End of training
Browse files- README.md +50 -50
- model.safetensors +1 -1
README.md
CHANGED
@@ -17,58 +17,58 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
This model is a fine-tuned version of [Goader/liberta-large](https://huggingface.co/Goader/liberta-large) on the universal_dependencies dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss: 0.
|
21 |
-
- : {'precision': 0.
|
22 |
-
- Arataxis: {'precision': 0.
|
23 |
-
- Arataxis:discourse: {'precision': 0.
|
24 |
-
- Arataxis:rel: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number':
|
25 |
-
- Ark: {'precision': 0.
|
26 |
-
- Ase: {'precision': 0.
|
27 |
-
- Bj: {'precision': 0.
|
28 |
-
- Bl: {'precision': 0.
|
29 |
-
- C: {'precision': 0.
|
30 |
-
- Cl: {'precision': 0.
|
31 |
-
- Cl:adv: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number':
|
32 |
-
- Cl:relcl: {'precision': 0.
|
33 |
-
- Comp: {'precision': 0.
|
34 |
-
- Comp:sp: {'precision': 0.
|
35 |
-
- Dvcl: {'precision': 0.
|
36 |
-
- Dvcl:sp: {'precision':
|
37 |
-
- Dvcl:svc: {'precision':
|
38 |
-
- Dvmod: {'precision': 0.
|
39 |
-
- Dvmod:det: {'precision':
|
40 |
-
- Et: {'precision': 0.
|
41 |
-
- Et:numgov: {'precision': 0.
|
42 |
-
- Et:nummod: {'precision':
|
43 |
-
- Iscourse: {'precision': 0.
|
44 |
-
- Islocated: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number':
|
45 |
-
- Ixed: {'precision': 0.
|
46 |
- Lat:abs: {'precision': 1.0, 'recall': 0.5, 'f1': 0.6666666666666666, 'number': 2}
|
47 |
-
- Lat:foreign: {'precision': 0.
|
48 |
-
- Lat:name: {'precision': 0.
|
49 |
-
- Lat:range: {'precision': 0.
|
50 |
- Lat:repeat: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 3}
|
51 |
-
- Lat:title: {'precision': 0.
|
52 |
-
- Mod: {'precision': 0.
|
53 |
-
- Obj: {'precision': 0.
|
54 |
-
- Ocative: {'precision':
|
55 |
- Oeswith: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1}
|
56 |
-
- Ompound: {'precision': 0.
|
57 |
-
- Onj: {'precision': 0.
|
58 |
-
- Oot: {'precision': 0.
|
59 |
-
- Op: {'precision': 0.
|
60 |
-
- Ppos: {'precision': 0.
|
61 |
-
- Rphan: {'precision': 0.
|
62 |
-
- Subj: {'precision': 0.
|
63 |
-
- Ummod: {'precision': 0.
|
64 |
-
- Ummod:gov: {'precision': 0.
|
65 |
-
- Unct: {'precision': 0.
|
66 |
-
- Ux: {'precision': 0.
|
67 |
-
- Xpl: {'precision': 0.
|
68 |
-
- Overall Precision: 0.
|
69 |
-
- Overall Recall: 0.
|
70 |
-
- Overall F1: 0.
|
71 |
-
- Overall Accuracy: 0.
|
72 |
|
73 |
## Model description
|
74 |
|
@@ -88,7 +88,7 @@ More information needed
|
|
88 |
|
89 |
The following hyperparameters were used during training:
|
90 |
- learning_rate: 5e-05
|
91 |
-
- train_batch_size:
|
92 |
- eval_batch_size: 8
|
93 |
- seed: 42
|
94 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
|
|
17 |
|
18 |
This model is a fine-tuned version of [Goader/liberta-large](https://huggingface.co/Goader/liberta-large) on the universal_dependencies dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.5901
|
21 |
+
- : {'precision': 0.42857142857142855, 'recall': 0.21428571428571427, 'f1': 0.2857142857142857, 'number': 14}
|
22 |
+
- Arataxis: {'precision': 0.5066666666666667, 'recall': 0.3486238532110092, 'f1': 0.41304347826086957, 'number': 109}
|
23 |
+
- Arataxis:discourse: {'precision': 0.4117647058823529, 'recall': 0.3684210526315789, 'f1': 0.3888888888888889, 'number': 19}
|
24 |
+
- Arataxis:rel: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 7}
|
25 |
+
- Ark: {'precision': 0.8214285714285714, 'recall': 0.7777777777777778, 'f1': 0.7990074441687344, 'number': 207}
|
26 |
+
- Ase: {'precision': 0.8921023359288098, 'recall': 0.8044132397191575, 'f1': 0.8459915611814346, 'number': 997}
|
27 |
+
- Bj: {'precision': 0.8446389496717724, 'recall': 0.7524366471734892, 'f1': 0.7958762886597938, 'number': 513}
|
28 |
+
- Bl: {'precision': 0.8267090620031796, 'recall': 0.7084468664850136, 'f1': 0.7630227439471754, 'number': 734}
|
29 |
+
- C: {'precision': 0.8328690807799443, 'recall': 0.7310513447432763, 'f1': 0.7786458333333331, 'number': 409}
|
30 |
+
- Cl: {'precision': 0.7894736842105263, 'recall': 0.3409090909090909, 'f1': 0.4761904761904762, 'number': 44}
|
31 |
+
- Cl:adv: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 4}
|
32 |
+
- Cl:relcl: {'precision': 0.7611940298507462, 'recall': 0.7083333333333334, 'f1': 0.7338129496402879, 'number': 144}
