Training in progress, step 500

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "microsoft/deberta-base",
+  "architectures": [
+    "DebertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "c2p",
+    "p2c"
+  ],
+  "position_biased_input": false,
+  "relative_attention": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "type_vocab_size": 0,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:850b89393b8bfd15825ca1d5092513a11dbebcacda6f676c139704e4df3914ca
+size 556799560

runs/Jul23_21-37-09_171e6dbaefe5/events.out.tfevents.1721770662.171e6dbaefe5.577.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dc8bbd674af677757fb75373ccba178cbc5e315d83b8fc2302a4723820a76fe
+size 9804

runs/Jul23_21-45-19_171e6dbaefe5/events.out.tfevents.1721771124.171e6dbaefe5.577.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa1752b251f56fa606385de928df8993457342c4c01e6eac6db2ccf43e23214c
+size 5895

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06d10b9e8f53d2082e9ccdfeafb5d3827f0495c2e6240f11ce36f9ae9def2059
+size 5176