add MT model

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 10.0,
+    "predict_bleu": 33.5965,
+    "predict_gen_len": 35.9891,
+    "predict_loss": 3.194124221801758,
+    "predict_runtime": 599.767,
+    "predict_samples": 1564,
+    "predict_samples_per_second": 2.608,
+    "predict_steps_per_second": 0.262,
+    "train_loss": 0.41970507476424374,
+    "train_runtime": 1822.4664,
+    "train_samples": 4790,
+    "train_samples_per_second": 26.283,
+    "train_steps_per_second": 2.628
+}

config.json

@@ -0,0 +1,59 @@
+{
+  "_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_bos_token_id": 250008,
+  "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": "4.12.0",
+  "use_cache": true,
+  "vocab_size": 250054
+}

predict_results.json

@@ -0,0 +1,9 @@
+{
+    "predict_bleu": 33.5965,
+    "predict_gen_len": 35.9891,
+    "predict_loss": 3.194124221801758,
+    "predict_runtime": 599.767,
+    "predict_samples": 1564,
+    "predict_samples_per_second": 2.608,
+    "predict_steps_per_second": 0.262
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce6b8c23d66f23e36191304028909225b31a7a743f31291b91d0164cffe5467d
+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": null, "tgt_lang": null, "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", "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"], "sp_model_kwargs": {}, "tokenizer_class": "MBart50Tokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "train_loss": 0.41970507476424374,
+    "train_runtime": 1822.4664,
+    "train_samples": 4790,
+    "train_samples_per_second": 26.283,
+    "train_steps_per_second": 2.628
+}

trainer_state.json

@@ -0,0 +1,79 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "global_step": 4790,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.04,
+      "learning_rate": 4.478079331941545e-05,
+      "loss": 1.8163,
+      "step": 500
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 3.95615866388309e-05,
+      "loss": 0.948,
+      "step": 1000
+    },
+    {
+      "epoch": 3.13,
+      "learning_rate": 3.434237995824635e-05,
+      "loss": 0.5674,
+      "step": 1500
+    },
+    {
+      "epoch": 4.18,
+      "learning_rate": 2.9123173277661797e-05,
+      "loss": 0.3141,
+      "step": 2000
+    },
+    {
+      "epoch": 5.22,
+      "learning_rate": 2.3903966597077245e-05,
+      "loss": 0.1675,
+      "step": 2500
+    },
+    {
+      "epoch": 6.26,
+      "learning_rate": 1.8684759916492694e-05,
+      "loss": 0.0957,
+      "step": 3000
+    },
+    {
+      "epoch": 7.31,
+      "learning_rate": 1.3465553235908144e-05,
+      "loss": 0.0545,
+      "step": 3500
+    },
+    {
+      "epoch": 8.35,
+      "learning_rate": 8.246346555323591e-06,
+      "loss": 0.0322,
+      "step": 4000
+    },
+    {
+      "epoch": 9.39,
+      "learning_rate": 3.02713987473904e-06,
+      "loss": 0.0182,
+      "step": 4500
+    },
+    {
+      "epoch": 10.0,
+      "step": 4790,
+      "total_flos": 1.270915792011264e+16,
+      "train_loss": 0.41970507476424374,
+      "train_runtime": 1822.4664,
+      "train_samples_per_second": 26.283,
+      "train_steps_per_second": 2.628
+    }
+  ],
+  "max_steps": 4790,
+  "num_train_epochs": 10,
+  "total_flos": 1.270915792011264e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5f6732ba465dab64f7c2ff2b41d6649669a035df6b54393552c01820ee28a26
+size 2927