Md Mushfiqur Rahman commited on
Commit
69e397f
1 Parent(s): 2a9d84b

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 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 76.92,
3
+ "eval_accuracy": 0.2892071891250798,
4
+ "eval_loss": 1.9474276304244995,
5
+ "eval_runtime": 1.9369,
6
+ "eval_samples": 381,
7
+ "eval_samples_per_second": 196.703,
8
+ "eval_steps_per_second": 24.781,
9
+ "test_accuracy": 0.26173720235226067,
10
+ "test_loss": 2.012873649597168,
11
+ "test_runtime": 2.056,
12
+ "test_samples": 403,
13
+ "test_samples_per_second": 196.01,
14
+ "test_steps_per_second": 24.805,
15
+ "train_loss": 1.4690344212849935,
16
+ "train_runtime": 809.6738,
17
+ "train_samples": 1227,
18
+ "train_samples_per_second": 592.831,
19
+ "train_steps_per_second": 18.526
20
+ }
config.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-multilingual-cased",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "ADJ",
14
+ "1": "ADP",
15
+ "2": "ADV",
16
+ "3": "AUX",
17
+ "4": "CCONJ",
18
+ "5": "DET",
19
+ "6": "INTJ",
20
+ "7": "NOUN",
21
+ "8": "NUM",
22
+ "9": "PART",
23
+ "10": "PRON",
24
+ "11": "PROPN",
25
+ "12": "PUNCT",
26
+ "13": "SCONJ",
27
+ "14": "SYM",
28
+ "15": "VERB",
29
+ "16": "X"
30
+ },
31
+ "initializer_range": 0.02,
32
+ "intermediate_size": 3072,
33
+ "label2id": {
34
+ "ADJ": 0,
35
+ "ADP": 1,
36
+ "ADV": 2,
37
+ "AUX": 3,
38
+ "CCONJ": 4,
39
+ "DET": 5,
40
+ "INTJ": 6,
41
+ "NOUN": 7,
42
+ "NUM": 8,
43
+ "PART": 9,
44
+ "PRON": 10,
45
+ "PROPN": 11,
46
+ "PUNCT": 12,
47
+ "SCONJ": 13,
48
+ "SYM": 14,
49
+ "VERB": 15,
50
+ "X": 16
51
+ },
52
+ "layer_norm_eps": 1e-12,
53
+ "max_position_embeddings": 512,
54
+ "model_type": "bert",
55
+ "num_attention_heads": 12,
56
+ "num_hidden_layers": 12,
57
+ "pad_token_id": 0,
58
+ "pooler_fc_size": 768,
59
+ "pooler_num_attention_heads": 12,
60
+ "pooler_num_fc_layers": 3,
61
+ "pooler_size_per_head": 128,
62
+ "pooler_type": "first_token_transform",
63
+ "position_embedding_type": "absolute",
64
+ "torch_dtype": "float32",
65
+ "transformers_version": "4.17.0",
66
+ "type_vocab_size": 2,
67
+ "use_cache": true,
68
+ "vocab_size": 119547
69
+ }
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:ed3c76ad59f3d32c634977589f05a9e42580750c733496b79ffcd6e3d3f47652
3
+ size 709189741
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-multilingual-cased", "tokenizer_class": "BertTokenizer"}
trainer_state.json ADDED
@@ -0,0 +1,259 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.2892071891250798,
3
+ "best_model_checkpoint": "/scratch/mrahma45/pixel/finetuned_models/mbert/mbert-base-finetuned-pos-ud-Coptic-Scriptorium/checkpoint-500",
4
+ "epoch": 76.92307692307692,
5
+ "global_step": 3000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 2.56,
12
+ "learning_rate": 7.92e-05,
13
+ "loss": 2.1425,
14
+ "step": 100
15
+ },
