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": "4.39.2",
+  "transformers_version": "4.45.0",
   "use_cache": true,
   "vocab_size": 50265
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a94bce3601b5b88b6e55d81ab31e23de532484faec135baa4c84c09b1087ab04
+oid sha256:2f4ff4240f7e70e7bd8ca7297e63d551574d0809d22ff47a60c545e14b7e9d63
 size 1625426996

runs/Sep26_03-04-25_82e017957fa9/events.out.tfevents.1727319866.82e017957fa9.646.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1cd41021051c03d022a28c572f8222a03b97dce2cdecf2535e3624d15553669
+size 6284

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5237958d5cd1d3f030dc8cf326fa57fb17d6f465536609ffefd0a3bfa530009b
-size 5048
+oid sha256:5471bedecdc7ea345184a9c7fd54313cbdf9d2082e26a399098cab43cda23c92
+size 5304