eljavatar commited on
Commit
b3599bf
·
verified ·
1 Parent(s): f6f3f85

upload test mini model utg4java pretained on codet5

Browse files
README.md CHANGED
@@ -1,3 +1,50 @@
1
  ---
 
 
 
 
 
 
2
  license: apache-2.0
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ base_model: Salesforce/codet5-small
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: pretrain_utg4java
7
+ results: []
8
  license: apache-2.0
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
+ # pretrain_utg4java
15
+
16
+ This model is a fine-tuned version of [Salesforce/codet5-small](https://huggingface.co/Salesforce/codet5-small) on an unknown dataset.
17
+
18
+ ## Model description
19
+
20
+ More information needed
21
+
22
+ ## Intended uses & limitations
23
+
24
+ More information needed
25
+
26
+ ## Training and evaluation data
27
+
28
+ More information needed
29
+
30
+ ## Training procedure
31
+
32
+ ### Training hyperparameters
33
+
34
+ The following hyperparameters were used during training:
35
+ - learning_rate: 0.0002
36
+ - train_batch_size: 4
37
+ - eval_batch_size: 8
38
+ - seed: 42
39
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
40
+ - lr_scheduler_type: linear
41
+ - lr_scheduler_warmup_steps: 150
42
+ - num_epochs: 4
43
+ - mixed_precision_training: Native AMP
44
+
45
+ ### Framework versions
46
+
47
+ - Transformers 4.38.2
48
+ - Pytorch 2.1.0+cu121
49
+ - Datasets 2.18.0
50
+ - Tokenizers 0.15.2
all_results.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.0,
3
+ "test_loss": 0.5490162372589111,
4
+ "test_runtime": 869.0719,
5
+ "test_samples_per_second": 2.166,
6
+ "test_steps_per_second": 0.272,
7
+ "train_loss": 0.7414002821479045,
8
+ "train_runtime": 7813.3494,
9
+ "train_samples_per_second": 7.706,
10
+ "train_steps_per_second": 1.926
11
+ }
codet5_modelconfigs.txt ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ T5Config {
2
+ "_name_or_path": "Salesforce/codet5-small",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "classifier_dropout": 0.0,
8
+ "d_ff": 2048,
9
+ "d_kv": 64,
10
+ "d_model": 512,
11
+ "decoder_start_token_id": 0,
12
+ "dense_act_fn": "relu",
13
+ "dropout_rate": 0.1,
14
+ "eos_token_id": 2,
15
+ "feed_forward_proj": "relu",
16
+ "gradient_checkpointing": false,
17
+ "id2label": {
18
+ "0": "LABEL_0"
19
+ },
20
+ "initializer_factor": 1.0,
21
+ "is_encoder_decoder": true,
22
+ "is_gated_act": false,
23
+ "label2id": {
24
+ "LABEL_0": 0
25
+ },
26
+ "layer_norm_epsilon": 1e-06,
27
+ "model_type": "t5",
28
+ "n_positions": 512,
29
+ "num_decoder_layers": 6,
30
+ "num_heads": 8,
31
+ "num_layers": 6,
32
+ "output_past": true,
33
+ "pad_token_id": 0,
34
+ "relative_attention_max_distance": 128,
35
+ "relative_attention_num_buckets": 32,
36
+ "task_specific_params": {
37
+ "summarization": {
38
+ "early_stopping": true,
39
+ "length_penalty": 2.0,
40
+ "max_length": 200,
41
+ "min_length": 30,
42
+ "no_repeat_ngram_size": 3,
43
+ "num_beams": 4,
44
+ "prefix": "summarize: "
45
+ },
46
+ "translation_en_to_de": {
47
+ "early_stopping": true,
48
+ "max_length": 300,
49
+ "num_beams": 4,
50
+ "prefix": "translate English to German: "
51
+ },
52
+ "translation_en_to_fr": {
53
+ "early_stopping": true,
54
+ "max_length": 300,
55
+ "num_beams": 4,
56
+ "prefix": "translate English to French: "
57
+ },
58
+ "translation_en_to_ro": {
59
+ "early_stopping": true,
60
+ "max_length": 300,
61
+ "num_beams": 4,
62
+ "prefix": "translate English to Romanian: "
63
+ }
64
+ },
65
+ "torch_dtype": "float32",
66
+ "transformers_version": "4.38.2",
67
+ "use_cache": true,
68
+ "vocab_size": 32100
69
+ }
config.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Salesforce/codet5-small",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "classifier_dropout": 0.0,
8
+ "d_ff": 2048,
9
+ "d_kv": 64,
10
+ "d_model": 512,
11
+ "decoder_start_token_id": 0,
12
+ "dense_act_fn": "relu",
13
+ "dropout_rate": 0.1,
14
+ "eos_token_id": 2,
15
+ "feed_forward_proj": "relu",
16
+ "gradient_checkpointing": false,
17
+ "id2label": {
18
+ "0": "LABEL_0"
19
+ },
20
+ "initializer_factor": 1.0,
21
+ "is_encoder_decoder": true,
22
+ "is_gated_act": false,
23
+ "label2id": {
24
+ "LABEL_0": 0
25
+ },
26
+ "layer_norm_epsilon": 1e-06,
27
+ "model_type": "t5",
28
+ "n_positions": 512,
29
+ "num_decoder_layers": 6,
30
+ "num_heads": 8,
31
+ "num_layers": 6,
32
+ "output_past": true,
33
+ "pad_token_id": 0,
34
+ "relative_attention_max_distance": 128,
35
+ "relative_attention_num_buckets": 32,
36
+ "task_specific_params": {
37
+ "summarization": {
38
+ "early_stopping": true,
39
+ "length_penalty": 2.0,
40
+ "max_length": 200,
41
+ "min_length": 30,
42
+ "no_repeat_ngram_size": 3,
43
+ "num_beams": 4,
44
+ "prefix": "summarize: "
45
+ },
46
+ "translation_en_to_de": {
47
+ "early_stopping": true,
48
+ "max_length": 300,
49
+ "num_beams": 4,
50
+ "prefix": "translate English to German: "
51
+ },
52
+ "translation_en_to_fr": {
53
+ "early_stopping": true,
54
+ "max_length": 300,
55
+ "num_beams": 4,
56
+ "prefix": "translate English to French: "
57
+ },
58
+ "translation_en_to_ro": {
59
+ "early_stopping": true,
60
+ "max_length": 300,
61
+ "num_beams": 4,
62
+ "prefix": "translate English to Romanian: "
63
+ }
64
+ },
65
+ "torch_dtype": "float32",
66
+ "transformers_version": "4.38.2",
67
+ "use_cache": true,
68
+ "vocab_size": 32100
69
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "decoder_start_token_id": 0,
5
+ "eos_token_id": 2,
6
+ "pad_token_id": 0,
7
+ "transformers_version": "4.38.2"
8
+ }
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 sha256:926c8a581ca5d835b80a55f4a7eca6d056b2278b297405b9e8dfd0a5a38a3f44
3
+ size 242014742
special_tokens_map.json ADDED
@@ -0,0 +1,753 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<extra_id_99>",
5
+ "lstrip": true,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<extra_id_98>",
12
+ "lstrip": true,
13
+ "normalized": true,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "<extra_id_97>",
19
+ "lstrip": true,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ {
25
+ "content": "<extra_id_96>",
26
+ "lstrip": true,
27
+ "normalized": true,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ {
32
+ "content": "<extra_id_95>",
33
+ "lstrip": true,
34
+ "normalized": true,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ },
38
+ {
39
+ "content": "<extra_id_94>",
40
+ "lstrip": true,
41
+ "normalized": true,
42
+ "rstrip": false,
43
+ "single_word": false
44
+ },
45
+ {
46
+ "content": "<extra_id_93>",
47
+ "lstrip": true,
48
+ "normalized": true,
49
+ "rstrip": false,
50
+ "single_word": false
51
+ },
52
+ {
53
+ "content": "<extra_id_92>",
54
+ "lstrip": true,
55
+ "normalized": true,
56
+ "rstrip": false,
57
+ "single_word": false
58
+ },
59
+ {
60
+ "content": "<extra_id_91>",
61
+ "lstrip": true,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false
65
+ },
66
+ {
67
+ "content": "<extra_id_90>",
68
+ "lstrip": true,
69
+ "normalized": true,
70
+ "rstrip": false,
71
+ "single_word": false
72
+ },
73
+ {
74
+ "content": "<extra_id_89>",
75
+ "lstrip": true,
76
+ "normalized": true,
77
+ "rstrip": false,
78
+ "single_word": false
79
+ },
80
+ {
81
+ "content": "<extra_id_88>",
82
+ "lstrip": true,
83
+ "normalized": true,
84
+ "rstrip": false,
85
+ "single_word": false
86
+ },
87
+ {
88
+ "content": "<extra_id_87>",
89
+ "lstrip": true,
90
+ "normalized": true,
91
+ "rstrip": false,
92
+ "single_word": false
93
+ },
94
+ {
95
+ "content": "<extra_id_86>",
96
+ "lstrip": true,
97
+ "normalized": true,
98
+ "rstrip": false,
99
+ "single_word": false
100
+ },
101
+ {
102
+ "content": "<extra_id_85>",
103
+ "lstrip": true,
104
+ "normalized": true,
105
+ "rstrip": false,
106
+ "single_word": false
107
+ },
108
+ {
109
+ "content": "<extra_id_84>",
110
+ "lstrip": true,
111
+ "normalized": true,
112
+ "rstrip": false,
113
+ "single_word": false
114
+ },
115
+ {
116
+ "content": "<extra_id_83>",
117
+ "lstrip": true,
118
+ "normalized": true,
119
+ "rstrip": false,
120
+ "single_word": false
121
+ },
122
+ {
123
+ "content": "<extra_id_82>",
124
+ "lstrip": true,
125
+ "normalized": true,
126
+ "rstrip": false,
127
+ "single_word": false
128
