Training in progress, epoch 1

config.json

@@ -0,0 +1,64 @@
+{
+  "_name_or_path": "microsoft/prophetnet-large-uncased",
+  "activation_dropout": 0.1,
+  "activation_function": "gelu",
+  "add_cross_attention": true,
+  "architectures": [
+    "ProphetNetForConditionalGeneration"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 102,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_max_position_embeddings": 514,
+  "decoder_start_token_id": 102,
+  "disable_ngram_loss": false,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_max_position_embeddings": 513,
+  "eos_token_id": 102,
+  "eps": 0.0,
+  "hidden_size": 1024,
+  "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": 2.0,
+  "max_length": 142,
+  "max_position_embeddings": 512,
+  "model_type": "prophetnet",
+  "ngram": 2,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "num_buckets": 32,
+  "num_decoder_attention_heads": 16,
+  "num_decoder_layers": 12,
+  "num_encoder_attention_heads": 16,
+  "num_encoder_layers": 12,
+  "output_past": false,
+  "pad_token_id": 0,
+  "prefix": " ",
+  "relative_max_distance": 128,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbf44e12d014c55260701692fe8ffc49507f76ba3737c5911464a4ae303d8057
+size 1565355112

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "ProphetNetTokenizer",
+  "unk_token": "[UNK]",
+  "x_sep_token": "[X_SEP]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14d78e5892a46869c5bc2442d96f7c5cc3d42b56c82e17fc7a72581bb16dc77e
+size 5112