MarkProMaster229 commited on
Commit
e285261
·
verified ·
1 Parent(s): 3de86eb
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2LMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 1,
8
+ "embd_pdrop": 0.1,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "id2label": {
12
+ "0": "LABEL_0"
13
+ },
14
+ "initializer_range": 0.02,
15
+ "label2id": {
16
+ "LABEL_0": 0
17
+ },
18
+ "layer_norm_epsilon": 1e-05,
19
+ "model_type": "gpt2",
20
+ "n_ctx": 2048,
21
+ "n_embd": 768,
22
+ "n_head": 12,
23
+ "n_inner": null,
24
+ "n_layer": 12,
25
+ "n_positions": 2048,
26
+ "pad_token_id": 0,
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
+ "torch_dtype": "float32",
37
+ "transformers_version": "4.52.4",
38
+ "use_cache": true,
39
+ "vocab_size": 50257
40
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.52.4"
7
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26f736f87452b4150295584bbcab1fe84d5ecafe14a279bb3c8e0b320856b973
3
+ size 500919936
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48fe01390dab2921ca8d3d1c18947d9e7911303736141637d0346c1d93221e33
3
+ size 1001933754
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e16ad8ca36309e69b7bca3cd12ec8eb8069ac7ffe9b311cbfd202b730f9505e
3
+ size 14244
scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5da4ea0c1bcacc6c536f51e41f20fb1c9301dc84cb8e04333e56f06168b8cb83
3
+ size 988
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db1b074aa330c0b0803c07179be61b9ac93aa3e1585ced1974992df5aeedb9c4
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "mask_token": {
17
+ "content": "<mask>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "pad_token": "</s>",
24
+ "unk_token": {
25
+ "content": "<unk>",
26
+ "lstrip": false,
27
+ "normalized": true,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<pad>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "3": {
30
+ "content": "<unk>",
31
+ "lstrip": false,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "4": {
38
+ "content": "<mask>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ }
45
+ },
46
+ "bos_token": "<s>",
47
+ "clean_up_tokenization_spaces": true,
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "extra_special_tokens": {},
51
+ "mask_token": "<mask>",
52
+ "model_max_length": 2048,
53
+ "pad_token": "</s>",
54
+ "padding_side": "left",
55
+ "tokenizer_class": "GPT2Tokenizer",
56
+ "truncation_side": "left",
57
+ "trust_remote_code": false,
58
+ "unk_token": "<unk>"
59
+ }
trainer_state.json ADDED
@@ -0,0 +1,370 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.8237082066869301,
6
+ "eval_steps": 500,
7
+ "global_step": 4800,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.037993920972644375,
14
+ "grad_norm": 0.5791582465171814,
15
+ "learning_rate": 0.0004952982522796353,
16
+ "loss": 1.9579,
17
+ "step": 100
18
+ },
19
+ {
20
+ "epoch": 0.07598784194528875,
21
+ "grad_norm": 0.578816831111908,
22
+ "learning_rate": 0.0004905490121580547,
23
+ "loss": 1.5938,
24
