Upload folder using huggingface_hub

README.md

@@ -0,0 +1,27 @@
+
+---
+library_name: transformers
+tags:
+- autotrain
+- text-classification
+base_model: studio-ousia/luke-japanese-base-lite
+widget:
+- text: "I love AutoTrain"
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Text Classification
+
+## Validation Metrics
+loss: 0.5321555137634277
+
+f1: 0.7355371900826446
+
+precision: 0.6544117647058824
+
+recall: 0.839622641509434
+
+auc: 0.8266129032258065
+
+accuracy: 0.7217391304347827

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<ent2>": 32771,
+  "<ent>": 32770
+}

checkpoint-230/config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "studio-ousia/luke-japanese-base-lite",
+  "_num_labels": 2,
+  "architectures": [
+    "LukeForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bert_model_name": "models/luke-japanese/hf_xlm_roberta",
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "cls_entity_prediction": false,
+  "entity_emb_size": 256,
+  "entity_vocab_size": 4,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "\u60aa\u3044",
+    "1": "\u826f\u3044"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "\u60aa\u3044": 0,
+    "\u826f\u3044": 1
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "luke",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "use_entity_aware_attention": true,
+  "vocab_size": 32772
+}

checkpoint-230/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de13ef21ccae838fb30a5ec29dd128906a5bfc49538967ccc3b269ce2043e573
+size 532307280

checkpoint-230/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c83aee057460784cfcc3a6b63cfbda532203292f4c7a25f41918a4960e3909e9
+size 889863098

checkpoint-230/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a00ae46a38a73f402956850b524194acd54becd011fcc7d9c07b576676cd3a60
+size 13990

checkpoint-230/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99d2857ac1c5e019d8e0780861a630b7d7dd2080a27821bbdf29e9280ee1c0f2
+size 1064

