Initial commit from mrm8488

config.json

@@ -0,0 +1,58 @@
+{
+  "_name_or_path": "facebook/mbart-large-cc25",
+  "_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,
+  "dropout": 0.1,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "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": 1024,
+  "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,
+  "task_specific_params": {
+    "translation_en_to_ro": {
+      "decoder_start_token_id": 250020
+    }
+  },
+  "transformers_version": "4.3.0.dev0",
+  "use_cache": true,
+  "vocab_size": 250027
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea4d108c55eeab2cdf4fd9591484d86f2343e49f43c9c0f7e2a9a8723d59c9c6
+size 2444606272

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"]}

tokenizer_config.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "tokenizer_file": null, "model_max_length": 1024, "name_or_path": "facebook/mbart-large-cc25"}

trainer_state.json

@@ -0,0 +1,352 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.4471057884231537,
+  "global_step": 28000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.993346640053227e-05,
+      "loss": 2.0933,
+      "step": 500
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.986693280106454e-05,
+      "loss": 1.7924,
+      "step": 1000
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.980039920159681e-05,
+      "loss": 1.0278,
+      "step": 1500
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.973386560212908e-05,
+      "loss": 1.0513,
+      "step": 2000
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.966733200266135e-05,
+      "loss": 0.9437,
+      "step": 2500
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.9600798403193615e-05,
+      "loss": 0.9916,
+      "step": 3000
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.953426480372588e-05,
+      "loss": 0.926,
+      "step": 3500
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.946773120425816e-05,
+      "loss": 0.9047,
+      "step": 4000
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.9401197604790424e-05,
+      "loss": 0.8648,
+      "step": 4500
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.933466400532269e-05,
+      "loss": 0.8708,
+      "step": 5000
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.9268130405854955e-05,
+      "loss": 0.856,
+      "step": 5500
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.920159680638723e-05,
+      "loss": 0.8403,
+      "step": 6000
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.91350632069195e-05,
+      "loss": 0.8486,
+      "step": 6500
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.9068529607451764e-05,
+      "loss": 0.8463,
+      "step": 7000
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.9001996007984036e-05,
+      "loss": 0.8168,
+      "step": 7500
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.89354624085163e-05,
+      "loss": 0.8255,
+      "step": 8000
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.886892880904857e-05,
+      "loss": 0.8256,
+      "step": 8500
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.8802395209580846e-05,
+      "loss": 0.8397,
+      "step": 9000
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.873586161011311e-05,
+      "loss": 0.8315,
+      "step": 9500
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.8669328010645376e-05,
+      "loss": 0.8033,
+      "step": 10000
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.860279441117765e-05,
+      "loss": 0.8076,
+      "step": 10500
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.8536260811709914e-05,
+      "loss": 0.8126,
+      "step": 11000
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.8469727212242186e-05,
+      "loss": 0.7916,
+      "step": 11500
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.840319361277446e-05,
+      "loss": 0.8119,
+      "step": 12000
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.833666001330672e-05,
+      "loss": 0.8081,
+      "step": 12500
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.827012641383899e-05,
+      "loss": 0.7944,
+      "step": 13000
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.820359281437126e-05,
+      "loss": 0.7926,
+      "step": 13500
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.813705921490353e-05,
+      "loss": 0.7993,
+      "step": 14000
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.80705256154358e-05,
+      "loss": 0.785,
+      "step": 14500
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.800399201596807e-05,
+      "loss": 0.7799,
+      "step": 15000
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.7937458416500335e-05,
+      "loss": 0.7773,
+      "step": 15500
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.78709248170326e-05,
+      "loss": 0.7806,
+      "step": 16000
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.780439121756487e-05,
+      "loss": 0.7824,
+      "step": 16500
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.7737857618097145e-05,
+      "loss": 0.7609,
+      "step": 17000
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.767132401862941e-05,
+      "loss": 0.7855,
+      "step": 17500
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.7604790419161675e-05,
+      "loss": 0.7805,
+      "step": 18000
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 4.753825681969395e-05,
+      "loss": 0.7591,
+      "step": 18500
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 4.747172322022622e-05,
+      "loss": 0.7765,
+      "step": 19000
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 4.7405189620758485e-05,
+      "loss": 0.7643,
+      "step": 19500
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.733865602129076e-05,
+      "loss": 0.767,
+      "step": 20000
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 4.727212242182302e-05,
+      "loss": 0.7648,
+      "step": 20500
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 4.720558882235529e-05,
+      "loss": 0.7711,
+      "step": 21000
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 4.713905522288756e-05,
+      "loss": 0.7772,
+      "step": 21500
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 4.707252162341983e-05,
+      "loss": 0.7644,
+      "step": 22000
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 4.70059880239521e-05,
+      "loss": 0.767,
+      "step": 22500
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 4.693945442448437e-05,
+      "loss": 0.7471,
+      "step": 23000
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 4.6872920825016634e-05,
+      "loss": 0.7594,
+      "step": 23500
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 4.6806387225548906e-05,
+      "loss": 0.7496,
+      "step": 24000
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 4.673985362608118e-05,
+      "loss": 0.7666,
+      "step": 24500
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 4.6673320026613444e-05,
+      "loss": 0.7476,
+      "step": 25000
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 4.660678642714571e-05,
+      "loss": 0.7393,
+      "step": 25500
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 4.6540252827677974e-05,
+      "loss": 0.7488,
+      "step": 26000
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 4.6473719228210246e-05,
+      "loss": 0.7408,
+      "step": 26500
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 4.640718562874252e-05,
+      "loss": 0.7609,
+      "step": 27000
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 4.6340652029274784e-05,
+      "loss": 0.7461,
+      "step": 27500
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 4.6274118429807056e-05,
+      "loss": 0.7369,
+      "step": 28000
+    }
+  ],
+  "max_steps": 375750,
+  "num_train_epochs": 6,
+  "total_flos": 51286279954268160,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b6c97e6a0bbc1b7f0e6d4916d99b09de994edcf12572dd5ccc84023cbf3c033
+size 2159