Hugging Face's logo

hai2131
/
absa

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
Metrics Community
hai2131 commited on
Commit
69f12d7
·
verified ·
1 Parent(s): f02adab

End of training

Browse files
Files changed (4) hide show
  1. README.md +57 -57
  2. config.json +6 -68
  3. model.safetensors +2 -2
  4. training_args.bin +1 -1
README.md CHANGED
@@ -19,9 +19,9 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 1.6213
23
- - Accuracy: 0.7059
24
- - F1: 0.4389
25
 
26
  ## Model description
27
 
@@ -41,8 +41,8 @@ More information needed
41
 
42
  The following hyperparameters were used during training:
43
  - learning_rate: 2e-05
44
- - train_batch_size: 64
45
- - eval_batch_size: 64
46
  - seed: 42
47
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
  - lr_scheduler_type: linear
@@ -50,58 +50,58 @@ The following hyperparameters were used during training:
50
 
51
  ### Training results
52
 
53
- | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
54
- |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
55
- | 2.2394 | 1.0 | 149 | 1.5797 | 0.6125 | 0.1657 |
56
- | 1.505 | 2.0 | 298 | 1.3557 | 0.6370 | 0.1928 |
57
- | 1.2839 | 3.0 | 447 | 1.2337 | 0.6753 | 0.2603 |
58
- | 1.1167 | 4.0 | 596 | 1.1764 | 0.6868 | 0.2958 |
59
- | 0.9805 | 5.0 | 745 | 1.1334 | 0.6925 | 0.3355 |
60
- | 0.8614 | 6.0 | 894 | 1.1179 | 0.6954 | 0.3472 |
61
- | 0.7573 | 7.0 | 1043 | 1.1196 | 0.7011 | 0.3701 |
62
- | 0.6696 | 8.0 | 1192 | 1.1380 | 0.6992 | 0.3821 |
63
- | 0.5909 | 9.0 | 1341 | 1.1420 | 0.7031 | 0.3892 |
64
- | 0.5244 | 10.0 | 1490 | 1.1554 | 0.7021 | 0.3972 |
65
- | 0.4637 | 11.0 | 1639 | 1.1932 | 0.6978 | 0.3915 |
66
- | 0.4116 | 12.0 | 1788 | 1.2032 | 0.6968 | 0.4044 |
67
- | 0.3679 | 13.0 | 1937 | 1.2351 | 0.6892 | 0.3857 |
68
- | 0.3333 | 14.0 | 2086 | 1.2645 | 0.7035 | 0.4071 |
69
- | 0.303 | 15.0 | 2235 | 1.2936 | 0.6992 | 0.4183 |
70
- | 0.2743 | 16.0 | 2384 | 1.3310 | 0.7045 | 0.4082 |
71
