pranaydeeps commited on
Commit
1d0a9e7
1 Parent(s): 9d31bbe

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - precision
7
+ - recall
8
+ - f1
9
+ - accuracy
10
+ model-index:
11
+ - name: pos_final_xlm_nl
12
+ results: []
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+ # pos_final_xlm_nl
19
+
20
+ This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 0.1066
23
+ - Precision: 0.9780
24
+ - Recall: 0.9783
25
+ - F1: 0.9782
26
+ - Accuracy: 0.9789
27
+
28
+ ## Model description
29
+
30
+ More information needed
31
+
32
+ ## Intended uses & limitations
33
+
34
+ More information needed
35
+
36
+ ## Training and evaluation data
37
+
38
+ More information needed
39
+
40
+ ## Training procedure
41
+
42
+ ### Training hyperparameters
43
+
44
+ The following hyperparameters were used during training:
45
+ - learning_rate: 5e-05
46
+ - train_batch_size: 256
47
+ - eval_batch_size: 256
48
+ - seed: 42
49
+ - gradient_accumulation_steps: 4
50
+ - total_train_batch_size: 1024
51
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
+ - lr_scheduler_type: linear
53
+ - lr_scheduler_warmup_steps: 500
54
+ - num_epochs: 40.0
55
+ - mixed_precision_training: Native AMP
56
+
57
+ ### Training results
58
+
59
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
60
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
61
+ | No log | 1.0 | 69 | 3.4837 | 0.2936 | 0.1709 | 0.2161 | 0.3200 |
62
+ | No log | 2.0 | 138 | 0.8299 | 0.8501 | 0.8416 | 0.8459 | 0.8497 |
63
+ | No log | 3.0 | 207 | 0.2765 | 0.9419 | 0.9408 | 0.9414 | 0.9429 |
64
+ | No log | 4.0 | 276 | 0.1704 | 0.9601 | 0.9596 | 0.9599 | 0.9611 |
65
+ | No log | 5.0 | 345 | 0.1259 | 0.9685 | 0.9686 | 0.9686 | 0.9693 |
66
+ | No log | 6.0 | 414 | 0.1085 | 0.9711 | 0.9713 | 0.9712 | 0.9719 |
67
+ | No log | 7.0 | 483 | 0.0984 | 0.9728 | 0.9731 | 0.9729 | 0.9738 |
68
+ | 1.1448 | 8.0 | 552 | 0.0906 | 0.9742 | 0.9745 | 0.9743 | 0.9752 |
69
+ | 1.1448 | 9.0 | 621 | 0.0888 | 0.9749 | 0.9752 | 0.9751 | 0.9758 |
70
+ | 1.1448 | 10.0 | 690 | 0.0864 | 0.9757 | 0.9759 | 0.9758 | 0.9765 |
71
+ | 1.1448 | 11.0 | 759 | 0.0842 | 0.9764 | 0.9767 | 0.9765 | 0.9772 |
72
+ | 1.1448 | 12.0 | 828 | 0.0840 | 0.9764 | 0.9768 | 0.9766 | 0.9773 |
73
+ | 1.1448 | 13.0 | 897 | 0.0846 | 0.9766 | 0.9769 | 0.9768 | 0.9775 |
74
+ | 1.1448 | 14.0 | 966 | 0.0854 | 0.9768 | 0.9771 | 0.9769 | 0.9776 |
75
+ | 0.0668 | 15.0 | 1035 | 0.0867 | 0.9767 | 0.9770 | 0.9768 | 0.9776 |
76
+ | 0.0668 | 16.0 | 1104 | 0.0859 | 0.9769 | 0.9772 | 0.9771 | 0.9778 |
77
+ | 0.0668 | 17.0 | 1173 | 0.0858 | 0.9772 | 0.9775 | 0.9773 | 0.9781 |
78
+ | 0.0668 | 18.0 | 1242 | 0.0878 | 0.9776 | 0.9779 | 0.9778 | 0.9785 |
79
+ | 0.0668 | 19.0 | 1311 | 0.0887 | 0.9775 | 0.9779 | 0.9777 | 0.9785 |
80
+ | 0.0668 | 20.0 | 1380 | 0.0902 | 0.9774 | 0.9777 | 0.9775 | 0.9783 |
81
+ | 0.0668 | 21.0 | 1449 | 0.0910 | 0.9772 | 0.9775 | 0.9774 | 0.9782 |
82
+ | 0.0375 | 22.0 | 1518 | 0.0926 | 0.9774 | 0.9777 | 0.9775 | 0.9783 |
83
+ | 0.0375 | 23.0 | 1587 | 0.0930 | 0.9777 | 0.9780 | 0.9779 | 0.9787 |
84
+ | 0.0375 | 24.0 | 1656 | 0.0955 | 0.9777 | 0.9781 | 0.9779 | 0.9787 |
85
+ | 0.0375 | 25.0 | 1725 | 0.0955 | 0.9778 | 0.9781 | 0.9780 | 0.9787 |
86
+ | 0.0375 | 26.0 | 1794 | 0.0978 | 0.9776 | 0.9779 | 0.9777 | 0.9785 |
87
+ | 0.0375 | 27.0 | 1863 | 0.0997 | 0.9772 | 0.9775 | 0.9774 | 0.9782 |
88
+ | 0.0375 | 28.0 | 1932 | 0.1000 | 0.9776 | 0.9779 | 0.9778 | 0.9786 |
89
+ | 0.0238 | 29.0 | 2001 | 0.1022 | 0.9775 | 0.9778 | 0.9776 | 0.9785 |
90
+ | 0.0238 | 30.0 | 2070 | 0.1030 | 0.9777 | 0.9780 | 0.9779 | 0.9787 |
91
+ | 0.0238 | 31.0 | 2139 | 0.1041 | 0.9778 | 0.9780 | 0.9779 | 0.9787 |
92
+ | 0.0238 | 32.0 | 2208 | 0.1054 | 0.9778 | 0.9781 | 0.9779 | 0.9787 |
93
+ | 0.0238 | 33.0 | 2277 | 0.1055 | 0.9777 | 0.9779 | 0.9778 | 0.9786 |
94
+ | 0.0238 | 34.0 | 2346 | 0.1063 | 0.9778 | 0.9780 | 0.9779 | 0.9787 |
95
+ | 0.0238 | 35.0 | 2415 | 0.1066 | 0.9780 | 0.9783 | 0.9782 | 0.9789 |
96
+ | 0.0238 | 36.0 | 2484 | 0.1075 | 0.9779 | 0.9781 | 0.9780 | 0.9788 |
97
+ | 0.0167 | 37.0 | 2553 | 0.1083 | 0.9780 | 0.9783 | 0.9781 | 0.9789 |
98
+ | 0.0167 | 38.0 | 2622 | 0.1083 | 0.9780 | 0.9783 | 0.9781 | 0.9789 |
99
+ | 0.0167 | 39.0 | 2691 | 0.1087 | 0.9779 | 0.9782 | 0.9781 | 0.9789 |
100
+ | 0.0167 | 40.0 | 2760 | 0.1088 | 0.9780 | 0.9782 | 0.9781 | 0.9789 |
101
