model files added

config.json

@@ -0,0 +1,31 @@
+{
+  "_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,
+  "transformers_version": "4.8.1",
+  "type_vocab_size": 0,
+  "vocab_size": 50265
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dac3500f89a76b7d1a0bb17189d9b588bcdc25a86ce205c101ad2a3ab15d930f
+size 556866752

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7d33f1ae1c81be849ea370c945677b611f7ca1bf1c935a56f81e32e0933e0b0
+size 16723

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d63fe5fc529e3123595de709977de4a24524ac5b5840c6956fe4a0af2f41441
+size 623

trainer_state.json

@@ -0,0 +1,100 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "global_step": 716,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.28,
+      "learning_rate": 5e-06,
+      "loss": 0.6789,
+      "step": 50
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1e-05,
+      "loss": 0.5907,
+      "step": 100
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.5e-05,
+      "loss": 0.4927,
+      "step": 150
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 2e-05,
+      "loss": 0.4183,
+      "step": 200
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 2.5e-05,
+      "loss": 0.3848,
+      "step": 250
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 3e-05,
+      "loss": 0.3815,
+      "step": 300
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 3.5e-05,
+      "loss": 0.3652,
+      "step": 350
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 4e-05,
+      "loss": 0.2917,
+      "step": 400
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 4.5e-05,
+      "loss": 0.2744,
+      "step": 450
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 5e-05,
+      "loss": 0.2875,
+      "step": 500
+    },
+    {
+      "epoch": 3.07,
+      "learning_rate": 4.367088607594937e-05,
+      "loss": 0.2423,
+      "step": 550
+    },
+    {
+      "epoch": 3.35,
+      "learning_rate": 3.7341772151898736e-05,
+      "loss": 0.1756,
+      "step": 600
+    },
+    {
+      "epoch": 3.63,
+      "learning_rate": 3.10126582278481e-05,
+      "loss": 0.1606,
+      "step": 650
+    },
+    {
+      "epoch": 3.91,
+      "learning_rate": 2.468354430379747e-05,
+      "loss": 0.1644,
+      "step": 700
+    }
+  ],
+  "max_steps": 895,
+  "num_train_epochs": 5,
+  "total_flos": 1342598254767024.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cd1277676cec5f2b9607565fd5a0aa1d3f91ab6f67d1bde5adab38c9a703c23
+size 2671