Training in progress, step 200

config.json

@@ -0,0 +1,51 @@
+{
+  "_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-ACCOUNT_NO.KEY",
+    "2": "I-ACCOUNT_NO.KEY",
+    "3": "B-ACCOUNT_NO.VALUE",
+    "4": "I-ACCOUNT_NO.VALUE",
+    "5": "B-ACCOUNT_NAME.KEY",
+    "6": "I-ACCOUNT_NAME.KEY",
+    "7": "B-ACCOUNT_NAME.VALUE",
+    "8": "I-ACCOUNT_NAME.VALUE"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-ACCOUNT_NAME.KEY": 5,
+    "B-ACCOUNT_NAME.VALUE": 7,
+    "B-ACCOUNT_NO.KEY": 1,
+    "B-ACCOUNT_NO.VALUE": 3,
+    "I-ACCOUNT_NAME.KEY": 6,
+    "I-ACCOUNT_NAME.VALUE": 8,
+    "I-ACCOUNT_NO.KEY": 2,
+    "I-ACCOUNT_NO.VALUE": 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": "4.35.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

logs/events.out.tfevents.1699258954.32625c4211ab.4622.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41816afa93a1096fd9d512d435e3b6346c8d3af8aaea060abc288fe3ea644fff
+size 5499

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22b381f1ac45ed11f0e80a1d47f08ac528d3b88bec0bd54a86451a3e35013043
+size 520733716

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c30e982aefecd10acbd342858ae85a68e3c44e2a1433a3552c52b315beb7faf
+size 4600