Training in progress, step 500

config.json

@@ -1,24 +1,31 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
-  "activation": "gelu",
+  "_name_or_path": "hfl/chinese-pert-base-mrc",
   "architectures": [
-    "DistilBertForQuestionAnswering"
+    "BertForQuestionAnswering"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "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": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "pad_token_id": 0,
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
+  "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": "4.35.2",
-  "vocab_size": 30522
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 21128
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f679f5dcaa5a7e46d729a576bc6e98e93dbbb3289b6d779df383056d4e0d72e4
-size 265470032
+oid sha256:ec8c46616f4a9ec0a904e5a60fb4b7ae5aef769639c81bea8a6b316289cc40d3
+size 406737680

runs/Dec19_05-58-31_67f3e57aa799/events.out.tfevents.1702965513.67f3e57aa799.665.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6dd742b8baa839cde35a2b8ca9817101412c64c82e25209ef3bd4bfada54f3e
+size 4184

runs/Dec19_06-02-21_67f3e57aa799/events.out.tfevents.1702965742.67f3e57aa799.3164.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9334854c169b33321f8b741241806561d12c9419471bdce3bf8c37c5342151a
+size 4570

tokenizer_config.json

@@ -43,13 +43,15 @@
   },
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
   "do_lower_case": true,
   "mask_token": "[MASK]",
-  "model_max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "strip_accents": null,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "DistilBertTokenizer",
+  "tokenizer_class": "BertTokenizer",
   "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cce26f5cf7dd80ee7cbeea870bc29bc64cfb8c021a71a72ba5d8d974f9cb0ca7
+oid sha256:4715e9ae060b2e2d8279e4725232f691e7a10b0f68b79118e9f9e00051299356
 size 4600