Upload folder using huggingface_hub

README.md

@@ -0,0 +1,26 @@
+
+---
+tags:
+- autotrain
+- text-regression
+base_model: distilbert/distilbert-base-cased
+widget:
+- text: "I love AutoTrain"
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Text Regression
+
+## Validation Metrics
+loss: 0.04696119576692581
+
+mse: 0.046961188316345215
+
+mae: 0.16446031630039215
+
+r2: 0.5230978727340698
+
+rmse: 0.216705302926221
+
+explained_variance: 0.5387225151062012

checkpoint-228/config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "distilbert/distilbert-base-cased",
+  "_num_labels": 1,
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "target"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "target": 0
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "problem_type": "regression",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.0",
+  "vocab_size": 28996
+}

checkpoint-228/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:705d4b85898e039d6d32d8851592d90fd631c16105efa2c7695c4151dbf63f1f
+size 263141604

checkpoint-228/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d10e2a2a2cce3afe07a6e0e6bbaf108b3cd6776d133d26e7f3cd233ba2731bbe
+size 526342522

checkpoint-228/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da289b7c136fb4f0be3b3b8bcd07137af289665b63b3ed6bfe09a03c11be6ecf
+size 13990

checkpoint-228/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c573af203cd37dc5e2d965d1183bd1cf3b240b8b0449f0532e927393eeb729c8
+size 1064

