Uploading model

config.json

@@ -0,0 +1,90 @@
+{
+  "_name_or_path": "/scratch/ba63/BERT_models/AraBART",
+  "activation_dropout": 0.1,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": true,
+  "architectures": [
+    "MBartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "classif_dropout": 0.1,
+  "classifier_dropout": 0.0,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 2,
+  "do_blenderbot_90_layernorm": false,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 2,
+  "extra_pos_embeddings": 2,
+  "force_bos_token_to_be_generated": false,
+  "forced_eos_token_id": 2,
+  "ged_id2label": {
+    "0": "<pad>",
+    "1": "DELETE",
+    "2": "MERGE-B",
+    "3": "MERGE-I",
+    "4": "REPLACE_M",
+    "5": "REPLACE_M+REPLACE_O",
+    "6": "REPLACE_O",
+    "7": "REPLACE_O+REPLACE_X",
+    "8": "REPLACE_P",
+    "9": "REPLACE_S",
+    "10": "REPLACE_X",
+    "11": "SPLIT",
+    "12": "UC"
+  },
+  "ged_label2id": {
+    "<pad>": 0,
+    "DELETE": 1,
+    "MERGE-B": 2,
+    "MERGE-I": 3,
+    "REPLACE_M": 4,
+    "REPLACE_M+REPLACE_O": 5,
+    "REPLACE_O": 6,
+    "REPLACE_O+REPLACE_X": 7,
+    "REPLACE_P": 8,
+    "REPLACE_S": 9,
+    "REPLACE_X": 10,
+    "SPLIT": 11,
+    "UC": 12
+  },
+  "ged_num_labels": 13,
+  "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_position_embeddings": 1024,
+  "model_type": "mbart",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": true,
+  "normalize_embedding": true,
+  "num_beams": 4,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "scale_embedding": false,
+  "static_position_embeddings": false,
+  "tokenizer_class": "BarthezTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.22.2",
+  "use_cache": true,
+  "vocab_size": 50002
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5eadbd894d7ba21e18ca53e118af20858b2e87a4d0b02f41d75e91e33919bb5f
+size 557213999

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbb59d772bc9bb2da5dc4a73a00c61c0912c6d2596aad970fa2cd3d69898b245
+size 1315170

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "name_or_path": "/scratch/ba63/BERT_models/AraBART",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": null,
+  "tokenizer_class": "BarthezTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,52 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.942339373970346,
+  "global_step": 3000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.82,
+      "learning_rate": 4.5881383855024714e-05,
+      "loss": 0.5588,
+      "step": 500
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 4.1762767710049426e-05,
+      "loss": 0.4,
+      "step": 1000
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 3.764415156507414e-05,
+      "loss": 0.3519,
+      "step": 1500
+    },
+    {
+      "epoch": 3.29,
+      "learning_rate": 3.352553542009885e-05,
+      "loss": 0.3179,
+      "step": 2000
+    },
+    {
+      "epoch": 4.12,
+      "learning_rate": 2.9406919275123562e-05,
+      "loss": 0.2926,
+      "step": 2500
+    },
+    {
+      "epoch": 4.94,
+      "learning_rate": 2.528830313014827e-05,
+      "loss": 0.2696,
+      "step": 3000
+    }
+  ],
+  "max_steps": 6070,
+  "num_train_epochs": 10,
+  "total_flos": 5476078662709248.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dec6137649289979d1287f943cb36decf4b9ea5a2719e27c9201c7c03e68923
+size 3631