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: 0.5158100724220276
+
+f1: 0.7777777777777778
+
+precision: 0.6712328767123288
+
+recall: 0.9245283018867925
+
+auc: 0.8304930006086427
+
+accuracy: 0.7565217391304347

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 sha256:7e875fdd6ff9f1f63a626c3fd95c5d7570e7de8e48c447c151e30ef08bdfcec0
+size 532307280

checkpoint-230/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f75ddb123e777de62e46d6c1ae5261e997113f9585033a45c4cf54be482723ae
+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 sha256:982f6a76f8ce7001d605ce8f2bf04b6ba28511c7e2e2b30a14b1670adad81285
+size 1064

checkpoint-230/trainer_state.json

@@ -0,0 +1,390 @@
+{
+  "best_metric": 0.5158100724220276,
+  "best_model_checkpoint": "2ClassLarge/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": 2.4869840145111084,
+      "learning_rate": 4.310344827586207e-06,
+      "loss": 0.685,
+      "step": 5
+    },
+    {
+      "epoch": 0.08695652173913043,
+      "grad_norm": 4.935397624969482,
+      "learning_rate": 8.620689655172414e-06,
+      "loss": 0.6875,
+      "step": 10
+    },
+    {
+      "epoch": 0.13043478260869565,
+      "grad_norm": 4.38919734954834,
+      "learning_rate": 1.2931034482758622e-05,
+      "loss": 0.6703,
+      "step": 15
+    },
+    {
+      "epoch": 0.17391304347826086,
+      "grad_norm": 2.8880741596221924,
+      "learning_rate": 1.7241379310344828e-05,
+      "loss": 0.7051,
+      "step": 20
+    },
+    {
+      "epoch": 0.21739130434782608,
+      "grad_norm": 2.1519901752471924,
+      "learning_rate": 2.1551724137931033e-05,
+      "loss": 0.696,
+      "step": 25
+    },
+    {
+      "epoch": 0.2608695652173913,
+      "grad_norm": 2.6489181518554688,
+      "learning_rate": 2.5862068965517244e-05,
+      "loss": 0.6522,
+      "step": 30
+    },
+    {
+      "epoch": 0.30434782608695654,
+      "grad_norm": 8.696531295776367,
+      "learning_rate": 3.017241379310345e-05,
+      "loss": 0.7208,
+      "step": 35
+    },
+    {
+      "epoch": 0.34782608695652173,
+      "grad_norm": 3.1740002632141113,
+      "learning_rate": 3.4482758620689657e-05,
+      "loss": 0.6975,
+      "step": 40
+    },
+    {
+      "epoch": 0.391304347826087,
+      "grad_norm": 4.449029445648193,
+      "learning_rate": 3.8793103448275865e-05,
+      "loss": 0.7015,
+      "step": 45
+    },
+    {
+      "epoch": 0.43478260869565216,
+      "grad_norm": 3.1051077842712402,
+      "learning_rate": 4.3103448275862066e-05,
+      "loss": 0.8118,
+      "step": 50
+    },
+    {
+      "epoch": 0.4782608695652174,
+      "grad_norm": 2.311675786972046,
+      "learning_rate": 4.741379310344828e-05,
+      "loss": 0.6846,
+      "step": 55
+    },
+    {
+      "epoch": 0.5217391304347826,
+      "grad_norm": 4.207972526550293,
+      "learning_rate": 4.9806576402321086e-05,
+      "loss": 0.6656,
+      "step": 60
+    },
+    {
+      "epoch": 0.5652173913043478,
+      "grad_norm": 1.8182612657546997,
+      "learning_rate": 4.932301740812379e-05,
+      "loss": 0.6918,
+      "step": 65
+    },
+    {
+      "epoch": 0.6086956521739131,
+      "grad_norm": 6.007029056549072,
+      "learning_rate": 4.8839458413926506e-05,
+      "loss": 0.6666,
+      "step": 70
+    },
+    {
+      "epoch": 0.6521739130434783,
+      "grad_norm": 3.8037335872650146,
+      "learning_rate": 4.835589941972921e-05,
+      "loss": 0.6205,
+      "step": 75
+    },
+    {
+      "epoch": 0.6956521739130435,
+      "grad_norm": 4.0360822677612305,
+      "learning_rate": 4.787234042553192e-05,
+      "loss": 0.6171,
+      "step": 80
+    },
+    {
+      "epoch": 0.7391304347826086,
+      "grad_norm": 4.280089855194092,
+      "learning_rate": 4.738878143133462e-05,
+      "loss": 0.7091,
+      "step": 85
+    },
+    {
+      "epoch": 0.782608695652174,
+      "grad_norm": 3.4874963760375977,
+      "learning_rate": 4.690522243713733e-05,
+      "loss": 0.7116,
+      "step": 90
+    },
+    {
+      "epoch": 0.8260869565217391,
+      "grad_norm": 2.0585179328918457,
+      "learning_rate": 4.642166344294004e-05,
+      "loss": 0.7636,
+      "step": 95
+    },
+    {
+      "epoch": 0.8695652173913043,
+      "grad_norm": 2.7472143173217773,
+      "learning_rate": 4.5938104448742745e-05,
+      "loss": 0.516,
+      "step": 100
+    },
+    {
+      "epoch": 0.9130434782608695,
+      "grad_norm": 5.185933589935303,
+      "learning_rate": 4.545454545454546e-05,
+      "loss": 0.8768,
+      "step": 105
+    },
+    {
+      "epoch": 0.9565217391304348,
+      "grad_norm": 6.4161481857299805,
+      "learning_rate": 4.4970986460348165e-05,
+      "loss": 0.6838,
+      "step": 110
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 6.210981369018555,
+      "learning_rate": 4.448742746615087e-05,
+      "loss": 0.654,
+      "step": 115
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7304347826086957,
+      "eval_auc": 0.8009738283627511,
+      "eval_f1": 0.7394957983193278,
+      "eval_loss": 0.5908015370368958,
+      "eval_precision": 0.6666666666666666,
+      "eval_recall": 0.8301886792452831,
