "loss": 4.4134,
32
+ "step": 20
33
+ },
34
+ {
35
+ "epoch": 0.0,
36
+ "learning_rate": 0.00013671662908680947,
37
+ "loss": 4.4621,
38
+ "step": 25
39
+ },
40
+ {
41
+ "epoch": 0.0,
42
+ "learning_rate": 0.00013661995490417137,
43
+ "loss": 4.3721,
44
+ "step": 30
45
+ },
46
+ {
47
+ "epoch": 0.0,
48
+ "learning_rate": 0.00013652328072153325,
49
+ "loss": 4.4321,
50
+ "step": 35
51
+ },
52
+ {
53
+ "epoch": 0.01,
54
+ "learning_rate": 0.00013642660653889516,
55
+ "loss": 4.4731,
56
+ "step": 40
57
+ },
58
+ {
59
+ "epoch": 0.01,
60
+ "learning_rate": 0.00013632993235625703,
61
+ "loss": 4.2376,
62
+ "step": 45
63
+ },
64
+ {
65
+ "epoch": 0.01,
66
+ "learning_rate": 0.00013623325817361894,
67
+ "loss": 4.0939,
68
+ "step": 50
69
+ },
70
+ {
71
+ "epoch": 0.01,
72
+ "learning_rate": 0.00013613658399098084,
73
+ "loss": 4.0892,
74
+ "step": 55
75
+ },
76
+ {
77
+ "epoch": 0.01,
78
+ "learning_rate": 0.00013603990980834272,
79
+ "loss": 4.0892,
80
+ "step": 60
81
+ },
82
+ {
83
+ "epoch": 0.01,
84
+ "learning_rate": 0.00013594323562570463,
85
+ "loss": 3.9798,
86
+ "step": 65
87
+ },
88
+ {
89
+ "epoch": 0.01,
90
+ "learning_rate": 0.0001358465614430665,
91
+ "loss": 4.0047,
92
+ "step": 70
93
+ },
94
+ {
95
+ "epoch": 0.01,
96
+ "learning_rate": 0.0001357498872604284,
97
+ "loss": 4.0813,
98
+ "step": 75
99
+ },
100
+ {
101
+ "epoch": 0.01,
102
+ "learning_rate": 0.00013565321307779029,
103
+ "loss": 4.1708,
104
+ "step": 80
105
+ },
106
+ {
107
+ "epoch": 0.01,
108
+ "learning_rate": 0.0001355565388951522,
109
+ "loss": 3.9233,
110
+ "step": 85
111
+ },
112
+ {
113
+ "epoch": 0.01,
114
+ "learning_rate": 0.0001354598647125141,
115
+ "loss": 4.0628,
116
+ "step": 90
117
+ },
118
+ {
119
+ "epoch": 0.01,
120
+ "learning_rate": 0.000135363190529876,
121
+ "loss": 3.9585,
122
+ "step": 95
123
+ },
124
+ {
125
+ "epoch": 0.01,
126
+ "learning_rate": 0.00013526651634723788,
127
+ "loss": 3.8871,
128
+ "step": 100
129
+ },
130
+ {
131
+ "epoch": 0.01,
132
+ "learning_rate": 0.00013516984216459978,
133
+ "loss": 3.6986,
134
+ "step": 105
135
+ },
136
+ {
137
+ "epoch": 0.02,
138
+ "learning_rate": 0.0001350731679819617,
139
+ "loss": 4.1341,
140
+ "step": 110
141
+ },
142
+ {
143
+ "epoch": 0.02,
144
+ "learning_rate": 0.00013497649379932356,
145
+ "loss": 3.706,
146
+ "step": 115
147
+ },
148
+ {
149
+ "epoch": 0.02,
150
+ "learning_rate": 0.00013487981961668547,
151
+ "loss": 3.9725,
152
+ "step": 120
153
+ },
154
+ {
155
+ "epoch": 0.02,
156
+ "learning_rate": 0.00013478314543404735,
157
+ "loss": 3.8891,
158
+ "step": 125
159
+ },
160
+ {
161
+ "epoch": 0.02,
162
+ "learning_rate": 0.00013468647125140925,