- | 0.2504 | 17.0 | 2533 | 1.3357 | 0.7026 | 0.4339 |
72
- | 0.2295 | 18.0 | 2682 | 1.3274 | 0.7050 | 0.4347 |
73
- | 0.212 | 19.0 | 2831 | 1.3709 | 0.6949 | 0.4229 |
74
- | 0.1953 | 20.0 | 2980 | 1.3922 | 0.6949 | 0.4394 |
75
- | 0.1863 | 21.0 | 3129 | 1.4025 | 0.7011 | 0.4407 |
76
- | 0.1726 | 22.0 | 3278 | 1.4215 | 0.7040 | 0.4266 |
77
- | 0.1625 | 23.0 | 3427 | 1.4324 | 0.6887 | 0.4300 |
78
- | 0.1536 | 24.0 | 3576 | 1.4505 | 0.7040 | 0.4198 |
79
- | 0.1452 | 25.0 | 3725 | 1.4800 | 0.7064 | 0.4356 |
80
- | 0.1369 | 26.0 | 3874 | 1.4869 | 0.6988 | 0.4409 |
81
- | 0.1333 | 27.0 | 4023 | 1.5108 | 0.6978 | 0.4317 |
82
- | 0.1294 | 28.0 | 4172 | 1.4938 | 0.7021 | 0.4408 |
83
- | 0.1225 | 29.0 | 4321 | 1.5053 | 0.7021 | 0.4356 |
84
- | 0.1169 | 30.0 | 4470 | 1.5472 | 0.6959 | 0.4292 |
85
- | 0.1105 | 31.0 | 4619 | 1.5470 | 0.6988 | 0.4393 |
86
- | 0.1086 | 32.0 | 4768 | 1.5285 | 0.7007 | 0.4311 |
87
- | 0.1017 | 33.0 | 4917 | 1.5598 | 0.6949 | 0.4250 |
88
- | 0.1022 | 34.0 | 5066 | 1.5873 | 0.7059 | 0.4374 |
89
- | 0.0965 | 35.0 | 5215 | 1.5721 | 0.7045 | 0.4345 |
90
- | 0.0964 | 36.0 | 5364 | 1.5777 | 0.7055 | 0.4345 |
91
- | 0.0951 | 37.0 | 5513 | 1.5789 | 0.6940 | 0.4323 |
92
- | 0.0894 | 38.0 | 5662 | 1.5818 | 0.6954 | 0.4305 |
93
- | 0.0878 | 39.0 | 5811 | 1.5938 | 0.7083 | 0.4387 |
94
- | 0.0828 | 40.0 | 5960 | 1.6007 | 0.7064 | 0.4406 |
95
- | 0.0846 | 41.0 | 6109 | 1.6040 | 0.6983 | 0.4299 |
96
- | 0.0783 | 42.0 | 6258 | 1.6126 | 0.7055 | 0.4393 |
97
- | 0.0807 | 43.0 | 6407 | 1.6083 | 0.7002 | 0.4313 |
98
- | 0.0774 | 44.0 | 6556 | 1.6123 | 0.7059 | 0.4407 |
99
- | 0.0765 | 45.0 | 6705 | 1.6197 | 0.7055 | 0.4378 |
100
- | 0.0751 | 46.0 | 6854 | 1.6168 | 0.7055 | 0.4365 |
101
- | 0.0729 | 47.0 | 7003 | 1.6190 | 0.7074 | 0.4432 |
102
- | 0.0718 | 48.0 | 7152 | 1.6217 | 0.7055 | 0.4393 |
103
- | 0.0706 | 49.0 | 7301 | 1.6212 | 0.7069 | 0.4401 |
104
- | 0.0665 | 50.0 | 7450 | 1.6213 | 0.7059 | 0.4389 |
105
 