+
102
+
103
+ ### Framework versions
104
+
105
+ - Transformers 4.25.1
106
+ - Pytorch 1.12.0
107
+ - Datasets 2.18.0
108
+ - Tokenizers 0.13.2
all_results.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 40.0,
3
+ "eval_accuracy": 0.9789456158142492,
4
+ "eval_f1": 0.978172514732208,
5
+ "eval_loss": 0.10656328499317169,
6
+ "eval_precision": 0.9780147183087772,
7
+ "eval_recall": 0.9783303620827442,
8
+ "eval_runtime": 11.1833,
9
+ "eval_samples": 2619,
10
+ "eval_samples_per_second": 703.641,
11
+ "eval_steps_per_second": 2.772,
12
+ "train_loss": 0.23496506378270576,
13
+ "train_runtime": 2350.6684,
14
+ "train_samples": 70812,
15
+ "train_samples_per_second": 1204.968,
16
+ "train_steps_per_second": 1.174
17
+ }
config.json ADDED
@@ -0,0 +1,359 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlm-roberta-base",
3
+ "architectures": [
4
+ "XLMRobertaForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "finetuning_task": "pos",
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "",
16
+ "1": "VNW(bez,det,2v,mv)",
17
+ "2": "TW(rang,prenom,stan)",
18
+ "3": "LID(onbep)",
19
+ "4": "VNW(aanw,pron,3o,ev)",
20
+ "5": "VNW(onbep,adv-pron,3o,getal)",
21
+ "6": "WW(od,nom,met-e,zonder-n)",
22
+ "7": "WW(vd,nom,met-e,mv-n)",
23
+ "8": "WW(pv,tegw,ev)",
24
+ "9": "VNW(pers,pron,2b,getal)",
25
+ "10": "VNW(onbep,grad,basis)",
26
+ "11": "N(soort,ev,basis,dat)",
27
+ "12": "VNW(aanw,pron,3,getal)",
28
+ "13": "TSW()",
29
+ "14": "WW(inf,prenom,zonder)",
30
+ "15": "VNW(pers,pron,3v,ev,fem)",
31
+ "16": "VNW(pr,pron,1,ev)",
32
+ "17": "VNW(excl,pron,3,getal)",
33
+ "18": "FW",
34
+ "19": "VNW(pers,pron,3,ev,onz)",
35
+ "20": "WW(pv,tgw,ev)",
36
+ "21": "N(soort,ev,basis,zijd,stan)",
37
+ "22": "SPEC(deeleigen)",
38
+ "23": "VNW(vb,pron,3p,mv)",
39
+ "24": "ADJ(prenom,basis,met-e,stan)",
40
+ "25": "~",
41
+ "26": "ADJ(postnom,basis,zonder)",
42
+ "27": "VNW(betr,det)",
43
+ "28": "VNW(vb,pron,3v,ev)",
44
+ "29": "ADJ(nom,basis,zonder,mv-n)",
45
+ "30": "ADJ(prenom,basis,met-e,bijz)",
46
+ "31": "#not\t#",
47
+ "32": "ADJ(postnom,comp,zonder)",
48
+ "33": "U",
49
+ "34": "LET()",
50
+ "35": "VNW(onbep,pron,3p,ev)",
51
+ "36": "VNW(pers,pron,3p,mv)",
52
+ "37": "VNW(pr,pron,1,mv)",
53
+ "38": "VNW(pers,pron,2,getal)",
54
+ "39": "VNW(pers,pron,1,mv)",
55
+ "40": "VZ(versm)",
56
+ "41": "#NS\t#",
57
+ "42": "ADJ(vrij,dim,zonder)",
58
+ "43": "WW(inf,prenom,met-e)",
59
+ "44": "ADJ(nom,basis,zonder,zonder-n)",
60
+ "45": "N(eigen,ev,basis,gen)",
61
+ "46": "TW(hoofd,prenom,stan)",
62
+ "47": "@",
63
+ "48": "VNW(bez,det,1,mv)",
64
+ "49": "VNW(vb,det)",
65
+ "50": "VNW(aanw,det)",
66
+ "51": "zonder-n)",
67
+ "52": "SPEC(symb)",
68
+ "53": "BW()",
69
+ "54": "VNW(vb,pron,3p,getal)",
70
+ "55": "N(eigen,mv,dim)",
71
+ "56": "WW(vd,nom,met-e,zonder-n)",
72
+ "57": "VNW(bez,det,2,getal)",
73
+ "58": "VNW(bez,det,3,ev)",
74
+ "59": "ADJ(nom,comp,met-e,mv-n)",
75
+ "60": "VNW(onbep,grad,comp)",
76
+ "61": "ADJ(prenom,basis,zonder,stan)",
77
+ "62": "TW(rang,prenom,bijz)",
78
+ "63": "N(eigen,ev,basis,zijd,stan)",
79
+ "64": "VNW(bez,det,3p,mv)",
80
+ "65": "N(soort,ev,basis,genus,stan)",
81
+ "66": "VNW(pers,pron,3,ev,fem)",
82
+ "67": "VNW(aanw,pron,3m,ev)",
83
+ "68": "VNW(pr,pron,2v,getal)",
84
+ "69": "ADJ(prenom,comp,met-e,stan)",
85
+ "70": "VNW(pers,pron,3,getal,fem)",
86
+ "71": "SPEC(vreemd)",
87
+ "72": "VNW(vb,pron,3o,ev)",
88
+ "73": "ADJ(nom,basis,met-e,zonder-n,bijz)",
89
+ "74": "VNW(pers,pron,3v,getal,fem)",
90
+ "75": "TW(rang,nom,mv-n)",
91
+ "76": "ADJ(vrij,comp,zonder)",
92
+ "77": "N(soort,mv,dim)",
93
+ "78": "WW(pv,tgw,mv)",
94
+ "79": "VNW(pers,pron,3,ev,masc)",
95
+ "80": "WW(od,nom,met-e,mv-n)",
96
+ "81": "VNW(betr,pron,persoon,getal)",
97
+ "82": "VNW(bez,det,2v,ev)",
98
+ "83": "WW(od,prenom,met-e)",
99
+ "84": "TW(hoofd,nom,zonder-n,basis)",
100
+ "85": "ADJ(vrij,verder,zonder)",
101
+ "86": "ADJ(nom,sup,met-e,mv-n)",
102
+ "87": "N(soort,ev,basis,gen)",
103
+ "88": "WW(od,prenom,zonder)",
104
+ "89": "WW(pv,tgw,met-t)",
105
+ "90": "TW(hoofd,nom,zonder-n,dim)",
106
+ "91": "ADJ(nom,sup,met-e,zonder-n,stan)",
107
+ "92": "N(soort,ev,basis,onz,stan)",
108
+ "93": "ADJ(prenom,sup,zonder)",
109
+ "94": "VNW(bez,det,3,mv)",
110
+ "95": "VNW(pers,pron,3m,ev)",
111
+ "96": "VNW(pers,pron,2v,ev)",
112
