Training in progress epoch 0

README.md

@@ -11,12 +11,12 @@ probably proofread and complete it, then remove this comment. -->
 
 # VanessaSchenkel/padrao-mbart-finetuned-news_commentary
 
-This model is a fine-tuned version of [Narrativa/mbart-large-50-finetuned-opus-en-pt-translation](https://huggingface.co/Narrativa/mbart-large-50-finetuned-opus-en-pt-translation) on an unknown dataset.
+This model is a fine-tuned version of [unicamp-dl/translation-en-pt-t5](https://huggingface.co/unicamp-dl/translation-en-pt-t5) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 1.3352
-- Validation Loss: 0.9963
-- Train Bleu: 42.2304
-- Train Gen Len: 39.4181
+- Train Loss: 1.4815
+- Validation Loss: 1.2135
+- Train Bleu: 40.5781
+- Train Gen Len: 34.7447
 - Epoch: 0
 
 ## Model description
@@ -43,7 +43,7 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Train Bleu | Train Gen Len | Epoch |
 |:----------:|:---------------:|:----------:|:-------------:|:-----:|
-| 1.3352     | 0.9963          | 42.2304    | 39.4181       | 0     |
+| 1.4815     | 1.2135          | 40.5781    | 34.7447       | 0     |
 
 
 ### Framework versions

config.json

@@ -1,57 +1,31 @@
 {
-  "_name_or_path": "Narrativa/mbart-large-50-finetuned-opus-en-pt-translation",
-  "_num_labels": 3,
-  "activation_dropout": 0.0,
-  "activation_function": "gelu",
-  "add_bias_logits": false,
-  "add_final_layer_norm": true,
+  "_name_or_path": "unicamp-dl/translation-en-pt-t5",
   "architectures": [
-    "MBartForConditionalGeneration"
+    "T5ForConditionalGeneration"
   ],
-  "attention_dropout": 0.0,
-  "bos_token_id": 0,
-  "classif_dropout": 0.0,
-  "classifier_dropout": 0.0,
-  "d_model": 1024,
-  "decoder_attention_heads": 16,
-  "decoder_ffn_dim": 4096,
-  "decoder_layerdrop": 0.0,
-  "decoder_layers": 12,
-  "decoder_start_token_id": 2,
-  "dropout": 0.1,
-  "early_stopping": true,
-  "encoder_attention_heads": 16,
-  "encoder_ffn_dim": 4096,
-  "encoder_layerdrop": 0.0,
-  "encoder_layers": 12,
-  "eos_token_id": 2,
-  "forced_eos_token_id": 2,
-  "gradient_checkpointing": false,
-  "id2label": {
-    "0": "LABEL_0",
-    "1": "LABEL_1",
-    "2": "LABEL_2"
-  },
-  "init_std": 0.02,
+  "d_ff": 3072,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "relu",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "relu",
+  "initializer_factor": 1.0,
   "is_encoder_decoder": true,
-  "label2id": {
-    "LABEL_0": 0,
-    "LABEL_1": 1,
-    "LABEL_2": 2
-  },
-  "max_length": 200,
-  "max_position_embeddings": 1024,
-  "model_type": "mbart",
-  "normalize_before": true,
-  "normalize_embedding": true,
-  "num_beams": 5,
-  "num_hidden_layers": 12,
+  "is_gated_act": false,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
   "output_past": true,
-  "pad_token_id": 1,
-  "scale_embedding": true,
-  "static_position_embeddings": false,
-  "tokenizer_class": "MBart50Tokenizer",
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "torch_dtype": "float32",
   "transformers_version": "4.21.1",
   "use_cache": true,
-  "vocab_size": 250054
+  "vocab_size": 32128
 }

logs/train/events.out.tfevents.1660141651.f4bbb5c638e3.143.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ded3b29a9a6c2f3110a9a78fb38e5e4453e03224705b519bc43226d74a747c8f
+size 5550300

logs/validation/events.out.tfevents.1660151899.f4bbb5c638e3.143.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd3562e58d3dd51857d466d6edf84fd3e2d3ef2edcfffb0ba069845c2eb3ef1d
+size 194

