Training in progress, epoch 1

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "nghuyong/ernie-2.0-base-en",
+  "architectures": [
+    "ErnieForMultipleChoice"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 512,
+  "model_type": "ernie",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "task_type_vocab_size": 3,
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.0.dev0",
+  "type_vocab_size": 4,
+  "use_cache": true,
+  "use_task_id": false,
+  "vocab_size": 30522
+}

log.txt

@@ -0,0 +1,5 @@
+{'loss': 1.3816, 'grad_norm': 1.4503111839294434, 'learning_rate': 4.708318749270797e-05, 'epoch': 0.18}
+{'loss': 1.3642, 'grad_norm': 1.2277671098709106, 'learning_rate': 4.416637498541594e-05, 'epoch': 0.35}
+{'loss': 1.3505, 'grad_norm': 1.8225963115692139, 'learning_rate': 4.124956247812391e-05, 'epoch': 0.53}
+{'loss': 1.3362, 'grad_norm': 1.5222986936569214, 'learning_rate': 3.8332749970831875e-05, 'epoch': 0.7}
+{'loss': 1.321, 'grad_norm': 2.3339385986328125, 'learning_rate': 3.5415937463539846e-05, 'epoch': 0.88}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41322cfa76544223c280fa96809e8bf06a62d1c7f44feb9213ceaaa04736f5d2
+size 437961884

runs/Mar12_19-30-48_cehsc-app-001.ad.unlv.edu/events.out.tfevents.1710297050.cehsc-app-001.ad.unlv.edu.2573046.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53eac1fd1cc8654b5fc814b7a1d3cc7d6d20a0b71089965df2ca1704c896c544
+size 6025

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 +1,58 @@
+{
+  "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,
+  "full_tokenizer_file": null,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "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 sha256:01604d65d3e3d061fca745d21d91d204b7d590ef0d80a42e9135d74460329f5c
+size 4920