Training in progress, epoch 1

config.json

@@ -1,15 +1,15 @@
 {
-  "_name_or_path": "facebook/bart-large-cnn",
-  "_num_labels": 3,
-  "activation_dropout": 0.0,
+  "_name_or_path": "facebook/bart-large",
+  "activation_dropout": 0.1,
   "activation_function": "gelu",
+  "add_bias_logits": false,
   "add_final_layer_norm": false,
   "architectures": [
     "BartForConditionalGeneration"
   ],
-  "attention_dropout": 0.0,
+  "attention_dropout": 0.1,
   "bos_token_id": 0,
-  "classif_dropout": 0.0,
+  "classif_dropout": 0.1,
   "classifier_dropout": 0.0,
   "d_model": 1024,
   "decoder_attention_heads": 16,
@@ -24,7 +24,6 @@
   "encoder_layerdrop": 0.0,
   "encoder_layers": 12,
   "eos_token_id": 2,
-  "force_bos_token_to_be_generated": true,
   "forced_eos_token_id": 2,
   "gradient_checkpointing": false,
   "id2label": {
@@ -39,31 +38,36 @@
     "LABEL_1": 1,
     "LABEL_2": 2
   },
-  "length_penalty": null,
-  "max_length": null,
   "max_position_embeddings": 1024,
-  "min_length": null,
   "model_type": "bart",
   "no_repeat_ngram_size": null,
   "normalize_before": false,
   "num_beams": null,
   "num_hidden_layers": 12,
-  "output_past": true,
   "pad_token_id": 1,
-  "prefix": " ",
   "scale_embedding": false,
   "task_specific_params": {
     "summarization": {
-      "early_stopping": true,
+      "length_penalty": 1.0,
+      "max_length": 128,
+      "min_length": 12,
+      "num_beams": 4
+    },
+    "summarization_cnn": {
       "length_penalty": 2.0,
       "max_length": 142,
       "min_length": 56,
-      "no_repeat_ngram_size": 3,
       "num_beams": 4
+    },
+    "summarization_xsum": {
+      "length_penalty": 1.0,
+      "max_length": 62,
+      "min_length": 11,
+      "num_beams": 6
     }
   },
   "torch_dtype": "float32",
   "transformers_version": "4.47.0",
   "use_cache": true,
-  "vocab_size": 50264
+  "vocab_size": 50265
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38e1cfcae9bd06f2e6076e4bae070159e40306fdfb9789ec320e298b930ce6e5
-size 1625422896
+oid sha256:0f599d4e5dd67dc6dc2dd809a9229d66e474213c242c7a94b27c54d4e6773217
+size 1625426996

tokenizer_config.json

@@ -49,7 +49,7 @@
   "errors": "replace",
   "extra_special_tokens": {},
   "mask_token": "<mask>",
-  "model_max_length": 1000000000000000019884624838656,
+  "model_max_length": 1024,
   "pad_token": "<pad>",
   "sep_token": "</s>",
   "tokenizer_class": "BartTokenizer",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6712ca00c8b8f360c3eae547892f34dbac725906de12df5620e5f04b9451be99
+oid sha256:e3ad536fa6018fce7598cb3f664c9c81f2e54ab6bce8fa5520b9158004ff0793
 size 5432