syafiqfaray commited on
Commit
2f11c7a
1 Parent(s): 88a7e7a

End of training

Browse files
README.md ADDED
@@ -0,0 +1,113 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: google/byt5-base
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - wer
8
+ model-index:
9
+ - name: byt5-base-indocollex-informal-to-formal-wordformation
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # byt5-base-indocollex-informal-to-formal-wordformation
17
+
18
+ This model is a fine-tuned version of [google/byt5-base](https://huggingface.co/google/byt5-base) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.1413
21
+ - Cer: 0.1978
22
+ - Wer: 0.4524
23
+ - Word Acc: 0.5476
24
+ - Gen Len: 7.6457
25
+
26
+ ## Model description
27
+
28
+ More information needed
29
+
30
+ ## Intended uses & limitations
31
+
32
+ More information needed
33
+
34
+ ## Training and evaluation data
35
+
36
+ More information needed
37
+
38
+ ## Training procedure
39
+
40
+ ### Training hyperparameters
41
+
42
+ The following hyperparameters were used during training:
43
+ - learning_rate: 2e-05
44
+ - train_batch_size: 16
45
+ - eval_batch_size: 16
46
+ - seed: 42
47
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
+ - lr_scheduler_type: linear
49
+ - num_epochs: 100
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Cer | Wer | Word Acc | Gen Len |
54
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:--------:|:-------:|
55
+ | No log | 0.54 | 50 | 16.1894 | 2.1868 | 2.2905 | -1.2905 | 19.0 |
56
+ | No log | 1.08 | 100 | 13.7479 | 2.1248 | 1.9333 | -0.9333 | 19.0 |
57
+ | No log | 1.61 | 150 | 11.6231 | 2.1095 | 1.4238 | -0.4238 | 18.7486 |
58
+ | No log | 2.15 | 200 | 8.9106 | 1.056 | 0.9857 | 0.0143 | 10.6171 |
59
+ | No log | 2.69 | 250 | 4.6844 | 0.8523 | 0.9762 | 0.0238 | 9.36 |
60
+ | No log | 3.23 | 300 | 4.1175 | 0.5756 | 0.9714 | 0.0286 | 7.4114 |
61
+ | No log | 3.76 | 350 | 3.3688 | 0.5951 | 0.9714 | 0.0286 | 7.8 |
62
+ | No log | 4.3 | 400 | 2.2287 | 0.6112 | 0.9857 | 0.0143 | 6.7543 |
63
+ | No log | 4.84 | 450 | 1.5164 | 0.6095 | 0.9571 | 0.0429 | 7.8857 |
64
+ | 8.4834 | 5.38 | 500 | 1.0363 | 0.5976 | 0.9476 | 0.0524 | 7.8229 |
65
+ | 8.4834 | 5.91 | 550 | 0.6893 | 0.5976 | 0.9476 | 0.0524 | 7.7943 |
66
+ | 8.4834 | 6.45 | 600 | 0.5438 | 0.5866 | 0.9381 | 0.0619 | 7.9943 |
67
+ | 8.4834 | 6.99 | 650 | 0.4720 | 0.5806 | 0.9333 | 0.0667 | 8.0057 |
68
+ | 8.4834 | 7.53 | 700 | 0.4305 | 0.5764 | 0.9333 | 0.0667 | 8.0057 |
69
+ | 8.4834 | 8.06 | 750 | 0.3931 | 0.5654 | 0.9333 | 0.0667 | 8.2971 |
70
+ | 8.4834 | 8.6 | 800 | 0.3450 | 0.4576 | 0.9952 | 0.0048 | 7.7086 |
71
+ | 8.4834 | 9.14 | 850 | 0.2773 | 0.3226 | 0.8238 | 0.1762 | 7.8743 |
72
+ | 8.4834 | 9.68 | 900 | 0.2184 | 0.2368 | 0.7286 | 0.2714 | 7.2171 |
73
+ | 8.4834 | 10.22 | 950 | 0.1992 | 0.2165 | 0.6333 | 0.3667 | 7.4343 |
74
+ | 0.7362 | 10.75 | 1000 | 0.1887 | 0.2097 | 0.5714 | 0.4286 | 7.5829 |
75
+ | 0.7362 | 11.29 | 1050 | 0.1815 | 0.2216 | 0.5905 | 0.4095 | 7.6171 |
76
+ | 0.7362 | 11.83 | 1100 | 0.1688 | 0.2046 | 0.5762 | 0.4238 | 7.4629 |
77
+ | 0.7362 | 12.37 | 1150 | 0.1679 | 0.2012 | 0.5286 | 0.4714 | 7.7143 |