+ },
129
+ {
130
+ "content": "<extra_id_81>",
131
+ "lstrip": true,
132
+ "normalized": true,
133
+ "rstrip": false,
134
+ "single_word": false
135
+ },
136
+ {
137
+ "content": "<extra_id_80>",
138
+ "lstrip": true,
139
+ "normalized": true,
140
+ "rstrip": false,
141
+ "single_word": false
142
+ },
143
+ {
144
+ "content": "<extra_id_79>",
145
+ "lstrip": true,
146
+ "normalized": true,
147
+ "rstrip": false,
148
+ "single_word": false
149
+ },
150
+ {
151
+ "content": "<extra_id_78>",
152
+ "lstrip": true,
153
+ "normalized": true,
154
+ "rstrip": false,
155
+ "single_word": false
156
+ },
157
+ {
158
+ "content": "<extra_id_77>",
159
+ "lstrip": true,
160
+ "normalized": true,
161
+ "rstrip": false,
162
+ "single_word": false
163
+ },
164
+ {
165
+ "content": "<extra_id_76>",
166
+ "lstrip": true,
167
+ "normalized": true,
168
+ "rstrip": false,
169
+ "single_word": false
170
+ },
171
+ {
172
+ "content": "<extra_id_75>",
173
+ "lstrip": true,
174
+ "normalized": true,
175
+ "rstrip": false,
176
+ "single_word": false
177
+ },
178
+ {
179
+ "content": "<extra_id_74>",
180
+ "lstrip": true,
181
+ "normalized": true,
182
+ "rstrip": false,
183
+ "single_word": false
184
+ },
185
+ {
186
+ "content": "<extra_id_73>",
187
+ "lstrip": true,
188
+ "normalized": true,
189
+ "rstrip": false,
190
+ "single_word": false
191
+ },
192
+ {
193
+ "content": "<extra_id_72>",
194
+ "lstrip": true,
195
+ "normalized": true,
196
+ "rstrip": false,
197
+ "single_word": false
198
+ },
199
+ {
200
+ "content": "<extra_id_71>",
201
+ "lstrip": true,
202
+ "normalized": true,
203
+ "rstrip": false,
204
+ "single_word": false
205
+ },
206
+ {
207
+ "content": "<extra_id_70>",
208
+ "lstrip": true,
209
+ "normalized": true,
210
+ "rstrip": false,
211
+ "single_word": false
212
+ },
213
+ {
214
+ "content": "<extra_id_69>",
215
+ "lstrip": true,
216
+ "normalized": true,
217
+ "rstrip": false,
218
+ "single_word": false
219
+ },
220
+ {
221
+ "content": "<extra_id_68>",
222
+ "lstrip": true,
223
+ "normalized": true,
224
+ "rstrip": false,
225
+ "single_word": false
226
+ },
227
+ {
228
+ "content": "<extra_id_67>",
229
+ "lstrip": true,
230
+ "normalized": true,
231
+ "rstrip": false,
232
+ "single_word": false
233
+ },
234
+ {
235
+ "content": "<extra_id_66>",
236
+ "lstrip": true,
237
+ "normalized": true,
238
+ "rstrip": false,
239
+ "single_word": false
240
+ },
241
+ {
242
+ "content": "<extra_id_65>",
243
+ "lstrip": true,
244
+ "normalized": true,
245
+ "rstrip": false,
246
+ "single_word": false
247
+ },
248
+ {
249
+ "content": "<extra_id_64>",
250
+ "lstrip": true,
251
+ "normalized": true,
252
+ "rstrip": false,
253
+ "single_word": false
254
+ },
255
+ {
256
+ "content": "<extra_id_63>",
257
+ "lstrip": true,
258
+ "normalized": true,
259
+ "rstrip": false,
260
+ "single_word": false
261
+ },
262
+ {
263
+ "content": "<extra_id_62>",
264
+ "lstrip": true,
265
+ "normalized": true,
266
+ "rstrip": false,
267
+ "single_word": false
268
+ },
269
+ {
270
+ "content": "<extra_id_61>",
271
+ "lstrip": true,
272
+ "normalized": true,
273
+ "rstrip": false,
274
+ "single_word": false
275
+ },
276
+ {
277
+ "content": "<extra_id_60>",
278
+ "lstrip": true,
279
+ "normalized": true,
280
+ "rstrip": false,
281
+ "single_word": false
282
+ },
283
+ {
284
+ "content": "<extra_id_59>",
285
+ "lstrip": true,
286
+ "normalized": true,
287
+ "rstrip": false,
288
+ "single_word": false
289
+ },
290
+ {
291
+ "content": "<extra_id_58>",
292
+ "lstrip": true,
293
+ "normalized": true,
294
+ "rstrip": false,
295
+ "single_word": false
296
+ },
297
+ {
298
+ "content": "<extra_id_57>",
299
+ "lstrip": true,
300
+ "normalized": true,
301
+ "rstrip": false,
302
+ "single_word": false
303
+ },
304
+ {
305
+ "content": "<extra_id_56>",
306
+ "lstrip": true,
307
+ "normalized": true,
308
+ "rstrip": false,
309
+ "single_word": false
310
+ },
311
+ {
312
+ "content": "<extra_id_55>",
313
+ "lstrip": true,
314
+ "normalized": true,
315
+ "rstrip": false,
316
+ "single_word": false
317
+ },
318
+ {
319
+ "content": "<extra_id_54>",
320
+ "lstrip": true,
321
+ "normalized": true,
322
+ "rstrip": false,
323
+ "single_word": false
324
+ },
325
+ {
326
+ "content": "<extra_id_53>",
327
+ "lstrip": true,
328
+ "normalized": true,
329
+ "rstrip": false,
330
+ "single_word": false
331
+ },
332
+ {
333
+ "content": "<extra_id_52>",
334
+ "lstrip": true,
335
+ "normalized": true,
336
+ "rstrip": false,
337
+ "single_word": false
338
+ },
339
+ {
340
+ "content": "<extra_id_51>",
341
+ "lstrip": true,
342
+ "normalized": true,
343
+ "rstrip": false,
344
+ "single_word": false
345
+ },
346
+ {
347
+ "content": "<extra_id_50>",
348
+ "lstrip": true,
349
+ "normalized": true,
350
+ "rstrip": false,
351
+ "single_word": false
352
+ },
353
+ {
354
+ "content": "<extra_id_49>",
355
+ "lstrip": true,
356
+ "normalized": true,
357
+ "rstrip": false,
358
+ "single_word": false
359
+ },
360
+ {
361
+ "content": "<extra_id_48>",
362
+ "lstrip": true,
363
+ "normalized": true,
364
+ "rstrip": false,
365
+ "single_word": false
366
+ },
367
+ {
368
+ "content": "<extra_id_47>",
369
+ "lstrip": true,
370
+ "normalized": true,
371
+ "rstrip": false,
372
+ "single_word": false
373
+ },
374
+ {
375
+ "content": "<extra_id_46>",
376
+ "lstrip": true,
377
+ "normalized": true,
378
+ "rstrip": false,
379
+ "single_word": false
380
+ },
381
+ {
382
+ "content": "<extra_id_45>",
383
+ "lstrip": true,
384
+ "normalized": true,
385
+ "rstrip": false,
386
+ "single_word": false
387
+ },
388
+ {
389
+ "content": "<extra_id_44>",
390
+ "lstrip": true,
391
+ "normalized": true,
392
+ "rstrip": false,
393
+ "single_word": false
394
+ },
395
+ {
396
+ "content": "<extra_id_43>",
397
+ "lstrip": true,
398
+ "normalized": true,
399
+ "rstrip": false,
400
+ "single_word": false
401
+ },
402
+ {
403
+ "content": "<extra_id_42>",
404
+ "lstrip": true,
405
+ "normalized": true,
406
+ "rstrip": false,
407
+ "single_word": false
408
+ },
409
+ {
410
+ "content": "<extra_id_41>",
411
+ "lstrip": true,
412
+ "normalized": true,
413
+ "rstrip": false,
414
+ "single_word": false
415
+ },
416
+ {
417
+ "content": "<extra_id_40>",
418
+ "lstrip": true,
419
+ "normalized": true,
420
+ "rstrip": false,
421
+ "single_word": false
422
+ },
423
+ {
424
+ "content": "<extra_id_39>",
425
+ "lstrip": true,
426
+ "normalized": true,
427
+ "rstrip": false,
428
+ "single_word": false
429
+ },
430
+ {
431
+ "content": "<extra_id_38>",
432
+ "lstrip": true,
433
+ "normalized": true,
434
+ "rstrip": false,
435
+ "single_word": false
436
+ },
437
+ {
438
+ "content": "<extra_id_37>",
439
+ "lstrip": true,
440
+ "normalized": true,
441
+ "rstrip": false,
442
+ "single_word": false
443
+ },
444
+ {
445
+ "content": "<extra_id_36>",
446
+ "lstrip": true,
447
+ "normalized": true,
448
+ "rstrip": false,
449
+ "single_word": false
450
+ },
451
+ {
452
+ "content": "<extra_id_35>",
453
+ "lstrip": true,
454
+ "normalized": true,
455
+ "rstrip": false,
456
+ "single_word": false
457
+ },
458
+ {
459
+ "content": "<extra_id_34>",
460
+ "lstrip": true,
461
+ "normalized": true,
462
+ "rstrip": false,
463
+ "single_word": false
464
+ },
465
+ {
466
+ "content": "<extra_id_33>",
467
+ "lstrip": true,
468
+ "normalized": true,
469
+ "rstrip": false,
470
+ "single_word": false
471
+ },
472
+ {
473
+ "content": "<extra_id_32>",
474
+ "lstrip": true,
475
+ "normalized": true,
476
+ "rstrip": false,
477
+ "single_word": false
478
+ },
479
+ {
480
+ "content": "<extra_id_31>",
481
+ "lstrip": true,
482
+ "normalized": true,
483
+ "rstrip": false,
484
+ "single_word": false
485
+ },
486
+ {
487
+ "content": "<extra_id_30>",
488
+ "lstrip": true,
489
+ "normalized": true,
490
+ "rstrip": false,
491
+ "single_word": false
492
+ },
493
+ {
494
+ "content": "<extra_id_29>",
495
+ "lstrip": true,
496
+ "normalized": true,
497
+ "rstrip": false,
498
+ "single_word": false
499
+ },
500
+ {
501
+ "content": "<extra_id_28>",
502
+ "lstrip": true,
503
+ "normalized": true,
504
+ "rstrip": false,
505
+ "single_word": false
506
+ },
507
+ {
508
+ "content": "<extra_id_27>",
509
+ "lstrip": true,
510
+ "normalized": true,
511
+ "rstrip": false,
512
