Training in progress, epoch 1

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "hfl/chinese-macbert-base",
+  "architectures": [
+    "DualModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 21128
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0fa0a23cf571b5e78db2f7f76398e1115bdb5da4ea0b116eb6850f6ebae0570
+size 409093920

runs/Sep16_07-27-48_6c4f3df34a5f/events.out.tfevents.1726471692.6c4f3df34a5f.1315.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1457d03759f69515c40a682d7248ccbc719f32dfbe82ee0976b160e22121eb26
+size 10776

runs/Sep16_07-27-48_6c4f3df34a5f/events.out.tfevents.1726472838.6c4f3df34a5f.1315.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:947ea82893f9bdf976cf0ebe4514a21c9c80330206252d7d419799b33a101467
+size 10776

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c29605c3c2407be5a0de2e4fa83052acaae303dda08c5ce7f787e62a818f756
+size 5240