Training in progress, step 500

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "andreasmadsen/efficient_mlm_m0.40",
+  "architectures": [
+    "RobertaPreLayerNormForCausalLM"
+  ],
+  "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": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta-prelayernorm",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "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 sha256:756f2bb9e26f34ef037f18df56d6566989afb5ceffbdf2fc848f0ea755df1c8d
+size 1421709940

runs/Apr24_00-39-15_47a4ecb9ecaa/events.out.tfevents.1713919156.47a4ecb9ecaa.1157.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51abe257d54492c7d5c07cb3bb97861b1384b80f4492d49da44e612b6c72bd6c
+size 4984

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6292b37b8e10ab59132e091683a940856a459d3388b2efab3d672d6848ef93a1
+size 4984