checkpoint-230/trainer_state.json

@@ -0,0 +1,390 @@
+{
+  "best_metric": 0.5321555137634277,
+  "best_model_checkpoint": "2classification/checkpoint-230",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 230,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.043478260869565216,
+      "grad_norm": 3.3017044067382812,
+      "learning_rate": 7.142857142857143e-06,
+      "loss": 0.701,
+      "step": 5
+    },
+    {
+      "epoch": 0.08695652173913043,
+      "grad_norm": 3.861875295639038,
+      "learning_rate": 1.4285714285714285e-05,
+      "loss": 0.6724,
+      "step": 10
+    },
+    {
+      "epoch": 0.13043478260869565,
+      "grad_norm": 5.9016523361206055,
+      "learning_rate": 2.1428571428571428e-05,
+      "loss": 0.7108,
+      "step": 15
+    },
+    {
+      "epoch": 0.17391304347826086,
+      "grad_norm": 2.023663282394409,
+      "learning_rate": 2.857142857142857e-05,
+      "loss": 0.7146,
+      "step": 20
+    },
+    {
+      "epoch": 0.21739130434782608,
+      "grad_norm": 2.016728401184082,
+      "learning_rate": 3.571428571428572e-05,
+      "loss": 0.7238,
+      "step": 25
+    },
+    {
+      "epoch": 0.2608695652173913,
+      "grad_norm": 1.6572303771972656,
+      "learning_rate": 4.2857142857142856e-05,
+      "loss": 0.6849,
+      "step": 30
+    },
+    {
+      "epoch": 0.30434782608695654,
+      "grad_norm": 4.739016532897949,
+      "learning_rate": 5e-05,
+      "loss": 0.7218,
+      "step": 35
+    },
+    {
+      "epoch": 0.34782608695652173,
+      "grad_norm": 2.0643484592437744,
+      "learning_rate": 4.9193548387096775e-05,
+      "loss": 0.6941,
+      "step": 40
+    },
+    {
+      "epoch": 0.391304347826087,
+      "grad_norm": 2.2051498889923096,
+      "learning_rate": 4.8387096774193554e-05,
+      "loss": 0.6904,
+      "step": 45
+    },
+    {
+      "epoch": 0.43478260869565216,
+      "grad_norm": 4.221965789794922,
+      "learning_rate": 4.7580645161290326e-05,
+      "loss": 0.7442,
+      "step": 50
+    },
+    {
+      "epoch": 0.4782608695652174,
+      "grad_norm": 3.326643466949463,
+      "learning_rate": 4.67741935483871e-05,
+      "loss": 0.7255,
+      "step": 55
+    },
+    {
+      "epoch": 0.5217391304347826,
+      "grad_norm": 5.108890533447266,
+      "learning_rate": 4.596774193548387e-05,
+      "loss": 0.6994,
+      "step": 60
+    },
+    {
+      "epoch": 0.5652173913043478,
+      "grad_norm": 1.680823802947998,
+      "learning_rate": 4.516129032258064e-05,
+      "loss": 0.6759,
+      "step": 65
+    },
+    {
+      "epoch": 0.6086956521739131,
+      "grad_norm": 4.85138463973999,
+      "learning_rate": 4.435483870967742e-05,
+      "loss": 0.6261,
+      "step": 70
+    },
+    {
+      "epoch": 0.6521739130434783,
+      "grad_norm": 4.047025680541992,
+      "learning_rate": 4.3548387096774194e-05,
+      "loss": 0.5949,
+      "step": 75
+    },
+    {
+      "epoch": 0.6956521739130435,
+      "grad_norm": 3.6327199935913086,
+      "learning_rate": 4.2741935483870973e-05,
+      "loss": 0.8464,
+      "step": 80
+    },
+    {
+      "epoch": 0.7391304347826086,
+      "grad_norm": 3.9471940994262695,
+      "learning_rate": 4.1935483870967746e-05,
+      "loss": 0.7577,
+      "step": 85
+    },
+    {
+      "epoch": 0.782608695652174,
+      "grad_norm": 4.150089263916016,
+      "learning_rate": 4.112903225806452e-05,
+      "loss": 0.6673,
+      "step": 90
+    },
+    {
+      "epoch": 0.8260869565217391,
+      "grad_norm": 2.2822818756103516,
+      "learning_rate": 4.032258064516129e-05,
+      "loss": 0.7113,
+      "step": 95
+    },
+    {
+      "epoch": 0.8695652173913043,
+      "grad_norm": 5.6378984451293945,
+      "learning_rate": 3.951612903225806e-05,
+      "loss": 0.6567,
+      "step": 100
+    },
+    {
+      "epoch": 0.9130434782608695,
+      "grad_norm": 1.9879374504089355,
+      "learning_rate": 3.870967741935484e-05,
+      "loss": 0.7019,
+      "step": 105
+    },
+    {
+      "epoch": 0.9565217391304348,
+      "grad_norm": 6.7003631591796875,
+      "learning_rate": 3.7903225806451614e-05,
+      "loss": 0.6505,
+      "step": 110
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 9.337882041931152,
+      "learning_rate": 3.7096774193548386e-05,
+      "loss": 0.6924,
+      "step": 115
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7043478260869566,
+      "eval_auc": 0.7728241022519781,
+      "eval_f1": 0.6991150442477876,
+      "eval_loss": 0.607258677482605,
+      "eval_precision": 0.6583333333333333,
+      "eval_recall": 0.7452830188679245,
+      "eval_runtime": 35.0981,
+      "eval_samples_per_second": 6.553,
+      "eval_steps_per_second": 0.427,
+      "step": 115
+    },
+    {
+      "epoch": 1.0434782608695652,
+      "grad_norm": 1.8164705038070679,
