End of training

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "total_flos": 987700271455806.0,
+    "train_loss": 0.7023818914368158,
+    "train_runtime": 241.6228,
+    "train_samples_per_second": 100.239,
+    "train_steps_per_second": 6.274
+}

config.json

@@ -0,0 +1,55 @@
+{
+  "_name_or_path": "kisti/korscideberta",
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_head_size": 64,
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6
+  },
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "padding_idx": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.1",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce9ac7b1a67b3e194e5a10a4e74f6d58877744b5309cff332dd142a44f06631d
+size 737784566

runs/Apr18_08-45-33_main1/events.out.tfevents.1744965979.main1.4756.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8debd799f6f563c12b0c5f712136f47ae46ca142016a5c350eaf379721eea02
+size 6958

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "total_flos": 987700271455806.0,
+    "train_loss": 0.7023818914368158,
+    "train_runtime": 241.6228,
+    "train_samples_per_second": 100.239,
+    "train_steps_per_second": 6.274
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6e3a2eae63b3ad970981b3e38f5ac42c59d42125adb5d7af383e09b4993f7cf
+size 4344