78
+ | 0.7362 | 12.9 | 1200 | 0.1579 | 0.1952 | 0.5333 | 0.4667 | 7.5257 |
79
+ | 0.7362 | 13.44 | 1250 | 0.1531 | 0.1969 | 0.5095 | 0.4905 | 7.5714 |
80
+ | 0.7362 | 13.98 | 1300 | 0.1484 | 0.1935 | 0.4952 | 0.5048 | 7.5543 |
81
+ | 0.7362 | 14.52 | 1350 | 0.1481 | 0.1969 | 0.4952 | 0.5048 | 7.5886 |
82
+ | 0.7362 | 15.05 | 1400 | 0.1417 | 0.191 | 0.481 | 0.519 | 7.5829 |
83
+ | 0.7362 | 15.59 | 1450 | 0.1429 | 0.1876 | 0.4762 | 0.5238 | 7.5829 |
84
+ | 0.195 | 16.13 | 1500 | 0.1407 | 0.1834 | 0.481 | 0.519 | 7.48 |
85
+ | 0.195 | 16.67 | 1550 | 0.1409 | 0.1995 | 0.481 | 0.519 | 7.7086 |
86
+ | 0.195 | 17.2 | 1600 | 0.1432 | 0.1817 | 0.4762 | 0.5238 | 7.4857 |
87
+ | 0.195 | 17.74 | 1650 | 0.1439 | 0.1885 | 0.4762 | 0.5238 | 7.5429 |
88
+ | 0.195 | 18.28 | 1700 | 0.1385 | 0.1766 | 0.4476 | 0.5524 | 7.5143 |
89
+ | 0.195 | 18.82 | 1750 | 0.1357 | 0.1834 | 0.4762 | 0.5238 | 7.4971 |
90
+ | 0.195 | 19.35 | 1800 | 0.1349 | 0.1935 | 0.4714 | 0.5286 | 7.4686 |
91
+ | 0.195 | 19.89 | 1850 | 0.1355 | 0.1842 | 0.4286 | 0.5714 | 7.5371 |
92
+ | 0.195 | 20.43 | 1900 | 0.1343 | 0.1902 | 0.4619 | 0.5381 | 7.5714 |
93
+ | 0.195 | 20.97 | 1950 | 0.1348 | 0.1808 | 0.4619 | 0.5381 | 7.4229 |
94
+ | 0.1287 | 21.51 | 2000 | 0.1341 | 0.1817 | 0.4524 | 0.5476 | 7.4571 |
95
+ | 0.1287 | 22.04 | 2050 | 0.1324 | 0.1868 | 0.4476 | 0.5524 | 7.5371 |
96
+ | 0.1287 | 22.58 | 2100 | 0.1329 | 0.1859 | 0.4571 | 0.5429 | 7.4571 |
97
+ | 0.1287 | 23.12 | 2150 | 0.1367 | 0.1868 | 0.4476 | 0.5524 | 7.56 |
98
+ | 0.1287 | 23.66 | 2200 | 0.1389 | 0.1919 | 0.4667 | 0.5333 | 7.48 |
99
+ | 0.1287 | 24.19 | 2250 | 0.1385 | 0.18 | 0.4333 | 0.5667 | 7.5029 |
100
+ | 0.1287 | 24.73 | 2300 | 0.1429 | 0.1944 | 0.4905 | 0.5095 | 7.4171 |
101
+ | 0.1287 | 25.27 | 2350 | 0.1414 | 0.1961 | 0.4667 | 0.5333 | 7.6057 |
102
+ | 0.1287 | 25.81 | 2400 | 0.1419 | 0.1876 | 0.4333 | 0.5667 | 7.5371 |
103
+ | 0.1287 | 26.34 | 2450 | 0.1433 | 0.1927 | 0.4667 | 0.5333 | 7.5886 |
104
+ | 0.0977 | 26.88 | 2500 | 0.1433 | 0.1927 | 0.4571 | 0.5429 | 7.5486 |
105
+ | 0.0977 | 27.42 | 2550 | 0.1413 | 0.1978 | 0.4524 | 0.5476 | 7.6457 |
106
+
107
+
108
+ ### Framework versions
109
+
110
+ - Transformers 4.33.0
111
+ - Pytorch 2.0.0
112
+ - Datasets 2.1.0
113
+ - Tokenizers 0.13.3
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/byt5-base",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 3968,
8
+ "d_kv": 64,
9
+ "d_model": 1536,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "gelu_new",
12
+ "dropout_rate": 0.1,
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "gated-gelu",
15
+ "gradient_checkpointing": false,
16
+ "initializer_factor": 1.0,
17
+ "is_encoder_decoder": true,
18
+ "is_gated_act": true,
19
+ "layer_norm_epsilon": 1e-06,
20
+ "model_type": "t5",
21
+ "num_decoder_layers": 6,
22
+ "num_heads": 12,
23
+ "num_layers": 18,
24
+ "output_past": true,
25
+ "pad_token_id": 0,
26
+ "relative_attention_max_distance": 128,
27
+ "relative_attention_num_buckets": 32,
28
+ "tie_word_embeddings": false,
29
+ "tokenizer_class": "ByT5Tokenizer",
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.33.0",
