Training in progress, step 600

config.json

@@ -1,47 +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": "4.41.1",
-  "type_vocab_size": 1,
-  "use_cache": true,
-  "vocab_size": 50265
-}
+{
+  "_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": "4.41.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

logs/events.out.tfevents.1716809082.c190ecb2bcd6.9598.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34834124819e7e7f443a1e33eafe1cb17799dd073fdf08eb552bb3db26d3b3c2
-size 5919
+oid sha256:e20132b1dd9c3b1ce7c5ca2da3ef24b63d71cd03e34e936e7b9fd3860d016b37
+size 7349

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e694d195a0b97cd39e8ead9130ff8b22468bdf00553a0494373fb9b238ef467
+oid sha256:6a9c40d8463e79fa4663c762f717d60592b86cb63a85b8059545c74a98c0b9fa
 size 520727564

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd6a1d1a08b8287aa4df188c26775d4a273baea8f1333fa2468a3fa46f30dd4b
-size 5176
+oid sha256:2d576c44fe2af979976296a9f99973c682b1f05b48e0c3b487911cfd7f515990
+size 5112