106
 
107
  ### Framework versions
 
19
 
20
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 1.0417
23
+ - Accuracy: 0.8779
24
+ - F1: 0.7493
25
 
26
  ## Model description
27
 
 
41
 
42
  The following hyperparameters were used during training:
43
  - learning_rate: 2e-05
44
+ - train_batch_size: 32
45
+ - eval_batch_size: 32
46
  - seed: 42
47
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
  - lr_scheduler_type: linear
 
50
 
51
  ### Training results
52
 
53
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
54
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|
55
+ | 0.4543 | 1.0 | 298 | 0.3298 | 0.8707 | 0.6817 |
56
+ | 0.2805 | 2.0 | 596 | 0.3210 | 0.8798 | 0.7341 |
57
+ | 0.208 | 3.0 | 894 | 0.3442 | 0.8841 | 0.7757 |
58
+ | 0.167 | 4.0 | 1192 | 0.3991 | 0.8841 | 0.7528 |
59
+ | 0.131 | 5.0 | 1490 | 0.4410 | 0.8798 | 0.7546 |
60
+ | 0.1039 | 6.0 | 1788 | 0.5180 | 0.8784 | 0.7626 |
61
+ | 0.0863 | 7.0 | 2086 | 0.5390 | 0.8793 | 0.7588 |
62
+ | 0.073 | 8.0 | 2384 | 0.5781 | 0.8702 | 0.7600 |
63
+ | 0.0651 | 9.0 | 2682 | 0.5738 | 0.875 | 0.7503 |
64
+ | 0.0535 | 10.0 | 2980 | 0.5999 | 0.8755 | 0.7501 |
65
+ | 0.0389 | 11.0 | 3278 | 0.6803 | 0.8760 | 0.7553 |
66
+ | 0.0385 | 12.0 | 3576 | 0.7202 | 0.8836 | 0.7301 |
67
+ | 0.0388 | 13.0 | 3874 | 0.7378 | 0.8774 | 0.7323 |
68
+ | 0.0324 | 14.0 | 4172 | 0.8089 | 0.8740 | 0.7334 |
69
+ | 0.0278 | 15.0 | 4470 | 0.7891 | 0.8769 | 0.7540 |
70
+ | 0.0224 | 16.0 | 4768 | 0.8061 | 0.8740 | 0.7448 |
71
+ | 0.022 | 17.0 | 5066 | 0.8205 | 0.8716 | 0.7492 |
72
+ | 0.0208 | 18.0 | 5364 | 0.7715 | 0.8716 | 0.7271 |
73
+ | 0.0184 | 19.0 | 5662 | 0.8142 | 0.8803 | 0.7440 |
74
+ | 0.0173 | 20.0 | 5960 | 0.8908 | 0.8764 | 0.7480 |
75
+ | 0.0149 | 21.0 | 6258 | 0.8814 | 0.8731 | 0.7427 |
76
+ | 0.0145 | 22.0 | 6556 | 0.8972 | 0.8784 | 0.7416 |
77
+ | 0.0161 | 23.0 | 6854 | 0.8861 | 0.8736 | 0.7395 |
78
+ | 0.0164 | 24.0 | 7152 | 0.9344 | 0.8736 | 0.7498 |
79
+ | 0.0168 | 25.0 | 7450 | 0.9008 | 0.8740 | 0.7466 |
80
+ | 0.0147 | 26.0 | 7748 | 0.9498 | 0.8769 | 0.7456 |
81
+ | 0.0124 | 27.0 | 8046 | 0.9168 | 0.8712 | 0.7254 |
82
+ | 0.0128 | 28.0 | 8344 | 0.9192 | 0.8774 | 0.7362 |
83
+ | 0.0138 | 29.0 | 8642 | 0.9745 | 0.8788 | 0.7612 |
84
+ | 0.0125 | 30.0 | 8940 | 0.9276 | 0.8784 | 0.7455 |
85
+ | 0.0118 | 31.0 | 9238 | 1.0205 | 0.8707 | 0.7552 |
86
+ | 0.0123 | 32.0 | 9536 | 0.9628 | 0.8764 | 0.7486 |
87
+ | 0.0139 | 33.0 | 9834 | 1.0042 | 0.8745 | 0.7541 |
88
+ | 0.0126 | 34.0 | 10132 | 0.9834 | 0.8760 | 0.7461 |
89
+ | 0.013 | 35.0 | 10430 | 0.9986 | 0.8769 | 0.7450 |
90
+ | 0.0134 | 36.0 | 10728 | 0.9907 | 0.8788 | 0.7490 |
91
+ | 0.0135 | 37.0 | 11026 | 1.0038 | 0.8736 | 0.7458 |
92
+ | 0.0121 | 38.0 | 11324 | 1.0175 | 0.8740 | 0.7476 |
93
+ | 0.0122 | 39.0 | 11622 | 1.0053 | 0.8755 | 0.7499 |
94
+ | 0.0112 | 40.0 | 11920 | 1.0120 | 0.8784 | 0.7467 |
95
+ | 0.0115 | 41.0 | 12218 | 1.0084 | 0.8764 | 0.7448 |
96
+ | 0.0129 | 42.0 | 12516 | 1.0021 | 0.8798 | 0.7491 |
97
+ | 0.0107 | 43.0 | 12814 | 1.0105 | 0.8784 | 0.7476 |
98
+ | 0.0108 | 44.0 | 13112 | 1.0131 | 0.8774 | 0.7454 |
99
+ | 0.0114 | 45.0 | 13410 | 1.0363 | 0.875 | 0.7504 |
100
+ | 0.0115 | 46.0 | 13708 | 1.0333 | 0.8798 | 0.7553 |
101
+ | 0.0106 | 47.0 | 14006 | 1.0297 | 0.8788 | 0.7500 |
102
+ | 0.0102 | 48.0 | 14304 | 1.0378 | 0.8779 | 0.7494 |
103
+ | 0.01 | 49.0 | 14602 | 1.0414 | 0.8769 | 0.7469 |
104
+ | 0.0107 | 50.0 | 14900 | 1.0417 | 0.8779 | 0.7493 |
105
 