+ "single_word": false
513
+ },
514
+ {
515
+ "content": "<extra_id_26>",
516
+ "lstrip": true,
517
+ "normalized": true,
518
+ "rstrip": false,
519
+ "single_word": false
520
+ },
521
+ {
522
+ "content": "<extra_id_25>",
523
+ "lstrip": true,
524
+ "normalized": true,
525
+ "rstrip": false,
526
+ "single_word": false
527
+ },
528
+ {
529
+ "content": "<extra_id_24>",
530
+ "lstrip": true,
531
+ "normalized": true,
532
+ "rstrip": false,
533
+ "single_word": false
534
+ },
535
+ {
536
+ "content": "<extra_id_23>",
537
+ "lstrip": true,
538
+ "normalized": true,
539
+ "rstrip": false,
540
+ "single_word": false
541
+ },
542
+ {
543
+ "content": "<extra_id_22>",
544
+ "lstrip": true,
545
+ "normalized": true,
546
+ "rstrip": false,
547
+ "single_word": false
548
+ },
549
+ {
550
+ "content": "<extra_id_21>",
551
+ "lstrip": true,
552
+ "normalized": true,
553
+ "rstrip": false,
554
+ "single_word": false
555
+ },
556
+ {
557
+ "content": "<extra_id_20>",
558
+ "lstrip": true,
559
+ "normalized": true,
560
+ "rstrip": false,
561
+ "single_word": false
562
+ },
563
+ {
564
+ "content": "<extra_id_19>",
565
+ "lstrip": true,
566
+ "normalized": true,
567
+ "rstrip": false,
568
+ "single_word": false
569
+ },
570
+ {
571
+ "content": "<extra_id_18>",
572
+ "lstrip": true,
573
+ "normalized": true,
574
+ "rstrip": false,
575
+ "single_word": false
576
+ },
577
+ {
578
+ "content": "<extra_id_17>",
579
+ "lstrip": true,
580
+ "normalized": true,
581
+ "rstrip": false,
582
+ "single_word": false
583
+ },
584
+ {
585
+ "content": "<extra_id_16>",
586
+ "lstrip": true,
587
+ "normalized": true,
588
+ "rstrip": false,
589
+ "single_word": false
590
+ },
591
+ {
592
+ "content": "<extra_id_15>",
593
+ "lstrip": true,
594
+ "normalized": true,
595
+ "rstrip": false,
596
+ "single_word": false
597
+ },
598
+ {
599
+ "content": "<extra_id_14>",
600
+ "lstrip": true,
601
+ "normalized": true,
602
+ "rstrip": false,
603
+ "single_word": false
604
+ },
605
+ {
606
+ "content": "<extra_id_13>",
607
+ "lstrip": true,
608
+ "normalized": true,
609
+ "rstrip": false,
610
+ "single_word": false
611
+ },
612
+ {
613
+ "content": "<extra_id_12>",
614
+ "lstrip": true,
615
+ "normalized": true,
616
+ "rstrip": false,
617
+ "single_word": false
618
+ },
619
+ {
620
+ "content": "<extra_id_11>",
621
+ "lstrip": true,
622
+ "normalized": true,
623
+ "rstrip": false,
624
+ "single_word": false
625
+ },
626
+ {
627
+ "content": "<extra_id_10>",
628
+ "lstrip": true,
629
+ "normalized": true,
630
+ "rstrip": false,
631
+ "single_word": false
632
+ },
633
+ {
634
+ "content": "<extra_id_9>",
635
+ "lstrip": true,
636
+ "normalized": true,
637
+ "rstrip": false,
638
+ "single_word": false
639
+ },
640
+ {
641
+ "content": "<extra_id_8>",
642
+ "lstrip": true,
643
+ "normalized": true,
644
+ "rstrip": false,
645
+ "single_word": false
646
+ },
647
+ {
648
+ "content": "<extra_id_7>",
649
+ "lstrip": true,
650
+ "normalized": true,
651
+ "rstrip": false,
652
+ "single_word": false
653
+ },
654
+ {
655
+ "content": "<extra_id_6>",
656
+ "lstrip": true,
657
+ "normalized": true,
658
+ "rstrip": false,
659
+ "single_word": false
660
+ },
661
+ {
662
+ "content": "<extra_id_5>",
663
+ "lstrip": true,
664
+ "normalized": true,
665
+ "rstrip": false,
666
+ "single_word": false
667
+ },
668
+ {
669
+ "content": "<extra_id_4>",
670
+ "lstrip": true,
671
+ "normalized": true,
672
+ "rstrip": false,
673
+ "single_word": false
674
+ },
675
+ {
676
+ "content": "<extra_id_3>",
677
+ "lstrip": true,
678
+ "normalized": true,
679
+ "rstrip": false,
680
+ "single_word": false
681
+ },
682
+ {
683
+ "content": "<extra_id_2>",
684
+ "lstrip": true,
685
+ "normalized": true,
686
+ "rstrip": false,
687
+ "single_word": false
688
+ },
689
+ {
690
+ "content": "<extra_id_1>",
691
+ "lstrip": true,
692
+ "normalized": true,
693
+ "rstrip": false,
694
+ "single_word": false
695
+ },
696
+ {
697
+ "content": "<extra_id_0>",
698
+ "lstrip": true,
699
+ "normalized": true,
700
+ "rstrip": false,
701
+ "single_word": false
702
+ }
703
+ ],
704
+ "bos_token": {
705
+ "content": "<s>",
706
+ "lstrip": false,
707
+ "normalized": true,
708
+ "rstrip": false,
709
+ "single_word": false
710
+ },
711
+ "cls_token": {
712
+ "content": "<s>",
713
+ "lstrip": false,
714
+ "normalized": true,
715
+ "rstrip": false,
716
+ "single_word": false
717
+ },
718
+ "eos_token": {
719
+ "content": "</s>",
720
+ "lstrip": false,
721
+ "normalized": true,
722
+ "rstrip": false,
723
+ "single_word": false
724
+ },
725
+ "mask_token": {
726
+ "content": "<mask>",
727
+ "lstrip": true,
728
+ "normalized": true,
729
+ "rstrip": false,
730
+ "single_word": false
731
+ },
732
+ "pad_token": {
733
+ "content": "<pad>",
734
+ "lstrip": false,
735
+ "normalized": true,
736
+ "rstrip": false,
737
+ "single_word": false
738
+ },
739
+ "sep_token": {
740
+ "content": "</s>",
741
+ "lstrip": false,
742
+ "normalized": true,
743
+ "rstrip": false,
744
+ "single_word": false
745
+ },
746
+ "unk_token": {
747
+ "content": "<unk>",
748
+ "lstrip": false,
749
+ "normalized": true,
750
+ "rstrip": false,
751
+ "single_word": false
752
+ }
753
+ }
test_results.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "test_loss": 0.5490162372589111,
3
+ "test_runtime": 869.0719,
4
+ "test_samples_per_second": 2.166,
5
+ "test_steps_per_second": 0.272
6
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,959 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<pad>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "32000": {
45
+ "content": "<extra_id_99>",
46
+ "lstrip": true,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "32001": {
53
+ "content": "<extra_id_98>",
54
+ "lstrip": true,
55
+ "normalized": true,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "32002": {
61
+ "content": "<extra_id_97>",
62
+ "lstrip": true,
63
+ "normalized": true,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "32003": {
69
+ "content": "<extra_id_96>",
70
+ "lstrip": true,
71
+ "normalized": true,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "32004": {
77
+ "content": "<extra_id_95>",
78
+ "lstrip": true,
79
+ "normalized": true,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "32005": {
85
+ "content": "<extra_id_94>",
86
+ "lstrip": true,
87
+ "normalized": true,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "32006": {
93
+ "content": "<extra_id_93>",
94
+ "lstrip": true,
95
+ "normalized": true,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "32007": {
101
+ "content": "<extra_id_92>",
102
+ "lstrip": true,
103
+ "normalized": true,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "32008": {
109
+ "content": "<extra_id_91>",
110
+ "lstrip": true,
111
+ "normalized": true,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "32009": {
117
+ "content": "<extra_id_90>",
118
+ "lstrip": true,
119
+ "normalized": true,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "32010": {
125
+ "content": "<extra_id_89>",
126
+ "lstrip": true,
127
+ "normalized": true,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "32011": {
133
+ "content": "<extra_id_88>",
134
+ "lstrip": true,
135
+ "normalized": true,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "32012": {
141
+ "content": "<extra_id_87>",
142
+ "lstrip": true,
143
+ "normalized": true,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "32013": {
149
+ "content": "<extra_id_86>",
150
+ "lstrip": true,
151
+ "normalized": true,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "32014": {
157
+ "content": "<extra_id_85>",
158
+ "lstrip": true,
159
+ "normalized": true,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "32015": {
165
+ "content": "<extra_id_84>",
166
+ "lstrip": true,
167
+ "normalized": true,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "32016": {
173
+ "content": "<extra_id_83>",
174
+ "lstrip": true,
175
+ "normalized": true,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "32017": {
181
+ "content": "<extra_id_82>",
182
+ "lstrip": true,
183
+ "normalized": true,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "32018": {
189
+ "content": "<extra_id_81>",
190
+ "lstrip": true,
191
