Training in progress, epoch 1

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "weiweishi/roc-bert-base-zh",
+  "architectures": [
+    "RoCBertForMultipleChoice"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "concat_input": true,
+  "directionality": "bidi",
+  "enable_cls": true,
+  "enable_pronunciation": true,
+  "enable_shape": true,
+  "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": "roc_bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "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",
+  "pronunciation_embed_dim": 768,
+  "pronunciation_vocab_size": 910,
+  "shape_embed_dim": 512,
+  "shape_vocab_size": 24858,
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 21128
+}

log.txt

@@ -0,0 +1,5 @@
+{'loss': 1.3893, 'grad_norm': 1.0231168270111084, 'learning_rate': 4.708318749270797e-05, 'epoch': 0.18}
+{'loss': 1.3887, 'grad_norm': 0.603848934173584, 'learning_rate': 4.416637498541594e-05, 'epoch': 0.35}
+{'loss': 1.389, 'grad_norm': 0.6142033338546753, 'learning_rate': 4.124956247812391e-05, 'epoch': 0.53}
+{'loss': 1.3882, 'grad_norm': 0.6350305676460266, 'learning_rate': 3.8332749970831875e-05, 'epoch': 0.7}
+{'loss': 1.388, 'grad_norm': 0.5414144396781921, 'learning_rate': 3.5415937463539846e-05, 'epoch': 0.88}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df99f3d85216c04d668c17985eeb6255afed80f4ace138252c11993563383e3f
+size 469097668

runs/Mar13_04-41-49_cehsc-app-001.ad.unlv.edu/events.out.tfevents.1710330112.cehsc-app-001.ad.unlv.edu.2865422.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21fb9f7ccf7aaebfff38e513252e56e5ae588472a0a1fe361aea2d87ada7bb5d
+size 6431

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 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "RoCBertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e33b160ac9b5d8a12b950e581fd29f520142d7b7769c5d09ef1e3be6e65ccc02
+size 4920