Training in progress, epoch 1

config.json

@@ -1,21 +1,20 @@
 {
-  "_name_or_path": "bert-base-uncased",
+  "_name_or_path": "prajjwal1/bert-medium",
   "architectures": [
     "BertForMultipleChoice"
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
-  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "hidden_size": 512,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 2048,
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "num_attention_heads": 8,
+  "num_hidden_layers": 8,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d34cbe0fd4a431dd5e7d210566818a3a2e994405e6fd1849bf631c6b6c680fb3
-size 437955572
+oid sha256:dda1828b9d59aea8b7214a64398b556b7b497307c03617355ecc7eb95f150c5e
+size 165510676

runs/Jan08_12-10-46_4edbae574425/events.out.tfevents.1736338247.4edbae574425.335.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13bab5da2fd5d6faa83bf5891173d1eccc6fab570108cc5bbf970a03ee2f49c7
-size 5380
+oid sha256:6b437f3d69439de5cdf40bc28b40b4354848b580175cdf6221c51324980d3fd2
+size 5697

runs/Jan08_12-19-29_4edbae574425/events.out.tfevents.1736338770.4edbae574425.335.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a962f626546e52c15e221619047e15c940e70c4c4f436063a9f0f311a10b1d7
+size 5305

tokenizer.json

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

tokenizer_config.json

@@ -41,12 +41,14 @@
       "special": true
     }
   },
-  "clean_up_tokenization_spaces": false,
+  "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
   "do_lower_case": true,
   "extra_special_tokens": {},
   "mask_token": "[MASK]",
-  "model_max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "strip_accents": null,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b4b55a349fee35e169f64adebcf608a92d6e901c4c08a5bdb931ba86dcf4a91
+oid sha256:87314ca26fd857c4b1a9f8f59978b61843db4ea0a8a3d23748140f2584b24a61
 size 5368