+ "normalized": true,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "32019": {
197
+ "content": "<extra_id_80>",
198
+ "lstrip": true,
199
+ "normalized": true,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "32020": {
205
+ "content": "<extra_id_79>",
206
+ "lstrip": true,
207
+ "normalized": true,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "32021": {
213
+ "content": "<extra_id_78>",
214
+ "lstrip": true,
215
+ "normalized": true,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "32022": {
221
+ "content": "<extra_id_77>",
222
+ "lstrip": true,
223
+ "normalized": true,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "32023": {
229
+ "content": "<extra_id_76>",
230
+ "lstrip": true,
231
+ "normalized": true,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "32024": {
237
+ "content": "<extra_id_75>",
238
+ "lstrip": true,
239
+ "normalized": true,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "32025": {
245
+ "content": "<extra_id_74>",
246
+ "lstrip": true,
247
+ "normalized": true,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "32026": {
253
+ "content": "<extra_id_73>",
254
+ "lstrip": true,
255
+ "normalized": true,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "32027": {
261
+ "content": "<extra_id_72>",
262
+ "lstrip": true,
263
+ "normalized": true,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "32028": {
269
+ "content": "<extra_id_71>",
270
+ "lstrip": true,
271
+ "normalized": true,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "32029": {
277
+ "content": "<extra_id_70>",
278
+ "lstrip": true,
279
+ "normalized": true,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "32030": {
285
+ "content": "<extra_id_69>",
286
+ "lstrip": true,
287
+ "normalized": true,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "32031": {
293
+ "content": "<extra_id_68>",
294
+ "lstrip": true,
295
+ "normalized": true,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "32032": {
301
+ "content": "<extra_id_67>",
302
+ "lstrip": true,
303
+ "normalized": true,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "32033": {
309
+ "content": "<extra_id_66>",
310
+ "lstrip": true,
311
+ "normalized": true,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "32034": {
317
+ "content": "<extra_id_65>",
318
+ "lstrip": true,
319
+ "normalized": true,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "32035": {
325
+ "content": "<extra_id_64>",
326
+ "lstrip": true,
327
+ "normalized": true,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "32036": {
333
+ "content": "<extra_id_63>",
334
+ "lstrip": true,
335
+ "normalized": true,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "32037": {
341
+ "content": "<extra_id_62>",
342
+ "lstrip": true,
343
+ "normalized": true,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "32038": {
349
+ "content": "<extra_id_61>",
350
+ "lstrip": true,
351
+ "normalized": true,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "32039": {
357
+ "content": "<extra_id_60>",
358
+ "lstrip": true,
359
+ "normalized": true,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "32040": {
365
+ "content": "<extra_id_59>",
366
+ "lstrip": true,
367
+ "normalized": true,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "32041": {
373
+ "content": "<extra_id_58>",
374
+ "lstrip": true,
375
+ "normalized": true,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "32042": {
381
+ "content": "<extra_id_57>",
382
+ "lstrip": true,
383
+ "normalized": true,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "32043": {
389
+ "content": "<extra_id_56>",
390
+ "lstrip": true,
391
+ "normalized": true,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "32044": {
397
+ "content": "<extra_id_55>",
398
+ "lstrip": true,
399
+ "normalized": true,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "32045": {
405
+ "content": "<extra_id_54>",
406
+ "lstrip": true,
407
+ "normalized": true,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "32046": {
413
+ "content": "<extra_id_53>",
414
+ "lstrip": true,
415
+ "normalized": true,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "32047": {
421
+ "content": "<extra_id_52>",
422
+ "lstrip": true,
423
+ "normalized": true,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "32048": {
429
+ "content": "<extra_id_51>",
430
+ "lstrip": true,
431
+ "normalized": true,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "32049": {
437
+ "content": "<extra_id_50>",
438
+ "lstrip": true,
439
+ "normalized": true,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "32050": {
445
+ "content": "<extra_id_49>",
446
+ "lstrip": true,
447
+ "normalized": true,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "32051": {
453
+ "content": "<extra_id_48>",
454
+ "lstrip": true,
455
+ "normalized": true,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "32052": {
461
+ "content": "<extra_id_47>",
462
+ "lstrip": true,
463
+ "normalized": true,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "32053": {
469
+ "content": "<extra_id_46>",
470
+ "lstrip": true,
471
+ "normalized": true,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "32054": {
477
+ "content": "<extra_id_45>",
478
+ "lstrip": true,
479
+ "normalized": true,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "32055": {
485
+ "content": "<extra_id_44>",
486
+ "lstrip": true,
487
+ "normalized": true,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "32056": {
493
+ "content": "<extra_id_43>",
494
+ "lstrip": true,
495
+ "normalized": true,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "32057": {
501
+ "content": "<extra_id_42>",
502
+ "lstrip": true,
503
+ "normalized": true,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "32058": {
509
+ "content": "<extra_id_41>",
510
+ "lstrip": true,
511
+ "normalized": true,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "32059": {
517
+ "content": "<extra_id_40>",
518
+ "lstrip": true,
519
+ "normalized": true,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "32060": {
525
+ "content": "<extra_id_39>",
526
+ "lstrip": true,
527
+ "normalized": true,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "32061": {
533
+ "content": "<extra_id_38>",
534
+ "lstrip": true,
535
+ "normalized": true,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "32062": {
541
+ "content": "<extra_id_37>",
542
+ "lstrip": true,
543
+ "normalized": true,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "32063": {
549
+ "content": "<extra_id_36>",
550
+ "lstrip": true,
551
+ "normalized": true,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "32064": {
557
+ "content": "<extra_id_35>",
558
+ "lstrip": true,
559
+ "normalized": true,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "32065": {
565
+ "content": "<extra_id_34>",
566
+ "lstrip": true,
567
+ "normalized": true,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "32066": {
573
+ "content": "<extra_id_33>",
574
+ "lstrip": true,
575
+ "normalized": true,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "32067": {
581
+ "content": "<extra_id_32>",
582
+ "lstrip": true,
583
+ "normalized": true,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "32068": {
589
+ "content": "<extra_id_31>",
590
+ "lstrip": true,
591
+ "normalized": true,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "32069": {
597
+ "content": "<extra_id_30>",
598
+ "lstrip": true,
599
+ "normalized": true,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "32070": {
605
+ "content": "<extra_id_29>",
606
+ "lstrip": true,
607
+ "normalized": true,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "32071": {
613
+ "content": "<extra_id_28>",
614
+ "lstrip": true,
615
+ "normalized": true,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "32072": {
621
+ "content": "<extra_id_27>",
622
+ "lstrip": true,
623
+ "normalized": true,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "32073": {
629
+ "content": "<extra_id_26>",
630
+ "lstrip": true,
631
+ "normalized": true,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "32074": {
637
+ "content": "<extra_id_25>",
638
+ "lstrip": true,
639
+ "normalized": true,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "32075": {
