Training in progress, step 1000

config.json

@@ -1,26 +1,25 @@
 {
-  "_name_or_path": "bert-base-cased",
+  "_name_or_path": "prajjwal1/bert-small",
   "architectures": [
     "BertForMaskedLM"
   ],
   "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": 4,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.38.2",
   "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 8554
+  "vocab_size": 6685
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b9c2fd0d32da24604c2cc1aff2adf157661b71dfbf2b4d23aabbeed1666e280
-size 370507248
+oid sha256:cc3a44a97fbf3562a94238654599df89478efdd03b9fb426437057ffcea3e169
+size 66275732

runs/Apr15_04-08-25_939fcec28df8/events.out.tfevents.1713154107.939fcec28df8.3234.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:191a656870789eb1aa6b2a2af0ecd18e9df3a88d5cf31afa5eed28c754d7d769
+size 4962

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68fbe51e355a3a4aeab047910b5484234bf92db1458be4c7cff6b676c8e8f152
+oid sha256:a40197a395c5eef5fea94cf0c52b0bf91b623a95f3d88dd1687a5fa7d768523e
 size 4920