Training in progress, step 500

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "distilbert/distilroberta-base",
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "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,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.3",
+  "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 sha256:82e8728ea0b85797f5617134e4e4e95f82055b348d11aa66efbe67bb22d46edf
+size 328693404

runs/Apr12_14-02-34_50900e6d355d/events.out.tfevents.1712930555.50900e6d355d.8118.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df8dcfdf70ace65e558bbf54d77101f2ddf66b63f5a1e50d53febe6979b4c419
+size 4841

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bfccef60695925a6ae37e9a94bdacfeac0ed321dd8a8639daf56a413e1e0a00
+size 4920