Upload 9 files

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "ku-nlp/deberta-v2-tiny-japanese",
+  "architectures": [
+    "DebertaV2ForQuestionAnswering"
+  ],
+  "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": 192,
+  "initializer_range": 0.02,
+  "intermediate_size": 768,
+  "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": 3,
+  "num_hidden_layers": 3,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 192,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.0",
+  "type_vocab_size": 0,
+  "vocab_size": 32000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2980d9b9547014b9ae3386c3fc3761c48ed82d1aca7b9bf7c7796bd9fccb3532
+size 30781416

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67282f09198b697cc4fc01f64ac810a9faecc9245d490af9e6af2888efb966fa
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca4561bc1749c5a3fba45634d1c61a0e7259acf46ec9632bac55bcc55100e52c
+size 627

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]"
+}

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "keep_accents": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,106 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "global_step": 7880,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.63,
+      "learning_rate": 4.7429305912596405e-05,
+      "loss": 4.0354,
+      "step": 500
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 4.42159383033419e-05,
+      "loss": 3.1227,
+      "step": 1000
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 4.1002570694087404e-05,
+      "loss": 2.8006,
+      "step": 1500
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 3.7789203084832907e-05,
+      "loss": 2.5518,
+      "step": 2000
+    },
+    {
+      "epoch": 3.17,
+      "learning_rate": 3.45758354755784e-05,
+      "loss": 2.4603,
+      "step": 2500
+    },
+    {
+      "epoch": 3.81,
+      "learning_rate": 3.1362467866323906e-05,
+      "loss": 2.3477,
+      "step": 3000
+    },
+    {
+      "epoch": 4.44,
+      "learning_rate": 2.8149100257069412e-05,
+      "loss": 2.2727,
+      "step": 3500
+    },
+    {
+      "epoch": 5.08,
+      "learning_rate": 2.493573264781491e-05,
+      "loss": 2.2234,
+      "step": 4000
+    },
+    {
+      "epoch": 5.71,
+      "learning_rate": 2.1722365038560414e-05,
+      "loss": 2.1827,
+      "step": 4500
+    },
+    {
+      "epoch": 6.35,
+      "learning_rate": 1.8508997429305914e-05,
+      "loss": 2.1235,
+      "step": 5000
+    },
+    {
+      "epoch": 6.98,
+      "learning_rate": 1.5295629820051416e-05,
+      "loss": 2.1156,
+      "step": 5500
+    },
+    {
+      "epoch": 7.61,
+      "learning_rate": 1.2082262210796916e-05,
+      "loss": 2.0648,
+      "step": 6000
+    },
+    {
+      "epoch": 8.25,
+      "learning_rate": 8.868894601542417e-06,
+      "loss": 2.0744,
+      "step": 6500
+    },
+    {
+      "epoch": 8.88,
+      "learning_rate": 5.6555269922879175e-06,
+      "loss": 2.0276,
+      "step": 7000
+    },
+    {
+      "epoch": 9.52,
+      "learning_rate": 2.442159383033419e-06,
+      "loss": 2.0262,
+      "step": 7500
+    }
+  ],
+  "max_steps": 7880,
+  "num_train_epochs": 10,
+  "total_flos": 502540376306640.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af23ce0d47c8222f71350e653c43deba3688944ca835cd5d11e5e4446a00d7cc
+size 3643