checkpoint-228/trainer_state.json

@@ -0,0 +1,613 @@
+{
+  "best_metric": 0.04696119576692581,
+  "best_model_checkpoint": "autotrain-bert-tone/checkpoint-228",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 228,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.039473684210526314,
+      "grad_norm": 1.268290400505066,
+      "learning_rate": 6.521739130434783e-06,
+      "loss": 0.1598,
+      "step": 3
+    },
+    {
+      "epoch": 0.07894736842105263,
+      "grad_norm": 2.4602935314178467,
+      "learning_rate": 1.3043478260869566e-05,
+      "loss": 0.1091,
+      "step": 6
+    },
+    {
+      "epoch": 0.11842105263157894,
+      "grad_norm": 3.914072275161743,
+      "learning_rate": 1.956521739130435e-05,
+      "loss": 0.0937,
+      "step": 9
+    },
+    {
+      "epoch": 0.15789473684210525,
+      "grad_norm": 0.8280628323554993,
+      "learning_rate": 2.608695652173913e-05,
+      "loss": 0.0976,
+      "step": 12
+    },
+    {
+      "epoch": 0.19736842105263158,
+      "grad_norm": 1.6599308252334595,
+      "learning_rate": 3.260869565217392e-05,
+      "loss": 0.106,
+      "step": 15
+    },
+    {
+      "epoch": 0.23684210526315788,
+      "grad_norm": 1.8458030223846436,
+      "learning_rate": 3.91304347826087e-05,
+      "loss": 0.0606,
+      "step": 18
+    },
+    {
+      "epoch": 0.27631578947368424,
+      "grad_norm": 2.4959943294525146,
+      "learning_rate": 4.565217391304348e-05,
+      "loss": 0.1703,
+      "step": 21
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 1.732654333114624,
+      "learning_rate": 4.975609756097561e-05,
+      "loss": 0.0757,
+      "step": 24
+    },
+    {
+      "epoch": 0.35526315789473684,
+      "grad_norm": 1.4400056600570679,
+      "learning_rate": 4.902439024390244e-05,
+      "loss": 0.0641,
+      "step": 27
+    },
+    {
+      "epoch": 0.39473684210526316,
+      "grad_norm": 4.92896032333374,
+      "learning_rate": 4.829268292682927e-05,
+      "loss": 0.1041,
+      "step": 30
+    },
+    {
+      "epoch": 0.4342105263157895,
+      "grad_norm": 1.7027392387390137,
+      "learning_rate": 4.75609756097561e-05,
+      "loss": 0.0797,
+      "step": 33
+    },
+    {
+      "epoch": 0.47368421052631576,
+      "grad_norm": 1.845708966255188,
+      "learning_rate": 4.682926829268293e-05,
+      "loss": 0.1277,
+      "step": 36
+    },
+    {
+      "epoch": 0.5131578947368421,
+      "grad_norm": 2.450996160507202,
+      "learning_rate": 4.609756097560976e-05,
+      "loss": 0.0925,
+      "step": 39
+    },
+    {
+      "epoch": 0.5526315789473685,
+      "grad_norm": 1.4300225973129272,
+      "learning_rate": 4.536585365853659e-05,
+      "loss": 0.0921,
+      "step": 42
+    },
+    {
+      "epoch": 0.5921052631578947,
+      "grad_norm": 1.470561146736145,
+      "learning_rate": 4.4634146341463416e-05,
+      "loss": 0.0468,
+      "step": 45
+    },
+    {
+      "epoch": 0.631578947368421,
+      "grad_norm": 1.5631119012832642,
+      "learning_rate": 4.390243902439025e-05,
+      "loss": 0.0562,
+      "step": 48
+    },
+    {
+      "epoch": 0.6710526315789473,
+      "grad_norm": 2.8870129585266113,
+      "learning_rate": 4.317073170731707e-05,
+      "loss": 0.0699,
+      "step": 51
+    },
+    {
+      "epoch": 0.7105263157894737,
+      "grad_norm": 3.935586929321289,
+      "learning_rate": 4.2439024390243905e-05,
+      "loss": 0.0971,
+      "step": 54
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 1.9553509950637817,
+      "learning_rate": 4.170731707317073e-05,
+      "loss": 0.0584,
+      "step": 57
+    },
+    {
+      "epoch": 0.7894736842105263,
+      "grad_norm": 2.7788777351379395,
+      "learning_rate": 4.097560975609756e-05,
+      "loss": 0.0691,
+      "step": 60
+    },
+    {
+      "epoch": 0.8289473684210527,
+      "grad_norm": 1.335891604423523,
+      "learning_rate": 4.0243902439024395e-05,
+      "loss": 0.0866,
+      "step": 63
+    },
+    {
+      "epoch": 0.868421052631579,
+      "grad_norm": 2.5660781860351562,
+      "learning_rate": 3.951219512195122e-05,
+      "loss": 0.0626,
+      "step": 66
+    },
+    {
+      "epoch": 0.9078947368421053,
+      "grad_norm": 1.0248908996582031,
+      "learning_rate": 3.878048780487805e-05,
+      "loss": 0.1038,
+      "step": 69
+    },
+    {
+      "epoch": 0.9473684210526315,
+      "grad_norm": 1.2834587097167969,
+      "learning_rate": 3.804878048780488e-05,
+      "loss": 0.0724,
+      "step": 72
+    },
+    {
+      "epoch": 0.9868421052631579,
+      "grad_norm": 1.8682374954223633,
+      "learning_rate": 3.731707317073171e-05,
+      "loss": 0.06,
+      "step": 75
+    },
+    {
+      "epoch": 1.0,
+      "eval_explained_variance": 0.4236792325973511,
+      "eval_loss": 0.10101328790187836,
+      "eval_mae": 0.25109994411468506,
+      "eval_mse": 0.10101328045129776,
+      "eval_r2": -0.025814056396484375,
+      "eval_rmse": 0.317825864981593,
+      "eval_runtime": 12.7804,
+      "eval_samples_per_second": 11.815,
+      "eval_steps_per_second": 0.782,
+      "step": 76
+    },
+    {