|
33 |
+
- Comp: {'precision': 0.7708333333333334, 'recall': 0.7602739726027398, 'f1': 0.7655172413793104, 'number': 146}
|
34 |
+
- Comp:sp: {'precision': 0.7931034482758621, 'recall': 0.5897435897435898, 'f1': 0.676470588235294, 'number': 39}
|
35 |
+
- Dvcl: {'precision': 0.8210526315789474, 'recall': 0.7027027027027027, 'f1': 0.7572815533980582, 'number': 111}
|
36 |
+
- Dvcl:sp: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 3}
|
37 |
+
- Dvcl:svc: {'precision': 1.0, 'recall': 0.2, 'f1': 0.33333333333333337, 'number': 5}
|
38 |
+
- Dvmod: {'precision': 0.8085585585585585, 'recall': 0.7638297872340426, 'f1': 0.7855579868708972, 'number': 470}
|
39 |
+
- Dvmod:det: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 2}
|
40 |
+
- Et: {'precision': 0.8657407407407407, 'recall': 0.7824267782426778, 'f1': 0.8219780219780219, 'number': 239}
|
41 |
+
- Et:numgov: {'precision': 0.75, 'recall': 0.75, 'f1': 0.75, 'number': 12}
|
42 |
+
- Et:nummod: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 3}
|
43 |
+
- Iscourse: {'precision': 0.753731343283582, 'recall': 0.6352201257861635, 'f1': 0.6894197952218429, 'number': 159}
|
44 |
+
- Islocated: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 5}
|
45 |
+
- Ixed: {'precision': 0.75, 'recall': 0.2608695652173913, 'f1': 0.3870967741935483, 'number': 23}
|
46 |
- Lat:abs: {'precision': 1.0, 'recall': 0.5, 'f1': 0.6666666666666666, 'number': 2}
|
47 |
+
- Lat:foreign: {'precision': 0.625, 'recall': 0.25, 'f1': 0.35714285714285715, 'number': 20}
|
48 |
+
- Lat:name: {'precision': 0.631578947368421, 'recall': 0.43636363636363634, 'f1': 0.5161290322580645, 'number': 55}
|
49 |
+
- Lat:range: {'precision': 0.75, 'recall': 0.5, 'f1': 0.6, 'number': 12}
|
50 |
- Lat:repeat: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 3}
|
51 |
+
- Lat:title: {'precision': 0.616, 'recall': 0.47530864197530864, 'f1': 0.5365853658536586, 'number': 162}
|
52 |
+
- Mod: {'precision': 0.7972646822204345, 'recall': 0.7155234657039711, 'f1': 0.7541856925418569, 'number': 1385}
|
53 |
+
- Obj: {'precision': 0.4090909090909091, 'recall': 0.6, 'f1': 0.4864864864864865, 'number': 15}
|
54 |
+
- Ocative: {'precision': 0.25, 'recall': 1.0, 'f1': 0.4, 'number': 1}
|
55 |
- Oeswith: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1}
|
56 |
+
- Ompound: {'precision': 0.6764705882352942, 'recall': 0.3898305084745763, 'f1': 0.49462365591397844, 'number': 59}
|
57 |
+
- Onj: {'precision': 0.7439024390243902, 'recall': 0.5831739961759083, 'f1': 0.6538049303322616, 'number': 523}
|
58 |
+
- Oot: {'precision': 0.9379310344827586, 'recall': 0.9066666666666666, 'f1': 0.9220338983050848, 'number': 600}
|
59 |
+
- Op: {'precision': 0.7592592592592593, 'recall': 0.7454545454545455, 'f1': 0.7522935779816514, 'number': 55}
|
60 |
+
- Ppos: {'precision': 0.4262295081967213, 'recall': 0.30952380952380953, 'f1': 0.3586206896551724, 'number': 84}
|
61 |
+
- Rphan: {'precision': 0.6, 'recall': 0.23076923076923078, 'f1': 0.33333333333333337, 'number': 13}
|
62 |
+
- Subj: {'precision': 0.8660084626234132, 'recall': 0.8143236074270557, 'f1': 0.8393711551606288, 'number': 754}
|
63 |
+
- Ummod: {'precision': 0.6153846153846154, 'recall': 0.6, 'f1': 0.6075949367088608, 'number': 40}
|
64 |
+
- Ummod:gov: {'precision': 0.7352941176470589, 'recall': 0.625, 'f1': 0.6756756756756757, 'number': 40}
|
65 |
+
- Unct: {'precision': 0.8604790419161676, 'recall': 0.7418688693856479, 'f1': 0.7967840310507347, 'number': 1937}
|
66 |
+
- Ux: {'precision': 0.6875, 'recall': 0.6111111111111112, 'f1': 0.6470588235294118, 'number': 18}
|
67 |
+
- Xpl: {'precision': 0.8333333333333334, 'recall': 0.7142857142857143, 'f1': 0.7692307692307692, 'number': 7}
|
68 |
+
- Overall Precision: 0.8253
|
69 |
+
- Overall Recall: 0.7232
|
70 |
+
- Overall F1: 0.7709
|
71 |
+
- Overall Accuracy: 0.8090
|
72 |
|
73 |
## Model description
|
74 |
|
|
|
88 |
|
89 |
The following hyperparameters were used during training:
|
90 |
- learning_rate: 5e-05
|
91 |
+
- train_batch_size: 32
|
92 |
- eval_batch_size: 8
|
93 |
- seed: 42
|
94 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1342707664
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:55c33a9ffda92b956064bb09972cc5dfc3eb3311dcb47064f9487595b08a4b34
|
3 |
size 1342707664
|