645
+ "content": "<extra_id_24>",
646
+ "lstrip": true,
647
+ "normalized": true,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "32076": {
653
+ "content": "<extra_id_23>",
654
+ "lstrip": true,
655
+ "normalized": true,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "32077": {
661
+ "content": "<extra_id_22>",
662
+ "lstrip": true,
663
+ "normalized": true,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "32078": {
669
+ "content": "<extra_id_21>",
670
+ "lstrip": true,
671
+ "normalized": true,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "32079": {
677
+ "content": "<extra_id_20>",
678
+ "lstrip": true,
679
+ "normalized": true,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "32080": {
685
+ "content": "<extra_id_19>",
686
+ "lstrip": true,
687
+ "normalized": true,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "32081": {
693
+ "content": "<extra_id_18>",
694
+ "lstrip": true,
695
+ "normalized": true,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "32082": {
701
+ "content": "<extra_id_17>",
702
+ "lstrip": true,
703
+ "normalized": true,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "32083": {
709
+ "content": "<extra_id_16>",
710
+ "lstrip": true,
711
+ "normalized": true,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "32084": {
717
+ "content": "<extra_id_15>",
718
+ "lstrip": true,
719
+ "normalized": true,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "32085": {
725
+ "content": "<extra_id_14>",
726
+ "lstrip": true,
727
+ "normalized": true,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "32086": {
733
+ "content": "<extra_id_13>",
734
+ "lstrip": true,
735
+ "normalized": true,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "32087": {
741
+ "content": "<extra_id_12>",
742
+ "lstrip": true,
743
+ "normalized": true,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "32088": {
749
+ "content": "<extra_id_11>",
750
+ "lstrip": true,
751
+ "normalized": true,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "32089": {
757
+ "content": "<extra_id_10>",
758
+ "lstrip": true,
759
+ "normalized": true,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "32090": {
765
+ "content": "<extra_id_9>",
766
+ "lstrip": true,
767
+ "normalized": true,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "32091": {
773
+ "content": "<extra_id_8>",
774
+ "lstrip": true,
775
+ "normalized": true,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "32092": {
781
+ "content": "<extra_id_7>",
782
+ "lstrip": true,
783
+ "normalized": true,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "32093": {
789
+ "content": "<extra_id_6>",
790
+ "lstrip": true,
791
+ "normalized": true,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "32094": {
797
+ "content": "<extra_id_5>",
798
+ "lstrip": true,
799
+ "normalized": true,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "32095": {
805
+ "content": "<extra_id_4>",
806
+ "lstrip": true,
807
+ "normalized": true,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "32096": {
813
+ "content": "<extra_id_3>",
814
+ "lstrip": true,
815
+ "normalized": true,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "32097": {
821
+ "content": "<extra_id_2>",
822
+ "lstrip": true,
823
+ "normalized": true,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": true
827
+ },
828
+ "32098": {
829
+ "content": "<extra_id_1>",
830
+ "lstrip": true,
831
+ "normalized": true,
832
+ "rstrip": false,
833
+ "single_word": false,
834
+ "special": true
835
+ },
836
+ "32099": {
837
+ "content": "<extra_id_0>",
838
+ "lstrip": true,
839
+ "normalized": true,
840
+ "rstrip": false,
841
+ "single_word": false,
842
+ "special": true
843
+ }
844
+ },
845
+ "additional_special_tokens": [
846
+ "<extra_id_99>",
847
+ "<extra_id_98>",
848
+ "<extra_id_97>",
849
+ "<extra_id_96>",
850
+ "<extra_id_95>",
851
+ "<extra_id_94>",
852
+ "<extra_id_93>",
853
+ "<extra_id_92>",
854
+ "<extra_id_91>",
855
+ "<extra_id_90>",
856
+ "<extra_id_89>",
857
+ "<extra_id_88>",
858
+ "<extra_id_87>",
859
+ "<extra_id_86>",
860
+ "<extra_id_85>",
861
+ "<extra_id_84>",
862
+ "<extra_id_83>",
863
+ "<extra_id_82>",
864
+ "<extra_id_81>",
865
+ "<extra_id_80>",
866
+ "<extra_id_79>",
867
+ "<extra_id_78>",
868
+ "<extra_id_77>",
869
+ "<extra_id_76>",
870
+ "<extra_id_75>",
871
+ "<extra_id_74>",
872
+ "<extra_id_73>",
873
+ "<extra_id_72>",
874
+ "<extra_id_71>",
875
+ "<extra_id_70>",
876
+ "<extra_id_69>",
877
+ "<extra_id_68>",
878
+ "<extra_id_67>",
879
+ "<extra_id_66>",
880
+ "<extra_id_65>",
881
+ "<extra_id_64>",
882
+ "<extra_id_63>",
883
+ "<extra_id_62>",
884
+ "<extra_id_61>",
885
+ "<extra_id_60>",
886
+ "<extra_id_59>",
887
+ "<extra_id_58>",
888
+ "<extra_id_57>",
889
+ "<extra_id_56>",
890
+ "<extra_id_55>",
891
+ "<extra_id_54>",
892
+ "<extra_id_53>",
893
+ "<extra_id_52>",
894
+ "<extra_id_51>",
895
+ "<extra_id_50>",
896
+ "<extra_id_49>",
897
+ "<extra_id_48>",
898
+ "<extra_id_47>",
899
+ "<extra_id_46>",
900
+ "<extra_id_45>",
901
+ "<extra_id_44>",
902
+ "<extra_id_43>",
903
+ "<extra_id_42>",
904
+ "<extra_id_41>",
905
+ "<extra_id_40>",
906
+ "<extra_id_39>",
907
+ "<extra_id_38>",
908
+ "<extra_id_37>",
909
+ "<extra_id_36>",
910
+ "<extra_id_35>",
911
+ "<extra_id_34>",
912
+ "<extra_id_33>",
913
+ "<extra_id_32>",
914
+ "<extra_id_31>",
915
+ "<extra_id_30>",
916
+ "<extra_id_29>",
917
+ "<extra_id_28>",
918
+ "<extra_id_27>",
919
+ "<extra_id_26>",
920
+ "<extra_id_25>",
921
+ "<extra_id_24>",
922
+ "<extra_id_23>",
923
+ "<extra_id_22>",
924
+ "<extra_id_21>",
925
+ "<extra_id_20>",
926
+ "<extra_id_19>",
927
+ "<extra_id_18>",
928
+ "<extra_id_17>",
929
+ "<extra_id_16>",
930
+ "<extra_id_15>",
931
+ "<extra_id_14>",
932
+ "<extra_id_13>",
933
+ "<extra_id_12>",
934
+ "<extra_id_11>",
935
+ "<extra_id_10>",
936
+ "<extra_id_9>",
937
+ "<extra_id_8>",
938
+ "<extra_id_7>",
939
+ "<extra_id_6>",
940
+ "<extra_id_5>",
941
+ "<extra_id_4>",
942
+ "<extra_id_3>",
943
+ "<extra_id_2>",
944
+ "<extra_id_1>",
945
+ "<extra_id_0>"
946
+ ],
947
+ "bos_token": "<s>",
948
+ "clean_up_tokenization_spaces": true,
949
+ "cls_token": "<s>",
950
+ "eos_token": "</s>",
951
+ "errors": "replace",
952
+ "mask_token": "<mask>",
953
+ "model_max_length": 512,
954
+ "pad_token": "<pad>",
955
+ "sep_token": "</s>",
956
+ "tokenizer_class": "RobertaTokenizer",
957
+ "trim_offsets": true,
958
+ "unk_token": "<unk>"
959
+ }
train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.0,
3
+ "train_loss": 0.7414002821479045,
4
+ "train_runtime": 7813.3494,
5
+ "train_samples_per_second": 7.706,
6
+ "train_steps_per_second": 1.926
7
+ }
trainer_state.json ADDED
@@ -0,0 +1,587 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5480290651321411,
3
+ "best_model_checkpoint": "E:/000_Tesis/test_executions/pretrain_utg4java\\checkpoint-15052",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 15052,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.05,
13
+ "grad_norm": 4.428943157196045,
14
+ "learning_rate": 0.00019936921218628373,
15
+ "loss": 1.6003,
16
+ "step": 200
17
+ },
18
+ {
19
+ "epoch": 0.11,
20
+ "grad_norm": 3.2689905166625977,
21
+ "learning_rate": 0.00019668500872366127,
22
+ "loss": 1.0391,
23
+ "step": 400
24
+ },
25
+ {
26
+ "epoch": 0.16,
27
+ "grad_norm": 3.4730663299560547,
28
+ "learning_rate": 0.00019400080526103878,
29
+ "loss": 0.9586,
30
+ "step": 600
31
+ },
32
+ {
33
+ "epoch": 0.21,
34
+ "grad_norm": 3.3503410816192627,
35
+ "learning_rate": 0.00019131660179841633,
36
+ "loss": 0.9416,
37
+ "step": 800
38
+ },
39
+ {
40
+ "epoch": 0.27,
41
+ "grad_norm": 3.9026317596435547,
42
+ "learning_rate": 0.00018863239833579387,
43
+ "loss": 0.9352,
44
+ "step": 1000
45
+ },
46
+ {
47
+ "epoch": 0.32,
48
+ "grad_norm": 3.4323599338531494,
49
+ "learning_rate": 0.00018594819487317138,
50
+ "loss": 0.9018,
51
+ "step": 1200
52
+ },
53
+ {
54
+ "epoch": 0.37,
55
+ "grad_norm": 2.90022349357605,
56
+ "learning_rate": 0.00018326399141054892,
57
+ "loss": 0.8959,
58
+ "step": 1400
59
+ },
60
+ {
61
+ "epoch": 0.43,
62
+ "grad_norm": 3.3339474201202393,
63
+ "learning_rate": 0.00018057978794792646,
64
+ "loss": 0.8777,
