Md Mushfiqur Rahman commited on
Commit
d75eb36
1 Parent(s): 04c8cb6

Upload with huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - canine
5
+ - pretrained-on-english-language
6
+ ---
7
+
8
+ ### How to use
9
+
10
+ Here is how to use this model:
11
+
12
+ ```python
13
+ from transformers import CanineModel
14
+ model = CanineModel.from_pretrained('mushfiqur11/<repo name>')
15
+ ```
all_results.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 29.41,
3
+ "eval_las": 76.59314722877838,
4
+ "eval_loss": 2.0029706954956055,
5
+ "eval_runtime": 3.6676,
6
+ "eval_samples": 507,
7
+ "eval_samples_per_second": 138.239,
8
+ "eval_steps_per_second": 17.45,
9
+ "eval_uas": 80.7682916904045,
10
+ "test_las": 73.48473223876016,
11
+ "test_loss": 2.3923442363739014,
12
+ "test_runtime": 3.9112,
13
+ "test_samples": 543,
14
+ "test_samples_per_second": 138.834,
15
+ "test_steps_per_second": 17.386,
16
+ "test_uas": 78.47168942765076,
17
+ "train_loss": 0.30513293038881745,
18
+ "train_runtime": 3575.6323,
19
+ "train_samples": 7050,
20
+ "train_samples_per_second": 134.242,
21
+ "train_steps_per_second": 4.195
22
+ }
config.json ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-cased",
3
+ "architectures": [
4
+ "BertForBiaffineParsing"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "_",
14
+ "1": "acl",
15
+ "2": "advcl",
16
+ "3": "advmod",
17
+ "4": "amod",
18
+ "5": "appos",
19
+ "6": "aux",
20
+ "7": "case",
21
+ "8": "cc",
22
+ "9": "ccomp",
23
+ "10": "clf",
24
+ "11": "compound",
25
+ "12": "conj",
26
+ "13": "cop",
27
+ "14": "csubj",
28
+ "15": "dep",
29
+ "16": "det",
30
+ "17": "discourse",
31
+ "18": "dislocated",
32
+ "19": "expl",
33
+ "20": "fixed",
34
+ "21": "flat",
35
+ "22": "goeswith",
36
+ "23": "iobj",
37
+ "24": "list",
38
+ "25": "mark",
39
+ "26": "nmod",
40
+ "27": "nsubj",
41
+ "28": "nummod",
42
+ "29": "obj",
43
+ "30": "obl",
44
+ "31": "orphan",
45
+ "32": "parataxis",
46
+ "33": "punct",
47
+ "34": "reparandum",
48
+ "35": "root",
49
+ "36": "vocative",
50
+ "37": "xcomp"
51
+ },
52
+ "initializer_range": 0.02,
53
+ "intermediate_size": 3072,
54
+ "label2id": {
55
+ "_": 0,
56
+ "acl": 1,
57
+ "advcl": 2,
58
+ "advmod": 3,
59
+ "amod": 4,
60
+ "appos": 5,
61
+ "aux": 6,
62
+ "case": 7,
63
+ "cc": 8,
64
+ "ccomp": 9,
65
+ "clf": 10,
66
+ "compound": 11,
67
+ "conj": 12,
68
+ "cop": 13,
69
+ "csubj": 14,
70
+ "dep": 15,
71
+ "det": 16,
72
+ "discourse": 17,
73
+ "dislocated": 18,
74
+ "expl": 19,
75
+ "fixed": 20,
76
+ "flat": 21,
77
+ "goeswith": 22,
78
+ "iobj": 23,
79
+ "list": 24,
80
+ "mark": 25,
81
+ "nmod": 26,
82
+ "nsubj": 27,
83
+ "nummod": 28,
84
+ "obj": 29,
85
+ "obl": 30,
86
+ "orphan": 31,
87
+ "parataxis": 32,
88
