Training in progress, step 500

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "peterchou/nezha-chinese-base",
+  "architectures": [
+    "BertLMHeadModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "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,
+  "max_relative_position": 64,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.17.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "use_relative_position": true,
+  "vocab_size": 21128
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78b90dde7837268e50915a26e7bf97cd0fba3e626fc05a053df64503d1cfc809
+size 409252370

runs/Apr07_20-26-18_ubuntu/1649334392.625932/events.out.tfevents.1649334392.ubuntu.9136.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12e95953d3e434648459e539aabc56e919520581c72ac3dd0da04b467a737f10
+size 4811

runs/Apr07_20-26-18_ubuntu/events.out.tfevents.1649334392.ubuntu.9136.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5b806e65ca76fb33f015a091159800c24da24afa8ed1d27bd728e617d3679c6
+size 3570

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:692e6a77fcf8504e11860e299cf3646f3923829641ca2a4af5ddcbe5ed3dc092
+size 3055