106
 
107
  ### Framework versions
config.json CHANGED
@@ -9,78 +9,16 @@
9
  "hidden_dropout_prob": 0.1,
10
  "hidden_size": 768,
11
  "id2label": {
12
- "0": "LABEL_0",
13
- "1": "LABEL_1",
14
- "2": "LABEL_2",
15
- "3": "LABEL_3",
16
- "4": "LABEL_4",
17
- "5": "LABEL_5",
18
- "6": "LABEL_6",
19
- "7": "LABEL_7",
20
- "8": "LABEL_8",
21
- "9": "LABEL_9",
22
- "10": "LABEL_10",
23
- "11": "LABEL_11",
24
- "12": "LABEL_12",
25
- "13": "LABEL_13",
26
- "14": "LABEL_14",
27
- "15": "LABEL_15",
28
- "16": "LABEL_16",
29
- "17": "LABEL_17",
30
- "18": "LABEL_18",
31
- "19": "LABEL_19",
32
- "20": "LABEL_20",
33
- "21": "LABEL_21",
34
- "22": "LABEL_22",
35
- "23": "LABEL_23",
36
- "24": "LABEL_24",
37
- "25": "LABEL_25",
38
- "26": "LABEL_26",
39
- "27": "LABEL_27",
40
- "28": "LABEL_28",
41
- "29": "LABEL_29",
42
- "30": "LABEL_30",
43
- "31": "LABEL_31",
44
- "32": "LABEL_32",
45
- "33": "LABEL_33"
46
  },
47
  "initializer_range": 0.02,
48
  "intermediate_size": 3072,
49
  "label2id": {
50
- "LABEL_0": 0,
51
- "LABEL_1": 1,
52
- "LABEL_10": 10,
53
- "LABEL_11": 11,
54
- "LABEL_12": 12,
55
- "LABEL_13": 13,
56
- "LABEL_14": 14,
57
- "LABEL_15": 15,
58
- "LABEL_16": 16,
59
- "LABEL_17": 17,
60
- "LABEL_18": 18,
61
- "LABEL_19": 19,
62
- "LABEL_2": 2,
63
- "LABEL_20": 20,
64
- "LABEL_21": 21,
65
- "LABEL_22": 22,
66
- "LABEL_23": 23,
67
- "LABEL_24": 24,
68
- "LABEL_25": 25,
69
- "LABEL_26": 26,
70
- "LABEL_27": 27,
71
- "LABEL_28": 28,
72
- "LABEL_29": 29,
73
- "LABEL_3": 3,
74
- "LABEL_30": 30,
75
- "LABEL_31": 31,
76
- "LABEL_32": 32,
77
- "LABEL_33": 33,
78
- "LABEL_4": 4,
79
- "LABEL_5": 5,
80
- "LABEL_6": 6,
81
- "LABEL_7": 7,
82
- "LABEL_8": 8,
83
- "LABEL_9": 9
84
  },
85
  "layer_norm_eps": 1e-12,
86
  "max_position_embeddings": 512,
 
9
  "hidden_dropout_prob": 0.1,
10
  "hidden_size": 768,
11
  "id2label": {
12
+ "0": "negative",
13
+ "1": "neutral",
14
+ "2": "positive"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
15
  },
16
  "initializer_range": 0.02,
17
  "intermediate_size": 3072,
18
  "label2id": {
19
+ "negative": 0,
20
+ "neutral": 1,
21
+ "positive": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
22
  },
23
  "layer_norm_eps": 1e-12,
24
  "max_position_embeddings": 512,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:524db4cf3331926733e0d9c3d0580696b8c3823e83387f45675068f93e4faf07
3
- size 438057080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5aa21bd0449b99f9376ae97848a4b661004abddb41db2981c1e9a97c7481c877
3
+ size 437961724
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2cab4c506efe9b2929974f23acb89723b54cc68b908288bdb562510d223bb13f
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71534f987b48c1cd8d5121d0291bd7c111d9b145eeed6ad2ede77c0627fb503f
3
  size 5304