frtna commited on
Commit
c834d3c
·
1 Parent(s): 61d570f

End of training

Browse files
config.json CHANGED
@@ -1,57 +1,59 @@
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
- "dropout_rate": 0.1,
11
- "eos_token_id": 1,
12
- "feed_forward_proj": "relu",
13
- "initializer_factor": 1.0,
 
 
 
 
 
 
 
 
 
 
 
 
 
14
  "is_encoder_decoder": true,
15
- "layer_norm_epsilon": 1e-06,
16
- "model_type": "t5",
17
- "n_positions": 512,
18
- "num_decoder_layers": 6,
19
- "num_heads": 8,
20
- "num_layers": 6,
21
- "output_past": true,
22
- "pad_token_id": 0,
23
- "relative_attention_num_buckets": 32,
24
- "task_specific_params": {
25
- "summarization": {
26
- "early_stopping": true,
27
- "length_penalty": 2.0,
28
- "max_length": 200,
29
- "min_length": 30,
30
- "no_repeat_ngram_size": 3,
31
- "num_beams": 4,
32
- "prefix": "summarize: "
33
- },
34
- "translation_en_to_de": {
35
- "early_stopping": true,
36
- "max_length": 300,
37
- "num_beams": 4,
38
- "prefix": "translate English to German: "
39
- },
40
- "translation_en_to_fr": {
41
- "early_stopping": true,
42
- "max_length": 300,
43
- "num_beams": 4,
44
- "prefix": "translate English to French: "
45
- },
46
- "translation_en_to_ro": {
47
- "early_stopping": true,
48
- "max_length": 300,
49
- "num_beams": 4,
50
- "prefix": "translate English to Romanian: "
51
- }
52
  },
 
 
 
 
 
 
 
 
 
 
53
  "torch_dtype": "float32",
54
  "transformers_version": "4.17.0",
55
  "use_cache": true,
56
- "vocab_size": 32128
57
  }
 
1
  {
2
+ "_name_or_path": "Helsinki-NLP/opus-mt-es-it",
3
+ "_num_labels": 3,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "swish",
6
+ "add_bias_logits": false,
7
+ "add_final_layer_norm": false,
8
  "architectures": [
9
+ "MarianMTModel"
10
  ],
11
+ "attention_dropout": 0.0,
12
+ "bad_words_ids": [
13
+ [
14
+ 59030
15
+ ]
16
+ ],
17
+ "bos_token_id": 0,
18
+ "classif_dropout": 0.0,
19
+ "classifier_dropout": 0.0,
20
  "d_model": 512,
21
+ "decoder_attention_heads": 8,
22
+ "decoder_ffn_dim": 2048,
23
+ "decoder_layerdrop": 0.0,
24
+ "decoder_layers": 6,
25
+ "decoder_start_token_id": 59030,
26
+ "dropout": 0.1,
27
+ "encoder_attention_heads": 8,
28
+ "encoder_ffn_dim": 2048,
29
+ "encoder_layerdrop": 0.0,
30
+ "encoder_layers": 6,
31
+ "eos_token_id": 0,
32
+ "forced_eos_token_id": 0,
33
+ "id2label": {
34
+ "0": "LABEL_0",
35
+ "1": "LABEL_1",
36
+ "2": "LABEL_2"
37
+ },
38
+ "init_std": 0.02,
39
  "is_encoder_decoder": true,
40
+ "label2id": {
41
+ "LABEL_0": 0,
42
+ "LABEL_1": 1,
43
+ "LABEL_2": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
44
  },
45
+ "max_length": 512,
46
+ "max_position_embeddings": 512,
47
+ "model_type": "marian",
48
+ "normalize_before": false,
49
+ "normalize_embedding": false,
50
+ "num_beams": 4,
51
+ "num_hidden_layers": 6,
52
+ "pad_token_id": 59030,
53
+ "scale_embedding": true,
54
+ "static_position_embeddings": true,
55
  "torch_dtype": "float32",
56
  "transformers_version": "4.17.0",
57
  "use_cache": true,
58
+ "vocab_size": 59031
59
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9248be8c44e68ff11b8f32eaf34795f0c8ea0ac8b3d31501a7a3b35e9006dca9
3
- size 242085627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09433c7ac8c32547474709a41e12157d0a0cff6b05c302f9b5abe31ad03888f4
3
+ size 297780677
special_tokens_map.json CHANGED
@@ -1 +1 @@
1
- {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"]}
 
1
+ {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
tokenizer_config.json CHANGED
@@ -1 +1 @@
1
- {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 100, "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"], "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "t5-small", "tokenizer_class": "T5Tokenizer"}
 
1
+ {"source_lang": "es", "target_lang": "it", "unk_token": "<unk>", "eos_token": "</s>", "pad_token": "<pad>", "model_max_length": 512, "sp_model_kwargs": {}, "special_tokens_map_file": null, "name_or_path": "Helsinki-NLP/opus-mt-es-it", "tokenizer_class": "MarianTokenizer"}
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:56b2be817b38c905f0ee372675dc35880c814c9980d26ed95e9f94ce67424dbb
3
  size 3247
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3eba7eaff0b77218f4a6817a17e22f67ba137d4f7d007a16c3a7e8d9c489ce71
3
  size 3247