Training in progress, step 500

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "roberta-base",
+  "architectures": [
+    "RobertaForCausalLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": true,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e764e1fc605f44edbb658291ff40139e3e454bd85f6022f08239dfb2d34d406
+size 498813948

runs/Apr25_07-40-50_89580b522c30/events.out.tfevents.1714030851.89580b522c30.1431.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0cda8afdceebd73eacaf8ed9425e2e21fc63a7dc574efd5f429a087c5d7bae9
+size 4931

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b07ad96bec39a3eefd8929d571d913804dd7d273106628e2ae0a6c007f38ab4a
+size 4984