Upload folder using huggingface_hub

README.md

@@ -0,0 +1,36 @@
+
+---
+tags:
+- autotrain
+- text-classification
+base_model: distilbert/distilbert-base-uncased-finetuned-sst-2-english
+widget:
+- text: "I love AutoTrain"
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Text Classification
+
+## Validation Metrics
+loss: 0.47395700216293335
+
+f1_macro: 0.8585052497990947
+
+f1_micro: 0.8928571428571429
+
+f1_weighted: 0.8907561750703225
+
+precision_macro: 0.8764483580832203
+
+precision_micro: 0.8928571428571429
+
+precision_weighted: 0.8908864823138299
+
+recall_macro: 0.8441908044288117
+
+recall_micro: 0.8928571428571429
+
+recall_weighted: 0.8928571428571429
+
+accuracy: 0.8928571428571429

checkpoint-1050/config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "distilbert/distilbert-base-uncased-finetuned-sst-2-english",
+  "_num_labels": 3,
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "finetuning_task": "sst-2",
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "negative",
+    "1": "neutral",
+    "2": "positive"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "negative": 0,
+    "neutral": 1,
+    "positive": 2
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.0",
+  "vocab_size": 30522
+}

checkpoint-1050/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b7ca4ed782ed1f9891987b5bd00feff2452af5f279c0e6a96d7d964a86027eb
+size 267835644

checkpoint-1050/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bba31f1b3f0640cd5d7c81b3f463deab0c5dd146ae4b310db2f6d77ec1ac4974
+size 535730554

checkpoint-1050/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13b790f16e11d019cf924994526f17b90b959297cc3c5ce41e2e2919f40573d7
+size 13990

checkpoint-1050/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad6be9079b0bd0f72616a2c9ae43a9ce03b8c525c0ed6f35bd38fca82083bced
+size 1064

