Model saved at the end of 4 epochs

config.json

@@ -0,0 +1,60 @@
+{
+  "_name_or_path": "google/pegasus-x-large",
+  "activation_dropout": 0.1,
+  "activation_function": "relu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": true,
+  "architectures": [
+    "PegasusXForConditionalGeneration"
+  ],
+  "attention_dropout": 0.1,
+  "block_size": 512,
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 16,
+  "decoder_start_token_id": 0,
+  "dropout": 0.1,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 16,
+  "eos_token_id": 1,
+  "extra_pos_embeddings": 1,
+  "force_bos_token_to_be_generated": false,
+  "forced_eos_token_id": 1,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "length_penalty": 0.8,
+  "max_length": 16384,
+  "max_position_embeddings": 16384,
+  "model_type": "pegasus_x",
+  "normalize_before": true,
+  "normalize_embedding": false,
+  "num_beams": 8,
+  "num_global_tokens": 128,
+  "num_hidden_layers": 16,
+  "pad_token_id": 0,
+  "scale_embedding": true,
+  "stagger_local_blocks": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.25.1",
+  "use_cache": true,
+  "vocab_size": 96103
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27d561e1cbc095da761ab65d6cd616754cad48b2399e0b8d06f354646146d48f
+size 1137504293