+ "step": 200
25
+ },
26
+ {
27
+ "epoch": 0.11398176291793313,
28
+ "grad_norm": 0.7128555774688721,
29
+ "learning_rate": 0.00048579977203647417,
30
+ "loss": 1.6012,
31
+ "step": 300
32
+ },
33
+ {
34
+ "epoch": 0.1519756838905775,
35
+ "grad_norm": 0.5568099021911621,
36
+ "learning_rate": 0.0004810505319148936,
37
+ "loss": 1.6271,
38
+ "step": 400
39
+ },
40
+ {
41
+ "epoch": 0.1899696048632219,
42
+ "grad_norm": 0.5209512114524841,
43
+ "learning_rate": 0.0004763012917933131,
44
+ "loss": 1.5465,
45
+ "step": 500
46
+ },
47
+ {
48
+ "epoch": 0.22796352583586627,
49
+ "grad_norm": 0.739372968673706,
50
+ "learning_rate": 0.00047155205167173257,
51
+ "loss": 1.5851,
52
+ "step": 600
53
+ },
54
+ {
55
+ "epoch": 0.26595744680851063,
56
+ "grad_norm": 0.48252037167549133,
57
+ "learning_rate": 0.000466802811550152,
58
+ "loss": 1.5936,
59
+ "step": 700
60
+ },
61
+ {
62
+ "epoch": 0.303951367781155,
63
+ "grad_norm": 0.5574118494987488,
64
+ "learning_rate": 0.0004620535714285715,
65
+ "loss": 1.547,
66
+ "step": 800
67
+ },
68
+ {
69
+ "epoch": 0.34194528875379937,
70
+ "grad_norm": 0.4584231674671173,
71
+ "learning_rate": 0.0004573043313069909,
72
+ "loss": 1.5526,
73
+ "step": 900
74
+ },
75
+ {
76
+ "epoch": 0.3799392097264438,
77
+ "grad_norm": 0.5431011319160461,
78
+ "learning_rate": 0.00045255509118541034,
79
+ "loss": 1.5691,
80
+ "step": 1000
81
+ },
82
+ {
83
+ "epoch": 0.41793313069908816,
84
+ "grad_norm": 0.5586347579956055,
85
+ "learning_rate": 0.00044780585106382983,
86
+ "loss": 1.5839,
87
+ "step": 1100
88
+ },
89
+ {
90
+ "epoch": 0.45592705167173253,
91
+ "grad_norm": 0.4354408085346222,
92
+ "learning_rate": 0.00044305661094224926,
93
+ "loss": 1.55,
94
+ "step": 1200
95
+ },
96
+ {
97
+ "epoch": 0.4939209726443769,
98
+ "grad_norm": 0.5265607237815857,
99
+ "learning_rate": 0.0004383073708206687,
100
+ "loss": 1.5339,
101
+ "step": 1300
102
+ },
103
+ {
104
+ "epoch": 0.5319148936170213,
105
+ "grad_norm": 0.4391303062438965,
106
+ "learning_rate": 0.0004335581306990882,
107
+ "loss": 1.5296,
108
+ "step": 1400
109
+ },
110
+ {
111
+ "epoch": 0.5699088145896657,
112
+ "grad_norm": 0.7169055342674255,
113
+ "learning_rate": 0.0004288088905775076,
114
+ "loss": 1.5336,
115
+ "step": 1500
116
+ },
117
+ {
118
+ "epoch": 0.60790273556231,
119
+ "grad_norm": 0.5826978087425232,
120
+ "learning_rate": 0.00042405965045592704,
121
+ "loss": 1.5803,
122
+ "step": 1600
123
+ },
124
+ {
125
+ "epoch": 0.6458966565349544,
126
+ "grad_norm": 0.6483295559883118,
127
+ "learning_rate": 0.0004193104103343465,
128
+ "loss": 1.5538,
129
+ "step": 1700
130
+ },
131
+ {
132
+ "epoch": 0.6838905775075987,
133
+ "grad_norm": 0.4572024941444397,
134
+ "learning_rate": 0.00041456117021276595,
135
+ "loss": 1.5207,
136
+ "step": 1800
137
+ },
138
+ {
139
+ "epoch": 0.7218844984802432,
140
+ "grad_norm": 0.509039580821991,
141
+ "learning_rate": 0.0004098119300911854,
142
+ "loss": 1.535,
143
+ "step": 1900
144