special_tokens_map.json

@@ -1,63 +1,107 @@
 {
   "additional_special_tokens": [
-    "ar_AR",
-    "cs_CZ",
-    "de_DE",
-    "en_XX",
-    "es_XX",
-    "et_EE",
-    "fi_FI",
-    "fr_XX",
-    "gu_IN",
-    "hi_IN",
-    "it_IT",
-    "ja_XX",
-    "kk_KZ",
-    "ko_KR",
-    "lt_LT",
-    "lv_LV",
-    "my_MM",
-    "ne_NP",
-    "nl_XX",
-    "ro_RO",
-    "ru_RU",
-    "si_LK",
-    "tr_TR",
-    "vi_VN",
-    "zh_CN",
-    "af_ZA",
-    "az_AZ",
-    "bn_IN",
-    "fa_IR",
-    "he_IL",
-    "hr_HR",
-    "id_ID",
-    "ka_GE",
-    "km_KH",
-    "mk_MK",
-    "ml_IN",
-    "mn_MN",
-    "mr_IN",
-    "pl_PL",
-    "ps_AF",
-    "pt_XX",
-    "sv_SE",
-    "sw_KE",
-    "ta_IN",
-    "te_IN",
-    "th_TH",
-    "tl_XX",
-    "uk_UA",
-    "ur_PK",
-    "xh_ZA",
-    "gl_ES",
-    "sl_SI"
+    "<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>"
   ],
-  "bos_token": "<s>",
-  "cls_token": "<s>",
   "eos_token": "</s>",
-  "mask_token": "<mask>",
   "pad_token": "<pad>",
-  "sep_token": "</s>",
   "unk_token": "<unk>"
 }

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcb25b1d67f04fce0e710d58430b606b4ee9887144fa2da22d123c44061cc62e
+size 755569

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5004292563b91d39d0e55dcc2ca5117c5157e17822eb9d342316d242899fab6
-size 2445079280
+oid sha256:d49894ef8500dac163acaed0504d0c63d65af34d8233a2a9fb6fc77d73496323
+size 892145048

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4a39cc65c0a7c37d92df7c3c5d137f392c4c7d4e925ef47b0bbeb4354ca6b84
-size 17094494
+oid sha256:0394be143a2f04d44c08b09d6a2d3c35134bb7dcc3efee1f8d7204ebc1f34f36
+size 2386119

tokenizer_config.json

@@ -1,77 +1,112 @@
 {
   "additional_special_tokens": [
-    "ar_AR",
-    "cs_CZ",
-    "de_DE",
-    "en_XX",
-    "es_XX",
-    "et_EE",
-    "fi_FI",
-    "fr_XX",
-    "gu_IN",
-    "hi_IN",
-    "it_IT",
-    "ja_XX",
-    "kk_KZ",
-    "ko_KR",
-    "lt_LT",
-    "lv_LV",
-    "my_MM",
-    "ne_NP",
-    "nl_XX",
-    "ro_RO",
-    "ru_RU",
-    "si_LK",
-    "tr_TR",
-    "vi_VN",
-    "zh_CN",
-    "af_ZA",
-    "az_AZ",
-    "bn_IN",
-    "fa_IR",
-    "he_IL",
-    "hr_HR",
-    "id_ID",
-    "ka_GE",
-    "km_KH",
-    "mk_MK",
-    "ml_IN",
-    "mn_MN",
-    "mr_IN",
-    "pl_PL",
-    "ps_AF",
-    "pt_XX",
-    "sv_SE",
-    "sw_KE",
-    "ta_IN",
-    "te_IN",
-    "th_TH",
-    "tl_XX",
-    "uk_UA",
-    "ur_PK",
-    "xh_ZA",
-    "gl_ES",
-    "sl_SI"
+    "<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>"
   ],
-  "bos_token": "<s>",
-  "cls_token": "<s>",
   "eos_token": "</s>",
-  "mask_token": {
-    "__type": "AddedToken",
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "model_max_length": 1024,
-  "name_or_path": "Narrativa/mbart-large-50-finetuned-opus-en-pt-translation",
+  "extra_ids": 100,
+  "name_or_path": "unicamp-dl/translation-en-pt-t5",
   "pad_token": "<pad>",
-  "sep_token": "</s>",
   "sp_model_kwargs": {},
-  "special_tokens_map_file": "/home/suraj/projects/mbart-50/hf_models/mbart-50-large/special_tokens_map.json",
-  "src_lang": "en_XX",
-  "tgt_lang": "pt_XX",
-  "tokenizer_class": "MBart50Tokenizer",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "T5Tokenizer",
   "unk_token": "<unk>"
 }