+ "punct": 33,
89
+ "reparandum": 34,
90
+ "root": 35,
91
+ "vocative": 36,
92
+ "xcomp": 37
93
+ },
94
+ "layer_norm_eps": 1e-12,
95
+ "max_position_embeddings": 512,
96
+ "model_type": "bert",
97
+ "num_attention_heads": 12,
98
+ "num_hidden_layers": 12,
99
+ "pad_token_id": -100,
100
+ "position_embedding_type": "absolute",
101
+ "torch_dtype": "float32",
102
+ "transformers_version": "4.17.0",
103
+ "type_vocab_size": 2,
104
+ "use_cache": true,
105
+ "vocab_size": 28996
106
+ }
eval_predictions.csv 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 sha256:6ef1f98b6a7e0b609fd38158310ff47c036224faf9db35c7eb27e40ed6b8563c
3
+ size 525577269
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
test_predictions.csv ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "add_prefix_space": false, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-cased", "tokenizer_class": "BertTokenizer"}
trainer_state.json ADDED
@@ -0,0 +1,545 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 76.59314722877838,
3
+ "best_model_checkpoint": "/scratch/mrahma45/pixel/finetuned_models/bert/bert-base-finetuned-parsing-ud-Japanese-GSD/checkpoint-4000",
4
+ "epoch": 29.41176470588235,
5
+ "global_step": 6500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.45,
12
+ "learning_rate": 7.52e-05,
13
+ "loss": 3.6592,
14
+ "step": 100
15
+ },
16
+ {
17
+ "epoch": 0.9,
18
+ "learning_rate": 7.949530201342283e-05,
19
+ "loss": 1.457,
20
+ "step": 200
21
+ },
22
+ {
23
+ "epoch": 1.36,
24
+ "learning_rate": 7.895838926174497e-05,
25
+ "loss": 1.1567,
26
+ "step": 300
27
+ },
28
+ {
29
+ "epoch": 1.81,
30
+ "learning_rate": 7.842147651006712e-05,
31
+ "loss": 1.0594,
32
+ "step": 400
33
+ },
34
+ {
35
+ "epoch": 2.26,
36
+ "learning_rate": 7.788456375838927e-05,
37
+ "loss": 0.9461,
38
+ "step": 500
39
+ },
40
+ {
41
+ "epoch": 2.26,
42
+ "eval_las": 72.71913404411167,
43
+ "eval_loss": 0.9768415689468384,
44
+ "eval_runtime": 3.6781,
45
+ "eval_samples_per_second": 137.841,
46
+ "eval_steps_per_second": 17.4,
47
+ "eval_uas": 77.79767233661593,
48
+ "step": 500
49
+ },
50
+ {
51
+ "epoch": 2.71,
52
+ "learning_rate": 7.734765100671142e-05,
53
+ "loss": 0.8798,
54
+ "step": 600
55
+ },
56
+ {
57
+ "epoch": 3.17,
58
+ "learning_rate": 7.681073825503357e-05,
59
+ "loss": 0.8167,
60
+ "step": 700
61
+ },
62
+ {
63
+ "epoch": 3.62,
64
+ "learning_rate": 7.627382550335572e-05,
65
+ "loss": 0.7486,
66
+ "step": 800
67
+ },
68
+ {
69
+ "epoch": 4.07,
70
+ "learning_rate": 7.573691275167786e-05,
71
+ "loss": 0.7195,
72
+ "step": 900
73
+ },
74
+ {
75
+ "epoch": 4.52,
76
+ "learning_rate": 7.52e-05,
77
+ "loss": 0.6067,
78
+ "step": 1000
79
+ },
80
+ {
81
+ "epoch": 4.52,
82
+ "eval_las": 75.72230813054448,