+ },
145
+ {
146
+ "epoch": 0.7598784194528876,
147
+ "grad_norm": 0.45722949504852295,
148
+ "learning_rate": 0.00040506268996960487,
149
+ "loss": 1.5684,
150
+ "step": 2000
151
+ },
152
+ {
153
+ "epoch": 0.7978723404255319,
154
+ "grad_norm": 0.4910150170326233,
155
+ "learning_rate": 0.0004003134498480243,
156
+ "loss": 1.581,
157
+ "step": 2100
158
+ },
159
+ {
160
+ "epoch": 0.8358662613981763,
161
+ "grad_norm": 0.4546220600605011,
162
+ "learning_rate": 0.0003955642097264438,
163
+ "loss": 1.5244,
164
+ "step": 2200
165
+ },
166
+ {
167
+ "epoch": 0.8738601823708206,
168
+ "grad_norm": 0.5551008582115173,
169
+ "learning_rate": 0.0003908149696048632,
170
+ "loss": 1.5148,
171
+ "step": 2300
172
+ },
173
+ {
174
+ "epoch": 0.9118541033434651,
175
+ "grad_norm": 0.5794001817703247,
176
+ "learning_rate": 0.00038606572948328264,
177
+ "loss": 1.5236,
178
+ "step": 2400
179
+ },
180
+ {
181
+ "epoch": 0.9498480243161094,
182
+ "grad_norm": 0.4178274869918823,
183
+ "learning_rate": 0.0003813164893617022,
184
+ "loss": 1.4909,
185
+ "step": 2500
186
+ },
187
+ {
188
+ "epoch": 0.9878419452887538,
189
+ "grad_norm": 0.4754296541213989,
190
+ "learning_rate": 0.0003765672492401216,
191
+ "loss": 1.5292,
192
+ "step": 2600
193
+ },
194
+ {
195
+ "epoch": 1.0258358662613982,
196
+ "grad_norm": 0.6230200529098511,
197
+ "learning_rate": 0.00037181800911854104,
198
+ "loss": 1.3509,
199
+ "step": 2700
200
+ },
201
+ {
202
+ "epoch": 1.0638297872340425,
203
+ "grad_norm": 0.6134634017944336,
204
+ "learning_rate": 0.00036706876899696053,
205
+ "loss": 1.2918,
206
+ "step": 2800
207
+ },
208
+ {
209
+ "epoch": 1.1018237082066868,
210
+ "grad_norm": 0.41924381256103516,
211
+ "learning_rate": 0.00036231952887537996,
212
+ "loss": 1.2676,
213
+ "step": 2900
214
+ },
215
+ {
216
+ "epoch": 1.1398176291793314,
217
+ "grad_norm": 0.43015140295028687,
218
+ "learning_rate": 0.0003575702887537994,
219
+ "loss": 1.3059,
220
+ "step": 3000
221
+ },
222
+ {
223
+ "epoch": 1.1778115501519757,
224
+ "grad_norm": 0.4945460855960846,
225
+ "learning_rate": 0.0003528210486322189,
226
+ "loss": 1.2662,
227
+ "step": 3100
228
+ },
229
+ {
230
+ "epoch": 1.21580547112462,
231
+ "grad_norm": 0.529432475566864,
232
+ "learning_rate": 0.0003480718085106383,
233
+ "loss": 1.3159,
234
+ "step": 3200
235
+ },
236
+ {
237
+ "epoch": 1.2537993920972643,
238
+ "grad_norm": 0.4257758557796478,
239
+ "learning_rate": 0.00034332256838905773,
240
+ "loss": 1.332,
241
+ "step": 3300
242
+ },
243
+ {
244
+ "epoch": 1.2917933130699089,
245
+ "grad_norm": 0.5150781869888306,
246
+ "learning_rate": 0.0003385733282674772,
247
+ "loss": 1.3296,
248
+ "step": 3400
249
+ },
250
+ {
251
+ "epoch": 1.3297872340425532,
252
+ "grad_norm": 0.6550915241241455,
253
+ "learning_rate": 0.00033382408814589665,
254
+ "loss": 1.3199,
255
+ "step": 3500
256
+ },
257
+ {
258
+ "epoch": 1.3677811550151975,
259
+ "grad_norm": 0.5338163375854492,
260
+ "learning_rate": 0.00032907484802431613,
