Training in progress, step 500

.gitignore

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

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "hfl/chinese-bert-wwm",
+  "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,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "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": "4.11.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 21128
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e036e9298755f451257553b1e5e2ed0d6004b46f09fa5fb868eb84e2732160e0
+size 409246059

runs/Oct21_00-04-11_fds001-CP3000-H1/1634745866.2594361/events.out.tfevents.1634745866.fds001-CP3000-H1.2816879.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e298e87c0d5a7f361b81a6f8e88393e63adb632af1846b5c0d0f970aa92b1ba
+size 4565

runs/Oct21_00-04-11_fds001-CP3000-H1/events.out.tfevents.1634745866.fds001-CP3000-H1.2816879.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9f37eb62349604865020843e61eff1c3a5e4df46e6eaba0cd70b30e551a9476
+size 3812

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1e1634321006ee1cff9c663bbdaa7127bdb7c62eee5f3acd7695aa026dab5f8
+size 2863