Training in progress, step 1000

config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0,
+  "classifier_dropout": null,
+  "embedding_size": 128,
+  "hidden_act": "relu",
+  "hidden_dropout_prob": 0,
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 196,
+  "model_type": "bert",
+  "normalization_type": "rms_norm",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 16000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06f92411bc98a19265d107b84eaabbbfa0e12b9f66ab43c35da439448ca0238e
+size 60696328

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af6f87e7d7db06e6a994f748fb4f1361b2ca59efc3070d2e28a6c661113b94b1
+size 4984