+      "learning_rate": 3.6290322580645165e-05,
+      "loss": 0.6439,
+      "step": 120
+    },
+    {
+      "epoch": 1.0869565217391304,
+      "grad_norm": 2.1826255321502686,
+      "learning_rate": 3.548387096774194e-05,
+      "loss": 0.647,
+      "step": 125
+    },
+    {
+      "epoch": 1.1304347826086956,
+      "grad_norm": 2.288874626159668,
+      "learning_rate": 3.467741935483872e-05,
+      "loss": 0.6064,
+      "step": 130
+    },
+    {
+      "epoch": 1.1739130434782608,
+      "grad_norm": 2.857973337173462,
+      "learning_rate": 3.387096774193548e-05,
+      "loss": 0.5087,
+      "step": 135
+    },
+    {
+      "epoch": 1.2173913043478262,
+      "grad_norm": 4.019787788391113,
+      "learning_rate": 3.306451612903226e-05,
+      "loss": 0.5771,
+      "step": 140
+    },
+    {
+      "epoch": 1.2608695652173914,
+      "grad_norm": 5.981603622436523,
+      "learning_rate": 3.2258064516129034e-05,
+      "loss": 0.5869,
+      "step": 145
+    },
+    {
+      "epoch": 1.3043478260869565,
+      "grad_norm": 12.450459480285645,
+      "learning_rate": 3.1451612903225806e-05,
+      "loss": 0.6328,
+      "step": 150
+    },
+    {
+      "epoch": 1.3478260869565217,
+      "grad_norm": 9.469613075256348,
+      "learning_rate": 3.0645161290322585e-05,
+      "loss": 0.6025,
+      "step": 155
+    },
+    {
+      "epoch": 1.391304347826087,
+      "grad_norm": 4.401791095733643,
+      "learning_rate": 2.9838709677419357e-05,
+      "loss": 0.4786,
+      "step": 160
+    },
+    {
+      "epoch": 1.434782608695652,
+      "grad_norm": 5.496943950653076,
+      "learning_rate": 2.9032258064516133e-05,
+      "loss": 0.7632,
+      "step": 165
+    },
+    {
+      "epoch": 1.4782608695652173,
+      "grad_norm": 2.510056495666504,
+      "learning_rate": 2.822580645161291e-05,
+      "loss": 0.412,
+      "step": 170
+    },
+    {
+      "epoch": 1.5217391304347827,
+      "grad_norm": 4.305450439453125,
+      "learning_rate": 2.7419354838709678e-05,
+      "loss": 0.4254,
+      "step": 175
+    },
+    {
+      "epoch": 1.5652173913043477,
+      "grad_norm": 4.428637504577637,
+      "learning_rate": 2.661290322580645e-05,
+      "loss": 0.6168,
+      "step": 180
+    },
+    {
+      "epoch": 1.608695652173913,
+      "grad_norm": 4.408801555633545,
+      "learning_rate": 2.5806451612903226e-05,
+      "loss": 0.5885,
+      "step": 185
+    },
+    {
+      "epoch": 1.6521739130434783,
+      "grad_norm": 5.0507097244262695,
+      "learning_rate": 2.5e-05,
+      "loss": 0.5953,
+      "step": 190
+    },
+    {
+      "epoch": 1.6956521739130435,
+      "grad_norm": 7.350249290466309,
+      "learning_rate": 2.4193548387096777e-05,
+      "loss": 0.5695,
+      "step": 195
+    },
+    {
+      "epoch": 1.7391304347826086,
+      "grad_norm": 7.184178352355957,
+      "learning_rate": 2.338709677419355e-05,
+      "loss": 0.6336,
+      "step": 200
+    },
+    {
+      "epoch": 1.7826086956521738,
+      "grad_norm": 4.202939987182617,
+      "learning_rate": 2.258064516129032e-05,
+      "loss": 0.7637,
+      "step": 205
+    },
+    {
+      "epoch": 1.8260869565217392,
+      "grad_norm": 6.9584431648254395,
+      "learning_rate": 2.1774193548387097e-05,
+      "loss": 0.5885,
+      "step": 210
+    },
+    {
+      "epoch": 1.8695652173913042,
+      "grad_norm": 3.880800724029541,
+      "learning_rate": 2.0967741935483873e-05,
+      "loss": 0.5884,
+      "step": 215
+    },
+    {
+      "epoch": 1.9130434782608696,
+      "grad_norm": 5.578256130218506,
+      "learning_rate": 2.0161290322580645e-05,
+      "loss": 0.5477,
+      "step": 220
+    },
+    {
+      "epoch": 1.9565217391304348,
+      "grad_norm": 5.322207450866699,
+      "learning_rate": 1.935483870967742e-05,
+      "loss": 0.5686,
+      "step": 225
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 5.499088287353516,
+      "learning_rate": 1.8548387096774193e-05,
+      "loss": 0.4809,
+      "step": 230
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7217391304347827,
+      "eval_auc": 0.8266129032258065,
+      "eval_f1": 0.7355371900826446,
+      "eval_loss": 0.5321555137634277,
+      "eval_precision": 0.6544117647058824,
+      "eval_recall": 0.839622641509434,
+      "eval_runtime": 33.1845,
+      "eval_samples_per_second": 6.931,
+      "eval_steps_per_second": 0.452,
+      "step": 230
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 345,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 0.01
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 150697802919936.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-230/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:554915da28fbd19adcee6c63005ebe3c27c6d5174ad2ddb01c22b93fd5948bfb
+size 5368