163
+ "loss": 3.6647,
164
+ "step": 130
165
+ },
166
+ {
167
+ "epoch": 0.02,
168
+ "learning_rate": 0.00013458979706877116,
169
+ "loss": 4.0744,
170
+ "step": 135
171
+ },
172
+ {
173
+ "epoch": 0.02,
174
+ "learning_rate": 0.00013449312288613303,
175
+ "loss": 3.9036,
176
+ "step": 140
177
+ },
178
+ {
179
+ "epoch": 0.02,
180
+ "learning_rate": 0.00013439644870349494,
181
+ "loss": 3.5998,
182
+ "step": 145
183
+ },
184
+ {
185
+ "epoch": 0.02,
186
+ "learning_rate": 0.00013429977452085682,
187
+ "loss": 3.7786,
188
+ "step": 150
189
+ },
190
+ {
191
+ "epoch": 0.02,
192
+ "learning_rate": 0.00013420310033821872,
193
+ "loss": 3.8889,
194
+ "step": 155
195
+ },
196
+ {
197
+ "epoch": 0.02,
198
+ "learning_rate": 0.00013410642615558062,
199
+ "loss": 3.8426,
200
+ "step": 160
201
+ },
202
+ {
203
+ "epoch": 0.02,
204
+ "learning_rate": 0.0001340097519729425,
205
+ "loss": 3.8768,
206
+ "step": 165
207
+ },
208
+ {
209
+ "epoch": 0.02,
210
+ "learning_rate": 0.0001339130777903044,
211
+ "loss": 3.8531,
212
+ "step": 170
213
+ },
214
+ {
215
+ "epoch": 0.02,
216
+ "learning_rate": 0.00013381640360766628,
217
+ "loss": 3.6838,
218
+ "step": 175
219
+ },
220
+ {
221
+ "epoch": 0.03,
222
+ "learning_rate": 0.0001337197294250282,
223
+ "loss": 3.7136,
224
+ "step": 180
225
+ },
226
+ {
227
+ "epoch": 0.03,
228
+ "learning_rate": 0.00013362305524239007,
229
+ "loss": 3.5738,
230
+ "step": 185
231
+ },
232
+ {
233
+ "epoch": 0.03,
234
+ "learning_rate": 0.00013352638105975197,
235
+ "loss": 3.5853,
236
+ "step": 190
237
+ },
238
+ {
239
+ "epoch": 0.03,
240
+ "learning_rate": 0.00013342970687711388,
241
+ "loss": 3.6714,
242
+ "step": 195
243
+ },
244
+ {
245
+ "epoch": 0.03,
246
+ "learning_rate": 0.00013333303269447575,
247
+ "loss": 3.7698,
248
+ "step": 200
249
+ },
250
+ {
251
+ "epoch": 0.03,
252
+ "learning_rate": 0.00013323635851183766,
253
+ "loss": 3.6374,
254
+ "step": 205
255
+ },
256
+ {
257
+ "epoch": 0.03,
258
+ "learning_rate": 0.00013313968432919954,
259
+ "loss": 3.6598,
260
+ "step": 210
261
+ },
262
+ {
263
+ "epoch": 0.03,
264
+ "learning_rate": 0.00013304301014656144,
265
+ "loss": 3.8166,
266
+ "step": 215
267
+ },
268
+ {
269
+ "epoch": 0.03,
270
+ "learning_rate": 0.00013294633596392335,
271
+ "loss": 3.7615,
272
+ "step": 220
273
+ },
274
+ {
275
+ "epoch": 0.03,
276
+ "learning_rate": 0.00013284966178128522,
277
+ "loss": 3.505,
278
+ "step": 225
279
+ },
280
+ {
281
+ "epoch": 0.03,
282
+ "learning_rate": 0.00013275298759864713,
283
+ "loss": 3.7888,
284
+ "step": 230
285
+ },
286
+ {
287
+ "epoch": 0.03,
288
+ "learning_rate": 0.000132656313416009,
289