83
+ "eval_loss": 0.9424547553062439,
84
+ "eval_runtime": 3.6759,
85
+ "eval_samples_per_second": 137.927,
86
+ "eval_steps_per_second": 17.411,
87
+ "eval_uas": 80.39391226499552,
88
+ "step": 1000
89
+ },
90
+ {
91
+ "epoch": 4.98,
92
+ "learning_rate": 7.466308724832215e-05,
93
+ "loss": 0.6358,
94
+ "step": 1100
95
+ },
96
+ {
97
+ "epoch": 5.43,
98
+ "learning_rate": 7.41261744966443e-05,
99
+ "loss": 0.4864,
100
+ "step": 1200
101
+ },
102
+ {
103
+ "epoch": 5.88,
104
+ "learning_rate": 7.358926174496644e-05,
105
+ "loss": 0.5311,
106
+ "step": 1300
107
+ },
108
+ {
109
+ "epoch": 6.33,
110
+ "learning_rate": 7.305234899328859e-05,
111
+ "loss": 0.4331,
112
+ "step": 1400
113
+ },
114
+ {
115
+ "epoch": 6.79,
116
+ "learning_rate": 7.251543624161074e-05,
117
+ "loss": 0.4255,
118
+ "step": 1500
119
+ },
120
+ {
121
+ "epoch": 6.79,
122
+ "eval_las": 75.43745421990722,
123
+ "eval_loss": 1.1136951446533203,
124
+ "eval_runtime": 3.6925,
125
+ "eval_samples_per_second": 137.307,
126
+ "eval_steps_per_second": 17.333,
127
+ "eval_uas": 80.19044518596891,
128
+ "step": 1500
129
+ },
130
+ {
131
+ "epoch": 7.24,
132
+ "learning_rate": 7.197852348993289e-05,
133
+ "loss": 0.3744,
134
+ "step": 1600
135
+ },
136
+ {
137
+ "epoch": 7.69,
138
+ "learning_rate": 7.144161073825504e-05,
139
+ "loss": 0.3474,
140
+ "step": 1700
141
+ },
142
+ {
143
+ "epoch": 8.14,
144
+ "learning_rate": 7.090469798657718e-05,
145
+ "loss": 0.3244,
146
+ "step": 1800
147
+ },
148
+ {
149
+ "epoch": 8.6,
150
+ "learning_rate": 7.036778523489933e-05,
151
+ "loss": 0.2716,
152
+ "step": 1900
153
+ },
154
+ {
155
+ "epoch": 9.05,
156
+ "learning_rate": 6.983087248322148e-05,
157
+ "loss": 0.2877,
158
+ "step": 2000
159
+ },
160
+ {
161
+ "epoch": 9.05,
162
+ "eval_las": 75.58395051680637,
163
+ "eval_loss": 1.3644814491271973,
164
+ "eval_runtime": 3.6735,
165
+ "eval_samples_per_second": 138.014,
166
+ "eval_steps_per_second": 17.422,
167
+ "eval_uas": 80.19858386912998,
168
+ "step": 2000
169
+ },
170
+ {
171
+ "epoch": 9.5,
172
+ "learning_rate": 6.929395973154363e-05,
173
+ "loss": 0.2162,
174
+ "step": 2100
175
+ },
176
+ {
177
+ "epoch": 9.95,
178
+ "learning_rate": 6.875704697986578e-05,
179
+ "loss": 0.2386,
180
+ "step": 2200
181
+ },
182
+ {
183
+ "epoch": 10.41,
184
+ "learning_rate": 6.822013422818793e-05,
185
+ "loss": 0.1861,
186
+ "step": 2300
187
+ },
188
+ {
189
+ "epoch": 10.86,
190
+ "learning_rate": 6.768322147651007e-05,
191
+ "loss": 0.1989,
192
+ "step": 2400
193
+ },
194
+ {
195
+ "epoch": 11.31,
196
+ "learning_rate": 6.714630872483222e-05,
197
+ "loss": 0.1631,
198
+ "step": 2500
199
+ },
200
+ {
201
+ "epoch": 11.31,
202
+ "eval_las": 75.29095792300807,
