Upload 10 files

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "ku-nlp/deberta-v2-base-japanese",
+  "architectures": [
+    "DebertaV2ForMultipleChoice"
+  ],
+  "attention_head_size": 64,
+  "attention_probs_dropout_prob": 0.1,
+  "conv_act": "gelu",
+  "conv_kernel_size": 3,
+  "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-v2",
+  "norm_rel_ebd": "layer_norm",
+  "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": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.24.0",
+  "type_vocab_size": 0,
+  "vocab_size": 32000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9ab27b7995e8c83e72ef1b7f805e08850e639f7b955f4ee49c5832f4deccd8f
+size 449630179

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:488b1ff0ce7300ebc232215fc1bec5d036940b119b0362387b0e5718eee4b268
+size 13547

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eac87a4f2092caa77b0f78d1f505d6896579ea2218b5fcbbc566c4882a5104fd
+size 623

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c111c16e2e52366dcac46b886e40650bb843fe2938a65f5970271fc5697a127
+size 805061

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "keep_accents": true,
+  "mask_token": "[MASK]",
+  "name_or_path": "ku-nlp/deberta-v2-base-japanese",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": null,
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,52 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9964221824686943,
+  "global_step": 3350,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.45,
+      "learning_rate": 4.2546213476446036e-05,
+      "loss": 1.0003,
+      "step": 500
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 3.509242695289207e-05,
+      "loss": 0.8309,
+      "step": 1000
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 2.7638640429338103e-05,
+      "loss": 0.4982,
+      "step": 1500
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 2.018485390578414e-05,
+      "loss": 0.4074,
+      "step": 2000
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 1.2731067382230174e-05,
+      "loss": 0.2627,
+      "step": 2500
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 5.277280858676208e-06,
+      "loss": 0.169,
+      "step": 3000
+    }
+  ],
+  "max_steps": 3354,
+  "num_train_epochs": 3,
+  "total_flos": 4496639672966400.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b72526e6f5f042c5b1f6d2e8ce7abe8ff724f67d924f53d6402ac194b7ec89bf
+size 3439