checkpoint-1050/trainer_state.json

@@ -0,0 +1,523 @@
+{
+  "best_metric": 0.47395700216293335,
+  "best_model_checkpoint": "autotrain-4d7s5-yxads/checkpoint-1050",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1050,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04857142857142857,
+      "grad_norm": 5.717668056488037,
+      "learning_rate": 8.095238095238097e-06,
+      "loss": 1.0368,
+      "step": 17
+    },
+    {
+      "epoch": 0.09714285714285714,
+      "grad_norm": 4.925649166107178,
+      "learning_rate": 1.6190476190476193e-05,
+      "loss": 1.0002,
+      "step": 34
+    },
+    {
+      "epoch": 0.1457142857142857,
+      "grad_norm": 4.120390892028809,
+      "learning_rate": 2.4285714285714288e-05,
+      "loss": 0.9781,
+      "step": 51
+    },
+    {
+      "epoch": 0.19428571428571428,
+      "grad_norm": 7.446722984313965,
+      "learning_rate": 3.2380952380952386e-05,
+      "loss": 0.8574,
+      "step": 68
+    },
+    {
+      "epoch": 0.24285714285714285,
+      "grad_norm": 5.055674076080322,
+      "learning_rate": 4.047619047619048e-05,
+      "loss": 0.8284,
+      "step": 85
+    },
+    {
+      "epoch": 0.2914285714285714,
+      "grad_norm": 6.370545387268066,
+      "learning_rate": 4.8571428571428576e-05,
+      "loss": 0.7786,
+      "step": 102
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 5.569090843200684,
+      "learning_rate": 4.925925925925926e-05,
+      "loss": 0.813,
+      "step": 119
+    },
+    {
+      "epoch": 0.38857142857142857,
+      "grad_norm": 9.335224151611328,
+      "learning_rate": 4.835978835978836e-05,
+      "loss": 0.7567,
+      "step": 136
+    },
+    {
+      "epoch": 0.43714285714285717,
+      "grad_norm": 7.3107476234436035,
+      "learning_rate": 4.746031746031746e-05,
+      "loss": 0.6932,
+      "step": 153
+    },
+    {
+      "epoch": 0.4857142857142857,
+      "grad_norm": 4.684781551361084,
+      "learning_rate": 4.656084656084656e-05,
+      "loss": 0.5975,
+      "step": 170
+    },
+    {
+      "epoch": 0.5342857142857143,
+      "grad_norm": 6.342061996459961,
+      "learning_rate": 4.5661375661375666e-05,
+      "loss": 0.7048,
+      "step": 187
+    },
+    {
+      "epoch": 0.5828571428571429,
+      "grad_norm": 1.3669540882110596,
+      "learning_rate": 4.476190476190477e-05,
+      "loss": 0.4949,
+      "step": 204
+    },
+    {
+      "epoch": 0.6314285714285715,
+      "grad_norm": 8.368840217590332,
+      "learning_rate": 4.386243386243387e-05,
+      "loss": 0.4151,
+      "step": 221
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 4.3537468910217285,
+      "learning_rate": 4.296296296296296e-05,
+      "loss": 0.6339,
+      "step": 238
+    },
+    {
+      "epoch": 0.7285714285714285,
+      "grad_norm": 3.9406490325927734,
+      "learning_rate": 4.2063492063492065e-05,
+      "loss": 0.4407,
+      "step": 255
+    },
+    {
+      "epoch": 0.7771428571428571,
+      "grad_norm": 9.089990615844727,
+      "learning_rate": 4.1164021164021166e-05,
+      "loss": 0.587,
+      "step": 272
+    },
+    {
+      "epoch": 0.8257142857142857,
+      "grad_norm": 8.443167686462402,
+      "learning_rate": 4.026455026455027e-05,
+      "loss": 0.6481,
+      "step": 289
+    },
+    {
+      "epoch": 0.8742857142857143,
+      "grad_norm": 6.344438076019287,
+      "learning_rate": 3.936507936507937e-05,
+      "loss": 0.361,
+      "step": 306
+    },
+    {
+      "epoch": 0.9228571428571428,
+      "grad_norm": 10.625802993774414,
+      "learning_rate": 3.846560846560846e-05,
+      "loss": 0.5475,
+      "step": 323
+    },
+    {
+      "epoch": 0.9714285714285714,
+      "grad_norm": 14.712811470031738,
+      "learning_rate": 3.7566137566137564e-05,
+      "loss": 0.4962,
+      "step": 340
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8385714285714285,
+      "eval_f1_macro": 0.7883351622987025,
+      "eval_f1_micro": 0.8385714285714285,
+      "eval_f1_weighted": 0.8341744255013881,
+      "eval_loss": 0.5001112818717957,
+      "eval_precision_macro": 0.8197149152283288,
+      "eval_precision_micro": 0.8385714285714285,
+      "eval_precision_weighted": 0.8359588728159495,
+      "eval_recall_macro": 0.7651883911896363,
+      "eval_recall_micro": 0.8385714285714285,
+      "eval_recall_weighted": 0.8385714285714285,
+      "eval_runtime": 76.1749,
+      "eval_samples_per_second": 9.189,
+      "eval_steps_per_second": 0.578,
+      "step": 350
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 5.372379779815674,
+      "learning_rate": 3.6666666666666666e-05,
+      "loss": 0.4164,
+      "step": 357
+    },
+    {
+      "epoch": 1.0685714285714285,
+      "grad_norm": 27.94418716430664,
