Training in progress, epoch 1

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "google/mobilebert-uncased",
+  "architectures": [
+    "MobileBertForMultipleChoice"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_activation": false,
+  "classifier_dropout": null,
+  "embedding_size": 128,
+  "hidden_act": "relu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "intra_bottleneck_size": 128,
+  "key_query_shared_bottleneck": true,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "mobilebert",
+  "normalization_type": "no_norm",
+  "num_attention_heads": 4,
+  "num_feedforward_networks": 4,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.0.dev0",
+  "trigram_input": true,
+  "true_hidden_size": 128,
+  "type_vocab_size": 2,
+  "use_bottleneck": true,
+  "use_bottleneck_attention": false,
+  "vocab_size": 30522
+}

log.txt

@@ -0,0 +1,5 @@
+{'loss': 6619.536, 'grad_norm': 570995.875, 'learning_rate': 4.708318749270797e-05, 'epoch': 0.18}
+{'loss': 41.9051, 'grad_norm': 50093.546875, 'learning_rate': 4.416637498541594e-05, 'epoch': 0.35}
+{'loss': 12.3949, 'grad_norm': 30450.115234375, 'learning_rate': 4.124956247812391e-05, 'epoch': 0.53}
+{'loss': 2.3106, 'grad_norm': 2060.141845703125, 'learning_rate': 3.8332749970831875e-05, 'epoch': 0.7}
+{'loss': 3.8107, 'grad_norm': 1.1463676691055298, 'learning_rate': 3.5415937463539846e-05, 'epoch': 0.88}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2575caffeb54f350381dde75dba1ce201d9d6ae213a0c5a55f85689806c04da
+size 98468060

runs/Mar12_23-46-21_cehsc-app-001.ad.unlv.edu/events.out.tfevents.1710312384.cehsc-app-001.ad.unlv.edu.2715464.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd699e1e622eee460a5160ceace60020c28919fa39ee9070b84d7d8690955867
+size 6236

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": "MobileBertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb6af806b87add948d41ff18f253e26978a0bd5a67ad045e212c9c758b9d3e4d
+size 4920