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": "4.17.0",
+  "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 sha256:3ba9e6239a938708d9f35d560d1eea97081cd85bab041b5d7424ea1e7fbf9cc5
+size 409252370

runs/Mar31_11-28-15_ubuntu/1648697369.6185336/events.out.tfevents.1648697369.ubuntu.55595.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45f8dfa11a599ea0b0f6dbe096c1b61a8112509cfc7c4aa2b6c591c04fa27988
+size 4805

runs/Mar31_11-28-15_ubuntu/events.out.tfevents.1648697367.ubuntu.55595.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88f887ac1a13ee454e430f9653dbf62c6b34afb8dc94c4ed1586c0ef8d4835c4
+size 3678

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e4a3e8a54e17ef0b12269f112b42abda784d1c184ed368e743f393c2fe2cc0b
+size 3055