+      "epoch": 1.0263157894736843,
+      "grad_norm": 2.012385606765747,
+      "learning_rate": 3.6585365853658535e-05,
+      "loss": 0.07,
+      "step": 78
+    },
+    {
+      "epoch": 1.0657894736842106,
+      "grad_norm": 1.5033577680587769,
+      "learning_rate": 3.585365853658537e-05,
+      "loss": 0.0595,
+      "step": 81
+    },
+    {
+      "epoch": 1.1052631578947367,
+      "grad_norm": 1.9349753856658936,
+      "learning_rate": 3.512195121951219e-05,
+      "loss": 0.0519,
+      "step": 84
+    },
+    {
+      "epoch": 1.1447368421052633,
+      "grad_norm": 1.1432642936706543,
+      "learning_rate": 3.4390243902439025e-05,
+      "loss": 0.0406,
+      "step": 87
+    },
+    {
+      "epoch": 1.1842105263157894,
+      "grad_norm": 1.307976245880127,
+      "learning_rate": 3.365853658536586e-05,
+      "loss": 0.0312,
+      "step": 90
+    },
+    {
+      "epoch": 1.2236842105263157,
+      "grad_norm": 2.569735050201416,
+      "learning_rate": 3.292682926829269e-05,
+      "loss": 0.0546,
+      "step": 93
+    },
+    {
+      "epoch": 1.263157894736842,
+      "grad_norm": 1.499475359916687,
+      "learning_rate": 3.2195121951219514e-05,
+      "loss": 0.0388,
+      "step": 96
+    },
+    {
+      "epoch": 1.3026315789473684,
+      "grad_norm": 2.22824764251709,
+      "learning_rate": 3.146341463414634e-05,
+      "loss": 0.0473,
+      "step": 99
+    },
+    {
+      "epoch": 1.3421052631578947,
+      "grad_norm": 2.3919763565063477,
+      "learning_rate": 3.073170731707317e-05,
+      "loss": 0.0633,
+      "step": 102
+    },
+    {
+      "epoch": 1.381578947368421,
+      "grad_norm": 2.487248420715332,
+      "learning_rate": 3e-05,
+      "loss": 0.0761,
+      "step": 105
+    },
+    {
+      "epoch": 1.4210526315789473,
+      "grad_norm": 1.0264114141464233,
+      "learning_rate": 2.926829268292683e-05,
+      "loss": 0.0243,
+      "step": 108
+    },
+    {
+      "epoch": 1.4605263157894737,
+      "grad_norm": 1.970423936843872,
+      "learning_rate": 2.8536585365853658e-05,
+      "loss": 0.0415,
+      "step": 111
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.9041996598243713,
+      "learning_rate": 2.780487804878049e-05,
+      "loss": 0.032,
+      "step": 114
+    },
+    {
+      "epoch": 1.5394736842105263,
+      "grad_norm": 1.3935425281524658,
+      "learning_rate": 2.707317073170732e-05,
+      "loss": 0.0447,
+      "step": 117
+    },
+    {
+      "epoch": 1.5789473684210527,
+      "grad_norm": 1.299230694770813,
+      "learning_rate": 2.6341463414634148e-05,
+      "loss": 0.0362,
+      "step": 120
+    },
+    {
+      "epoch": 1.618421052631579,
+      "grad_norm": 1.1066516637802124,
+      "learning_rate": 2.5609756097560977e-05,
+      "loss": 0.0172,
+      "step": 123
+    },
+    {
+      "epoch": 1.6578947368421053,
+      "grad_norm": 1.3599709272384644,
+      "learning_rate": 2.4878048780487805e-05,
+      "loss": 0.0248,
+      "step": 126
+    },
+    {
+      "epoch": 1.6973684210526314,
+      "grad_norm": 1.9708794355392456,
+      "learning_rate": 2.4146341463414634e-05,
+      "loss": 0.0593,
+      "step": 129
+    },
+    {
+      "epoch": 1.736842105263158,
+      "grad_norm": 1.0266876220703125,
+      "learning_rate": 2.3414634146341466e-05,
+      "loss": 0.0247,
+      "step": 132
+    },
+    {
+      "epoch": 1.776315789473684,
+      "grad_norm": 2.81319260597229,
+      "learning_rate": 2.2682926829268295e-05,
+      "loss": 0.0489,
+      "step": 135
+    },
+    {
+      "epoch": 1.8157894736842106,
+      "grad_norm": 0.9068326950073242,
+      "learning_rate": 2.1951219512195124e-05,
+      "loss": 0.0494,
+      "step": 138
+    },
+    {
+      "epoch": 1.8552631578947367,
+      "grad_norm": 0.703267514705658,
+      "learning_rate": 2.1219512195121953e-05,
+      "loss": 0.0473,
+      "step": 141
+    },
+    {
+      "epoch": 1.8947368421052633,
+      "grad_norm": 1.852679967880249,
+      "learning_rate": 2.048780487804878e-05,
+      "loss": 0.0359,
+      "step": 144
+    },
+    {
+      "epoch": 1.9342105263157894,
+      "grad_norm": 1.1914632320404053,
+      "learning_rate": 1.975609756097561e-05,
+      "loss": 0.0228,
+      "step": 147
+    },
+    {
+      "epoch": 1.973684210526316,
+      "grad_norm": 1.3655986785888672,
+      "learning_rate": 1.902439024390244e-05,
+      "loss": 0.0281,
+      "step": 150
+    },
+    {
+      "epoch": 2.0,
+      "eval_explained_variance": 0.4443961977958679,
+      "eval_loss": 0.05540888383984566,
+      "eval_mae": 0.18671312928199768,
+      "eval_mse": 0.055408887565135956,
+      "eval_r2": 0.43730950355529785,
+      "eval_rmse": 0.23539092498466452,
+      "eval_runtime": 13.0934,
+      "eval_samples_per_second": 11.533,
+      "eval_steps_per_second": 0.764,
+      "step": 152
+    },
+    {
+      "epoch": 2.013157894736842,
+      "grad_norm": 1.1334549188613892,
+      "learning_rate": 1.8292682926829268e-05,
+      "loss": 0.0353,
+      "step": 153
+    },
+    {
+      "epoch": 2.0526315789473686,
+      "grad_norm": 1.1114447116851807,
