Training in progress, step 500

config.json

@@ -0,0 +1,27 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForMaskedLM"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": null,
+  "dim": 768,
+  "dropout": 0.1,
+  "dtype": "float32",
+  "eos_token_id": null,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.1.0",
+  "use_cache": false,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efd1d6fbf74469549fb29c0daf03276765c893f4de5ab4f5e476284684051d4a
+size 267954768

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0b032a7c0bb6935085895105bb37c037568dc1a49efad8c213d11b2735ead08
+size 4792