config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "studio-ousia/luke-japanese-base-lite",
+  "_num_labels": 2,
+  "architectures": [
+    "LukeForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bert_model_name": "models/luke-japanese/hf_xlm_roberta",
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "cls_entity_prediction": false,
+  "entity_emb_size": 256,
+  "entity_vocab_size": 4,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "\u60aa\u3044",
+    "1": "\u826f\u3044"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "\u60aa\u3044": 0,
+    "\u826f\u3044": 1
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "luke",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "use_entity_aware_attention": true,
+  "vocab_size": 32772
+}

entity_vocab.json

@@ -0,0 +1,6 @@
+{
+  "[MASK2]": 3,
+  "[MASK]": 0,
+  "[PAD]": 2,
+  "[UNK]": 1
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de13ef21ccae838fb30a5ec29dd128906a5bfc49538967ccc3b269ce2043e573
+size 532307280

runs/Sep22_00-59-01_r-manato003-dlsite-voice-rec-ip32f285-4552b-n9vba/events.out.tfevents.1758502744.r-manato003-dlsite-voice-rec-ip32f285-4552b-n9vba.63.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d8048e4a26995dfd1949376e9ca7713d5dbc936fd649fc1280bc9724ad9bfee
-size 17146
+oid sha256:326cc783775f1c7994c7d3e9a65884671e8d27031e0a3d35d9110857c786a62f
+size 21817

runs/Sep22_00-59-01_r-manato003-dlsite-voice-rec-ip32f285-4552b-n9vba/events.out.tfevents.1758504439.r-manato003-dlsite-voice-rec-ip32f285-4552b-n9vba.63.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8336f04b736207eb0ae8da9e9ba17e2278c206ec0d6dbeb822632388da0d8f69
+size 607

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8b73a5e054936c920cf5b7d1ec21ce9c281977078269963beb821c6c86fbff7
+size 841889

special_tokens_map.json

@@ -0,0 +1,95 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<ent>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<ent2>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<ent>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<ent2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<ent>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<ent2>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,105 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32769": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32770": {
+      "content": "<ent>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32771": {
+      "content": "<ent2>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<ent>",
+    "<ent2>",
+    "<ent>",
+    "<ent2>",
+    "<ent>",
+    "<ent2>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "entity_mask2_token": "[MASK2]",
+  "entity_mask_token": "[MASK]",
+  "entity_pad_token": "[PAD]",
+  "entity_token_1": {
+    "__type": "AddedToken",
+    "content": "<ent>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false,
+    "special": false
+  },
+  "entity_token_2": {
+    "__type": "AddedToken",
+    "content": "<ent2>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false,
+    "special": false
+  },
+  "entity_unk_token": "[UNK]",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "max_entity_length": 32,
+  "max_mention_length": 30,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "task": null,
+  "tokenizer_class": "MLukeTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:554915da28fbd19adcee6c63005ebe3c27c6d5174ad2ddb01c22b93fd5948bfb
+size 5368

training_params.json

@@ -0,0 +1,30 @@
+{
+    "data_path": "2classification/autotrain-data",
+    "model": "studio-ousia/luke-japanese-base-lite",
+    "lr": 5e-05,
+    "epochs": 3,
+    "max_seq_length": 128,
+    "batch_size": 8,
+    "warmup_ratio": 0.1,
+    "gradient_accumulation": 1,
+    "optimizer": "adamw_torch",
+    "scheduler": "linear",
+    "weight_decay": 0.0,
+    "max_grad_norm": 1.0,
+    "seed": 42,
+    "train_split": "train",
+    "valid_split": "validation",
+    "text_column": "autotrain_text",
+    "target_column": "autotrain_label",
+    "logging_steps": -1,
+    "project_name": "2classification",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "eval_strategy": "epoch",
+    "username": "manato003",
+    "log": "tensorboard",
+    "early_stopping_patience": 5,
+    "early_stopping_threshold": 0.01
+}