Training in progress, step 500

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "distilroberta-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,
+  "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": "4.38.2",
+  "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 sha256:46c251af52c5610fceab40a6f8d077aeafaa96c2cb9b304f3f3170f5c90a56a6
+size 328693404

runs/Apr02_05-17-08_cd72545afb69/events.out.tfevents.1712035133.cd72545afb69.4448.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68e349d4db92d7006f63e88bbe9f6da3fa136f4bc42b3fad0848cc6b26adad73
+size 4664

runs/Apr02_05-19-59_cd72545afb69/events.out.tfevents.1712035209.cd72545afb69.4448.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0da3ec14576b3bf11bb8e87a238e8c2cbe2937e9562f21c7399e2d1ad11d769
+size 4873

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea802a5f848b0c8825e3264d01f0e53bf9cf9c87e981892ae9c4c52a74e550b7
+size 4984