Training in progress, step 200

config.json

@@ -19,7 +19,7 @@
   "decoder_layers": 12,
   "decoder_start_token_id": 2,
   "dropout": 0.1,
-  "early_stopping": true,
+  "early_stopping": null,
   "encoder_attention_heads": 16,
   "encoder_ffn_dim": 4096,
   "encoder_layerdrop": 0.0,
@@ -39,12 +39,12 @@
     "LABEL_1": 1,
     "LABEL_2": 2
   },
-  "max_length": 200,
+  "max_length": null,
   "max_position_embeddings": 1024,
   "model_type": "mbart",
   "normalize_before": true,
   "normalize_embedding": true,
-  "num_beams": 5,
+  "num_beams": null,
   "num_hidden_layers": 12,
   "output_past": true,
   "pad_token_id": 1,
@@ -52,7 +52,7 @@
   "static_position_embeddings": false,
   "tokenizer_class": "MBart50Tokenizer",
   "torch_dtype": "float32",
-  "transformers_version": "4.44.2",
+  "transformers_version": "4.47.1",
   "use_cache": true,
   "vocab_size": 250054
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d17a83b505fad6c5dfe5e1ef5816724f293ea8f60b7ffb39689ca32e41b36969
+oid sha256:ce59d7200b320c3b0437b2e2d8dd6399a6cd97a8d59580c66e7b6da1a83c71f4
 size 2444578688

runs/Jan12_12-23-38_353270b004df/events.out.tfevents.1736684621.353270b004df.5788.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0476996cf640844731084ecf9ebe6e442355e19eca5f110126c215f13af5049
+size 6274

tokenizer_config.json

@@ -512,9 +512,10 @@
     "sl_SI"
   ],
   "bos_token": "<s>",
-  "clean_up_tokenization_spaces": true,
+  "clean_up_tokenization_spaces": false,
   "cls_token": "<s>",
   "eos_token": "</s>",
+  "extra_special_tokens": {},
   "mask_token": "<mask>",
   "model_max_length": 1024,
   "pad_token": "<pad>",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13cd0bd21678ed91f069f8b1ad12f8236f000a68ee5098b1828161f899cd412b
-size 5240
+oid sha256:d301f3fbdbedde770349cfa2ec0b5495f9744dae3761587eb280877dc59320bc
+size 5368