+ "loss": 3.7419,
290
+ "step": 235
291
+ },
292
+ {
293
+ "epoch": 0.03,
294
+ "learning_rate": 0.0001325596392333709,
295
+ "loss": 3.6353,
296
+ "step": 240
297
+ },
298
+ {
299
+ "epoch": 0.03,
300
+ "learning_rate": 0.00013246296505073281,
301
+ "loss": 3.6078,
302
+ "step": 245
303
+ },
304
+ {
305
+ "epoch": 0.04,
306
+ "learning_rate": 0.0001323662908680947,
307
+ "loss": 3.6796,
308
+ "step": 250
309
+ },
310
+ {
311
+ "epoch": 0.04,
312
+ "learning_rate": 0.0001322696166854566,
313
+ "loss": 3.4874,
314
+ "step": 255
315
+ },
316
+ {
317
+ "epoch": 0.04,
318
+ "learning_rate": 0.00013217294250281847,
319
+ "loss": 3.6487,
320
+ "step": 260
321
+ },
322
+ {
323
+ "epoch": 0.04,
324
+ "learning_rate": 0.00013207626832018038,
325
+ "loss": 3.6231,
326
+ "step": 265
327
+ },
328
+ {
329
+ "epoch": 0.04,
330
+ "learning_rate": 0.00013197959413754228,
331
+ "loss": 3.092,
332
+ "step": 270
333
+ },
334
+ {
335
+ "epoch": 0.04,
336
+ "learning_rate": 0.00013188291995490416,
337
+ "loss": 3.6174,
338
+ "step": 275
339
+ },
340
+ {
341
+ "epoch": 0.04,
342
+ "learning_rate": 0.00013178624577226607,
343
+ "loss": 3.5277,
344
+ "step": 280
345
+ },
346
+ {
347
+ "epoch": 0.04,
348
+ "learning_rate": 0.00013168957158962797,
349
+ "loss": 3.5095,
350
+ "step": 285
351
+ },
352
+ {
353
+ "epoch": 0.04,
354
+ "learning_rate": 0.00013159289740698985,
355
+ "loss": 3.5402,
356
+ "step": 290
357
+ },
358
+ {
359
+ "epoch": 0.04,
360
+ "learning_rate": 0.00013149622322435175,
361
+ "loss": 3.6156,
362
+ "step": 295
363
+ },
364
+ {
365
+ "epoch": 0.04,
366
+ "learning_rate": 0.00013139954904171366,
367
+ "loss": 3.6664,
368
+ "step": 300
369
+ },
370
+ {
371
+ "epoch": 0.04,
372
+ "learning_rate": 0.00013130287485907553,
373
+ "loss": 3.4951,
374
+ "step": 305
375
+ },
376
+ {
377
+ "epoch": 0.04,
378
+ "learning_rate": 0.00013120620067643744,
379
+ "loss": 3.4296,
380
+ "step": 310
381
+ },
382
+ {
383
+ "epoch": 0.04,
384
+ "learning_rate": 0.00013110952649379932,
385
+ "loss": 3.6549,
386
+ "step": 315
387
+ },
388
+ {
389
+ "epoch": 0.05,
390
+ "learning_rate": 0.00013101285231116122,
391
+ "loss": 3.3626,
392
+ "step": 320
393
+ },
394
+ {
395
+ "epoch": 0.05,
396
+ "learning_rate": 0.00013091617812852313,
397
+ "loss": 3.4253,
398
+ "step": 325
399
+ },
400
+ {
401
+ "epoch": 0.05,
402
+ "learning_rate": 0.000130819503945885,
403
+ "loss": 3.6132,
404
+ "step": 330
405
+ },
406
+ {
407
+ "epoch": 0.05,
408
+ "learning_rate": 0.0001307228297632469,
409
+ "loss": 3.6372,
410
+ "step": 335
411
+ },
412
+ {
413
+ "epoch": 0.05,
414
+ "learning_rate": 0.00013062615558060879,
415
+ "loss": 3.4259,
416
