Hugging Face's logo

ShyamVarahagiri
/
MachineTranslation

Text2Text Generation
Transformers
PyTorch
TensorBoard
mt5
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
7
ShyamVarahagiri commited on
Commit
436729d
·
1 Parent(s): 4cde267

End of training

Browse files
Files changed (18) hide show
  1. .gitattributes +1 -0
  2. config.json +13 -42
  3. pytorch_model.bin +2 -2
  4. runs/Mar24_12-50-22_63ee71009cc8/1679662298.826909/events.out.tfevents.1679662298.63ee71009cc8.224.1 +3 -0
  5. runs/Mar24_12-50-22_63ee71009cc8/events.out.tfevents.1679662298.63ee71009cc8.224.0 +3 -0
  6. runs/Mar24_13-27-35_63ee71009cc8/1679664460.004087/events.out.tfevents.1679664460.63ee71009cc8.224.3 +3 -0
  7. runs/Mar24_13-27-35_63ee71009cc8/events.out.tfevents.1679664459.63ee71009cc8.224.2 +3 -0
  8. runs/Mar24_13-32-25_63ee71009cc8/1679664749.6987383/events.out.tfevents.1679664749.63ee71009cc8.224.5 +3 -0
  9. runs/Mar24_13-32-25_63ee71009cc8/events.out.tfevents.1679664749.63ee71009cc8.224.4 +3 -0
  10. runs/Mar24_13-36-16_63ee71009cc8/1679664984.0124655/events.out.tfevents.1679664984.63ee71009cc8.15224.1 +3 -0
  11. runs/Mar24_13-36-16_63ee71009cc8/events.out.tfevents.1679664984.63ee71009cc8.15224.0 +3 -0
  12. runs/Mar24_13-38-06_63ee71009cc8/1679665093.5625057/events.out.tfevents.1679665093.63ee71009cc8.16274.1 +3 -0
  13. runs/Mar24_13-38-06_63ee71009cc8/events.out.tfevents.1679665093.63ee71009cc8.16274.0 +3 -0
  14. special_tokens_map.json +0 -102
  15. spiece.model +3 -0
  16. tokenizer.json +0 -0
  17. tokenizer_config.json +5 -104
  18. training_args.bin +1 -1
.gitattributes CHANGED
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json CHANGED
@@ -1,60 +1,31 @@
1
  {
2
- "_name_or_path": "T5-small",
3
  "architectures": [
4
- "T5ForConditionalGeneration"
5
  ],
6
- "d_ff": 2048,
7
  "d_kv": 64,
8
  "d_model": 512,
9
  "decoder_start_token_id": 0,
10
- "dense_act_fn": "relu",
11
  "dropout_rate": 0.1,
12
  "eos_token_id": 1,
13
- "feed_forward_proj": "relu",
14
  "initializer_factor": 1.0,
15
  "is_encoder_decoder": true,
16
- "is_gated_act": false,
17
  "layer_norm_epsilon": 1e-06,
18
- "model_type": "t5",
19
- "n_positions": 512,
20
- "num_decoder_layers": 6,
21
- "num_heads": 8,
22
- "num_layers": 6,
23
- "output_past": true,
24
  "pad_token_id": 0,
25
  "relative_attention_max_distance": 128,
26
  "relative_attention_num_buckets": 32,
27
- "task_specific_params": {
28
- "summarization": {
29
- "early_stopping": true,
30
- "length_penalty": 2.0,
31
- "max_length": 200,
32
- "min_length": 30,
33
- "no_repeat_ngram_size": 3,
34
- "num_beams": 4,
35
- "prefix": "summarize: "
36
- },
37
- "translation_en_to_de": {
38
- "early_stopping": true,
39
- "max_length": 300,
40
- "num_beams": 4,
41
- "prefix": "translate English to German: "
42
- },
43
- "translation_en_to_fr": {
44
- "early_stopping": true,
45
- "max_length": 300,
46
- "num_beams": 4,
47
- "prefix": "translate English to French: "
48
- },
49
- "translation_en_to_ro": {
50
- "early_stopping": true,
51
- "max_length": 300,
52
- "num_beams": 4,
53
- "prefix": "translate English to Romanian: "
54
- }
55
- },
56
  "torch_dtype": "float32",
57
  "transformers_version": "4.27.3",
58
  "use_cache": true,
59
- "vocab_size": 32128
60
  }
 
1
  {
2
+ "_name_or_path": "google/mt5-small",
3
  "architectures": [
4
+ "MT5ForConditionalGeneration"
5
  ],
6
+ "d_ff": 1024,
7
  "d_kv": 64,
8
  "d_model": 512,
9
  "decoder_start_token_id": 0,
10
+ "dense_act_fn": "gelu_new",
11
  "dropout_rate": 0.1,
12
  "eos_token_id": 1,
13
+ "feed_forward_proj": "gated-gelu",
14
  "initializer_factor": 1.0,
15
  "is_encoder_decoder": true,
16
+ "is_gated_act": true,
17
  "layer_norm_epsilon": 1e-06,
18
+ "model_type": "mt5",
19
+ "num_decoder_layers": 8,
20
+ "num_heads": 6,
21
+ "num_layers": 8,
 
