Upload 9 files

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "ku-nlp/deberta-v2-tiny-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": 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:ac3953234ae143d9cd87d2fb1ed8556110bc0d08e33f7c60a41e027a59703b4b
+size 30929518

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0a1ebb02d7e41013711ead171b5c19091d620c4a72460d00570a22357fd0255
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bbdf7fdb4d261129ba27ec500dea6777a3f14cc0db6c54175225515c2031ae4
+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 +1,70 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "global_step": 560,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.39946380697050937,
+      "eval_f1": 0.39951655391963925,
+      "eval_loss": 1.6062450408935547,
+      "eval_precision": 0.3999992623496508,
+      "eval_recall": 0.39946380697050937,
+      "eval_runtime": 1.0662,
+      "eval_samples_per_second": 1049.495,
+      "eval_steps_per_second": 13.13,
+      "step": 112
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.4486148346738159,
+      "eval_f1": 0.44879096075280017,
+      "eval_loss": 1.557194471359253,
+      "eval_precision": 0.45032387618136827,
+      "eval_recall": 0.4486148346738159,
+      "eval_runtime": 0.9645,
+      "eval_samples_per_second": 1160.176,
+      "eval_steps_per_second": 14.515,
+      "step": 224
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.48078641644325293,
+      "eval_f1": 0.48044306647023427,
+      "eval_loss": 1.4841872453689575,
+      "eval_precision": 0.48189831555981366,
+      "eval_recall": 0.48078641644325293,
+      "eval_runtime": 0.9592,
+      "eval_samples_per_second": 1166.651,
+      "eval_steps_per_second": 14.596,
+      "step": 336
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5102770330652369,
+      "eval_f1": 0.5099868458795241,
+      "eval_loss": 1.4472650289535522,
+      "eval_precision": 0.5119449274550995,
+      "eval_recall": 0.5102770330652369,
+      "eval_runtime": 1.0814,
+      "eval_samples_per_second": 1034.774,
+      "eval_steps_per_second": 12.946,
+      "step": 448
+    },
+    {
+      "epoch": 4.46,
+      "learning_rate": 1.0714285714285714e-06,
+      "loss": 1.5567,
+      "step": 500
+    }
+  ],
+  "max_steps": 560,
+  "num_train_epochs": 5,
+  "total_flos": 127329432988800.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2480d44c6dbb53526d5342191c3533d6103582e25f8747f7a193fe07233b72a9
+size 3643