+ "97": "WW(inf,nom,zonder,zonder-n)",
113
+ "98": "WW(od,vrij,zonder)",
114
+ "99": "WW(pv,verl,mv)",
115
+ "100": "SPEC(afk)",
116
+ "101": "SPEC(meta)",
117
+ "102": "VNW(pr,pron,2,getal)",
118
+ "103": "ADJ(prenom,basis,zonder)",
119
+ "104": "VGW()",
120
+ "105": "VNW(bez,det,1,ev)",
121
+ "106": "Jan",
122
+ "107": "N(soort,mv,basis,zijd,stan)",
123
+ "108": "VNW(pers,pron,3,mv)",
124
+ "109": "VNW(vb,pron,3m,ev)",
125
+ "110": "ADJ(nom,sup,zonder,zonder-n)",
126
+ "111": "VG(onder)",
127
+ "112": "VNW(aanw,adv-pron,3,getal)",
128
+ "113": "VNW(betr,pron,3,ev)",
129
+ "114": "VNW(onbep,pron,3o,ev)",
130
+ "115": "ADJ(prenom,comp,zonder)",
131
+ "116": "WW(vd,vrij,zonder)",
132
+ "117": "N(eigen,ev,basis,genus,stan)",
133
+ "118": "VZ(init)",
134
+ "119": "ADJ(prenom,sup,met-e,stan)",
135
+ "120": "ADJ(vrij,basis,zonder)",
136
+ "121": "VNW(onbep,grad,sup)",
137
+ "122": "VNW(pers,pron,1,ev)",
138
+ "123": "#",
139
+ "124": "VNW(aanw,adv-pron,3o,getal)",
140
+ "125": "TW(hoofd,nom,zonder,zonder-n)",
141
+ "126": "VNW(pers,pron,3m,ev,masc)",
142
+ "127": "TW(hoofd,prenom,bijz)",
143
+ "128": "WW(vd,prenom,met-e)",
144
+ "129": "TW(rang,nom,zonder-n)",
145
+ "130": "VNW(bez,det,3v,ev)",
146
+ "131": "VNW(bez,det,3m,ev)",
147
+ "132": "ADJ(nom,comp,met-e,zonder-n,stan)",
148
+ "133": "WW(pv,conj,ev)",
149
+ "134": "LID(bep)",
150
+ "135": "VNW(bez,det,2,mv)",
151
+ "136": "SPEC(enof)",
152
+ "137": "VNW(pers,pron,2v,mv)",
153
+ "138": "VNW(onbep,det)",
154
+ "139": "ADJ(postnom,basis,met-s)",
155
+ "140": "VNW(vb,adv-pron,3o,getal)",
156
+ "141": "WW(vd,prenom,zonder)",
157
+ "142": "VNW(recip,pron,persoon,mv)",
158
+ "143": "Boulevard\tN(eigen,ev,basis,genus,stan)",
159
+ "144": "WW(inf,vrij,zonder)",
160
+ "145": "VNW(onbep,adv-pron,3,getal)",
161
+ "146": "ADJ(nom,basis,met-e,mv-n)",
162
+ "147": "N(soort,mv,basis)",
163
+ "148": "TW(hoofd,nom,mv-n,basis)",
164
+ "149": "TW(hoofd,vrij)",
165
+ "150": "N(soort,ev,dim,onz,stan)",
166
+ "151": "N(eigen,ev,dim,onz,stan)",
167
+ "152": "N(eigen,ev,basis,onz,stan)",
168
+ "153": "VZ(fin)",
169
+ "154": "VG(neven)",
170
+ "155": "VNW(pers,pron,3p,ev,masc)",
171
+ "156": "N(eigen,mv,basis)",
172
+ "157": "VNW(refl,pron,3,getal)",
173
+ "158": "SPEC(afgebr)",
174
+ "159": "WW(pv,verl,ev)",
175
+ "160": "ADJ(vrij,sup,zonder)",
176
+ "161": "ADJ(nom,basis,met-e,zonder-n,stan)",
177
+ "162": "ADJ(postnom,comp,met-s)"
178
+ },
179
+ "initializer_range": 0.02,
180
+ "intermediate_size": 3072,
181
+ "label2id": {
182
+ "": 0,
183
+ "#": 123,
184
+ "#NS\t#": 41,
185
+ "#not\t#": 31,
186
+ "@": 47,
187
+ "ADJ(nom,basis,met-e,mv-n)": 146,
188
+ "ADJ(nom,basis,met-e,zonder-n,bijz)": 73,
189
+ "ADJ(nom,basis,met-e,zonder-n,stan)": 161,
190
+ "ADJ(nom,basis,zonder,mv-n)": 29,
191
+ "ADJ(nom,basis,zonder,zonder-n)": 44,
192
+ "ADJ(nom,comp,met-e,mv-n)": 59,
193
+ "ADJ(nom,comp,met-e,zonder-n,stan)": 132,
194
+ "ADJ(nom,sup,met-e,mv-n)": 86,
195
+ "ADJ(nom,sup,met-e,zonder-n,stan)": 91,
196
+ "ADJ(nom,sup,zonder,zonder-n)": 110,
197
+ "ADJ(postnom,basis,met-s)": 139,
198
+ "ADJ(postnom,basis,zonder)": 26,
199
+ "ADJ(postnom,comp,met-s)": 162,
200
+ "ADJ(postnom,comp,zonder)": 32,
201
+ "ADJ(prenom,basis,met-e,bijz)": 30,
202
+ "ADJ(prenom,basis,met-e,stan)": 24,
203
+ "ADJ(prenom,basis,zonder)": 103,
204
+ "ADJ(prenom,basis,zonder,stan)": 61,
205
+ "ADJ(prenom,comp,met-e,stan)": 69,
206
+ "ADJ(prenom,comp,zonder)": 115,
207
+ "ADJ(prenom,sup,met-e,stan)": 119,
208
+ "ADJ(prenom,sup,zonder)": 93,
209
+ "ADJ(vrij,basis,zonder)": 120,
210
+ "ADJ(vrij,comp,zonder)": 76,
211
+ "ADJ(vrij,dim,zonder)": 42,
212
+ "ADJ(vrij,sup,zonder)": 160,
213
+ "ADJ(vrij,verder,zonder)": 85,
214
+ "BW()": 53,
215
+ "Boulevard\tN(eigen,ev,basis,genus,stan)": 143,
216
+ "FW": 18,
217
+ "Jan": 106,
218
+ "LET()": 34,
219
+ "LID(bep)": 134,
220
+ "LID(onbep)": 3,
221
+ "N(eigen,ev,basis,gen)": 45,
222
+ "N(eigen,ev,basis,genus,stan)": 117,
223
+ "N(eigen,ev,basis,onz,stan)": 152,
224
+ "N(eigen,ev,basis,zijd,stan)": 63,
225
+ "N(eigen,ev,dim,onz,stan)": 151,
226
+ "N(eigen,mv,basis)": 156,
227
+ "N(eigen,mv,dim)": 55,
228
+ "N(soort,ev,basis,dat)": 11,
229
+ "N(soort,ev,basis,gen)": 87,
230
+ "N(soort,ev,basis,genus,stan)": 65,
231
+ "N(soort,ev,basis,onz,stan)": 92,
232
+ "N(soort,ev,basis,zijd,stan)": 21,
233
+ "N(soort,ev,dim,onz,stan)": 150,
234