+      "learning_rate": 1.7560975609756096e-05,
+      "loss": 0.0164,
+      "step": 156
+    },
+    {
+      "epoch": 2.0921052631578947,
+      "grad_norm": 1.5025893449783325,
+      "learning_rate": 1.682926829268293e-05,
+      "loss": 0.0221,
+      "step": 159
+    },
+    {
+      "epoch": 2.1315789473684212,
+      "grad_norm": 0.915424644947052,
+      "learning_rate": 1.6097560975609757e-05,
+      "loss": 0.0126,
+      "step": 162
+    },
+    {
+      "epoch": 2.1710526315789473,
+      "grad_norm": 1.6687657833099365,
+      "learning_rate": 1.5365853658536586e-05,
+      "loss": 0.0235,
+      "step": 165
+    },
+    {
+      "epoch": 2.2105263157894735,
+      "grad_norm": 1.230404257774353,
+      "learning_rate": 1.4634146341463415e-05,
+      "loss": 0.0232,
+      "step": 168
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 0.943490207195282,
+      "learning_rate": 1.3902439024390245e-05,
+      "loss": 0.0152,
+      "step": 171
+    },
+    {
+      "epoch": 2.2894736842105265,
+      "grad_norm": 0.6173422932624817,
+      "learning_rate": 1.3170731707317074e-05,
+      "loss": 0.0126,
+      "step": 174
+    },
+    {
+      "epoch": 2.3289473684210527,
+      "grad_norm": 1.986954689025879,
+      "learning_rate": 1.2439024390243903e-05,
+      "loss": 0.0211,
+      "step": 177
+    },
+    {
+      "epoch": 2.3684210526315788,
+      "grad_norm": 0.650972843170166,
+      "learning_rate": 1.1707317073170733e-05,
+      "loss": 0.01,
+      "step": 180
+    },
+    {
+      "epoch": 2.4078947368421053,
+      "grad_norm": 2.853421688079834,
+      "learning_rate": 1.0975609756097562e-05,
+      "loss": 0.0286,
+      "step": 183
+    },
+    {
+      "epoch": 2.4473684210526314,
+      "grad_norm": 1.0729972124099731,
+      "learning_rate": 1.024390243902439e-05,
+      "loss": 0.02,
+      "step": 186
+    },
+    {
+      "epoch": 2.486842105263158,
+      "grad_norm": 0.8739410638809204,
+      "learning_rate": 9.51219512195122e-06,
+      "loss": 0.0124,
+      "step": 189
+    },
+    {
+      "epoch": 2.526315789473684,
+      "grad_norm": 0.8854183554649353,
+      "learning_rate": 8.780487804878048e-06,
+      "loss": 0.0117,
+      "step": 192
+    },
+    {
+      "epoch": 2.5657894736842106,
+      "grad_norm": 1.0242164134979248,
+      "learning_rate": 8.048780487804879e-06,
+      "loss": 0.0293,
+      "step": 195
+    },
+    {
+      "epoch": 2.6052631578947367,
+      "grad_norm": 1.419499158859253,
+      "learning_rate": 7.317073170731707e-06,
+      "loss": 0.0283,
+      "step": 198
+    },
+    {
+      "epoch": 2.6447368421052633,
+      "grad_norm": 0.8783360123634338,
+      "learning_rate": 6.585365853658537e-06,
+      "loss": 0.0318,
+      "step": 201
+    },
+    {
+      "epoch": 2.6842105263157894,
+      "grad_norm": 0.4939420521259308,
+      "learning_rate": 5.853658536585367e-06,
+      "loss": 0.0107,
+      "step": 204
+    },
+    {
+      "epoch": 2.723684210526316,
+      "grad_norm": 1.3545787334442139,
+      "learning_rate": 5.121951219512195e-06,
+      "loss": 0.0125,
+      "step": 207
+    },
+    {
+      "epoch": 2.763157894736842,
+      "grad_norm": 1.0449341535568237,
+      "learning_rate": 4.390243902439024e-06,
+      "loss": 0.0211,
+      "step": 210
+    },
+    {
+      "epoch": 2.8026315789473686,
+      "grad_norm": 1.5390199422836304,
+      "learning_rate": 3.6585365853658537e-06,
+      "loss": 0.0243,
+      "step": 213
+    },
+    {
+      "epoch": 2.8421052631578947,
+      "grad_norm": 1.0012524127960205,
+      "learning_rate": 2.9268292682926833e-06,
+      "loss": 0.026,
+      "step": 216
+    },
+    {
+      "epoch": 2.8815789473684212,
+      "grad_norm": 0.413464218378067,
+      "learning_rate": 2.195121951219512e-06,
+      "loss": 0.0155,
+      "step": 219
+    },
+    {
+      "epoch": 2.9210526315789473,
+      "grad_norm": 0.6869584918022156,
+      "learning_rate": 1.4634146341463416e-06,
+      "loss": 0.0174,
+      "step": 222
+    },
+    {
+      "epoch": 2.9605263157894735,
+      "grad_norm": 1.1535204648971558,
+      "learning_rate": 7.317073170731708e-07,
+      "loss": 0.0122,
+      "step": 225
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.9466148614883423,
+      "learning_rate": 0.0,
+      "loss": 0.0198,
+      "step": 228
+    },
+    {
+      "epoch": 3.0,
+      "eval_explained_variance": 0.5387225151062012,
+      "eval_loss": 0.04696119576692581,
+      "eval_mae": 0.16446031630039215,
+      "eval_mse": 0.046961188316345215,
+      "eval_r2": 0.5230978727340698,
+      "eval_rmse": 0.216705302926221,
+      "eval_runtime": 12.6393,
+      "eval_samples_per_second": 11.947,
+      "eval_steps_per_second": 0.791,
+      "step": 228
+    }
+  ],
+  "logging_steps": 3,
+  "max_steps": 228,
+  "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": 1
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 60006661438464.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-228/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42cb593a413645126d2d1fc5c868a0cd79926c751e6e34f7e579d72a21ec645b
+size 5368