261
+ "loss": 1.3259,
262
+ "step": 3600
263
+ },
264
+ {
265
+ "epoch": 1.405775075987842,
266
+ "grad_norm": 0.47377586364746094,
267
+ "learning_rate": 0.00032432560790273556,
268
+ "loss": 1.3242,
269
+ "step": 3700
270
+ },
271
+ {
272
+ "epoch": 1.4437689969604863,
273
+ "grad_norm": 0.5152885317802429,
274
+ "learning_rate": 0.000319576367781155,
275
+ "loss": 1.3159,
276
+ "step": 3800
277
+ },
278
+ {
279
+ "epoch": 1.4817629179331306,
280
+ "grad_norm": 0.539071261882782,
281
+ "learning_rate": 0.0003148271276595745,
282
+ "loss": 1.2949,
283
+ "step": 3900
284
+ },
285
+ {
286
+ "epoch": 1.5197568389057752,
287
+ "grad_norm": 0.48675107955932617,
288
+ "learning_rate": 0.0003100778875379939,
289
+ "loss": 1.3048,
290
+ "step": 4000
291
+ },
292
+ {
293
+ "epoch": 1.5577507598784195,
294
+ "grad_norm": 0.49419140815734863,
295
+ "learning_rate": 0.00030532864741641334,
296
+ "loss": 1.3517,
297
+ "step": 4100
298
+ },
299
+ {
300
+ "epoch": 1.5957446808510638,
301
+ "grad_norm": 0.5641041398048401,
302
+ "learning_rate": 0.0003005794072948328,
303
+ "loss": 1.3546,
304
+ "step": 4200
305
+ },
306
+ {
307
+ "epoch": 1.6337386018237083,
308
+ "grad_norm": 0.5435624122619629,
309
+ "learning_rate": 0.0002958301671732523,
310
+ "loss": 1.3001,
311
+ "step": 4300
312
+ },
313
+ {
314
+ "epoch": 1.6717325227963524,
315
+ "grad_norm": 0.5236312747001648,
316
+ "learning_rate": 0.00029108092705167174,
317
+ "loss": 1.3159,
318
+ "step": 4400
319
+ },
320
+ {
321
+ "epoch": 1.709726443768997,
322
+ "grad_norm": 0.5345861315727234,
323
+ "learning_rate": 0.0002863316869300912,
324
+ "loss": 1.3137,
325
+ "step": 4500
326
+ },
327
+ {
328
+ "epoch": 1.7477203647416415,
329
+ "grad_norm": 0.6117902994155884,
330
+ "learning_rate": 0.00028158244680851066,
331
+ "loss": 1.3116,
332
+ "step": 4600
333
+ },
334
+ {
335
+ "epoch": 1.7857142857142856,
336
+ "grad_norm": 0.45284005999565125,
337
+ "learning_rate": 0.0002768332066869301,
338
+ "loss": 1.3079,
339
+ "step": 4700
340
+ },
341
+ {
342
+ "epoch": 1.8237082066869301,
343
+ "grad_norm": 0.46459677815437317,
344
+ "learning_rate": 0.00027208396656534957,
345
+ "loss": 1.3346,
346
+ "step": 4800
347
+ }
348
+ ],
349
+ "logging_steps": 100,
350
+ "max_steps": 10528,
351
+ "num_input_tokens_seen": 0,
352
+ "num_train_epochs": 4,
353
+ "save_steps": 300,
354
+ "stateful_callbacks": {
355
+ "TrainerControl": {
356
+ "args": {
357
+ "should_epoch_stop": false,
358
+ "should_evaluate": false,
359
+ "should_log": false,
360
+ "should_save": true,
361
+ "should_training_stop": false
362
+ },
363
+ "attributes": {}
364
+ }
365
+ },
366
+ "total_flos": 3.7625268731904e+16,
367
+ "train_batch_size": 15,
368
+ "trial_name": null,
369
+ "trial_params": null
370
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2531b729b2c525145b70199c5dd822cae4174318f25eaeb788a247f5ac17d01f
3
+ size 5304
vocab.json ADDED
The diff for this file is too large to render. See raw diff