+ "N(soort,mv,basis)": 147,
235
+ "N(soort,mv,basis,zijd,stan)": 107,
236
+ "N(soort,mv,dim)": 77,
237
+ "SPEC(afgebr)": 158,
238
+ "SPEC(afk)": 100,
239
+ "SPEC(deeleigen)": 22,
240
+ "SPEC(enof)": 136,
241
+ "SPEC(meta)": 101,
242
+ "SPEC(symb)": 52,
243
+ "SPEC(vreemd)": 71,
244
+ "TSW()": 13,
245
+ "TW(hoofd,nom,mv-n,basis)": 148,
246
+ "TW(hoofd,nom,zonder,zonder-n)": 125,
247
+ "TW(hoofd,nom,zonder-n,basis)": 84,
248
+ "TW(hoofd,nom,zonder-n,dim)": 90,
249
+ "TW(hoofd,prenom,bijz)": 127,
250
+ "TW(hoofd,prenom,stan)": 46,
251
+ "TW(hoofd,vrij)": 149,
252
+ "TW(rang,nom,mv-n)": 75,
253
+ "TW(rang,nom,zonder-n)": 129,
254
+ "TW(rang,prenom,bijz)": 62,
255
+ "TW(rang,prenom,stan)": 2,
256
+ "U": 33,
257
+ "VG(neven)": 154,
258
+ "VG(onder)": 111,
259
+ "VGW()": 104,
260
+ "VNW(aanw,adv-pron,3,getal)": 112,
261
+ "VNW(aanw,adv-pron,3o,getal)": 124,
262
+ "VNW(aanw,det)": 50,
263
+ "VNW(aanw,pron,3,getal)": 12,
264
+ "VNW(aanw,pron,3m,ev)": 67,
265
+ "VNW(aanw,pron,3o,ev)": 4,
266
+ "VNW(betr,det)": 27,
267
+ "VNW(betr,pron,3,ev)": 113,
268
+ "VNW(betr,pron,persoon,getal)": 81,
269
+ "VNW(bez,det,1,ev)": 105,
270
+ "VNW(bez,det,1,mv)": 48,
271
+ "VNW(bez,det,2,getal)": 57,
272
+ "VNW(bez,det,2,mv)": 135,
273
+ "VNW(bez,det,2v,ev)": 82,
274
+ "VNW(bez,det,2v,mv)": 1,
275
+ "VNW(bez,det,3,ev)": 58,
276
+ "VNW(bez,det,3,mv)": 94,
277
+ "VNW(bez,det,3m,ev)": 131,
278
+ "VNW(bez,det,3p,mv)": 64,
279
+ "VNW(bez,det,3v,ev)": 130,
280
+ "VNW(excl,pron,3,getal)": 17,
281
+ "VNW(onbep,adv-pron,3,getal)": 145,
282
+ "VNW(onbep,adv-pron,3o,getal)": 5,
283
+ "VNW(onbep,det)": 138,
284
+ "VNW(onbep,grad,basis)": 10,
285
+ "VNW(onbep,grad,comp)": 60,
286
+ "VNW(onbep,grad,sup)": 121,
287
+ "VNW(onbep,pron,3o,ev)": 114,
288
+ "VNW(onbep,pron,3p,ev)": 35,
289
+ "VNW(pers,pron,1,ev)": 122,
290
+ "VNW(pers,pron,1,mv)": 39,
291
+ "VNW(pers,pron,2,getal)": 38,
292
+ "VNW(pers,pron,2b,getal)": 9,
293
+ "VNW(pers,pron,2v,ev)": 96,
294
+ "VNW(pers,pron,2v,mv)": 137,
295
+ "VNW(pers,pron,3,ev,fem)": 66,
296
+ "VNW(pers,pron,3,ev,masc)": 79,
297
+ "VNW(pers,pron,3,ev,onz)": 19,
298
+ "VNW(pers,pron,3,getal,fem)": 70,
299
+ "VNW(pers,pron,3,mv)": 108,
300
+ "VNW(pers,pron,3m,ev)": 95,
301
+ "VNW(pers,pron,3m,ev,masc)": 126,
302
+ "VNW(pers,pron,3p,ev,masc)": 155,
303
+ "VNW(pers,pron,3p,mv)": 36,
304
+ "VNW(pers,pron,3v,ev,fem)": 15,
305
+ "VNW(pers,pron,3v,getal,fem)": 74,
306
+ "VNW(pr,pron,1,ev)": 16,
307
+ "VNW(pr,pron,1,mv)": 37,
308
+ "VNW(pr,pron,2,getal)": 102,
309
+ "VNW(pr,pron,2v,getal)": 68,
310
+ "VNW(recip,pron,persoon,mv)": 142,
311
+ "VNW(refl,pron,3,getal)": 157,
312
+ "VNW(vb,adv-pron,3o,getal)": 140,
313
+ "VNW(vb,det)": 49,
314
+ "VNW(vb,pron,3m,ev)": 109,
315
+ "VNW(vb,pron,3o,ev)": 72,
316
+ "VNW(vb,pron,3p,getal)": 54,
317
+ "VNW(vb,pron,3p,mv)": 23,
318
+ "VNW(vb,pron,3v,ev)": 28,
319
+ "VZ(fin)": 153,
320
+ "VZ(init)": 118,
321
+ "VZ(versm)": 40,
322
+ "WW(inf,nom,zonder,zonder-n)": 97,
323
+ "WW(inf,prenom,met-e)": 43,
324
+ "WW(inf,prenom,zonder)": 14,
325
+ "WW(inf,vrij,zonder)": 144,
326
+ "WW(od,nom,met-e,mv-n)": 80,
327
+ "WW(od,nom,met-e,zonder-n)": 6,
328
+ "WW(od,prenom,met-e)": 83,
329
+ "WW(od,prenom,zonder)": 88,
330
+ "WW(od,vrij,zonder)": 98,
331
+ "WW(pv,conj,ev)": 133,
332
+ "WW(pv,tegw,ev)": 8,
333
+ "WW(pv,tgw,ev)": 20,
334
+ "WW(pv,tgw,met-t)": 89,
335
+ "WW(pv,tgw,mv)": 78,
336
+ "WW(pv,verl,ev)": 159,
337
+ "WW(pv,verl,mv)": 99,
338
+ "WW(vd,nom,met-e,mv-n)": 7,
339
+ "WW(vd,nom,met-e,zonder-n)": 56,
340
+ "WW(vd,prenom,met-e)": 128,
341
+ "WW(vd,prenom,zonder)": 141,
342
+ "WW(vd,vrij,zonder)": 116,
343
+ "zonder-n)": 51,
344
+ "~": 25
345
+ },
346
+ "layer_norm_eps": 1e-05,
347
+ "max_position_embeddings": 514,
348
+ "model_type": "xlm-roberta",
349
+ "num_attention_heads": 12,
350
+ "num_hidden_layers": 12,
351
+ "output_past": true,
352
+ "pad_token_id": 1,
353
+ "position_embedding_type": "absolute",
354
+ "torch_dtype": "float32",
355
+ "transformers_version": "4.25.1",
356
+ "type_vocab_size": 1,
357
+ "use_cache": true,
358
+ "vocab_size": 250002
359
+ }
eval_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 40.0,
3
+ "eval_accuracy": 0.9789456158142492,
4
+ "eval_f1": 0.978172514732208,
5
+ "eval_loss": 0.10656328499317169,
6
+ "eval_precision": 0.9780147183087772,
7
+ "eval_recall": 0.9783303620827442,
8
