Training in progress, step 500

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "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 sha256:101bbdd78d31eeb5251d0f9b8d10a93fd1a239422a8f1552d88b44fbfb489cee
+size 328693404

runs/Apr18_11-16-12_capycoony-m16/events.out.tfevents.1713410194.capycoony-m16.46500.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ffcb218967a45d3487efe877744de9d873cc4a1ee012f9055bc9fb3d67cfc9f
+size 4817

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aec63695379c7d7240eef10cf6ded29b919e05e76a93cbe3afe793add5c978ce
+size 4984