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "distilbert/distilbert-base-cased",
+  "_num_labels": 1,
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "target"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "target": 0
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "problem_type": "regression",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.0",
+  "vocab_size": 28996
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:705d4b85898e039d6d32d8851592d90fd631c16105efa2c7695c4151dbf63f1f
+size 263141604

runs/Jul13_14-25-53_r-sebsa-asai-newstextbert-wpktfh4a-f38c3-0o175/events.out.tfevents.1752416754.r-sebsa-asai-newstextbert-wpktfh4a-f38c3-0o175.108.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:177198aa076736b880abd4c924207261b4ff4e8010daacb63a55864358d0db26
-size 20511
+oid sha256:9409fee11df43ec818eab7faede27077a1814ae256852a9017238ecee7ce0750
+size 22863

runs/Jul13_14-25-53_r-sebsa-asai-newstextbert-wpktfh4a-f38c3-0o175/events.out.tfevents.1752417444.r-sebsa-asai-newstextbert-wpktfh4a-f38c3-0o175.108.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0673a8b599992c59f83cbc3e1bd6902cb67bfadd691bbec8f551fa4deba2cd03
+size 609

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42cb593a413645126d2d1fc5c868a0cd79926c751e6e34f7e579d72a21ec645b
+size 5368

training_params.json

@@ -0,0 +1,30 @@
+{
+    "data_path": "autotrain-bert-tone/autotrain-data",
+    "model": "distilbert/distilbert-base-cased",
+    "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": "autotrain-bert-tone",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "eval_strategy": "epoch",
+    "username": "Sebsa",
+    "log": "tensorboard",
+    "early_stopping_patience": 5,
+    "early_stopping_threshold": 0.01
+}