Training in progress, epoch 1

config.json

@@ -1,25 +1,24 @@
 {
-  "_name_or_path": "prajjwal1/bert-medium",
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
   "architectures": [
-    "BertForMultipleChoice"
+    "DistilBertForMultipleChoice"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 512,
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
   "initializer_range": 0.02,
-  "intermediate_size": 2048,
-  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 8,
-  "num_hidden_layers": 8,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
   "pad_token_id": 0,
-  "position_embedding_type": "absolute",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.47.1",
-  "type_vocab_size": 2,
-  "use_cache": true,
   "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dda1828b9d59aea8b7214a64398b556b7b497307c03617355ecc7eb95f150c5e
-size 165510676
+oid sha256:0b51ec0e1257c7480035c452195df65e1a6d108f0c7cdd94f2fddd3ab9b6723d
+size 267829484

runs/Jan08_12-30-54_4edbae574425/events.out.tfevents.1736339455.4edbae574425.335.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:022d2965f2ebadae74889ed488a9b919e784b98d8e0fa7537d9907af8ef9a406
+size 5030

runs/Jan08_12-32-50_4edbae574425/events.out.tfevents.1736339571.4edbae574425.335.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c7fd1375c9d333c76ec1469d596280c039969ee32d5556dd2928dbc73b4b73c
+size 5274

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 512,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {

tokenizer_config.json

@@ -41,18 +41,16 @@
       "special": true
     }
   },
-  "clean_up_tokenization_spaces": true,
+  "clean_up_tokenization_spaces": false,
   "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
   "do_lower_case": true,
   "extra_special_tokens": {},
   "mask_token": "[MASK]",
-  "model_max_length": 1000000000000000019884624838656,
-  "never_split": null,
+  "model_max_length": 512,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "strip_accents": null,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
+  "tokenizer_class": "DistilBertTokenizer",
   "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87314ca26fd857c4b1a9f8f59978b61843db4ea0a8a3d23748140f2584b24a61
+oid sha256:45c8c71ec2fea2baec3bfb3bd9ac65a5facd4229ab827b54f7685b41dae20050
 size 5368