Training in progress, step 500

config.json

@@ -1,34 +1,26 @@
 {
-  "_name_or_path": "google/bigbird-roberta-base",
+  "_name_or_path": "google-bert/bert-base-uncased",
   "architectures": [
-    "BigBirdForQuestionAnswering"
+    "BertForQuestionAnswering"
   ],
   "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_act": "gelu",
   "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",
+  "max_position_embeddings": 512,
+  "model_type": "bert",
   "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": "4.39.3",
   "type_vocab_size": 2,
-  "use_bias": true,
   "use_cache": true,
-  "vocab_size": 50358
+  "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba39fafbba6789185624e6dc6a259dcc41cd2f00a9f1e1b5c3fdf48df957f1a4
-size 526438888
+oid sha256:88f679617b8be751568a477d84c8282d75b20f765c12e3cca99ba60ead68c123
+size 435596088

runs/Jun04_08-52-05_cb7fc95f01c2/events.out.tfevents.1717491126.cb7fc95f01c2.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e295b9568e02cb715443be84feb300bc5573a8ae248c19b50fc688257d518f3
+size 5100

special_tokens_map.json

@@ -1,51 +1,7 @@
 {
-  "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
-  }
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
 }

tokenizer_config.json

@@ -1,71 +1,55 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "<pad>",
+      "content": "[PAD]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "1": {
-      "content": "</s>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "2": {
-      "content": "<s>",
+    "100": {
+      "content": "[UNK]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "65": {
+    "101": {
       "content": "[CLS]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "66": {
+    "102": {
       "content": "[SEP]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "67": {
+    "103": {
       "content": "[MASK]",
-      "lstrip": true,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "100": {
-      "content": "<unk>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
-  "bos_token": "</s>",
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
-  "eos_token": "<s>",
+  "do_lower_case": true,
   "mask_token": "[MASK]",
-  "model_max_length": 4096,
-  "pad_token": "<pad>",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
   "sep_token": "[SEP]",
-  "sp_model_kwargs": {},
-  "tokenizer_class": "BigBirdTokenizer",
-  "unk_token": "<unk>"
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33fb19301f1bb67b2e0dec028b8534f2786bf87fa37843a15f706b696e788b57
+oid sha256:ae07ad3e4e783a8e9354ccd830320148ad3d7d294a472e783772073d2ad19dbc
 size 4920