Hugging Face's logo

galkowskim
/
roberta_base_QA_SQUAD_adafactor

Text Classification
Transformers
TensorBoard
Safetensors
roberta
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Metrics Community
galkowskim commited on
Commit
cf8c2b2
·
verified ·
1 Parent(s): 254f5b4

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_adafactor
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_adafactor
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 2.19.0
53
+ - Tokenizers 0.19.1
test_metrics.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "exact_match": 84.34247871333964,
3
+ "f1": 91.39748486674911
4
+ }
train_losses.csv ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ loss,epoch
2
+ 2.0833,0.04517528008673654
3
+ 1.3382,0.09035056017347308
4
+ 1.2042,0.1355258402602096
5
+ 1.1654,0.18070112034694616
6
+ 1.1136,0.22587640043368268
7
+ 1.0547,0.2710516805204192
8
+ 1.0335,0.31622696060715577
9
+ 0.9834,0.3614022406938923
10
+ 0.9938,0.40657752078062886
11
+ 0.9644,0.45175280086736536
12
+ 1.0091,0.4969280809541019
13
+ 0.9771,0.5421033610408384
14
+ 0.9896,0.587278641127575
15
+ 0.9686,0.6324539212143115
16
+ 0.9507,0.6776292013010481
17
+ 0.9284,0.7228044813877846
18
+ 0.9188,0.7679797614745212
19
+ 0.9092,0.8131550415612577
20
+ 0.9291,0.8583303216479942
21
+ 0.8653,0.9035056017347307
22
+ 0.9,0.9486808818214673
23
+ 0.9007,0.9938561619082038
24
+ 0.7321,1.0390314419949405
25
+ 0.7392,1.084206722081677
26
+ 0.7169,1.1293820021684136
27
+ 0.7194,1.17455728225515
28
+ 0.7145,1.2197325623418864
29
+ 0.7026,1.264907842428623
30
+ 0.7097,1.3100831225153595
31
+ 0.7049,1.3552584026020962
32
+ 0.6926,1.4004336826888326
33
+ 0.7542,1.4456089627755693
34
+ 0.7002,1.4907842428623057
35
+ 0.7054,1.5359595229490424
36
+ 0.7094,1.5811348030357788
37
+ 0.6801,1.6263100831225152
38
+ 0.7305,1.671485363209252
39
+ 0.7247,1.7166606432959886
40
+ 0.7082,1.761835923382725
41
+ 0.7127,1.8070112034694614
42
+ 0.7034,1.852186483556198
43
+ 0.7349,1.8973617636429347
44
+ 0.679,1.9425370437296712
45
+ 0.698,1.9877123238164076
46
+ 0.5872,2.032887603903144
47
+ 0.5234,2.078062883989881
48
+ 0.5196,2.1232381640766174
49
+ 0.5713,2.168413444163354
50
+ 0.5481,2.2135887242500902
51
+ 0.5207,2.258764004336827
52
+ 0.5218,2.3039392844235635
53
+ 0.5506,2.3491145645103
54
+ 0.5151,2.3942898445970364
55
+ 0.5188,2.439465124683773
56
+ 0.5429,2.4846404047705097
57
+ 0.5888,2.529815684857246
58
+ 0.5333,2.5749909649439826
59
+ 0.5699,2.620166245030719
60
+ 0.5351,2.665341525117456
61
+ 0.5252,2.7105168052041924
62
+ 0.5523,2.755692085290929
63
+ 0.5565,2.8008673653776652
64
+ 0.5445,2.8460426454644017
65
+ 0.5506,2.8912179255511385
66
+ 0.5423,2.936393205637875
67
+ 0.5456,2.9815684857246114
68
+ 0.4672,3.026743765811348
69
+ 0.3967,3.0719190458980847
70
+ 0.4096,3.117094325984821
71
+ 0.4059,3.1622696060715576
72
+ 0.4127,3.207444886158294
73
+ 0.4189,3.2526201662450305
74
+ 0.3989,3.2977954463317674
75
+ 0.4124,3.342970726418504
76
+ 0.3945,3.3881460065052402
77
+ 0.3976,3.433321286591977
78
+ 0.4082,3.4784965666787135
79
+ 0.4226,3.52367184676545
80
+ 0.4082,3.5688471268521864
81
+ 0.4082,3.614022406938923
82
+ 0.4167,3.6591976870256593
83
+ 0.4095,3.704372967112396
84
+ 0.4153,3.7495482471991326
85
+ 0.4182,3.794723527285869
86
+ 0.4167,3.839898807372606
87
+ 0.4247,3.8850740874593424
88
+ 0.4046,3.930249367546079
89
+ 0.4167,3.9754246476328152
90
+ 0.3793,4.020599927719552
91
+ 0.3281,4.065775207806288
92
+ 0.3306,4.1109504878930245
93
+ 0.3244,4.156125767979762
94
+ 0.333,4.201301048066498
95
+ 0.3059,4.246476328153235
96
+ 0.3131,4.291651608239971
97
+ 0.3348,4.336826888326708
98
+ 0.3412,4.382002168413444
99
+ 0.2996,4.4271774485001805
100
+ 0.3344,4.472352728586917
101
+ 0.3143,4.517528008673654
102
+ 0.3186,4.562703288760391
103
+ 0.3118,4.607878568847127
104
+ 0.3207,4.6530538489338635
105
+ 0.3282,4.6982291290206
106
+ 0.3207,4.743404409107336
107
+ 0.3384,4.788579689194073
108
+ 0.3223,4.833754969280809
109
+ 0.3279,4.878930249367546
110
+ 0.3136,4.924105529454282
111
+ 0.3328,4.9692808095410195
112
+ 0.6079734846362578,5.0