65
+ "step": 1600
66
+ },
67
+ {
68
+ "epoch": 0.48,
69
+ "grad_norm": 5.839554309844971,
70
+ "learning_rate": 0.00017789558448530398,
71
+ "loss": 0.8719,
72
+ "step": 1800
73
+ },
74
+ {
75
+ "epoch": 0.53,
76
+ "grad_norm": 3.7872190475463867,
77
+ "learning_rate": 0.00017521138102268152,
78
+ "loss": 0.8763,
79
+ "step": 2000
80
+ },
81
+ {
82
+ "epoch": 0.58,
83
+ "grad_norm": 3.5567479133605957,
84
+ "learning_rate": 0.00017252717756005906,
85
+ "loss": 0.8601,
86
+ "step": 2200
87
+ },
88
+ {
89
+ "epoch": 0.64,
90
+ "grad_norm": 2.728114604949951,
91
+ "learning_rate": 0.0001698429740974366,
92
+ "loss": 0.8522,
93
+ "step": 2400
94
+ },
95
+ {
96
+ "epoch": 0.69,
97
+ "grad_norm": 2.7635385990142822,
98
+ "learning_rate": 0.00016717219165212724,
99
+ "loss": 0.852,
100
+ "step": 2600
101
+ },
102
+ {
103
+ "epoch": 0.74,
104
+ "grad_norm": 2.332137107849121,
105
+ "learning_rate": 0.00016448798818950478,
106
+ "loss": 0.8622,
107
+ "step": 2800
108
+ },
109
+ {
110
+ "epoch": 0.8,
111
+ "grad_norm": 2.689222812652588,
112
+ "learning_rate": 0.00016180378472688232,
113
+ "loss": 0.8814,
114
+ "step": 3000
115
+ },
116
+ {
117
+ "epoch": 0.85,
118
+ "grad_norm": 3.2268168926239014,
119
+ "learning_rate": 0.00015911958126425983,
120
+ "loss": 0.8223,
121
+ "step": 3200
122
+ },
123
+ {
124
+ "epoch": 0.9,
125
+ "grad_norm": 2.7432162761688232,
126
+ "learning_rate": 0.00015643537780163738,
127
+ "loss": 0.8538,
128
+ "step": 3400
129
+ },
130
+ {
131
+ "epoch": 0.96,
132
+ "grad_norm": 3.417742967605591,
133
+ "learning_rate": 0.00015375117433901492,
134
+ "loss": 0.8118,
135
+ "step": 3600
136
+ },
137
+ {
138
+ "epoch": 1.0,
139
+ "eval_loss": 0.7114242315292358,
140
+ "eval_runtime": 144.1269,
141
+ "eval_samples_per_second": 13.051,
142
+ "eval_steps_per_second": 1.637,
143
+ "step": 3763
144
+ },
145
+ {
146
+ "epoch": 1.01,
147
+ "grad_norm": 2.479877233505249,
148
+ "learning_rate": 0.00015106697087639243,
149
+ "loss": 0.7983,
150
+ "step": 3800
151
+ },
152
+ {
153
+ "epoch": 1.06,
154
+ "grad_norm": 2.73120379447937,
155
+ "learning_rate": 0.00014838276741376997,
156
+ "loss": 0.7892,
157
+ "step": 4000
158
+ },
159
+ {
160
+ "epoch": 1.12,
161
+ "grad_norm": 2.924459934234619,
162
+ "learning_rate": 0.00014569856395114749,
163
+ "loss": 0.7747,
164
+ "step": 4200
165
+ },
166
+ {
167
+ "epoch": 1.17,
168
+ "grad_norm": 3.1980695724487305,
169
+ "learning_rate": 0.00014301436048852503,
170
+ "loss": 0.7758,
171
+ "step": 4400
172
+ },
173
+ {
174
+ "epoch": 1.22,
175
+ "grad_norm": 2.564530849456787,
176
+ "learning_rate": 0.00014033015702590257,
177
+ "loss": 0.7814,
178
+ "step": 4600
179
+ },
180
+ {
181
+ "epoch": 1.28,
182
+ "grad_norm": 2.7397029399871826,
183
+ "learning_rate": 0.0001376593745805932,
184
+ "loss": 0.7501,
185
+ "step": 4800
186
+ },
187
+ {
188
+ "epoch": 1.33,
189
+ "grad_norm": 2.7164580821990967,
190
+ "learning_rate": 0.00013497517111797075,
191
+ "loss": 0.7712,
192
+ "step": 5000
193
+ },
194
+ {
195
+ "epoch": 1.38,
196
+ "grad_norm": 2.4152510166168213,
197
+ "learning_rate": 0.0001322909676553483,
198
+ "loss": 0.7999,
199
+ "step": 5200
200
+ },
201
+ {
202
+ "epoch": 1.44,
203
+ "grad_norm": 2.9376044273376465,
204
+ "learning_rate": 0.00012960676419272583,
205
+ "loss": 0.7516,
206
+ "step": 5400
207
+ },
208
+ {
209
+ "epoch": 1.49,
210
+ "grad_norm": 3.0849993228912354,
211
+ "learning_rate": 0.00012692256073010337,
212
+ "loss": 0.7663,
213
+ "step": 5600
214
+ },
215
+ {
216
+ "epoch": 1.54,
217
+ "grad_norm": 2.0552046298980713,
218
+ "learning_rate": 0.00012423835726748088,
219
+ "loss": 0.7725,
220
+ "step": 5800
221
+ },
222
+ {
223
+ "epoch": 1.59,
224
+ "grad_norm": 4.300168991088867,
225
+ "learning_rate": 0.00012155415380485841,
226
+ "loss": 0.748,
227
+ "step": 6000
228
+ },
229
+ {
230
+ "epoch": 1.65,
231
+ "grad_norm": 2.172149658203125,
232
+ "learning_rate": 0.00011886995034223594,
233
+ "loss": 0.7219,
234
+ "step": 6200
235
+ },
236
+ {
237
+ "epoch": 1.7,
238
+ "grad_norm": 4.83528470993042,
239
+ "learning_rate": 0.00011618574687961348,
240
+ "loss": 0.7565,
241
+ "step": 6400
242
+ },
243
+ {
244
+ "epoch": 1.75,
245
+ "grad_norm": 2.4364535808563232,
246
+ "learning_rate": 0.00011350154341699102,
247
+ "loss": 0.7433,
248
+ "step": 6600
249
+ },
250
+ {
251
+ "epoch": 1.81,
252
+ "grad_norm": 3.630072593688965,
253
+ "learning_rate": 0.00011081733995436854,
254
+ "loss": 0.729,
255
+ "step": 6800
256
+ },
257
+ {
258
+ "epoch": 1.86,
259
+ "grad_norm": 3.485239267349243,
260
+ "learning_rate": 0.00010813313649174608,
261
+ "loss": 0.7178,
262
+ "step": 7000
263
+ },
264
+ {
265
+ "epoch": 1.91,
266
+ "grad_norm": 2.265608787536621,
267
+ "learning_rate": 0.00010544893302912362,
268
+ "loss": 0.7507,
269
+ "step": 7200
270
+ },
271
+ {
272
+ "epoch": 1.97,
273
+ "grad_norm": 2.48197340965271,
274
+ "learning_rate": 0.00010276472956650113,
275
+ "loss": 0.763,
276
+ "step": 7400
277
+ },
278
+ {
279
+ "epoch": 2.0,
280
+ "eval_loss": 0.6458454728126526,
281
+ "eval_runtime": 138.1168,
282
+ "eval_samples_per_second": 13.619,
283
+ "eval_steps_per_second": 1.709,
284
+ "step": 7526
285
+ },
286
+ {
287
+ "epoch": 2.02,
288
+ "grad_norm": 3.2982826232910156,
289
+ "learning_rate": 0.00010008052610387867,
290
+ "loss": 0.7165,
291
+ "step": 7600
292
+ },
293
+ {
294
+ "epoch": 2.07,
295
+ "grad_norm": 2.9913341999053955,
296
+ "learning_rate": 9.739632264125621e-05,
297
+ "loss": 0.7093,
298
+ "step": 7800
299
+ },
300
+ {
301
+ "epoch": 2.13,
302
+ "grad_norm": 3.782381057739258,
303
+ "learning_rate": 9.471211917863374e-05,
304
+ "loss": 0.7007,
305
+ "step": 8000
306
+ },
307
+ {
308
+ "epoch": 2.18,
309
+ "grad_norm": 1.392814040184021,
310
+ "learning_rate": 9.202791571601128e-05,
311
+ "loss": 0.6961,
312
+ "step": 8200
313
+ },
314
+ {
315
+ "epoch": 2.23,
316
+ "grad_norm": 1.976282000541687,
317
+ "learning_rate": 8.934371225338881e-05,
318
+ "loss": 0.7014,
319
+ "step": 8400
320
+ },
321
+ {
322
+ "epoch": 2.29,
323
+ "grad_norm": 1.8080275058746338,
324
+ "learning_rate": 8.665950879076634e-05,
325
+ "loss": 0.6845,
326
+ "step": 8600
327
+ },
328
+ {
329
+ "epoch": 2.34,
330
+ "grad_norm": 2.2179641723632812,
331
+ "learning_rate": 8.397530532814388e-05,
332
+ "loss": 0.6766,
333
+ "step": 8800
334
+ },
335
+ {
336
+ "epoch": 2.39,
337
+ "grad_norm": 4.8770551681518555,
338
+ "learning_rate": 8.129110186552141e-05,
339
+ "loss": 0.6716,
340
+ "step": 9000
341
+ },
342
+ {
343
+ "epoch": 2.44,
344
+ "grad_norm": 2.4720568656921387,
345
+ "learning_rate": 7.860689840289895e-05,
346
+ "loss": 0.663,
347
+ "step": 9200
348
+ },
349
+ {
350
+ "epoch": 2.5,
351
+ "grad_norm": 2.546283006668091,
352
+ "learning_rate": 7.592269494027648e-05,
353
+ "loss": 0.6629,
354
+ "step": 9400
355
+ },
356
+ {
357
+ "epoch": 2.55,
358
+ "grad_norm": 2.2792224884033203,
359
+ "learning_rate": 7.323849147765402e-05,
360
+ "loss": 0.6677,
361
+ "step": 9600
362
+ },
363
+ {
364
+ "epoch": 2.6,
365
+ "grad_norm": 2.87917160987854,
366
+ "learning_rate": 7.055428801503155e-05,
367
+ "loss": 0.6697,
368
+ "step": 9800
369
+ },
370
+ {
371
+ "epoch": 2.66,
372
+ "grad_norm": 4.642680644989014,
373
+ "learning_rate": 6.787008455240907e-05,
374
+ "loss": 0.661,
375
+ "step": 10000
376
+ },
377
+ {
378
+ "epoch": 2.71,
379
+ "grad_norm": 2.9181325435638428,
380
+ "learning_rate": 6.51858810897866e-05,
381
+ "loss": 0.6447,
382
+ "step": 10200
383
+ },
384
+ {
385
+ "epoch": 2.76,
386
+ "grad_norm": 1.9983739852905273,
387
+ "learning_rate": 6.250167762716414e-05,
388
+ "loss": 0.6668,
389
+ "step": 10400
390
+ },
391
+ {
392
+ "epoch": 2.82,
393
+ "grad_norm": 3.3339133262634277,
394
+ "learning_rate": 5.9817474164541676e-05,
395
+ "loss": 0.6494,
396
+ "step": 10600
397
+ },
398
+ {
399
+ "epoch": 2.87,
400
+ "grad_norm": 2.7515461444854736,
401
+ "learning_rate": 5.7133270701919204e-05,
402
+ "loss": 0.6471,
403
+ "step": 10800
404
+ },
405
+ {
406
+ "epoch": 2.92,
407
+ "grad_norm": 2.502366781234741,
408
+ "learning_rate": 5.4462488256609854e-05,
409
+ "loss": 0.6513,
410
+ "step": 11000
411
+ },
412
+ {
413
+ "epoch": 2.98,
414
+ "grad_norm": 2.680753707885742,