+ "eval_runtime": 11.1833,
9
+ "eval_samples": 2619,
10
+ "eval_samples_per_second": 703.641,
11
+ "eval_steps_per_second": 2.772
12
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c207b4075f596543a4c83655dde81906eb9a11707924c585e674ccb3361eee9
3
+ size 1110384689
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2c509a525eb51aebb33fb59c24ee923c1d4c1db23c3ae81fe05ccf354084f7b
3
+ size 17082758
tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "__type": "AddedToken",
7
+ "content": "<mask>",
8
+ "lstrip": true,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "model_max_length": 512,
14
+ "name_or_path": "xlm-roberta-base",
15
+ "pad_token": "<pad>",
16
+ "sep_token": "</s>",
17
+ "special_tokens_map_file": null,
18
+ "token": null,
19
+ "tokenizer_class": "XLMRobertaTokenizer",
20
+ "unk_token": "<unk>"
21
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 40.0,
3
+ "train_loss": 0.23496506378270576,
4
+ "train_runtime": 2350.6684,
5
+ "train_samples": 70812,
6
+ "train_samples_per_second": 1204.968,
7
+ "train_steps_per_second": 1.174
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,535 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.978172514732208,
3
+ "best_model_checkpoint": "models/pos_final_xlm_nl/checkpoint-2415",
4
+ "epoch": 39.99638989169675,
5
+ "global_step": 2760,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "eval_accuracy": 0.3200084762438131,
13
+ "eval_f1": 0.2160928249139116,
14
+ "eval_loss": 3.483713388442993,
15
+ "eval_precision": 0.2936494317356812,
16
+ "eval_recall": 0.17094424294584126,
17
+ "eval_runtime": 10.7415,
18
+ "eval_samples_per_second": 732.58,
19
+ "eval_steps_per_second": 2.886,
20
+ "step": 69
21
+ },
22
+ {
23
+ "epoch": 2.0,
24
+ "eval_accuracy": 0.8496904657393253,
25
+ "eval_f1": 0.8458663165617639,
26
+ "eval_loss": 0.8298526406288147,
27
+ "eval_precision": 0.8501404908642128,
28
+ "eval_recall": 0.8416349050224381,
29
+ "eval_runtime": 11.2158,
30
+ "eval_samples_per_second": 701.6,
31
+ "eval_steps_per_second": 2.764,
32
+ "step": 138
33
+ },
34
+ {
35
+ "epoch": 3.0,
36
+ "eval_accuracy": 0.9429140115337461,
37
+ "eval_f1": 0.9413686917810061,
38
+ "eval_loss": 0.27647557854652405,
39
+ "eval_precision": 0.941929974380871,
40
+ "eval_recall": 0.9408080777033258,
41
+ "eval_runtime": 10.9493,
42
+ "eval_samples_per_second": 718.679,
43
+ "eval_steps_per_second": 2.831,
44
+ "step": 207
45
+ },
46
+ {
47
+ "epoch": 4.0,
48
+ "eval_accuracy": 0.961107663432576,
49
+ "eval_f1": 0.9598816317903192,
50
+ "eval_loss": 0.17041535675525665,
51
+ "eval_precision": 0.9601288546848211,
52
+ "eval_recall": 0.9596345361775374,
53
+ "eval_runtime": 10.8629,
54
+ "eval_samples_per_second": 724.391,
55
+ "eval_steps_per_second": 2.854,
56
+ "step": 276
57
+ },
58
+ {
59
+ "epoch": 5.0,
60
+ "eval_accuracy": 0.969288752327183,
61
+ "eval_f1": 0.9685681024447033,
62
+ "eval_loss": 0.1259436309337616,
63
+ "eval_precision": 0.9685494963155347,
64
+ "eval_recall": 0.9685867092887441,
65
+ "eval_runtime": 11.2662,
66
+ "eval_samples_per_second": 698.46,
67
+ "eval_steps_per_second": 2.752,
68
+ "step": 345
69
+ },
70
+ {
71
+ "epoch": 6.0,
72
+ "eval_accuracy": 0.9719451465936095,
73
+ "eval_f1": 0.9712171621320507,
74
+ "eval_loss": 0.10845372825860977,
75
+ "eval_precision": 0.9711350819772891,
76
+ "eval_recall": 0.9712992561627836,
77
+ "eval_runtime": 10.8884,
78
+ "eval_samples_per_second": 722.693,
79
+ "eval_steps_per_second": 2.847,
80
+ "step": 414
81
+ },
82
+ {
83
+ "epoch": 7.0,
84
+ "eval_accuracy": 0.9737614845535593,
85
+ "eval_f1": 0.9729360106642491,
86
+ "eval_loss": 0.09838376194238663,
87
+ "eval_precision": 0.9727977383942906,
88
+ "eval_recall": 0.9730743222474949,
89
+ "eval_runtime": 11.171,
90
+ "eval_samples_per_second": 704.411,
91
+ "eval_steps_per_second": 2.775,
92
+ "step": 483
93
+ },
94
+ {
95
+ "epoch": 7.25,
96
+ "learning_rate": 4.99e-05,
97
+ "loss": 1.1448,
98
+ "step": 500
99
+ },
100
+ {
101
+ "epoch": 8.0,
102
+ "eval_accuracy": 0.9751691464725203,
103
+ "eval_f1": 0.9743453807855432,
104
+ "eval_loss": 0.09059575200080872,
105
+ "eval_precision": 0.9742256161268514,
106
+ "eval_recall": 0.9744651748939571,
107
+ "eval_runtime": 10.9149,
108
+ "eval_samples_per_second": 720.942,
109
+ "eval_steps_per_second": 2.84,
110
+ "step": 552
111
