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": "4.40.0.dev0",
+  "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:ec3b177b31b2529324e3e66eeb4ef991b616450a8c0671ade74fa74f32051a41
+size 328693404

runs/Apr17_05-33-02_AnnMacBook-Pro.local/events.out.tfevents.1713303257.AnnMacBook-Pro.local.1045.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:422ef3bb64641aa38128ae57cedd929f431602b6c170cb166a33150f6a0ec74b
+size 4715

runs/Apr17_06-21-46_AnnMacBook-Pro.local/events.out.tfevents.1713306135.AnnMacBook-Pro.local.1045.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48a915c5067f55ab602345a311d3b363beb6bc45fd9e943d5bcee6365518e9e3
+size 4926

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f458890939615b70ed913319c5ec0cab73a4e657e9af99052b3983ac78bb4e6f
+size 4984