 
22
  "pad_token_id": 0,
23
  "relative_attention_max_distance": 128,
24
  "relative_attention_num_buckets": 32,
25
+ "tie_word_embeddings": false,
26
+ "tokenizer_class": "T5Tokenizer",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
27
  "torch_dtype": "float32",
28
  "transformers_version": "4.27.3",
29
  "use_cache": true,
30
+ "vocab_size": 250112
31
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e5a189015c1bc3969bfde3fd883ab0818915f5e36906dbaa5e01feb0910ab4bb
3
- size 242071641
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29eb75be46bc194733036b535a8d3f4e67599a7a3a91d5898c4314f19a378149
3
+ size 1200772485
runs/Mar24_12-50-22_63ee71009cc8/1679662298.826909/events.out.tfevents.1679662298.63ee71009cc8.224.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67e960432258f3d6115ae08b790e272b1fbaa03e0f4b26be6144c0ecfa24d591
3
+ size 6017
runs/Mar24_12-50-22_63ee71009cc8/events.out.tfevents.1679662298.63ee71009cc8.224.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12e6add3a9b369d4f07f9f529e6bcc3470935144a229a869d1c4de7d32cc376c
3
+ size 4154
runs/Mar24_13-27-35_63ee71009cc8/1679664460.004087/events.out.tfevents.1679664460.63ee71009cc8.224.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a589f69fb3664bafad2f9347d659146aaa4633e85f301bd0739a5a848900556
3
+ size 6017
runs/Mar24_13-27-35_63ee71009cc8/events.out.tfevents.1679664459.63ee71009cc8.224.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:932cf910313d81f23f871441ff0a4bd491e2d464aceb76bf0b0faf9c555e2234
3
+ size 4154
runs/Mar24_13-32-25_63ee71009cc8/1679664749.6987383/events.out.tfevents.1679664749.63ee71009cc8.224.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f296eb77081ad519b52a9d314dfa32f8ffacd912a9d3e5652ad001c8ccc4865e
3
+ size 6017
runs/Mar24_13-32-25_63ee71009cc8/events.out.tfevents.1679664749.63ee71009cc8.224.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffd3313a745d0f1f8b220ac3fe4d1d65f72b1b5b080f3d974f8974d413397ffa
3
+ size 4136
runs/Mar24_13-36-16_63ee71009cc8/1679664984.0124655/events.out.tfevents.1679664984.63ee71009cc8.15224.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5338675e7094939c1c0b1171fe7e6856ee454fe2f6812dbc46d632e60d20cc86
3
+ size 6017
runs/Mar24_13-36-16_63ee71009cc8/events.out.tfevents.1679664984.63ee71009cc8.15224.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75dfe2b59f655c6bda824e2bbb7f31f4494e322cee31f54ce3f4b93c3cc4a695
3
+ size 4136
runs/Mar24_13-38-06_63ee71009cc8/1679665093.5625057/events.out.tfevents.1679665093.63ee71009cc8.16274.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7f7aaf808275b20b03c021a78124e7a1dd200df4f15cd619bb967ab95c88dc2
3
+ size 6017
runs/Mar24_13-38-06_63ee71009cc8/events.out.tfevents.1679665093.63ee71009cc8.16274.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4981318bf9635dbf86dc64141b4ea9a3c8a28b9d1fa42f1daead0cd4a7bce0b2
3
+ size 6335
special_tokens_map.json CHANGED
@@ -1,106 +1,4 @@
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>",
106
  "unk_token": "<unk>"
 
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "eos_token": "</s>",
3
  "pad_token": "<pad>",
4
  "unk_token": "<unk>"
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
3
+ size 4309802
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
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
  "eos_token": "</s>",
105
- "extra_ids": 100,
106
  "model_max_length": 1000000000000000019884624838656,
107
  "pad_token": "<pad>",
108
- "special_tokens_map_file": null,
 
 
109
  "tokenizer_class": "T5Tokenizer",
110
  "unk_token": "<unk>"
111
  }
 
1
  {
2
+ "additional_special_tokens": null,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  "eos_token": "</s>",
4
+ "extra_ids": 0,
5
  "model_max_length": 1000000000000000019884624838656,
6
  "pad_token": "<pad>",
7
+ "return_tensors": "pt",
8
+ "sp_model_kwargs": {},
9
+ "special_tokens_map_file": "/root/.cache/huggingface/hub/models--google--mt5-small/snapshots/38f23af8ec210eb6c376d40e9c56bd25a80f195d/special_tokens_map.json",
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:b489f45000ef306040b0d1f3d9b0f5181c6951c22078c1b8b94c9169fa8ae473
3
  size 3707
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:485390d79ca14bb3768f29c43edf6512561de707cfe46f823fbb45938bc3c417
3
  size 3707