Training in progress, step 200

config.json

@@ -0,0 +1,47 @@
+{
+  "_name_or_path": "SCUT-DLVCLab/lilt-roberta-en-base",
+  "architectures": [
+    "LiltForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "channel_shrink_ratio": 4,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-HEADER",
+    "2": "I-HEADER",
+    "3": "B-QUESTION",
+    "4": "I-QUESTION",
+    "5": "B-ANSWER",
+    "6": "I-ANSWER"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-ANSWER": 5,
+    "B-HEADER": 1,
+    "B-QUESTION": 3,
+    "I-ANSWER": 6,
+    "I-HEADER": 2,
+    "I-QUESTION": 4,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_2d_position_embeddings": 1024,
+  "max_position_embeddings": 514,
+  "model_type": "lilt",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

logs/events.out.tfevents.1701427157.b50951106c01.329.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3678e14798ad1b9af72ac0a14f63936cd7d44fed54fdc11012c215491357b629
+size 5267

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9106d8f1dce4f02d8b5f0960630c6f033667041edca92d4412f60a83bbbc24b6
+size 520727564

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7b46328c02decd17d3b1589698b17061f5ee9c171579c31178c2152128cf656
+size 4600