+ },
112
+ {
113
+ "epoch": 9.0,
114
+ "eval_accuracy": 0.9758427051326684,
115
+ "eval_f1": 0.9750796169168182,
116
+ "eval_loss": 0.08883357048034668,
117
+ "eval_precision": 0.9749410400006145,
118
+ "eval_recall": 0.9752182332329256,
119
+ "eval_runtime": 10.9703,
120
+ "eval_samples_per_second": 717.298,
121
+ "eval_steps_per_second": 2.826,
122
+ "step": 621
123
+ },
124
+ {
125
+ "epoch": 10.0,
126
+ "eval_accuracy": 0.9765313999424826,
127
+ "eval_f1": 0.975770544327188,
128
+ "eval_loss": 0.08642476052045822,
129
+ "eval_precision": 0.9756543517174092,
130
+ "eval_recall": 0.9758867646154792,
131
+ "eval_runtime": 10.8323,
132
+ "eval_samples_per_second": 726.436,
133
+ "eval_steps_per_second": 2.862,
134
+ "step": 690
135
+ },
136
+ {
137
+ "epoch": 11.0,
138
+ "eval_accuracy": 0.9772427989767963,
139
+ "eval_f1": 0.9765426312513927,
140
+ "eval_loss": 0.08421829342842102,
141
+ "eval_precision": 0.9764300969531214,
142
+ "eval_recall": 0.9766551914919777,
143
+ "eval_runtime": 11.0199,
144
+ "eval_samples_per_second": 714.071,
145
+ "eval_steps_per_second": 2.813,
146
+ "step": 759
147
+ },
148
+ {
149
+ "epoch": 12.0,
150
+ "eval_accuracy": 0.9773260477999607,
151
+ "eval_f1": 0.9765903503380455,
152
+ "eval_loss": 0.08395781368017197,
153
+ "eval_precision": 0.9764103115590241,
154
+ "eval_recall": 0.9767704555234524,
155
+ "eval_runtime": 10.9053,
156
+ "eval_samples_per_second": 721.579,
157
+ "eval_steps_per_second": 2.843,
158
+ "step": 828
159
+ },
160
+ {
161
+ "epoch": 13.0,
162
+ "eval_accuracy": 0.9775076815959556,
163
+ "eval_f1": 0.976759194523621,
164
+ "eval_loss": 0.08459737151861191,
165
+ "eval_precision": 0.9765866248790155,
166
+ "eval_recall": 0.9769318251675171,
167
+ "eval_runtime": 11.552,
168
+ "eval_samples_per_second": 681.178,
169
+ "eval_steps_per_second": 2.684,
170
+ "step": 897
171
+ },
172
+ {
173
+ "epoch": 14.0,
174
+ "eval_accuracy": 0.9776363388681187,
175
+ "eval_f1": 0.9769464516897355,
176
+ "eval_loss": 0.0853676050901413,
177
+ "eval_precision": 0.9768151124290356,
178
+ "eval_recall": 0.9770778262740517,
179
+ "eval_runtime": 11.6095,
180
+ "eval_samples_per_second": 677.81,
181
+ "eval_steps_per_second": 2.67,
182
+ "step": 966
183
+ },
184
+ {
185
+ "epoch": 14.49,
186
+ "learning_rate": 3.896017699115044e-05,
187
+ "loss": 0.0668,
188
+ "step": 1000
189
+ },
190
+ {
191
+ "epoch": 15.0,
192
+ "eval_accuracy": 0.9775909304191199,
193
+ "eval_f1": 0.976843172808015,
194
+ "eval_loss": 0.08673886954784393,
195
+ "eval_precision": 0.9766930924287119,
196
+ "eval_recall": 0.9769932993176369,
197
+ "eval_runtime": 11.3435,
198
+ "eval_samples_per_second": 693.7,
199
+ "eval_steps_per_second": 2.733,
200
+ "step": 1035
201
+ },
202
+ {
203
+ "epoch": 16.0,
204
+ "eval_accuracy": 0.9778028365144474,
205
+ "eval_f1": 0.9770540169876339,
206
+ "eval_loss": 0.0859028622508049,
207
+ "eval_precision": 0.9769226632660116,
208
+ "eval_recall": 0.9771854060367615,
209
+ "eval_runtime": 11.0228,
210
+ "eval_samples_per_second": 713.886,
211
+ "eval_steps_per_second": 2.812,
212
+ "step": 1104
213
+ },
214
+ {
215
+ "epoch": 17.0,
216
+ "eval_accuracy": 0.9780979914329393,
217
+ "eval_f1": 0.9773386449285661,
218
+ "eval_loss": 0.08584524691104889,
219
+ "eval_precision": 0.9771922412137507,
220
+ "eval_recall": 0.9774850925185959,
221
+ "eval_runtime": 11.0063,
222
+ "eval_samples_per_second": 714.952,
223
+ "eval_steps_per_second": 2.817,
224
+ "step": 1173
225
+ },
226
+ {
227
+ "epoch": 18.0,
228
+ "eval_accuracy": 0.9784990993990949,
229
+ "eval_f1": 0.9777723141226096,
230
+ "eval_loss": 0.08779104799032211,
231
+ "eval_precision": 0.9776446185757087,
232
+ "eval_recall": 0.977900043031905,
233
+ "eval_runtime": 11.0526,
234
+ "eval_samples_per_second": 711.958,
235
+ "eval_steps_per_second": 2.805,
236
+ "step": 1242
237
+ },
238
+ {
239
+ "epoch": 19.0,
240
+ "eval_accuracy": 0.9784839632494287,
241
+ "eval_f1": 0.9777277546442126,
242
+ "eval_loss": 0.08868438750505447,
243
+ "eval_precision": 0.9775324914738686,
244
+ "eval_recall": 0.9779230958382,
245
+ "eval_runtime": 10.952,
246
+ "eval_samples_per_second": 718.498,
247
+ "eval_steps_per_second": 2.831,
248
+ "step": 1311
249
+ },
250
+ {
251
+ "epoch": 20.0,
252
+ "eval_accuracy": 0.9782796252289343,
253
+ "eval_f1": 0.977526622308957,
