Training in progress, epoch 1

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "google/bigbird-roberta-base",
+  "architectures": [
+    "BigBirdForMultipleChoice"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "attention_type": "block_sparse",
+  "block_size": 64,
+  "bos_token_id": 1,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 4096,
+  "model_type": "big_bird",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "num_random_blocks": 3,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "rescale_embeddings": false,
+  "sep_token_id": 66,
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.0.dev0",
+  "type_vocab_size": 2,
+  "use_bias": true,
+  "use_cache": true,
+  "vocab_size": 50358
+}

log.txt

@@ -0,0 +1,5 @@
+{'loss': 1.3895, 'grad_norm': 0.917380154132843, 'learning_rate': 4.708318749270797e-05, 'epoch': 0.18}
+{'loss': 1.3891, 'grad_norm': 0.43125149607658386, 'learning_rate': 4.416637498541594e-05, 'epoch': 0.35}
+{'loss': 1.3883, 'grad_norm': 0.3787681758403778, 'learning_rate': 4.124956247812391e-05, 'epoch': 0.53}
+{'loss': 1.3882, 'grad_norm': 0.400529682636261, 'learning_rate': 3.8332749970831875e-05, 'epoch': 0.7}
+{'loss': 1.3882, 'grad_norm': 0.31423699855804443, 'learning_rate': 3.5415937463539846e-05, 'epoch': 0.88}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d6dd30730271cbe2f23639c21037488adc6543b449ab34cfb787d692f499fef
+size 509901812

runs/Mar12_12-22-43_cehsc-app-001.ad.unlv.edu/events.out.tfevents.1710271366.cehsc-app-001.ad.unlv.edu.2392965.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbfe7fdc822eba85392d786f6d5273d10ad59d72ac5517990712396a6d768c95
+size 6227

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdc81e1fc9d42e0c08b86d5b280d05d7c5e9747c4231c648f2b56b8e1d893c82
+size 845731

tokenizer_config.json

@@ -0,0 +1,71 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "65": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "66": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "67": {
+      "content": "[MASK]",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "</s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "eos_token": "<s>",
+  "mask_token": "[MASK]",
+  "model_max_length": 4096,
+  "pad_token": "<pad>",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "BigBirdTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:021a2495c5716891a8af3d9ecc817ea9268829bd81c466b63664adcd87120223
+size 4920