+ "step": 340
417
+ },
418
+ {
419
+ "epoch": 0.05,
420
+ "learning_rate": 0.0001305294813979707,
421
+ "loss": 3.5789,
422
+ "step": 345
423
+ },
424
+ {
425
+ "epoch": 0.05,
426
+ "learning_rate": 0.0001304328072153326,
427
+ "loss": 3.241,
428
+ "step": 350
429
+ },
430
+ {
431
+ "epoch": 0.05,
432
+ "learning_rate": 0.00013033613303269447,
433
+ "loss": 3.4509,
434
+ "step": 355
435
+ },
436
+ {
437
+ "epoch": 0.05,
438
+ "learning_rate": 0.00013023945885005638,
439
+ "loss": 3.2602,
440
+ "step": 360
441
+ },
442
+ {
443
+ "epoch": 0.05,
444
+ "learning_rate": 0.00013014278466741826,
445
+ "loss": 3.4156,
446
+ "step": 365
447
+ },
448
+ {
449
+ "epoch": 0.05,
450
+ "learning_rate": 0.00013004611048478016,
451
+ "loss": 3.5812,
452
+ "step": 370
453
+ },
454
+ {
455
+ "epoch": 0.05,
456
+ "learning_rate": 0.00012994943630214206,
457
+ "loss": 3.4564,
458
+ "step": 375
459
+ },
460
+ {
461
+ "epoch": 0.05,
462
+ "learning_rate": 0.00012985276211950394,
463
+ "loss": 3.2844,
464
+ "step": 380
465
+ },
466
+ {
467
+ "epoch": 0.05,
468
+ "learning_rate": 0.00012975608793686585,
469
+ "loss": 3.5908,
470
+ "step": 385
471
+ },
472
+ {
473
+ "epoch": 0.05,
474
+ "learning_rate": 0.00012965941375422772,
475
+ "loss": 3.6446,
476
+ "step": 390
477
+ },
478
+ {
479
+ "epoch": 0.06,
480
+ "learning_rate": 0.00012956273957158963,
481
+ "loss": 3.4755,
482
+ "step": 395
483
+ },
484
+ {
485
+ "epoch": 0.06,
486
+ "learning_rate": 0.00012946606538895153,
487
+ "loss": 3.4062,
488
+ "step": 400
489
+ },
490
+ {
491
+ "epoch": 0.06,
492
+ "learning_rate": 0.0001293693912063134,
493
+ "loss": 3.6347,
494
+ "step": 405
495
+ },
496
+ {
497
+ "epoch": 0.06,
498
+ "learning_rate": 0.00012927271702367532,
499
+ "loss": 3.5745,
500
+ "step": 410
501
+ },
502
+ {
503
+ "epoch": 0.06,
504
+ "learning_rate": 0.0001291760428410372,
505
+ "loss": 3.4545,
506
+ "step": 415
507
+ },
508
+ {
509
+ "epoch": 0.06,
510
+ "learning_rate": 0.0001290793686583991,
511
+ "loss": 3.4523,
512
+ "step": 420
513
+ },
514
+ {
515
+ "epoch": 0.06,
516
+ "learning_rate": 0.00012898269447576098,
517
+ "loss": 3.6903,
518
+ "step": 425
519
+ },
520
+ {
521
+ "epoch": 0.06,
522
+ "learning_rate": 0.00012888602029312288,
523
+ "loss": 3.3899,
524
+ "step": 430
525
+ },
526
+ {
527
+ "epoch": 0.06,
528
+ "learning_rate": 0.00012878934611048479,
529
+ "loss": 3.4281,
530
+ "step": 435
531
+ },
532
+ {
533
+ "epoch": 0.06,
534
+ "learning_rate": 0.00012869267192784666,
535
+ "loss": 3.4402,
536
+ "step": 440
537
+ },
538
+ {
539
+ "epoch": 0.06,
540
+ "learning_rate": 0.00012859599774520857,
541
+ "loss": 3.5602,
542
+ "step": 445
543
+ },
