Training in progress, step 100

config.json

@@ -18,12 +18,13 @@
   "decoder_layers": 6,
   "decoder_start_token_id": 2,
   "dropout": 0.1,
-  "early_stopping": null,
+  "early_stopping": true,
   "encoder_attention_heads": 12,
   "encoder_ffn_dim": 3072,
   "encoder_layerdrop": 0.0,
   "encoder_layers": 6,
   "eos_token_id": 2,
+  "forced_bos_token_id": 0,
   "forced_eos_token_id": 2,
   "gradient_checkpointing": false,
   "id2label": {
@@ -40,10 +41,10 @@
   },
   "max_position_embeddings": 1024,
   "model_type": "bart",
-  "no_repeat_ngram_size": null,
+  "no_repeat_ngram_size": 3,
   "normalize_before": false,
   "normalize_embedding": true,
-  "num_beams": null,
+  "num_beams": 4,
   "num_hidden_layers": 6,
   "pad_token_id": 1,
   "scale_embedding": false,
@@ -68,7 +69,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.47.1",
+  "transformers_version": "4.44.2",
   "use_cache": true,
   "vocab_size": 80265
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52887023c2f4f7e88cc13d26e69a86fdaf51a87f9a7427f71c024f401ab8bda5
+oid sha256:16a254d0b2c9dfefedbe89e0f6627556286ecb399daafd5cb1c32ad52ec77149
 size 650192620

tokenizer_config.json

@@ -43,11 +43,10 @@
     }
   },
   "bos_token": "<s>",
-  "clean_up_tokenization_spaces": false,
+  "clean_up_tokenization_spaces": true,
   "cls_token": "<s>",
   "eos_token": "</s>",
   "errors": "replace",
-  "extra_special_tokens": {},
   "mask_token": "<mask>",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f1b053364614a43d705d5d66aaf8393acd82095c7504c608499d71ab7052957
-size 5304
+oid sha256:5481fc6bade3f8f522b15280db35bfccc1a177152779f0d0a9b7802eca076bc9
+size 5176