254
+ "eval_loss": 0.09024880826473236,
255
+ "eval_precision": 0.9773914513105737,
256
+ "eval_recall": 0.9776618307001905,
257
+ "eval_runtime": 10.9428,
258
+ "eval_samples_per_second": 719.1,
259
+ "eval_steps_per_second": 2.833,
260
+ "step": 1380
261
+ },
262
+ {
263
+ "epoch": 21.0,
264
+ "eval_accuracy": 0.9782115125554361,
265
+ "eval_f1": 0.9773772343294419,
266
+ "eval_loss": 0.09100791066884995,
267
+ "eval_precision": 0.9772233190194889,
268
+ "eval_recall": 0.9775311981311858,
269
+ "eval_runtime": 10.9089,
270
+ "eval_samples_per_second": 721.337,
271
+ "eval_steps_per_second": 2.842,
272
+ "step": 1449
273
+ },
274
+ {
275
+ "epoch": 21.74,
276
+ "learning_rate": 2.7898230088495575e-05,
277
+ "loss": 0.0375,
278
+ "step": 1500
279
+ },
280
+ {
281
+ "epoch": 22.0,
282
+ "eval_accuracy": 0.9783098975282668,
283
+ "eval_f1": 0.9775235578160474,
284
+ "eval_loss": 0.09260567277669907,
285
+ "eval_precision": 0.9773546062789501,
286
+ "eval_recall": 0.9776925677752505,
287
+ "eval_runtime": 10.9627,
288
+ "eval_samples_per_second": 717.797,
289
+ "eval_steps_per_second": 2.828,
290
+ "step": 1518
291
+ },
292
+ {
293
+ "epoch": 23.0,
294
+ "eval_accuracy": 0.9786731651202567,
295
+ "eval_f1": 0.9778607567218708,
296
+ "eval_loss": 0.09297080338001251,
297
+ "eval_precision": 0.9777292945433315,
298
+ "eval_recall": 0.9779922542570849,
299
+ "eval_runtime": 11.0584,
300
+ "eval_samples_per_second": 711.584,
301
+ "eval_steps_per_second": 2.803,
302
+ "step": 1587
303
+ },
304
+ {
305
+ "epoch": 24.0,
306
+ "eval_accuracy": 0.9787034374195892,
307
+ "eval_f1": 0.9779114614545398,
308
+ "eval_loss": 0.09545727074146271,
309
+ "eval_precision": 0.9777461975725918,
310
+ "eval_recall": 0.9780767812134997,
311
+ "eval_runtime": 12.1178,
312
+ "eval_samples_per_second": 649.374,
313
+ "eval_steps_per_second": 2.558,
314
+ "step": 1656
315
+ },
316
+ {
317
+ "epoch": 25.0,
318
+ "eval_accuracy": 0.9787488458685879,
319
+ "eval_f1": 0.9779918790071952,
320
+ "eval_loss": 0.09549739956855774,
321
+ "eval_precision": 0.9778378669042919,
322
+ "eval_recall": 0.9781459396323846,
323
+ "eval_runtime": 11.1672,
324
+ "eval_samples_per_second": 704.655,
325
+ "eval_steps_per_second": 2.776,
326
+ "step": 1725
327
+ },
328
+ {
329
+ "epoch": 26.0,
330
+ "eval_accuracy": 0.9785445078480935,
331
+ "eval_f1": 0.977742949116863,
332
+ "eval_loss": 0.09780567139387131,
333
+ "eval_precision": 0.9775551902662345,
334
+ "eval_recall": 0.977930780106965,
335
+ "eval_runtime": 10.9619,
336
+ "eval_samples_per_second": 717.851,
337
+ "eval_steps_per_second": 2.828,
338
+ "step": 1794
339
+ },
340
+ {
341
+ "epoch": 27.0,
342
+ "eval_accuracy": 0.9782115125554361,
343
+ "eval_f1": 0.9773690296457643,
344
+ "eval_loss": 0.09968989342451096,
345
+ "eval_precision": 0.9772376335742984,
346
+ "eval_recall": 0.9775004610561259,
347
+ "eval_runtime": 10.8805,
348
+ "eval_samples_per_second": 723.22,
349
+ "eval_steps_per_second": 2.849,
350
+ "step": 1863
351
+ },
352
+ {
353
+ "epoch": 28.0,
354
+ "eval_accuracy": 0.9785596439977599,
355
+ "eval_f1": 0.9777683870843819,
356
+ "eval_loss": 0.10001282393932343,
357
+ "eval_precision": 0.9776444468344998,
358
+ "eval_recall": 0.9778923587631401,
359
+ "eval_runtime": 11.0278,
360
+ "eval_samples_per_second": 713.561,
361
+ "eval_steps_per_second": 2.811,
362
+ "step": 1932
363
+ },
364
+ {
365
+ "epoch": 28.98,
366
+ "learning_rate": 1.683628318584071e-05,
367
+ "loss": 0.0238,
368
+ "step": 2000
369
+ },
370
+ {
371
+ "epoch": 29.0,
372
+ "eval_accuracy": 0.9784612590249292,
373
+ "eval_f1": 0.9776150651725449,
374
+ "eval_loss": 0.10220629721879959,
375
+ "eval_precision": 0.977476127922073,
376
+ "eval_recall": 0.9777540419253704,
377
+ "eval_runtime": 11.5178,
378
+ "eval_samples_per_second": 683.205,
379
+ "eval_steps_per_second": 2.691,
380
+ "step": 2001
381
+ },
382
+ {
383
+ "epoch": 30.0,
384
+ "eval_accuracy": 0.9787034374195892,
385
+ "eval_f1": 0.9778532436450527,
386
+ "eval_loss": 0.10299359261989594,
387
+ "eval_precision": 0.9777142725449978,
388
+ "eval_recall": 0.9779922542570849,
389
+ "eval_runtime": 11.5247,
390
+ "eval_samples_per_second": 682.796,
391
+ "eval_steps_per_second": 2.69,
392
+ "step": 2070
393
+ },
394
+ {
395
+ "epoch": 31.0,
396
+ "eval_accuracy": 0.9786504608957574,
397
