Hugging Face's logo

galkowskim
/
roberta_base_QA_SQUAD

Question Answering
Transformers
Safetensors
roberta
Generated from Trainer
Model card Files
xet
 Community
galkowskim commited on
Commit
56813da
·
verified ·
1 Parent(s): 5e9b77d

Training complete

Browse files
Files changed (3) hide show
  1. README.md +53 -0
  2. test_metrics.json +4 -0
  3. train_losses.csv +112 -0
README.md ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: FacebookAI/roberta-base
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: roberta_base_QA_SQUAD
8
+ results: []
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
+ # roberta_base_QA_SQUAD
15
+
16
+ This model is a fine-tuned version of [FacebookAI/roberta-base](https://huggingface.co/FacebookAI/roberta-base) 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: 2e-05
36
+ - train_batch_size: 8
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
+ - num_epochs: 5
42
+ - mixed_precision_training: Native AMP
43
+
44
+ ### Training results
45
+
46
+
47
+
48
+ ### Framework versions
49
+
50
+ - Transformers 4.40.0
51
+ - Pytorch 2.2.1
52
+ - Datasets 2.18.0
53
+ - Tokenizers 0.19.1
test_metrics.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "exact_match": 84.65468306527909,
3
+ "f1": 91.55804062843333
4
+ }
train_losses.csv ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ loss,epoch
2
+ 2.073,0.04516303856923494
3
+ 1.3268,0.09032607713846988
4
+ 1.2112,0.1354891157077048
5
+ 1.1183,0.18065215427693976
6
+ 1.0995,0.22581519284617468
7
+ 1.0734,0.2709782314154096
8
+ 1.0258,0.3161412699846446
9
+ 1.0602,0.3613043085538795
10
+ 1.0067,0.40646734712311444
11
+ 0.9985,0.45163038569234937
12
+ 0.9358,0.4967934242615843
13
+ 1.0052,0.5419564628308192
14
+ 0.9595,0.5871195014000542
15
+ 0.9575,0.6322825399692892
16
+ 0.9399,0.677445578538524
17
+ 0.9114,0.722608617107759
18
+ 0.9735,0.7677716556769939
19
+ 0.9248,0.8129346942462289
20
+ 0.9132,0.8580977328154639
21
+ 0.9043,0.9032607713846987
22
+ 0.9073,0.9484238099539337
23
+ 0.908,0.9935868485231686
24
+ 0.7482,1.0387498870924037
25
+ 0.7074,1.0839129256616384
26
+ 0.702,1.1290759642308734
27
+ 0.7315,1.1742390028001084
28
+ 0.6674,1.2194020413693434
29
+ 0.759,1.2645650799385781
30
+ 0.7187,1.3097281185078131
31
+ 0.6939,1.354891157077048
32
+ 0.7177,1.400054195646283
33
+ 0.7284,1.445217234215518
34
+ 0.6842,1.490380272784753
35
+ 0.7188,1.535543311353988
36
+ 0.7052,1.5807063499232228
37
+ 0.7088,1.6258693884924578
38
+ 0.7039,1.6710324270616927
39
+ 0.7191,1.7161954656309275
40
+ 0.7319,1.7613585042001625
41
+ 0.6991,1.8065215427693975
42
+ 0.7152,1.8516845813386325
43
+ 0.7149,1.8968476199078674
44
+ 0.7272,1.9420106584771024
45
+ 0.6842,1.9871736970463374
46
+ 0.5655,2.0323367356155724
47
+ 0.5356,2.0774997741848074
48
+ 0.5181,2.122662812754042
49
+ 0.5664,2.167825851323277
50
+ 0.5077,2.212988889892512
51
+ 0.5628,2.258151928461747
52
+ 0.5437,2.303314967030982
53
+ 0.5575,2.348478005600217
54
+ 0.5216,2.393641044169452
55
+ 0.522,2.4388040827386868
56
+ 0.5374,2.4839671213079217
57
+ 0.538,2.5291301598771563
58
+ 0.5293,2.5742931984463917
59
+ 0.549,2.6194562370156262
60
+ 0.5579,2.6646192755848612
61
+ 0.5228,2.709782314154096
62
+ 0.5352,2.754945352723331
63
+ 0.5427,2.800108391292566
64
+ 0.5062,2.845271429861801
65
+ 0.5242,2.890434468431036
66
+ 0.5492,2.935597507000271
67
+ 0.5455,2.980760545569506
68
+ 0.4557,3.025923584138741
69
+ 0.4097,3.0710866227079756
70
+ 0.4264,3.1162496612772106
71
+ 0.4034,3.1614126998464456
72
+ 0.4014,3.2065757384156806
73
+ 0.4157,3.2517387769849155
74
+ 0.417,3.2969018155541505
75
+ 0.4055,3.3420648541233855
76
+ 0.4273,3.3872278926926205
77
+ 0.4075,3.4323909312618555
78
+ 0.3917,3.4775539698310904
79
+ 0.4171,3.522717008400325
80
+ 0.4211,3.56788004696956
81
+ 0.4009,3.613043085538795
82
+ 0.3833,3.65820612410803
83
+ 0.3732,3.703369162677265
84
+ 0.4157,3.7485322012465
85
+ 0.3983,3.793695239815735
86
+ 0.3876,3.83885827838497
87
+ 0.3889,3.884021316954205
88
+ 0.4027,3.9291843555234394
89
+ 0.3962,3.974347394092675
90
+ 0.3449,4.019510432661909
91
+ 0.3182,4.064673471231145
92
+ 0.302,4.109836509800379
93
+ 0.3066,4.154999548369615
94
+ 0.3204,4.200162586938849
95
+ 0.3105,4.245325625508084
96
+ 0.3105,4.290488664077319
97
+ 0.3184,4.335651702646554
98
+ 0.3306,4.380814741215789
99
+ 0.3136,4.425977779785024
100
+ 0.3074,4.471140818354259
101
+ 0.3458,4.516303856923494
102
+ 0.302,4.561466895492729
103
+ 0.3051,4.606629934061964
104
+ 0.3089,4.651792972631199
105
+ 0.2946,4.696956011200434
106
+ 0.3046,4.742119049769668
107
+ 0.3206,4.787282088338904
108
+ 0.2986,4.832445126908138
109
+ 0.2949,4.8776081654773735
110
+ 0.2964,4.922771204046608
111
+ 0.2939,4.9679342426158435
112
+ 0.6032335646784992,5.0