+      "eval_runtime": 146.397,
+      "eval_samples_per_second": 1.571,
+      "eval_steps_per_second": 0.102,
+      "step": 115
+    },
+    {
+      "epoch": 1.0434782608695652,
+      "grad_norm": 2.2397806644439697,
+      "learning_rate": 4.400386847195358e-05,
+      "loss": 0.6489,
+      "step": 120
+    },
+    {
+      "epoch": 1.0869565217391304,
+      "grad_norm": 2.275467872619629,
+      "learning_rate": 4.352030947775629e-05,
+      "loss": 0.6314,
+      "step": 125
+    },
+    {
+      "epoch": 1.1304347826086956,
+      "grad_norm": 2.6709554195404053,
+      "learning_rate": 4.3036750483559e-05,
+      "loss": 0.5121,
+      "step": 130
+    },
+    {
+      "epoch": 1.1739130434782608,
+      "grad_norm": 6.607785701751709,
+      "learning_rate": 4.2553191489361704e-05,
+      "loss": 0.4302,
+      "step": 135
+    },
+    {
+      "epoch": 1.2173913043478262,
+      "grad_norm": 18.070392608642578,
+      "learning_rate": 4.206963249516441e-05,
+      "loss": 0.6407,
+      "step": 140
+    },
+    {
+      "epoch": 1.2608695652173914,
+      "grad_norm": 3.231846570968628,
+      "learning_rate": 4.1586073500967124e-05,
+      "loss": 0.4142,
+      "step": 145
+    },
+    {
+      "epoch": 1.3043478260869565,
+      "grad_norm": 14.255928993225098,
+      "learning_rate": 4.110251450676983e-05,
+      "loss": 0.5749,
+      "step": 150
+    },
+    {
+      "epoch": 1.3478260869565217,
+      "grad_norm": 3.993816614151001,
+      "learning_rate": 4.061895551257254e-05,
+      "loss": 0.6971,
+      "step": 155
+    },
+    {
+      "epoch": 1.391304347826087,
+      "grad_norm": 6.085445404052734,
+      "learning_rate": 4.0135396518375244e-05,
+      "loss": 0.6003,
+      "step": 160
+    },
+    {
+      "epoch": 1.434782608695652,
+      "grad_norm": 4.129803657531738,
+      "learning_rate": 3.965183752417796e-05,
+      "loss": 0.6509,
+      "step": 165
+    },
+    {
+      "epoch": 1.4782608695652173,
+      "grad_norm": 4.400495529174805,
+      "learning_rate": 3.9168278529980664e-05,
+      "loss": 0.523,
+      "step": 170
+    },
+    {
+      "epoch": 1.5217391304347827,
+      "grad_norm": 4.820560932159424,
+      "learning_rate": 3.868471953578336e-05,
+      "loss": 0.4522,
+      "step": 175
+    },
+    {
+      "epoch": 1.5652173913043477,
+      "grad_norm": 13.549372673034668,
+      "learning_rate": 3.820116054158607e-05,
+      "loss": 0.5863,
+      "step": 180
+    },
+    {
+      "epoch": 1.608695652173913,
+      "grad_norm": 3.1626596450805664,
+      "learning_rate": 3.771760154738878e-05,
+      "loss": 0.4827,
+      "step": 185
+    },
+    {
+      "epoch": 1.6521739130434783,
+      "grad_norm": 3.709228992462158,
+      "learning_rate": 3.723404255319149e-05,
+      "loss": 0.5505,
+      "step": 190
+    },
+    {
+      "epoch": 1.6956521739130435,
+      "grad_norm": 4.613496780395508,
+      "learning_rate": 3.6750483558994196e-05,
+      "loss": 0.6062,
+      "step": 195
+    },
+    {
+      "epoch": 1.7391304347826086,
+      "grad_norm": 8.096386909484863,
+      "learning_rate": 3.62669245647969e-05,
+      "loss": 0.657,
+      "step": 200
+    },
+    {
+      "epoch": 1.7826086956521738,
+      "grad_norm": 7.13643741607666,
+      "learning_rate": 3.5783365570599616e-05,
+      "loss": 0.7452,
+      "step": 205
+    },
+    {
+      "epoch": 1.8260869565217392,
+      "grad_norm": 6.733407020568848,
+      "learning_rate": 3.529980657640232e-05,
+      "loss": 0.3675,
+      "step": 210
+    },
+    {
+      "epoch": 1.8695652173913042,
+      "grad_norm": 3.988879442214966,
+      "learning_rate": 3.481624758220503e-05,
+      "loss": 0.5059,
+      "step": 215
+    },
+    {
+      "epoch": 1.9130434782608696,
+      "grad_norm": 13.215219497680664,
+      "learning_rate": 3.4332688588007736e-05,
+      "loss": 0.5753,
+      "step": 220
+    },
+    {
+      "epoch": 1.9565217391304348,
+      "grad_norm": 20.60140037536621,
+      "learning_rate": 3.384912959381045e-05,
+      "loss": 0.6854,
+      "step": 225
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 7.606060981750488,
+      "learning_rate": 3.3365570599613155e-05,
+      "loss": 0.4706,
+      "step": 230
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7565217391304347,
+      "eval_auc": 0.8304930006086427,
+      "eval_f1": 0.7777777777777778,
+      "eval_loss": 0.5158100724220276,
+      "eval_precision": 0.6712328767123288,
+      "eval_recall": 0.9245283018867925,
+      "eval_runtime": 179.768,
+      "eval_samples_per_second": 1.279,
+      "eval_steps_per_second": 0.083,
+      "step": 230
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 575,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "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": 602791211679744.0,
+  "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 sha256:247bb778f59afd588c7d469992fb16aa065e3c43260f1c36d02137c15be47d63
+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 sha256:7e875fdd6ff9f1f63a626c3fd95c5d7570e7de8e48c447c151e30ef08bdfcec0
+size 532307280