203
+ "eval_loss": 1.5608779191970825,
204
+ "eval_runtime": 3.672,
205
+ "eval_samples_per_second": 138.07,
206
+ "eval_steps_per_second": 17.429,
207
+ "eval_uas": 80.17416781964678,
208
+ "step": 2500
209
+ },
210
+ {
211
+ "epoch": 11.76,
212
+ "learning_rate": 6.660939597315437e-05,
213
+ "loss": 0.1637,
214
+ "step": 2600
215
+ },
216
+ {
217
+ "epoch": 12.22,
218
+ "learning_rate": 6.607248322147652e-05,
219
+ "loss": 0.1513,
220
+ "step": 2700
221
+ },
222
+ {
223
+ "epoch": 12.67,
224
+ "learning_rate": 6.553557046979867e-05,
225
+ "loss": 0.1318,
226
+ "step": 2800
227
+ },
228
+ {
229
+ "epoch": 13.12,
230
+ "learning_rate": 6.499865771812081e-05,
231
+ "loss": 0.1326,
232
+ "step": 2900
233
+ },
234
+ {
235
+ "epoch": 13.57,
236
+ "learning_rate": 6.446174496644296e-05,
237
+ "loss": 0.1156,
238
+ "step": 3000
239
+ },
240
+ {
241
+ "epoch": 13.57,
242
+ "eval_las": 75.71416944738341,
243
+ "eval_loss": 1.6040022373199463,
244
+ "eval_runtime": 3.6712,
245
+ "eval_samples_per_second": 138.103,
246
+ "eval_steps_per_second": 17.433,
247
+ "eval_uas": 80.20672255229104,
248
+ "step": 3000
249
+ },
250
+ {
251
+ "epoch": 14.03,
252
+ "learning_rate": 6.392483221476511e-05,
253
+ "loss": 0.117,
254
+ "step": 3100
255
+ },
256
+ {
257
+ "epoch": 14.48,
258
+ "learning_rate": 6.338791946308726e-05,
259
+ "loss": 0.0966,
260
+ "step": 3200
261
+ },
262
+ {
263
+ "epoch": 14.93,
264
+ "learning_rate": 6.28510067114094e-05,
265
+ "loss": 0.1057,
266
+ "step": 3300
267
+ },
268
+ {
269
+ "epoch": 15.38,
270
+ "learning_rate": 6.231409395973154e-05,
271
+ "loss": 0.091,
272
+ "step": 3400
273
+ },
274
+ {
275
+ "epoch": 15.84,
276
+ "learning_rate": 6.177718120805369e-05,
277
+ "loss": 0.09,
278
+ "step": 3500
279
+ },
280
+ {
281
+ "epoch": 15.84,
282
+ "eval_las": 75.79555627899406,
283
+ "eval_loss": 1.8544515371322632,
284
+ "eval_runtime": 3.6721,
285
+ "eval_samples_per_second": 138.068,
286
+ "eval_steps_per_second": 17.429,
287
+ "eval_uas": 80.03581020590869,
288
+ "step": 3500
289
+ },
290
+ {
291
+ "epoch": 16.29,
292
+ "learning_rate": 6.124026845637584e-05,
293
+ "loss": 0.0816,
294
+ "step": 3600
295
+ },
296
+ {
297
+ "epoch": 16.74,
298
+ "learning_rate": 6.070335570469799e-05,
299
+ "loss": 0.0809,
300
+ "step": 3700
301
+ },
302
+ {
303
+ "epoch": 17.19,
304
+ "learning_rate": 6.0166442953020136e-05,
305
+ "loss": 0.0753,
306
+ "step": 3800
307
+ },
308
+ {
309
+ "epoch": 17.65,
310
+ "learning_rate": 5.962953020134229e-05,
311
+ "loss": 0.073,
312
+ "step": 3900
313
+ },
314
+ {
315
+ "epoch": 18.1,
316
+ "learning_rate": 5.909261744966444e-05,
317
+ "loss": 0.07,
318
+ "step": 4000
319
+ },
320
+ {
321
+ "epoch": 18.1,
322