+ "eval_f1": 0.9778916595277151,
398
+ "eval_loss": 0.10408657044172287,
399
+ "eval_precision": 0.9777526829680502,
400
+ "eval_recall": 0.9780306756009098,
401
+ "eval_runtime": 11.971,
402
+ "eval_samples_per_second": 657.341,
403
+ "eval_steps_per_second": 2.59,
404
+ "step": 2139
405
+ },
406
+ {
407
+ "epoch": 32.0,
408
+ "eval_accuracy": 0.9787185735692554,
409
+ "eval_f1": 0.9779299058419483,
410
+ "eval_loss": 0.10540538281202316,
411
+ "eval_precision": 0.9777984343671018,
412
+ "eval_recall": 0.9780614126759698,
413
+ "eval_runtime": 11.5819,
414
+ "eval_samples_per_second": 679.422,
415
+ "eval_steps_per_second": 2.677,
416
+ "step": 2208
417
+ },
418
+ {
419
+ "epoch": 33.0,
420
+ "eval_accuracy": 0.978635324746091,
421
+ "eval_f1": 0.9777916076017933,
422
+ "eval_loss": 0.10549841076135635,
423
+ "eval_precision": 0.9776601547195612,
424
+ "eval_recall": 0.9779230958382,
425
+ "eval_runtime": 12.6843,
426
+ "eval_samples_per_second": 620.372,
427
+ "eval_steps_per_second": 2.444,
428
+ "step": 2277
429
+ },
430
+ {
431
+ "epoch": 34.0,
432
+ "eval_accuracy": 0.9787488458685879,
433
+ "eval_f1": 0.9778990030925261,
434
+ "eval_loss": 0.10634943097829819,
435
+ "eval_precision": 0.9777750462859821,
436
+ "eval_recall": 0.9780229913321449,
437
+ "eval_runtime": 11.6157,
438
+ "eval_samples_per_second": 677.447,
439
+ "eval_steps_per_second": 2.669,
440
+ "step": 2346
441
+ },
442
+ {
443
+ "epoch": 35.0,
444
+ "eval_accuracy": 0.9789456158142492,
445
+ "eval_f1": 0.978172514732208,
446
+ "eval_loss": 0.10656328499317169,
447
+ "eval_precision": 0.9780147183087772,
448
+ "eval_recall": 0.9783303620827442,
449
+ "eval_runtime": 11.2324,
450
+ "eval_samples_per_second": 700.56,
451
+ "eval_steps_per_second": 2.76,
452
+ "step": 2415
453
+ },
454
+ {
455
+ "epoch": 36.0,
456
+ "eval_accuracy": 0.978756413943421,
457
+ "eval_f1": 0.9780024740493733,
458
+ "eval_loss": 0.10749900341033936,
459
+ "eval_precision": 0.9778897715225174,
460
+ "eval_recall": 0.9781152025573246,
461
+ "eval_runtime": 11.1336,
462
+ "eval_samples_per_second": 706.779,
463
+ "eval_steps_per_second": 2.784,
464
+ "step": 2484
465
+ },
466
+ {
467
+ "epoch": 36.23,
468
+ "learning_rate": 5.774336283185841e-06,
469
+ "loss": 0.0167,
470
+ "step": 2500
471
+ },
472
+ {
473
+ "epoch": 37.0,
474
+ "eval_accuracy": 0.9789153435149167,
475
+ "eval_f1": 0.9781257443163047,
476
+ "eval_loss": 0.10826310515403748,
477
+ "eval_precision": 0.977998002611969,
478
+ "eval_recall": 0.9782535193950944,
479
+ "eval_runtime": 11.1448,
480
+ "eval_samples_per_second": 706.071,
481
+ "eval_steps_per_second": 2.782,
482
+ "step": 2553
483
+ },
484
+ {
485
+ "epoch": 38.0,
486
+ "eval_accuracy": 0.9789002073652504,
487
+ "eval_f1": 0.9781295019304278,
488
+ "eval_loss": 0.1082502156496048,
489
+ "eval_precision": 0.978005515906245,
490
+ "eval_recall": 0.9782535193950944,
491
+ "eval_runtime": 11.2628,
492
+ "eval_samples_per_second": 698.669,
493
+ "eval_steps_per_second": 2.752,
494
+ "step": 2622
495
+ },
496
+ {
497
+ "epoch": 39.0,
498
+ "eval_accuracy": 0.9788547989162517,
499
+ "eval_f1": 0.9780682040821029,
500
+ "eval_loss": 0.10867351293563843,
501
+ "eval_precision": 0.9779367140146423,
502
+ "eval_recall": 0.9781997295137395,
503
+ "eval_runtime": 11.7323,
504
+ "eval_samples_per_second": 670.712,
505
+ "eval_steps_per_second": 2.642,
506
+ "step": 2691
507
+ },
508
+ {
509
+ "epoch": 40.0,
510
+ "eval_accuracy": 0.9788926392904173,
511
+ "eval_f1": 0.978110377786144,
512
+ "eval_loss": 0.1087782010436058,
513
+ "eval_precision": 0.9779826380886533,
514
+ "eval_recall": 0.9782381508575644,
515
+ "eval_runtime": 11.2634,
516
+ "eval_samples_per_second": 698.633,
517
+ "eval_steps_per_second": 2.752,
518
+ "step": 2760
519
+ },
520
+ {
521
+ "epoch": 40.0,
522
+ "step": 2760,
523
+ "total_flos": 1.673403126150724e+17,
524
+ "train_loss": 0.23496506378270576,
525
+ "train_runtime": 2350.6684,
526
+ "train_samples_per_second": 1204.968,
527
+ "train_steps_per_second": 1.174
528
+ }
529
+ ],
530
+ "max_steps": 2760,
531
+ "num_train_epochs": 40,
532
+ "total_flos": 1.673403126150724e+17,
533
+ "trial_name": null,
534
+ "trial_params": null
535
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:051e61435d7b641c10abb33ee47d32f1634a495820d849ba85d07be0a799abcb
3
+ size 3439