16
+ {
17
+ "epoch": 5.13,
18
+ "learning_rate": 7.946845637583894e-05,
19
+ "loss": 1.9316,
20
+ "step": 200
21
+ },
22
+ {
23
+ "epoch": 7.69,
24
+ "learning_rate": 7.893154362416109e-05,
25
+ "loss": 1.9066,
26
+ "step": 300
27
+ },
28
+ {
29
+ "epoch": 10.26,
30
+ "learning_rate": 7.839463087248322e-05,
31
+ "loss": 1.8917,
32
+ "step": 400
33
+ },
34
+ {
35
+ "epoch": 12.82,
36
+ "learning_rate": 7.785771812080537e-05,
37
+ "loss": 1.88,
38
+ "step": 500
39
+ },
40
+ {
41
+ "epoch": 12.82,
42
+ "eval_accuracy": 0.2892071891250798,
43
+ "eval_loss": 1.9474276304244995,
44
+ "eval_runtime": 1.9459,
45
+ "eval_samples_per_second": 195.796,
46
+ "eval_steps_per_second": 24.667,
47
+ "step": 500
48
+ },
49
+ {
50
+ "epoch": 15.38,
51
+ "learning_rate": 7.732080536912752e-05,
52
+ "loss": 1.8777,
53
+ "step": 600
54
+ },
55
+ {
56
+ "epoch": 17.95,
57
+ "learning_rate": 7.678389261744967e-05,
58
+ "loss": 1.8674,
59
+ "step": 700
60
+ },
61
+ {
62
+ "epoch": 20.51,
63
+ "learning_rate": 7.624697986577182e-05,
64
+ "loss": 1.8495,
65
+ "step": 800
66
+ },
67
+ {
68
+ "epoch": 23.08,
69
+ "learning_rate": 7.571006711409396e-05,
70
+ "loss": 1.838,
71
+ "step": 900
72
+ },
73
+ {
74
+ "epoch": 25.64,
75
+ "learning_rate": 7.517315436241611e-05,
76
+ "loss": 1.8131,
77
+ "step": 1000
78
+ },
79
+ {
80
+ "epoch": 25.64,
81
+ "eval_accuracy": 0.28847732871088405,
82
+ "eval_loss": 1.996766209602356,
83
+ "eval_runtime": 1.9595,
84
+ "eval_samples_per_second": 194.438,
85
+ "eval_steps_per_second": 24.496,
86
+ "step": 1000
87
+ },
88
+ {
89
+ "epoch": 28.21,
90
+ "learning_rate": 7.463624161073826e-05,
91
+ "loss": 1.7921,
92
+ "step": 1100
93
+ },
94
+ {
95
+ "epoch": 30.77,
96
+ "learning_rate": 7.409932885906041e-05,
97
+ "loss": 1.7496,
98
+ "step": 1200
99
+ },
100
+ {
101
+ "epoch": 33.33,
102
+ "learning_rate": 7.356241610738256e-05,
103
+ "loss": 1.7099,
104
+ "step": 1300
105
+ },
106
+ {
107
+ "epoch": 35.9,
108
+ "learning_rate": 7.30255033557047e-05,
109
+ "loss": 1.6553,
110
+ "step": 1400
111
+ },
112
+ {
113
+ "epoch": 38.46,
114
+ "learning_rate": 7.248859060402685e-05,
115
+ "loss": 1.5873,
116
+ "step": 1500
117
+ },
118
+ {
119
+ "epoch": 38.46,
120
+ "eval_accuracy": 0.261290028282091,
121
+ "eval_loss": 2.346529960632324,
122
+ "eval_runtime": 1.9481,
123
+ "eval_samples_per_second": 195.576,
124
+ "eval_steps_per_second": 24.639,
125
+ "step": 1500
126
+ },
127
+ {
128
+ "epoch": 41.03,
129
+ "learning_rate": 7.1951677852349e-05,
130
+ "loss": 1.5155,
131
+ "step": 1600
132
+ },
133
+ {
134
+ "epoch": 43.59,
135
+ "learning_rate": 7.141476510067115e-05,
136
+ "loss": 1.4393,
137
+ "step": 1700
138
+ },
139
+ {
140
+ "epoch": 46.15,
141
+ "learning_rate": 7.08778523489933e-05,
142
+ "loss": 1.362,
143
+ "step": 1800
144
+ },
145
+ {
146
+ "epoch": 48.72,
147