544
+ {
545
+ "epoch": 0.06,
546
+ "learning_rate": 0.00012849932356257044,
547
+ "loss": 3.3455,
548
+ "step": 450
549
+ },
550
+ {
551
+ "epoch": 0.06,
552
+ "learning_rate": 0.00012840264937993235,
553
+ "loss": 3.4315,
554
+ "step": 455
555
+ },
556
+ {
557
+ "epoch": 0.06,
558
+ "learning_rate": 0.00012830597519729425,
559
+ "loss": 3.287,
560
+ "step": 460
561
+ },
562
+ {
563
+ "epoch": 0.07,
564
+ "learning_rate": 0.00012820930101465616,
565
+ "loss": 3.5182,
566
+ "step": 465
567
+ },
568
+ {
569
+ "epoch": 0.07,
570
+ "learning_rate": 0.00012811262683201804,
571
+ "loss": 3.5295,
572
+ "step": 470
573
+ },
574
+ {
575
+ "epoch": 0.07,
576
+ "learning_rate": 0.00012801595264937994,
577
+ "loss": 3.4328,
578
+ "step": 475
579
+ },
580
+ {
581
+ "epoch": 0.07,
582
+ "learning_rate": 0.00012791927846674185,
583
+ "loss": 3.3478,
584
+ "step": 480
585
+ },
586
+ {
587
+ "epoch": 0.07,
588
+ "learning_rate": 0.00012782260428410372,
589
+ "loss": 3.4981,
590
+ "step": 485
591
+ },
592
+ {
593
+ "epoch": 0.07,
594
+ "learning_rate": 0.00012772593010146563,
595
+ "loss": 3.252,
596
+ "step": 490
597
+ },
598
+ {
599
+ "epoch": 0.07,
600
+ "learning_rate": 0.0001276292559188275,
601
+ "loss": 3.4785,
602
+ "step": 495
603
+ },
604
+ {
605
+ "epoch": 0.07,
606
+ "learning_rate": 0.0001275325817361894,
607
+ "loss": 3.327,
608
+ "step": 500
609
+ }
610
+ ],
611
+ "max_steps": 7096,
612
+ "num_train_epochs": 1,
613
+ "total_flos": 261292032000000.0,
614
+ "trial_name": null,
615
+ "trial_params": null
616
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b16158cc06119d2847d60a322befe625d91f9797ab18bffec420cddc6eae5cd6
3
+ size 3183
last-checkpoint/vocab.json ADDED
The diff for this file is too large to render. See raw diff
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 sha256:49c391befd6890f902bb453609f9bf21692247faccf132ff190c2d68e4e38d5c
3
+ size 510396521
runs/Jun02_18-32-12_0076a51e6274/1654194775.362782/events.out.tfevents.1654194775.0076a51e6274.73.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac46e90c915bebc8b536f74612b888912fa0a002677faaad256b87ff4b292378
3
+ size 5154
runs/Jun02_18-32-12_0076a51e6274/events.out.tfevents.1654194775.0076a51e6274.73.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3359f09da8b03dfcd5c6cc89e99eaa8061c5bf26b0644f63813b36e05d5ffbbc
3
+ size 19471
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": "gpt2", "tokenizer_class": "GPT2Tokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b16158cc06119d2847d60a322befe625d91f9797ab18bffec420cddc6eae5cd6
3
+ size 3183
vocab.json ADDED
The diff for this file is too large to render. See raw diff