harouzie commited on
Commit
8b591dd
1 Parent(s): 7d962fa

harouzie/mt5-small-translation-en2vi

Browse files
README.md CHANGED
@@ -1,8 +1,10 @@
1
  ---
2
  license: apache-2.0
3
- base_model: t5-small
4
  tags:
5
  - generated_from_trainer
 
 
6
  model-index:
7
  - name: mt5-small-translation-en2vi
8
  results: []
@@ -13,7 +15,11 @@ should probably proofread and complete it, then remove this comment. -->
13
 
14
  # mt5-small-translation-en2vi
15
 
16
- This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset.
 
 
 
 
17
 
18
  ## Model description
19
 
@@ -44,9 +50,9 @@ The following hyperparameters were used during training:
44
 
45
  ### Training results
46
 
47
- | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
48
- |:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|
49
- | No log | 0.99 | 63 | 3.1527 | 0.0849 | 16.5512 |
50
 
51
 
52
  ### Framework versions
 
1
  ---
2
  license: apache-2.0
3
+ base_model: google/mt5-small
4
  tags:
5
  - generated_from_trainer
6
+ metrics:
7
+ - bleu
8
  model-index:
9
  - name: mt5-small-translation-en2vi
10
  results: []
 
15
 
16
  # mt5-small-translation-en2vi
17
 
18
+ This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 1.5244
21
+ - Bleu: 10.0212
22
+ - Gen Len: 15.7035
23
 
24
  ## Model description
25
 
 
50
 
51
  ### Training results
52
 
53
+ | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
54
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
55
+ | 2.331 | 1.0 | 6352 | 1.5244 | 10.0212 | 15.7035 |
56
 
57
 
58
  ### Framework versions
config.json CHANGED
@@ -1,61 +1,32 @@
1
  {
2
- "_name_or_path": "t5-small",
3
  "architectures": [
4
- "T5ForConditionalGeneration"
5
  ],
6
  "classifier_dropout": 0.0,
7
- "d_ff": 2048,
8
  "d_kv": 64,
9
  "d_model": 512,
10
  "decoder_start_token_id": 0,
11
- "dense_act_fn": "relu",
12
  "dropout_rate": 0.1,
13
  "eos_token_id": 1,
14
- "feed_forward_proj": "relu",
15
  "initializer_factor": 1.0,
16
  "is_encoder_decoder": true,
17
- "is_gated_act": false,
18
  "layer_norm_epsilon": 1e-06,
19
- "model_type": "t5",
20
- "n_positions": 512,
21
- "num_decoder_layers": 6,
22
- "num_heads": 8,
23
- "num_layers": 6,
24
- "output_past": true,
25
  "pad_token_id": 0,
26
  "relative_attention_max_distance": 128,
27
  "relative_attention_num_buckets": 32,
28
- "task_specific_params": {
29
- "summarization": {
30
- "early_stopping": true,
31
- "length_penalty": 2.0,
32
- "max_length": 200,
33
- "min_length": 30,
34
- "no_repeat_ngram_size": 3,
35
- "num_beams": 4,
36
- "prefix": "summarize: "
37
- },
38
- "translation_en_to_de": {
39
- "early_stopping": true,
40
- "max_length": 300,
41
- "num_beams": 4,
42
- "prefix": "translate English to German: "
43
- },
44
- "translation_en_to_fr": {
45
- "early_stopping": true,
46
- "max_length": 300,
47
- "num_beams": 4,
48
- "prefix": "translate English to French: "
49
- },
50
- "translation_en_to_ro": {
51
- "early_stopping": true,
52
- "max_length": 300,
53
- "num_beams": 4,
54
- "prefix": "translate English to Romanian: "
55
- }
56
- },
57
  "torch_dtype": "float32",
58
  "transformers_version": "4.33.0",
59
  "use_cache": true,
60
- "vocab_size": 32128
61
  }
 
1
  {
2
+ "_name_or_path": "google/mt5-small",
3
  "architectures": [
4
+ "MT5ForConditionalGeneration"
5
  ],
6
  "classifier_dropout": 0.0,
7
+ "d_ff": 1024,
8
  "d_kv": 64,
9
  "d_model": 512,
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
  "initializer_factor": 1.0,
16
  "is_encoder_decoder": true,
17
+ "is_gated_act": true,
18
  "layer_norm_epsilon": 1e-06,
19
+ "model_type": "mt5",
20
+ "num_decoder_layers": 8,
21
+ "num_heads": 6,
22
+ "num_layers": 8,
 
 
23
  "pad_token_id": 0,
24
  "relative_attention_max_distance": 128,
25
  "relative_attention_num_buckets": 32,
26
+ "tie_word_embeddings": false,
27
+ "tokenizer_class": "T5Tokenizer",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
28
  "torch_dtype": "float32",
29
  "transformers_version": "4.33.0",
30
  "use_cache": true,
31
+ "vocab_size": 250102
32
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5a87f61489226b0581a04639c187594bf4ac801f11606d1ea5e5cc5b00ce0620
3
- size 242071641
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05c90c43bc77e461fa53b22fea68a47379f71c286c35a48b97886435f1bf8bcc
3
+ size 1200731653
special_tokens_map.json CHANGED
@@ -1,105 +1,7 @@
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
  ],
104
  "eos_token": "</s>",
105
  "pad_token": "<pad>",
 
1
  {
2
  "additional_special_tokens": [
3
+ "<EN>",
4
+ "<VI>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  ],
6
  "eos_token": "</s>",
7
  "pad_token": "<pad>",
spiece.model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
- size 791656
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
3
+ size 4309802
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:325982f929fb03e41968f4c0cdee41fa6d0cff2f6e15393ff2c72aec979a09fb
3
- size 2422193
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cbcabfb607c298d1227e002738e53c8305dab81ac47204ec675346227d2f5c8
3
+ size 16330996
tokenizer_config.json CHANGED
@@ -1,111 +1,12 @@
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
- ],
104
  "clean_up_tokenization_spaces": true,
105
  "eos_token": "</s>",
106
- "extra_ids": 100,
107
- "model_max_length": 512,
 
108
  "pad_token": "<pad>",
 
109
  "tokenizer_class": "T5Tokenizer",
110
  "unk_token": "<unk>"
111
  }
 
1
  {
2
+ "additional_special_tokens": null,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  "clean_up_tokenization_spaces": true,
4
  "eos_token": "</s>",
5
+ "extra_ids": 0,
6
+ "legacy": true,
7
+ "model_max_length": 1000000000000000019884624838656,
8
  "pad_token": "<pad>",
9
+ "sp_model_kwargs": {},
10
  "tokenizer_class": "T5Tokenizer",
11
  "unk_token": "<unk>"
12
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:561f904ac7cb77b2b92ca4edf10e9adb1526fafa387dbe23e3e61879159eb23f
3
  size 4219
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db1077c746bd0db474cc3c61b27f350dc669271134cc47577ffeba3c1c32c82e
3
  size 4219