Training in progress, epoch 1

config.json

@@ -18,6 +18,7 @@
   "decoder_layers": 6,
   "decoder_start_token_id": 2,
   "dropout": 0.1,
+  "early_stopping": null,
   "encoder_attention_heads": 12,
   "encoder_ffn_dim": 3072,
   "encoder_layerdrop": 0.0,
@@ -39,8 +40,10 @@
   },
   "max_position_embeddings": 1024,
   "model_type": "bart",
+  "no_repeat_ngram_size": null,
   "normalize_before": false,
   "normalize_embedding": true,
+  "num_beams": null,
   "num_hidden_layers": 6,
   "pad_token_id": 1,
   "scale_embedding": false,
@@ -65,7 +68,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.44.0",
-  "use_cache": false,
+  "transformers_version": "4.48.3",
+  "use_cache": true,
   "vocab_size": 50268
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8aac7c6a2453c168a7246c99ddcf790e608081e07eb144bea7546deb0004949f
+oid sha256:eccb53925bf23549584cf71f87e8d2409b9039f8c5b2e4a2690ef090cb7a5fd8
 size 557921848

tokenizer_config.json

@@ -71,6 +71,7 @@
   "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:cb1fa59e312a0e7d6f88d03aaff9027dc24e628526a243d25a7025e826754ea7
-size 5368
+oid sha256:9217fab219605b4404b206ef29b429a8769cf1949b94829563ec7350335a795f
+size 5496