32
+ "use_cache": true,
33
+ "vocab_size": 384
34
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "decoder_start_token_id": 0,
3
+ "eos_token_id": 1,
4
+ "pad_token_id": 0,
5
+ "transformers_version": "4.33.0"
6
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5a7f5d13e6e5b49d3129e134ba03dec826a946e59659d3e96452f8a206c4909
3
+ size 2326700029
special_tokens_map.json ADDED
@@ -0,0 +1,150 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>",
103
+ "<extra_id_100>",
104
+ "<extra_id_101>",
105
+ "<extra_id_102>",
106
+ "<extra_id_103>",
107
+ "<extra_id_104>",
108
+ "<extra_id_105>",
109
+ "<extra_id_106>",
110
+ "<extra_id_107>",
111
+ "<extra_id_108>",
112
+ "<extra_id_109>",
113
+ "<extra_id_110>",
114
+ "<extra_id_111>",
115
+ "<extra_id_112>",
116
+ "<extra_id_113>",
117
+ "<extra_id_114>",
118
+ "<extra_id_115>",
119
+ "<extra_id_116>",
120
+ "<extra_id_117>",
121
+ "<extra_id_118>",
122
+ "<extra_id_119>",
123
+ "<extra_id_120>",
124
+ "<extra_id_121>",
125
+ "<extra_id_122>",
126
+ "<extra_id_123>",
127
+ "<extra_id_124>"
128
+ ],
129
+ "eos_token": {
130
+ "content": "</s>",
131
+ "lstrip": false,
132
+ "normalized": true,
133
+ "rstrip": false,
134
+ "single_word": false
135
+ },
136
+ "pad_token": {
137
+ "content": "<pad>",
138
+ "lstrip": false,
139
+ "normalized": true,
140
+ "rstrip": false,
141
+ "single_word": false
142
+ },
143
+ "unk_token": {
144
+ "content": "<unk>",
145
+ "lstrip": false,
146
+ "normalized": true,
147
+ "rstrip": false,
148
+ "single_word": false
149
+ }
150
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,157 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>",
103
+ "<extra_id_100>",
104
+ "<extra_id_101>",
105
+ "<extra_id_102>",
106
+ "<extra_id_103>",
107
+ "<extra_id_104>",
108
+ "<extra_id_105>",
109
+ "<extra_id_106>",
110
+ "<extra_id_107>",
111
+ "<extra_id_108>",
112
+ "<extra_id_109>",
113
+ "<extra_id_110>",
114
+ "<extra_id_111>",
115
+ "<extra_id_112>",
116
+ "<extra_id_113>",
117
+ "<extra_id_114>",
118
+ "<extra_id_115>",
119
+ "<extra_id_116>",
120
+ "<extra_id_117>",
121
+ "<extra_id_118>",
122
+ "<extra_id_119>",
123
+ "<extra_id_120>",
124
+ "<extra_id_121>",
125
+ "<extra_id_122>",
126
+ "<extra_id_123>",
127
+ "<extra_id_124>"
128
+ ],
129
+ "clean_up_tokenization_spaces": true,
130
+ "eos_token": {
131
+ "__type": "AddedToken",
132
+ "content": "</s>",
133
+ "lstrip": false,
134
+ "normalized": true,
135
+ "rstrip": false,
136
+ "single_word": false
137
+ },
138
+ "extra_ids": 125,
139
+ "model_max_length": 1000000000000000019884624838656,
140
+ "pad_token": {
141
+ "__type": "AddedToken",
142
+ "content": "<pad>",
143
+ "lstrip": false,
144
+ "normalized": true,
145
+ "rstrip": false,
146
+ "single_word": false
147
+ },
148
+ "tokenizer_class": "ByT5Tokenizer",
149
+ "unk_token": {
150
+ "__type": "AddedToken",
151
+ "content": "<unk>",
152
+ "lstrip": false,
153
+ "normalized": true,
154
+ "rstrip": false,
155
+ "single_word": false
156
+ }
157
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be07019f7060c0548468f45c725d5d3b8d12a3fc5d9a7cea626ad8248c117e10
3
+ size 4283