415
+ "learning_rate": 5.177828479398739e-05,
416
+ "loss": 0.6701,
417
+ "step": 11200
418
+ },
419
+ {
420
+ "epoch": 3.0,
421
+ "eval_loss": 0.5908769369125366,
422
+ "eval_runtime": 267.1069,
423
+ "eval_samples_per_second": 7.042,
424
+ "eval_steps_per_second": 0.884,
425
+ "step": 11289
426
+ },
427
+ {
428
+ "epoch": 3.03,
429
+ "grad_norm": 1.714341640472412,
430
+ "learning_rate": 4.909408133136492e-05,
431
+ "loss": 0.6571,
432
+ "step": 11400
433
+ },
434
+ {
435
+ "epoch": 3.08,
436
+ "grad_norm": 2.996971607208252,
437
+ "learning_rate": 4.640987786874245e-05,
438
+ "loss": 0.6627,
439
+ "step": 11600
440
+ },
441
+ {
442
+ "epoch": 3.14,
443
+ "grad_norm": 2.6136629581451416,
444
+ "learning_rate": 4.3725674406119985e-05,
445
+ "loss": 0.6486,
446
+ "step": 11800
447
+ },
448
+ {
449
+ "epoch": 3.19,
450
+ "grad_norm": 1.8732506036758423,
451
+ "learning_rate": 4.104147094349752e-05,
452
+ "loss": 0.5942,
453
+ "step": 12000
454
+ },
455
+ {
456
+ "epoch": 3.24,
457
+ "grad_norm": 3.316340923309326,
458
+ "learning_rate": 3.8357267480875054e-05,
459
+ "loss": 0.6228,
460
+ "step": 12200
461
+ },
462
+ {
463
+ "epoch": 3.3,
464
+ "grad_norm": 2.4904277324676514,
465
+ "learning_rate": 3.567306401825258e-05,
466
+ "loss": 0.6313,
467
+ "step": 12400
468
+ },
469
+ {
470
+ "epoch": 3.35,
471
+ "grad_norm": 2.3936824798583984,
472
+ "learning_rate": 3.2988860555630116e-05,
473
+ "loss": 0.6132,
474
+ "step": 12600
475
+ },
476
+ {
477
+ "epoch": 3.4,
478
+ "grad_norm": 2.5523078441619873,
479
+ "learning_rate": 3.030465709300765e-05,
480
+ "loss": 0.6108,
481
+ "step": 12800
482
+ },
483
+ {
484
+ "epoch": 3.45,
485
+ "grad_norm": 2.3019254207611084,
486
+ "learning_rate": 2.7620453630385185e-05,
487
+ "loss": 0.6133,
488
+ "step": 13000
489
+ },
490
+ {
491
+ "epoch": 3.51,
492
+ "grad_norm": 2.492788791656494,
493
+ "learning_rate": 2.493625016776272e-05,
494
+ "loss": 0.6241,
495
+ "step": 13200
496
+ },
497
+ {
498
+ "epoch": 3.56,
499
+ "grad_norm": 2.1467068195343018,
500
+ "learning_rate": 2.2265467722453363e-05,
501
+ "loss": 0.6023,
502
+ "step": 13400
503
+ },
504
+ {
505
+ "epoch": 3.61,
506
+ "grad_norm": 1.78839910030365,
507
+ "learning_rate": 1.9581264259830894e-05,
508
+ "loss": 0.6059,
509
+ "step": 13600
510
+ },
511
+ {
512
+ "epoch": 3.67,
513
+ "grad_norm": 2.343613624572754,
514
+ "learning_rate": 1.689706079720843e-05,
515
+ "loss": 0.5922,
516
+ "step": 13800
517
+ },
518
+ {
519
+ "epoch": 3.72,
520
+ "grad_norm": 2.2175772190093994,
521
+ "learning_rate": 1.4212857334585964e-05,
522
+ "loss": 0.6092,
523
+ "step": 14000
524
+ },
525
+ {
526
+ "epoch": 3.77,
527
+ "grad_norm": 1.8630731105804443,
528
+ "learning_rate": 1.1528653871963495e-05,
529
+ "loss": 0.6055,
530
+ "step": 14200
531
+ },
532
+ {
533
+ "epoch": 3.83,
534
+ "grad_norm": 1.4924801588058472,
535
+ "learning_rate": 8.84445040934103e-06,
536
+ "loss": 0.6053,
537
+ "step": 14400
538
+ },
539
+ {
540
+ "epoch": 3.88,
541
+ "grad_norm": 3.014918088912964,
542
+ "learning_rate": 6.1602469467185615e-06,
543
+ "loss": 0.5846,
544
+ "step": 14600
545
+ },
546
+ {
547
+ "epoch": 3.93,
548
+ "grad_norm": 1.5459446907043457,
549
+ "learning_rate": 3.4760434840960946e-06,
550
+ "loss": 0.5826,
551
+ "step": 14800
552
+ },
553
+ {
554
+ "epoch": 3.99,
555
+ "grad_norm": 3.936332941055298,
556
+ "learning_rate": 7.918400214736277e-07,
557
+ "loss": 0.608,
558
+ "step": 15000
559
+ },
560
+ {
561
+ "epoch": 4.0,
562
+ "eval_loss": 0.5480290651321411,
563
+ "eval_runtime": 221.6429,
564
+ "eval_samples_per_second": 8.487,
565
+ "eval_steps_per_second": 1.065,
566
+ "step": 15052
567
+ },
568
+ {
569
+ "epoch": 4.0,
570
+ "step": 15052,
571
+ "total_flos": 8148659183026176.0,
572
+ "train_loss": 0.7414002821479045,
573
+ "train_runtime": 7813.3494,
574
+ "train_samples_per_second": 7.706,
575
+ "train_steps_per_second": 1.926
576
+ }
577
+ ],
578
+ "logging_steps": 200,
579
+ "max_steps": 15052,
580
+ "num_input_tokens_seen": 0,
581
+ "num_train_epochs": 4,
582
+ "save_steps": 500,
583
+ "total_flos": 8148659183026176.0,
584
+ "train_batch_size": 4,
585
+ "trial_name": null,
586
+ "trial_params": null
587
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71d0caeab6de59de6c8e244b47620bfe631f6686af3890bb773774ea02045d78
3
+ size 5112
utg4java_pretrain_bleu_metrics.txt ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ TESTING RESULTS:
2
+
3
+ Elapsed time: 879.7387535572052 seconds
4
+ Elapsed time (formatted): 00:14:39
5
+ BLEU: 0.39087605476379395
6
+ CodeBLEU: 0.5950998528774771
utg4java_pretrain_log_history.txt ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Log History:
2
+ {"loss": 1.6003, "grad_norm": 4.428943157196045, "learning_rate": 0.00019936921218628373, "epoch": 0.05, "step": 200}
3
+ {"loss": 1.0391, "grad_norm": 3.2689905166625977, "learning_rate": 0.00019668500872366127, "epoch": 0.11, "step": 400}
4
+ {"loss": 0.9586, "grad_norm": 3.4730663299560547, "learning_rate": 0.00019400080526103878, "epoch": 0.16, "step": 600}
5
+ {"loss": 0.9416, "grad_norm": 3.3503410816192627, "learning_rate": 0.00019131660179841633, "epoch": 0.21, "step": 800}
6
+ {"loss": 0.9352, "grad_norm": 3.9026317596435547, "learning_rate": 0.00018863239833579387, "epoch": 0.27, "step": 1000}
7
+ {"loss": 0.9018, "grad_norm": 3.4323599338531494, "learning_rate": 0.00018594819487317138, "epoch": 0.32, "step": 1200}
8
+ {"loss": 0.8959, "grad_norm": 2.90022349357605, "learning_rate": 0.00018326399141054892, "epoch": 0.37, "step": 1400}
9
+ {"loss": 0.8777, "grad_norm": 3.3339474201202393, "learning_rate": 0.00018057978794792646, "epoch": 0.43, "step": 1600}
10
+ {"loss": 0.8719, "grad_norm": 5.839554309844971, "learning_rate": 0.00017789558448530398, "epoch": 0.48, "step": 1800}
11
+ {"loss": 0.8763, "grad_norm": 3.7872190475463867, "learning_rate": 0.00017521138102268152, "epoch": 0.53, "step": 2000}
12
+ {"loss": 0.8601, "grad_norm": 3.5567479133605957, "learning_rate": 0.00017252717756005906, "epoch": 0.58, "step": 2200}
13
+ {"loss": 0.8522, "grad_norm": 2.728114604949951, "learning_rate": 0.0001698429740974366, "epoch": 0.64, "step": 2400}
14
+ {"loss": 0.852, "grad_norm": 2.7635385990142822, "learning_rate": 0.00016717219165212724, "epoch": 0.69, "step": 2600}
15
+ {"loss": 0.8622, "grad_norm": 2.332137107849121, "learning_rate": 0.00016448798818950478, "epoch": 0.74, "step": 2800}
16
+ {"loss": 0.8814, "grad_norm": 2.689222812652588, "learning_rate": 0.00016180378472688232, "epoch": 0.8, "step": 3000}
17
+ {"loss": 0.8223, "grad_norm": 3.2268168926239014, "learning_rate": 0.00015911958126425983, "epoch": 0.85, "step": 3200}
18
+ {"loss": 0.8538, "grad_norm": 2.7432162761688232, "learning_rate": 0.00015643537780163738, "epoch": 0.9, "step": 3400}
19
+ {"loss": 0.8118, "grad_norm": 3.417742967605591, "learning_rate": 0.00015375117433901492, "epoch": 0.96, "step": 3600}
20
+ {"eval_loss": 0.7114242315292358, "eval_runtime": 144.1269, "eval_samples_per_second": 13.051, "eval_steps_per_second": 1.637, "epoch": 1.0, "step": 3763}
21
+ {"loss": 0.7983, "grad_norm": 2.479877233505249, "learning_rate": 0.00015106697087639243, "epoch": 1.01, "step": 3800}
22
+ {"loss": 0.7892, "grad_norm": 2.73120379447937, "learning_rate": 0.00014838276741376997, "epoch": 1.06, "step": 4000}
23
+ {"loss": 0.7747, "grad_norm": 2.924459934234619, "learning_rate": 0.00014569856395114749, "epoch": 1.12, "step": 4200}
24
+ {"loss": 0.7758, "grad_norm": 3.1980695724487305, "learning_rate": 0.00014301436048852503, "epoch": 1.17, "step": 4400}
25
+ {"loss": 0.7814, "grad_norm": 2.564530849456787, "learning_rate": 0.00014033015702590257, "epoch": 1.22, "step": 4600}
26
+ {"loss": 0.7501, "grad_norm": 2.7397029399871826, "learning_rate": 0.0001376593745805932, "epoch": 1.28, "step": 4800}
27
+ {"loss": 0.7712, "grad_norm": 2.7164580821990967, "learning_rate": 0.00013497517111797075, "epoch": 1.33, "step": 5000}
28
+ {"loss": 0.7999, "grad_norm": 2.4152510166168213, "learning_rate": 0.0001322909676553483, "epoch": 1.38, "step": 5200}
29
+ {"loss": 0.7516, "grad_norm": 2.9376044273376465, "learning_rate": 0.00012960676419272583, "epoch": 1.44, "step": 5400}