+ "eval_las": 76.59314722877838,
323
+ "eval_loss": 2.0029706954956055,
324
+ "eval_runtime": 3.6667,
325
+ "eval_samples_per_second": 138.273,
326
+ "eval_steps_per_second": 17.455,
327
+ "eval_uas": 80.7682916904045,
328
+ "step": 4000
329
+ },
330
+ {
331
+ "epoch": 18.55,
332
+ "learning_rate": 5.855570469798659e-05,
333
+ "loss": 0.0641,
334
+ "step": 4100
335
+ },
336
+ {
337
+ "epoch": 19.0,
338
+ "learning_rate": 5.8018791946308735e-05,
339
+ "loss": 0.0687,
340
+ "step": 4200
341
+ },
342
+ {
343
+ "epoch": 19.46,
344
+ "learning_rate": 5.7481879194630884e-05,
345
+ "loss": 0.0548,
346
+ "step": 4300
347
+ },
348
+ {
349
+ "epoch": 19.91,
350
+ "learning_rate": 5.694496644295303e-05,
351
+ "loss": 0.0608,
352
+ "step": 4400
353
+ },
354
+ {
355
+ "epoch": 20.36,
356
+ "learning_rate": 5.6408053691275166e-05,
357
+ "loss": 0.0526,
358
+ "step": 4500
359
+ },
360
+ {
361
+ "epoch": 20.36,
362
+ "eval_las": 75.82811101163833,
363
+ "eval_loss": 2.0474750995635986,
364
+ "eval_runtime": 3.6759,
365
+ "eval_samples_per_second": 137.925,
366
+ "eval_steps_per_second": 17.411,
367
+ "eval_uas": 80.42646699763978,
368
+ "step": 4500
369
+ },
370
+ {
371
+ "epoch": 20.81,
372
+ "learning_rate": 5.5871140939597315e-05,
373
+ "loss": 0.0574,
374
+ "step": 4600
375
+ },
376
+ {
377
+ "epoch": 21.27,
378
+ "learning_rate": 5.533422818791946e-05,
379
+ "loss": 0.0506,
380
+ "step": 4700
381
+ },
382
+ {
383
+ "epoch": 21.72,
384
+ "learning_rate": 5.479731543624161e-05,
385
+ "loss": 0.0506,
386
+ "step": 4800
387
+ },
388
+ {
389
+ "epoch": 22.17,
390
+ "learning_rate": 5.426040268456376e-05,
391
+ "loss": 0.0478,
392
+ "step": 4900
393
+ },
394
+ {
395
+ "epoch": 22.62,
396
+ "learning_rate": 5.372348993288591e-05,
397
+ "loss": 0.0455,
398
+ "step": 5000
399
+ },
400
+ {
401
+ "epoch": 22.62,
402
+ "eval_las": 75.73044681370554,
403
+ "eval_loss": 2.1534557342529297,
404
+ "eval_runtime": 3.6739,
405
+ "eval_samples_per_second": 138.001,
406
+ "eval_steps_per_second": 17.42,
407
+ "eval_uas": 80.47529909660616,
408
+ "step": 5000
409
+ },
410
+ {
411
+ "epoch": 23.08,
412
+ "learning_rate": 5.3186577181208056e-05,
413
+ "loss": 0.0446,
414
+ "step": 5100
415
+ },
416
+ {
417
+ "epoch": 23.53,
418
+ "learning_rate": 5.2649664429530204e-05,
419
+ "loss": 0.0409,
420
+ "step": 5200
421
+ },
422
+ {
423
+ "epoch": 23.98,
424
+ "learning_rate": 5.211275167785235e-05,
425
+ "loss": 0.0448,
426
+ "step": 5300
427
+ },
428
+ {
429
+ "epoch": 24.43,
430
+ "learning_rate": 5.15758389261745e-05,
431
+ "loss": 0.0379,
432
+ "step": 5400
433
+ },
434
+ {
435
+ "epoch": 24.89,
436
+ "learning_rate": 5.1038926174496656e-05,
437
+ "loss": 0.0416,
438
+ "step": 5500
439
+ },
440
+ {
441
+ "epoch": 24.89,
