Training in progress, epoch 1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "facebook/mbart-large-50-many-to-one-mmt",
+  "_name_or_path": "facebook/mbart-large-50-one-to-many-mmt",
   "_num_labels": 3,
   "activation_dropout": 0.0,
   "activation_function": "relu",
@@ -19,6 +19,7 @@
   "decoder_layers": 12,
   "decoder_start_token_id": 2,
   "dropout": 0.1,
+  "early_stopping": null,
   "encoder_attention_heads": 16,
   "encoder_ffn_dim": 4096,
   "encoder_layerdrop": 0.0,
@@ -49,11 +50,6 @@
   "pad_token_id": 1,
   "scale_embedding": true,
   "static_position_embeddings": false,
-  "task_specific_params": {
-    "translation_en_to_ro": {
-      "decoder_start_token_id": 250020
-    }
-  },
   "tokenizer_class": "MBart50Tokenizer",
   "torch_dtype": "float32",
   "transformers_version": "4.46.3",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08be3f816c64d3dc9332077781e70cea90f40f6e0af24e06b72e779982b9462e
+oid sha256:206f7fd660ee33f772d62c151148fea38ef4c3c71c7f2d6130e29b900b960f13
 size 2444578688

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1254f6cd23bcabbdabb3679e3bd64add7924688f15de238c34be00ffc9b5844e
+oid sha256:8e09c3b2f0a855274a1f10b3b2e6b689746960f11047d3ccebe28626e5133866
 size 5432