+ "learning_rate": 7.034093959731545e-05,
148
+ "loss": 1.2868,
149
+ "step": 1900
150
+ },
151
+ {
152
+ "epoch": 51.28,
153
+ "learning_rate": 6.98040268456376e-05,
154
+ "loss": 1.2522,
155
+ "step": 2000
156
+ },
157
+ {
158
+ "epoch": 51.28,
159
+ "eval_accuracy": 0.23583614633701305,
160
+ "eval_loss": 3.054924249649048,
161
+ "eval_runtime": 1.9514,
162
+ "eval_samples_per_second": 195.244,
163
+ "eval_steps_per_second": 24.598,
164
+ "step": 2000
165
+ },
166
+ {
167
+ "epoch": 53.85,
168
+ "learning_rate": 6.927248322147651e-05,
169
+ "loss": 1.1646,
170
+ "step": 2100
171
+ },
172
+ {
173
+ "epoch": 56.41,
174
+ "learning_rate": 6.873557046979866e-05,
175
+ "loss": 1.1278,
176
+ "step": 2200
177
+ },
178
+ {
179
+ "epoch": 58.97,
180
+ "learning_rate": 6.820402684563758e-05,
181
+ "loss": 1.0644,
182
+ "step": 2300
183
+ },
184
+ {
185
+ "epoch": 61.54,
186
+ "learning_rate": 6.766711409395973e-05,
187
+ "loss": 1.021,
188
+ "step": 2400
189
+ },
190
+ {
191
+ "epoch": 64.1,
192
+ "learning_rate": 6.713020134228188e-05,
193
+ "loss": 0.9782,
194
+ "step": 2500
195
+ },
196
+ {
197
+ "epoch": 64.1,
198
+ "eval_accuracy": 0.2366572393029833,
199
+ "eval_loss": 3.7386221885681152,
200
+ "eval_runtime": 1.9495,
201
+ "eval_samples_per_second": 195.433,
202
+ "eval_steps_per_second": 24.622,
203
+ "step": 2500
204
+ },
205
+ {
206
+ "epoch": 66.67,
207
+ "learning_rate": 6.659328859060403e-05,
208
+ "loss": 0.9309,
209
+ "step": 2600
210
+ },
211
+ {
212
+ "epoch": 69.23,
213
+ "learning_rate": 6.605637583892618e-05,
214
+ "loss": 0.9079,
215
+ "step": 2700
216
+ },
217
+ {
218
+ "epoch": 71.79,
219
+ "learning_rate": 6.551946308724832e-05,
220
+ "loss": 0.8622,
221
+ "step": 2800
222
+ },
223
+ {
224
+ "epoch": 74.36,
225
+ "learning_rate": 6.498255033557047e-05,
226
+ "loss": 0.8537,
227
+ "step": 2900
228
+ },
229
+ {
230
+ "epoch": 76.92,
231
+ "learning_rate": 6.444563758389262e-05,
232
+ "loss": 0.8122,
233
+ "step": 3000
234
+ },
235
+ {
236
+ "epoch": 76.92,
237
+ "eval_accuracy": 0.22726028647021257,
238
+ "eval_loss": 3.944620132446289,
239
+ "eval_runtime": 1.958,
240
+ "eval_samples_per_second": 194.582,
241
+ "eval_steps_per_second": 24.514,
242
+ "step": 3000
243
+ },
244
+ {
245
+ "epoch": 76.92,
246
+ "step": 3000,
247
+ "total_flos": 1.2335402138867712e+16,
248
+ "train_loss": 1.4690344212849935,
249
+ "train_runtime": 809.6738,
250
+ "train_samples_per_second": 592.831,
251
+ "train_steps_per_second": 18.526
252
+ }
253
+ ],
254
+ "max_steps": 15000,
255
+ "num_train_epochs": 385,
256
+ "total_flos": 1.2335402138867712e+16,
257
+ "trial_name": null,
258
+ "trial_params": null
259
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49b61197efc5fb58be2473528b708d5f2c2c09675a8650712c0ec59c142fede6
3
+ size 3387
vocab.txt ADDED
The diff for this file is too large to render. See raw diff