runs/Sep22_02-26-55_r-manato003-dlsite-voice-rec-5mtoqgub-ebe78-a8qm5/events.out.tfevents.1758508017.r-manato003-dlsite-voice-rec-5mtoqgub-ebe78-a8qm5.63.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e60dee4e2ad56421f4c4057c8631751956bc9fa45355490aa082439c3d5856c9
-size 31254
+oid sha256:0b349a1b735166cd1a05e421783c243767cfe22bcaf6e3ac51f73801026c3194
+size 32549

runs/Sep22_02-26-55_r-manato003-dlsite-voice-rec-5mtoqgub-ebe78-a8qm5/events.out.tfevents.1758521866.r-manato003-dlsite-voice-rec-5mtoqgub-ebe78-a8qm5.63.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b292d489a9c9e2157a47fc1ceed68265ce57f7776d1dab16387b985f0739927
+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 sha256:247bb778f59afd588c7d469992fb16aa065e3c43260f1c36d02137c15be47d63
+size 5368

training_params.json

@@ -0,0 +1,30 @@
+{
+    "data_path": "2ClassLarge/autotrain-data",
+    "model": "studio-ousia/luke-japanese-base-lite",
+    "lr": 5e-05,
+    "epochs": 5,
+    "max_seq_length": 512,
+    "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": "2ClassLarge",
+    "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
+}