Training in progress, epoch 1

config.json

@@ -1,37 +1,58 @@
 {
-  "_name_or_path": "smitmenon/e2m_translation_project",
+  "_name_or_path": "facebook/mbart-large-50-one-to-many-mmt",
+  "_num_labels": 3,
   "activation_dropout": 0.0,
   "activation_function": "relu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": true,
   "architectures": [
-    "M2M100ForConditionalGeneration"
+    "MBartForConditionalGeneration"
   ],
-  "attention_dropout": 0.1,
+  "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": 0.05,
+  "decoder_layerdrop": 0.0,
   "decoder_layers": 12,
   "decoder_start_token_id": 2,
   "dropout": 0.1,
   "early_stopping": null,
   "encoder_attention_heads": 16,
   "encoder_ffn_dim": 4096,
-  "encoder_layerdrop": 0.05,
+  "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": null,
   "max_position_embeddings": 1024,
-  "model_type": "m2m_100",
+  "model_type": "mbart",
+  "normalize_before": true,
+  "normalize_embedding": true,
   "num_beams": null,
   "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": "4.46.3",
   "use_cache": true,
-  "vocab_size": 128112
+  "vocab_size": 250054
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9edeafd67088077c3d767d3c13195d9a98396a39af99c19efd0392dfeefb1edf
-size 1935681888
+oid sha256:b4e2a65db272d096591bfe5c38c630a866c5ca3a1e4b3a650698f972386b9a0e
+size 2444578688

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e888c4d8e8a8a147697a6ff4694d17109309a32215637a1c94a2ad232a2c6e2
+oid sha256:8d8faf2398860ca292877eda796ce8559c03a72802fe57e3987573c06350396a
 size 5432