Training in progress, step 500

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 sha256:779cfc60407735d782237c1a7b451b6116d409cd9992cada187630eeac77b24a
+oid sha256:4197740b2a3c6d20b5ab0568fb661482635f435d41f1534bb8eed64402b30b37
 size 2444578688

runs/Dec26_09-21-45_b2490b81dc7f/events.out.tfevents.1735204907.b2490b81dc7f.1522.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83213e1fb97d780511921acb7db9e4f643070c9fd195ffa310a325dbe11c20e4
+size 4184

tokenizer_config.json

@@ -515,6 +515,7 @@
   "clean_up_tokenization_spaces": false,
   "cls_token": "<s>",
   "eos_token": "</s>",
+  "extra_special_tokens": {},
   "language_codes": "ML50",
   "mask_token": "<mask>",
   "model_max_length": 1000000000000000019884624838656,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfe48c4af70752f73b00fa994efec6a2bc86e797bc017c7a4fe17c3ee987a3d2
-size 5368
+oid sha256:a7bfeb092857041f7b746bb058effb95e6ff6f5ec3a51c8966b59d288f8e9bb5
+size 5496