Training in progress, step 336

config.json

@@ -0,0 +1,26 @@
+{
+  "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-12,
+  "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": "4.48.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 52000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3626a78aa61b8ba248e1ac2d5771a7d5fa11ea2f255d45eb2e0b62e9a6878a93
+size 334030264

runs/Mar07_11-40-18_fg-wenemali/events.out.tfevents.1741365618.fg-wenemali.43125.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8371988938bcdf002636d354a4d7a5ba89bc101ee6ef9ec3894fe2fd0e45386f
+size 5335

runs/Mar07_11-48-38_fg-wenemali/events.out.tfevents.1741366119.fg-wenemali.43125.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:923fb432f23f59c07b3cc25e19a93f4d253065512fda6d72f72141cdaa8ec635
+size 5298

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb9178d6e0976decce8635680f65a23544ea9757fca1ca7e4a2978c7e751bd2c
+size 5304