add model

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

README.md

@@ -0,0 +1,70 @@
+---
+tags:
+- generated_from_trainer
+model_index:
+- name: mbart50-ft-si-en
+  results:
+  - task:
+      name: Sequence-to-sequence Language Modeling
+      type: text2text-generation
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# mbart50-ft-si-en
+
+This model was trained from scratch on an unkown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 5.0476
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0005
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| No log        | 0.98  | 30   | 5.6367          |
+| No log        | 1.98  | 60   | 4.1221          |
+| No log        | 2.98  | 90   | 3.1880          |
+| No log        | 3.98  | 120  | 3.1175          |
+| No log        | 4.98  | 150  | 3.3575          |
+| No log        | 5.98  | 180  | 3.7855          |
+| No log        | 6.98  | 210  | 4.3530          |
+| No log        | 7.98  | 240  | 4.7216          |
+| No log        | 8.98  | 270  | 4.9202          |
+| No log        | 9.98  | 300  | 5.0476          |
+
+
+### Framework versions
+
+- Transformers 4.9.2
+- Pytorch 1.6.0
+- Datasets 1.11.0
+- Tokenizers 0.10.3

config.json

@@ -0,0 +1,58 @@
+{
+  "_name_or_path": "facebook/mbart-large-50",
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": true,
+  "architectures": [
+    "MBartForConditionalGeneration"
+  ],
+  "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,
+  "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,
+  "output_past": true,
+  "pad_token_id": 1,
+  "scale_embedding": true,
+  "static_position_embeddings": false,
+  "tokenizer_class": "MBart50Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.9.2",
+  "use_cache": true,
+  "vocab_size": 250054
+}

logs/1630242154.849394/events.out.tfevents.1630242154.NLPC-Sita-MLM.222817.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:363863b5abd173603b29d93ce2de906da9e13b7ecd2954829c9c38661bacbde6
+size 4293

logs/events.out.tfevents.1630242154.NLPC-Sita-MLM.222817.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:697b0d624c5a2107ac7d458ab9bd95da9af5c66873525802eecf68cc354fa702
+size 6776

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf1771e7af02423a0cc8ac4e796f6f9750cf6d7f639c518b9993ea95c7acae44
+size 2444722195

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": "<mask>", "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"]}

tokenizer_config.json

@@ -0,0 +1 @@
+{"src_lang": "si_LK", "tgt_lang": "en_XX", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": "<s>", "model_max_length": 1024, "name_or_path": "facebook/mbart-large-50", "special_tokens_map_file": "/home/suraj/projects/mbart-50/hf_models/mbart-50-large/special_tokens_map.json", "sp_model_kwargs": {}, "tokenizer_class": "MBart50Tokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89b3959b3ad206ea31e5e8adc8ddc5c2a4c355026e80da5449d879e096978bad
+size 2671