Training in progress, epoch 1

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "google-bert/bert-large-uncased",
+  "architectures": [
+    "BertForMultipleChoice"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

log.txt

@@ -0,0 +1,11 @@
+{'loss': 1.4007, 'grad_norm': 1.7373141050338745, 'learning_rate': 4.991249562478124e-05, 'epoch': 0.09}
+{'loss': 1.3979, 'grad_norm': 1.4521712064743042, 'learning_rate': 4.982499124956248e-05, 'epoch': 0.18}
+{'loss': 1.396, 'grad_norm': 1.4701424837112427, 'learning_rate': 4.973748687434372e-05, 'epoch': 0.26}
+{'loss': 1.3946, 'grad_norm': 1.407281756401062, 'learning_rate': 4.964998249912496e-05, 'epoch': 0.35}
+{'loss': 1.3936, 'grad_norm': 1.4591513872146606, 'learning_rate': 4.95624781239062e-05, 'epoch': 0.44}
+{'loss': 1.3905, 'grad_norm': 1.5211539268493652, 'learning_rate': 4.947497374868744e-05, 'epoch': 0.53}
+{'loss': 1.391, 'grad_norm': 1.1787604093551636, 'learning_rate': 4.9387469373468674e-05, 'epoch': 0.61}
+{'loss': 1.3908, 'grad_norm': 1.2173224687576294, 'learning_rate': 4.929996499824991e-05, 'epoch': 0.7}
+{'loss': 1.3912, 'grad_norm': 1.7298877239227295, 'learning_rate': 4.9212460623031155e-05, 'epoch': 0.79}
+{'loss': 1.3908, 'grad_norm': 1.3088189363479614, 'learning_rate': 4.912495624781239e-05, 'epoch': 0.88}
+{'loss': 1.3908, 'grad_norm': 1.181019902229309, 'learning_rate': 4.903745187259363e-05, 'epoch': 0.96}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fc12805fbf7a7aad0e8d653cde67ac21b64e07bc628012f5c693dc2056edae6
+size 1340618660

runs/Mar14_00-18-03_cehsc-app-001.ad.unlv.edu/events.out.tfevents.1710400686.cehsc-app-001.ad.unlv.edu.3750986.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2407bfae483e62bfc80a4d76c24ede51fa6b9eb84e860c73f3ba806e1ac369b6
+size 4778

runs/Mar14_00-20-30_cehsc-app-001.ad.unlv.edu/events.out.tfevents.1710400834.cehsc-app-001.ad.unlv.edu.3751445.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e853ac7dd0cbe92b460d07f0de0a6ad56783b3eeb542f50af37eb19fc454266d
+size 7314

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 +1,55 @@
+{
+  "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_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "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:db155bafba12cfeb0eed4233563ccb529a4ebc4ed7be5ef238914ad2174c4c4d
+size 4984