Training in progress, epoch 1

config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "distilbert/distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForMultipleChoice"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.0.dev0",
+  "vocab_size": 30522
+}

log.txt

@@ -0,0 +1,5 @@
+{'loss': 1.3703, 'grad_norm': 0.9787009954452515, 'learning_rate': 4.708318749270797e-05, 'epoch': 0.18}
+{'loss': 1.3523, 'grad_norm': 1.3269044160842896, 'learning_rate': 4.416637498541594e-05, 'epoch': 0.35}
+{'loss': 1.3357, 'grad_norm': 1.7331138849258423, 'learning_rate': 4.124956247812391e-05, 'epoch': 0.53}
+{'loss': 1.3207, 'grad_norm': 1.8865785598754883, 'learning_rate': 3.8332749970831875e-05, 'epoch': 0.7}
+{'loss': 1.3072, 'grad_norm': 2.1460351943969727, 'learning_rate': 3.5415937463539846e-05, 'epoch': 0.88}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df26e7da005d9cd28726a5cd73b5b7917f00424207b9ffa2c44c3d05d03e3782
+size 267829484

runs/Mar12_18-03-10_cehsc-app-001.ad.unlv.edu/events.out.tfevents.1710291792.cehsc-app-001.ad.unlv.edu.2502223.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a859a5d408226e7a760371986c13e431cdfcb97657f78bae0ae78f235915d05b
+size 5925

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": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff0a9f88e59bed652c1a756b83fc75f1289d360ad38effb3bedd218abcd9a3a3
+size 4984