Training in progress, step 500

config.json

@@ -18,13 +18,12 @@
   "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,
   "encoder_layers": 12,
   "eos_token_id": 2,
-  "forced_bos_token_id": 0,
   "forced_eos_token_id": 2,
   "gradient_checkpointing": false,
   "id2label": {
@@ -41,9 +40,9 @@
   },
   "max_position_embeddings": 1024,
   "model_type": "bart",
-  "no_repeat_ngram_size": 3,
+  "no_repeat_ngram_size": null,
   "normalize_before": false,
-  "num_beams": 4,
+  "num_beams": null,
   "num_hidden_layers": 12,
   "pad_token_id": 1,
   "scale_embedding": false,
@@ -68,7 +67,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.44.2",
+  "transformers_version": "4.46.2",
   "use_cache": true,
   "vocab_size": 50265
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01f185956294c1f5059fdc84566ea3e9bcd09ed8379fcc23659aa7e05bce7279
+oid sha256:3c4fd7522bb268e5deb3e19fbbe32d3ac3573fe8a9a2d85f395126966280698b
 size 1625426996

runs/Nov19_21-30-14_cda94b1a2dc2/events.out.tfevents.1732051815.cda94b1a2dc2.922.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c634aa98493dac0ddc0d8de6181e3efe6944449ca72f199b3528989d52db966e
+size 6429

tokenizer_config.json

@@ -43,7 +43,7 @@
     }
   },
   "bos_token": "<s>",
-  "clean_up_tokenization_spaces": true,
+  "clean_up_tokenization_spaces": false,
   "cls_token": "<s>",
   "eos_token": "</s>",
   "errors": "replace",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da05687ac974781ea5e48d90abb3ce23cd2b732e9a1d600be56358e37620e188
-size 5368
+oid sha256:feacf76aa300beae8a919f184ec2276e6eaecb3e9a14cc2e710dd4ee9c178c56
+size 5496