Trained with normal text replication (+ bart noise [Multilingual BERT])

config.json

@@ -1,6 +1,6 @@
 {
   "_commit_hash": null,
-  "_name_or_path": "finetuned",
+  "_name_or_path": "calibrated-decoder",
   "architectures": [
     "EncoderDecoderModel"
   ],
@@ -100,74 +100,66 @@
   },
   "decoder_start_token_id": 0,
   "encoder": {
-    "_name_or_path": "facebook/mbart-large-cc25",
-    "_num_labels": 3,
-    "activation_dropout": 0.0,
-    "activation_function": "gelu",
-    "add_bias_logits": false,
+    "_name_or_path": "bert-base-multilingual-cased",
     "add_cross_attention": false,
-    "add_final_layer_norm": true,
     "architectures": [
-      "MBartForConditionalGeneration"
+      "BertForMaskedLM"
     ],
-    "attention_dropout": 0.0,
+    "attention_probs_dropout_prob": 0.1,
     "bad_words_ids": null,
     "begin_suppress_tokens": null,
-    "bos_token_id": 0,
+    "bos_token_id": null,
     "chunk_size_feed_forward": 0,
-    "classif_dropout": 0.0,
-    "classifier_dropout": 0.0,
+    "classifier_dropout": null,
     "cross_attention_hidden_size": null,
-    "d_model": 1024,
-    "decoder_attention_heads": 16,
-    "decoder_ffn_dim": 4096,
-    "decoder_layerdrop": 0.0,
-    "decoder_layers": 12,
     "decoder_start_token_id": null,
+    "directionality": "bidi",
     "diversity_penalty": 0.0,
     "do_sample": false,
-    "dropout": 0.1,
     "early_stopping": false,
-    "encoder_attention_heads": 16,
-    "encoder_ffn_dim": 4096,
-    "encoder_layerdrop": 0.0,
-    "encoder_layers": 12,
     "encoder_no_repeat_ngram_size": 0,
-    "eos_token_id": 2,
+    "eos_token_id": null,
     "exponential_decay_length_penalty": null,
     "finetuning_task": null,
     "forced_bos_token_id": null,
-    "forced_eos_token_id": 2,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 768,
     "id2label": {
       "0": "LABEL_0",
-      "1": "LABEL_1",
-      "2": "LABEL_2"
+      "1": "LABEL_1"
     },
-    "init_std": 0.02,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
     "is_decoder": false,
-    "is_encoder_decoder": true,
+    "is_encoder_decoder": false,
     "label2id": {
       "LABEL_0": 0,
-      "LABEL_1": 1,
-      "LABEL_2": 2
+      "LABEL_1": 1
     },
+    "layer_norm_eps": 1e-12,
     "length_penalty": 1.0,
-    "max_length": 1024,
-    "max_position_embeddings": 1024,
+    "max_length": 20,
+    "max_position_embeddings": 512,
     "min_length": 0,
-    "model_type": "mbart",
+    "model_type": "bert",
     "no_repeat_ngram_size": 0,
-    "normalize_before": true,
-    "normalize_embedding": true,
+    "num_attention_heads": 12,
     "num_beam_groups": 1,
-    "num_beams": 5,
+    "num_beams": 1,
     "num_hidden_layers": 12,
     "num_return_sequences": 1,
     "output_attentions": false,
     "output_hidden_states": false,
-    "output_past": true,
     "output_scores": false,
-    "pad_token_id": 1,
+    "pad_token_id": 0,
+    "pooler_fc_size": 768,
+    "pooler_num_attention_heads": 12,
+    "pooler_num_fc_layers": 3,
+    "pooler_size_per_head": 128,
+    "pooler_type": "first_token_transform",
+    "position_embedding_type": "absolute",
     "prefix": null,
     "problem_type": null,
     "pruned_heads": {},
@@ -175,15 +167,9 @@
     "repetition_penalty": 1.0,
     "return_dict": true,
     "return_dict_in_generate": false,
-    "scale_embedding": true,
     "sep_token_id": null,
-    "static_position_embeddings": false,
     "suppress_tokens": null,
-    "task_specific_params": {
-      "translation_en_to_ro": {
-        "decoder_start_token_id": 250020
-      }
-    },
+    "task_specific_params": null,
     "temperature": 1.0,
     "tf_legacy_loss": false,
     "tie_encoder_decoder": false,
@@ -194,10 +180,11 @@
     "torch_dtype": null,
     "torchscript": false,
     "transformers_version": "4.25.1",
+    "type_vocab_size": 2,
     "typical_p": 1.0,
     "use_bfloat16": false,
     "use_cache": true,
-    "vocab_size": 250027
+    "vocab_size": 119547
   },
   "eos_token_id": 2,
   "is_encoder_decoder": true,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df2b107b48308eb2bbc31ee8604579e8c479eab3f188d256d211f29d9117d334
-size 639661093
+oid sha256:08bf677a1db9a7596d394f0ae22b06dd3d8055e601b4036c912e1b0a1ef5f34d
+size 636511709