442
+ "eval_las": 76.22690648653048,
443
+ "eval_loss": 2.1511826515197754,
444
+ "eval_runtime": 3.6773,
445
+ "eval_samples_per_second": 137.872,
446
+ "eval_steps_per_second": 17.404,
447
+ "eval_uas": 80.80898510620982,
448
+ "step": 5500
449
+ },
450
+ {
451
+ "epoch": 25.34,
452
+ "learning_rate": 5.050201342281879e-05,
453
+ "loss": 0.0352,
454
+ "step": 5600
455
+ },
456
+ {
457
+ "epoch": 25.79,
458
+ "learning_rate": 4.996510067114094e-05,
459
+ "loss": 0.0369,
460
+ "step": 5700
461
+ },
462
+ {
463
+ "epoch": 26.24,
464
+ "learning_rate": 4.942818791946309e-05,
465
+ "loss": 0.0354,
466
+ "step": 5800
467
+ },
468
+ {
469
+ "epoch": 26.7,
470
+ "learning_rate": 4.8891275167785235e-05,
471
+ "loss": 0.0342,
472
+ "step": 5900
473
+ },
474
+ {
475
+ "epoch": 27.15,
476
+ "learning_rate": 4.835436241610738e-05,
477
+ "loss": 0.0342,
478
+ "step": 6000
479
+ },
480
+ {
481
+ "epoch": 27.15,
482
+ "eval_las": 75.9908846748596,
483
+ "eval_loss": 2.3812143802642822,
484
+ "eval_runtime": 3.6674,
485
+ "eval_samples_per_second": 138.245,
486
+ "eval_steps_per_second": 17.451,
487
+ "eval_uas": 80.6299340766664,
488
+ "step": 6000
489
+ },
490
+ {
491
+ "epoch": 27.6,
492
+ "learning_rate": 4.781744966442953e-05,
493
+ "loss": 0.0296,
494
+ "step": 6100
495
+ },
496
+ {
497
+ "epoch": 28.05,
498
+ "learning_rate": 4.728053691275168e-05,
499
+ "loss": 0.0304,
500
+ "step": 6200
501
+ },
502
+ {
503
+ "epoch": 28.51,
504
+ "learning_rate": 4.674362416107383e-05,
505
+ "loss": 0.0304,
506
+ "step": 6300
507
+ },
508
+ {
509
+ "epoch": 28.96,
510
+ "learning_rate": 4.6206711409395976e-05,
511
+ "loss": 0.0319,
512
+ "step": 6400
513
+ },
514
+ {
515
+ "epoch": 29.41,
516
+ "learning_rate": 4.5669798657718125e-05,
517
+ "loss": 0.0264,
518
+ "step": 6500
519
+ },
520
+ {
521
+ "epoch": 29.41,
522
+ "eval_las": 75.8769431106047,
523
+ "eval_loss": 2.4017791748046875,
524
+ "eval_runtime": 3.6647,
525
+ "eval_samples_per_second": 138.347,
526
+ "eval_steps_per_second": 17.464,
527
+ "eval_uas": 80.4671604134451,
528
+ "step": 6500
529
+ },
530
+ {
531
+ "epoch": 29.41,
532
+ "step": 6500,
533
+ "total_flos": 3.4624658436900864e+16,
534
+ "train_loss": 0.30513293038881745,
535
+ "train_runtime": 3575.6323,
536
+ "train_samples_per_second": 134.242,
537
+ "train_steps_per_second": 4.195
538
+ }
539
+ ],
540
+ "max_steps": 15000,
541
+ "num_train_epochs": 68,
542
+ "total_flos": 3.4624658436900864e+16,
543
+ "trial_name": null,
544
+ "trial_params": null
545
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec296e36cf98d0966a00f70014d3b1668d53c15b1d0910a0869130066db47b9a
3
+ size 3387
vocab.txt ADDED
The diff for this file is too large to render. See raw diff