Training in progress, epoch 1

.gitignore

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

config.json

@@ -0,0 +1,69 @@
+{
+  "_name_or_path": "hfl/chinese-roberta-wwm-ext",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "\u6559\u80b2",
+    "1": "\u91d1\u878d",
+    "2": "\u623f",
+    "3": "\u65c5\u6e38",
+    "4": "\u79d1\u6280",
+    "5": "\u4f53\u80b2",
+    "6": "\u6e38\u620f",
+    "7": "\u6587\u5316",
+    "8": "\u8f66",
+    "9": "\u6545\u4e8b",
+    "10": "\u5a31\u4e50",
+    "11": "\u519b\u4e8b",
+    "12": "\u519c\u4e1a",
+    "13": "\u4e16\u754c",
+    "14": "\u80a1\u5e02"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "\u4e16\u754c": 13,
+    "\u4f53\u80b2": 5,
+    "\u519b\u4e8b": 11,
+    "\u519c\u4e1a": 12,
+    "\u5a31\u4e50": 10,
+    "\u623f": 2,
+    "\u6545\u4e8b": 9,
+    "\u6559\u80b2": 0,
+    "\u6587\u5316": 7,
+    "\u65c5\u6e38": 3,
+    "\u6e38\u620f": 6,
+    "\u79d1\u6280": 4,
+    "\u80a1\u5e02": 14,
+    "\u8f66": 8,
+    "\u91d1\u878d": 1
+  },
+  "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",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.25.1",
+  "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:f48f55ac9c862cc4c5e98d94eed5c313e17506dde8825053cf2113638a47eab5
+size 409186741

runs/Dec25_13-56-30_e8bd451f7dd7/1671976598.0157118/events.out.tfevents.1671976598.e8bd451f7dd7.14687.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7831ef2f2ff3ea50b774363b8237d853269efc37b74d8782fa8af9f750ace77
+size 5536

runs/Dec25_13-56-30_e8bd451f7dd7/events.out.tfevents.1671976597.e8bd451f7dd7.14687.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99b632e115040f1e43158c93a4897a0c43bbc9c1d048badb1465ce949e52ff84
+size 5195

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "hfl/chinese-roberta-wwm-ext",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": "/root/.cache/huggingface/hub/models--hfl--chinese-roberta-wwm-ext/snapshots/5c58d0b8ec1d9014354d691c538661bf00bfdb44/special_tokens_map.json",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c532480a6b37c838f11f92fa778698e96f66ca54abd4e6ee526ab44a617bb24b
+size 3451