30
+ {"loss": 0.7663, "grad_norm": 3.0849993228912354, "learning_rate": 0.00012692256073010337, "epoch": 1.49, "step": 5600}
31
+ {"loss": 0.7725, "grad_norm": 2.0552046298980713, "learning_rate": 0.00012423835726748088, "epoch": 1.54, "step": 5800}
32
+ {"loss": 0.748, "grad_norm": 4.300168991088867, "learning_rate": 0.00012155415380485841, "epoch": 1.59, "step": 6000}
33
+ {"loss": 0.7219, "grad_norm": 2.172149658203125, "learning_rate": 0.00011886995034223594, "epoch": 1.65, "step": 6200}
34
+ {"loss": 0.7565, "grad_norm": 4.83528470993042, "learning_rate": 0.00011618574687961348, "epoch": 1.7, "step": 6400}
35
+ {"loss": 0.7433, "grad_norm": 2.4364535808563232, "learning_rate": 0.00011350154341699102, "epoch": 1.75, "step": 6600}
36
+ {"loss": 0.729, "grad_norm": 3.630072593688965, "learning_rate": 0.00011081733995436854, "epoch": 1.81, "step": 6800}
37
+ {"loss": 0.7178, "grad_norm": 3.485239267349243, "learning_rate": 0.00010813313649174608, "epoch": 1.86, "step": 7000}
38
+ {"loss": 0.7507, "grad_norm": 2.265608787536621, "learning_rate": 0.00010544893302912362, "epoch": 1.91, "step": 7200}
39
+ {"loss": 0.763, "grad_norm": 2.48197340965271, "learning_rate": 0.00010276472956650113, "epoch": 1.97, "step": 7400}
40
+ {"eval_loss": 0.6458454728126526, "eval_runtime": 138.1168, "eval_samples_per_second": 13.619, "eval_steps_per_second": 1.709, "epoch": 2.0, "step": 7526}
41
+ {"loss": 0.7165, "grad_norm": 3.2982826232910156, "learning_rate": 0.00010008052610387867, "epoch": 2.02, "step": 7600}
42
+ {"loss": 0.7093, "grad_norm": 2.9913341999053955, "learning_rate": 9.739632264125621e-05, "epoch": 2.07, "step": 7800}
43
+ {"loss": 0.7007, "grad_norm": 3.782381057739258, "learning_rate": 9.471211917863374e-05, "epoch": 2.13, "step": 8000}
44
+ {"loss": 0.6961, "grad_norm": 1.392814040184021, "learning_rate": 9.202791571601128e-05, "epoch": 2.18, "step": 8200}
45
+ {"loss": 0.7014, "grad_norm": 1.976282000541687, "learning_rate": 8.934371225338881e-05, "epoch": 2.23, "step": 8400}
46
+ {"loss": 0.6845, "grad_norm": 1.8080275058746338, "learning_rate": 8.665950879076634e-05, "epoch": 2.29, "step": 8600}
47
+ {"loss": 0.6766, "grad_norm": 2.2179641723632812, "learning_rate": 8.397530532814388e-05, "epoch": 2.34, "step": 8800}
48
+ {"loss": 0.6716, "grad_norm": 4.8770551681518555, "learning_rate": 8.129110186552141e-05, "epoch": 2.39, "step": 9000}
49
+ {"loss": 0.663, "grad_norm": 2.4720568656921387, "learning_rate": 7.860689840289895e-05, "epoch": 2.44, "step": 9200}
50
+ {"loss": 0.6629, "grad_norm": 2.546283006668091, "learning_rate": 7.592269494027648e-05, "epoch": 2.5, "step": 9400}
51
+ {"loss": 0.6677, "grad_norm": 2.2792224884033203, "learning_rate": 7.323849147765402e-05, "epoch": 2.55, "step": 9600}
52
+ {"loss": 0.6697, "grad_norm": 2.87917160987854, "learning_rate": 7.055428801503155e-05, "epoch": 2.6, "step": 9800}
53
+ {"loss": 0.661, "grad_norm": 4.642680644989014, "learning_rate": 6.787008455240907e-05, "epoch": 2.66, "step": 10000}
54
+ {"loss": 0.6447, "grad_norm": 2.9181325435638428, "learning_rate": 6.51858810897866e-05, "epoch": 2.71, "step": 10200}
55
+ {"loss": 0.6668, "grad_norm": 1.9983739852905273, "learning_rate": 6.250167762716414e-05, "epoch": 2.76, "step": 10400}
56
+ {"loss": 0.6494, "grad_norm": 3.3339133262634277, "learning_rate": 5.9817474164541676e-05, "epoch": 2.82, "step": 10600}
57
+ {"loss": 0.6471, "grad_norm": 2.7515461444854736, "learning_rate": 5.7133270701919204e-05, "epoch": 2.87, "step": 10800}
58
+ {"loss": 0.6513, "grad_norm": 2.502366781234741, "learning_rate": 5.4462488256609854e-05, "epoch": 2.92, "step": 11000}
59
+ {"loss": 0.6701, "grad_norm": 2.680753707885742, "learning_rate": 5.177828479398739e-05, "epoch": 2.98, "step": 11200}
60
+ {"eval_loss": 0.5908769369125366, "eval_runtime": 267.1069, "eval_samples_per_second": 7.042, "eval_steps_per_second": 0.884, "epoch": 3.0, "step": 11289}
61
+ {"loss": 0.6571, "grad_norm": 1.714341640472412, "learning_rate": 4.909408133136492e-05, "epoch": 3.03, "step": 11400}
62
+ {"loss": 0.6627, "grad_norm": 2.996971607208252, "learning_rate": 4.640987786874245e-05, "epoch": 3.08, "step": 11600}
63
+ {"loss": 0.6486, "grad_norm": 2.6136629581451416, "learning_rate": 4.3725674406119985e-05, "epoch": 3.14, "step": 11800}
64
+ {"loss": 0.5942, "grad_norm": 1.8732506036758423, "learning_rate": 4.104147094349752e-05, "epoch": 3.19, "step": 12000}
65
+ {"loss": 0.6228, "grad_norm": 3.316340923309326, "learning_rate": 3.8357267480875054e-05, "epoch": 3.24, "step": 12200}
66
+ {"loss": 0.6313, "grad_norm": 2.4904277324676514, "learning_rate": 3.567306401825258e-05, "epoch": 3.3, "step": 12400}
67
+ {"loss": 0.6132, "grad_norm": 2.3936824798583984, "learning_rate": 3.2988860555630116e-05, "epoch": 3.35, "step": 12600}
68
+ {"loss": 0.6108, "grad_norm": 2.5523078441619873, "learning_rate": 3.030465709300765e-05, "epoch": 3.4, "step": 12800}
69
+ {"loss": 0.6133, "grad_norm": 2.3019254207611084, "learning_rate": 2.7620453630385185e-05, "epoch": 3.45, "step": 13000}
70
+ {"loss": 0.6241, "grad_norm": 2.492788791656494, "learning_rate": 2.493625016776272e-05, "epoch": 3.51, "step": 13200}
71
+ {"loss": 0.6023, "grad_norm": 2.1467068195343018, "learning_rate": 2.2265467722453363e-05, "epoch": 3.56, "step": 13400}
72
+ {"loss": 0.6059, "grad_norm": 1.78839910030365, "learning_rate": 1.9581264259830894e-05, "epoch": 3.61, "step": 13600}
73
+ {"loss": 0.5922, "grad_norm": 2.343613624572754, "learning_rate": 1.689706079720843e-05, "epoch": 3.67, "step": 13800}
74
+ {"loss": 0.6092, "grad_norm": 2.2175772190093994, "learning_rate": 1.4212857334585964e-05, "epoch": 3.72, "step": 14000}
75
+ {"loss": 0.6055, "grad_norm": 1.8630731105804443, "learning_rate": 1.1528653871963495e-05, "epoch": 3.77, "step": 14200}
76
+ {"loss": 0.6053, "grad_norm": 1.4924801588058472, "learning_rate": 8.84445040934103e-06, "epoch": 3.83, "step": 14400}
77
+ {"loss": 0.5846, "grad_norm": 3.014918088912964, "learning_rate": 6.1602469467185615e-06, "epoch": 3.88, "step": 14600}
78
+ {"loss": 0.5826, "grad_norm": 1.5459446907043457, "learning_rate": 3.4760434840960946e-06, "epoch": 3.93, "step": 14800}
79
+ {"loss": 0.608, "grad_norm": 3.936332941055298, "learning_rate": 7.918400214736277e-07, "epoch": 3.99, "step": 15000}
80
+ {"eval_loss": 0.5480290651321411, "eval_runtime": 221.6429, "eval_samples_per_second": 8.487, "eval_steps_per_second": 1.065, "epoch": 4.0, "step": 15052}
81
+ {"train_runtime": 7813.3494, "train_samples_per_second": 7.706, "train_steps_per_second": 1.926, "total_flos": 8148659183026176.0, "train_loss": 0.7414002821479045, "epoch": 4.0, "step": 15052}
utg4java_pretrain_results.txt ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ SUMMARY MODEL:
2
+
3
+ Model Params Size: 60492288
4
+ Model Params Size Formatted: 60.49 M
5
+ Model Disk Size: 242030465
6
+ Model Disk Size Formatted: 242.03 MB
7
+
8
+
9
+ TRAINING AND VALIDATION RESULTS:
10
+
11
+ Training batch size: 4
12
+ Validation batch size: 8
13
+ Total expected epochs: 4
14
+ Total expected trainig steps: 15052
15
+ Total expected trainig steps 2: 15052
16
+ Total trained epochs: 4.0
17
+ Total trained steps: 15052
18
+ Elapsed time: 7849.268085718155 seconds
19
+ Elapsed time (formatted): 02:10:49
20
+ Total flos: 8148659183026176.0
21
+ Total flos (formatted): 8.148659e+15
22
+ Best epoch val_loss: 0.5480290651321411
23
+ Best model checkpoint: E:/000_Tesis/test_executions/pretrain_utg4java\checkpoint-15052
24
+
25
+
26
+
27
+ SUMMARY DATASETS:
28
+
29
+ Loaded Dataset:
30
+ DatasetDict({
31
+ train: Dataset({
32
+ features: ['text'],
33
+ num_rows: 15052
34
+ })
35
+ valid: Dataset({
36
+ features: ['text'],
37
+ num_rows: 1881
38
+ })
39
+ test: Dataset({
40
+ features: ['text'],
41
+ num_rows: 1882
42
+ })
43
+ })
44
+
45
+ Tokenized Dataset:
46
+ DatasetDict({
47
+ train: Dataset({
48
+ features: ['input_ids'],
49
+ num_rows: 15052
50
+ })
51
+ valid: Dataset({
52
+ features: ['input_ids'],
53
+ num_rows: 1881
54
+ })
55
+ test: Dataset({
56
+ features: ['input_ids'],
57
+ num_rows: 1882
58
+ })
59
+ })
60
+
vocab.json ADDED
The diff for this file is too large to render. See raw diff