+      "learning_rate": 3.5767195767195774e-05,
+      "loss": 0.2832,
+      "step": 374
+    },
+    {
+      "epoch": 1.1171428571428572,
+      "grad_norm": 1.799539566040039,
+      "learning_rate": 3.486772486772487e-05,
+      "loss": 0.3711,
+      "step": 391
+    },
+    {
+      "epoch": 1.1657142857142857,
+      "grad_norm": 0.3417045474052429,
+      "learning_rate": 3.396825396825397e-05,
+      "loss": 0.242,
+      "step": 408
+    },
+    {
+      "epoch": 1.2142857142857142,
+      "grad_norm": 28.81987762451172,
+      "learning_rate": 3.306878306878307e-05,
+      "loss": 0.4427,
+      "step": 425
+    },
+    {
+      "epoch": 1.262857142857143,
+      "grad_norm": 26.209278106689453,
+      "learning_rate": 3.216931216931217e-05,
+      "loss": 0.4501,
+      "step": 442
+    },
+    {
+      "epoch": 1.3114285714285714,
+      "grad_norm": 13.091431617736816,
+      "learning_rate": 3.1269841269841274e-05,
+      "loss": 0.2545,
+      "step": 459
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "grad_norm": 5.050440311431885,
+      "learning_rate": 3.037037037037037e-05,
+      "loss": 0.285,
+      "step": 476
+    },
+    {
+      "epoch": 1.4085714285714286,
+      "grad_norm": 0.9298226833343506,
+      "learning_rate": 2.9470899470899473e-05,
+      "loss": 0.3392,
+      "step": 493
+    },
+    {
+      "epoch": 1.457142857142857,
+      "grad_norm": 0.5489844679832458,
+      "learning_rate": 2.857142857142857e-05,
+      "loss": 0.3678,
+      "step": 510
+    },
+    {
+      "epoch": 1.5057142857142858,
+      "grad_norm": 10.013340950012207,
+      "learning_rate": 2.7671957671957672e-05,
+      "loss": 0.3737,
+      "step": 527
+    },
+    {
+      "epoch": 1.5542857142857143,
+      "grad_norm": 0.32325175404548645,
+      "learning_rate": 2.677248677248677e-05,
+      "loss": 0.314,
+      "step": 544
+    },
+    {
+      "epoch": 1.6028571428571428,
+      "grad_norm": 11.575883865356445,
+      "learning_rate": 2.5873015873015878e-05,
+      "loss": 0.4452,
+      "step": 561
+    },
+    {
+      "epoch": 1.6514285714285715,
+      "grad_norm": 6.775808334350586,
+      "learning_rate": 2.4973544973544973e-05,
+      "loss": 0.3117,
+      "step": 578
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 8.51729965209961,
+      "learning_rate": 2.4074074074074074e-05,
+      "loss": 0.3418,
+      "step": 595
+    },
+    {
+      "epoch": 1.7485714285714287,
+      "grad_norm": 7.481166839599609,
+      "learning_rate": 2.3174603174603175e-05,
+      "loss": 0.444,
+      "step": 612
+    },
+    {
+      "epoch": 1.7971428571428572,
+      "grad_norm": 18.95454216003418,
+      "learning_rate": 2.2275132275132277e-05,
+      "loss": 0.1702,
+      "step": 629
+    },
+    {
+      "epoch": 1.8457142857142856,
+      "grad_norm": 7.999231338500977,
+      "learning_rate": 2.1375661375661378e-05,
+      "loss": 0.3524,
+      "step": 646
+    },
+    {
+      "epoch": 1.8942857142857141,
+      "grad_norm": 31.50586700439453,
+      "learning_rate": 2.0476190476190476e-05,
+      "loss": 0.1909,
+      "step": 663
+    },
+    {
+      "epoch": 1.9428571428571428,
+      "grad_norm": 29.285133361816406,
+      "learning_rate": 1.9576719576719577e-05,
+      "loss": 0.2772,
+      "step": 680
+    },
+    {
+      "epoch": 1.9914285714285715,
+      "grad_norm": 3.731112241744995,
+      "learning_rate": 1.867724867724868e-05,
+      "loss": 0.3267,
+      "step": 697
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8757142857142857,
+      "eval_f1_macro": 0.8377118790538569,
+      "eval_f1_micro": 0.8757142857142857,
+      "eval_f1_weighted": 0.872517301229779,
+      "eval_loss": 0.4786055088043213,
+      "eval_precision_macro": 0.8588521140737896,
+      "eval_precision_micro": 0.8757142857142857,
+      "eval_precision_weighted": 0.8740051281374396,
+      "eval_recall_macro": 0.8253140067976269,
+      "eval_recall_micro": 0.8757142857142857,
+      "eval_recall_weighted": 0.8757142857142857,
+      "eval_runtime": 73.9486,
+      "eval_samples_per_second": 9.466,
+      "eval_steps_per_second": 0.595,
+      "step": 700
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 0.29130664467811584,
+      "learning_rate": 1.777777777777778e-05,
+      "loss": 0.1401,
+      "step": 714
+    },
+    {
+      "epoch": 2.0885714285714285,
+      "grad_norm": 0.48758184909820557,
+      "learning_rate": 1.6878306878306878e-05,
+      "loss": 0.1069,
+      "step": 731
+    },
+    {
+      "epoch": 2.137142857142857,
+      "grad_norm": 0.32419487833976746,
+      "learning_rate": 1.597883597883598e-05,
+      "loss": 0.1531,
+      "step": 748
+    },
+    {
+      "epoch": 2.185714285714286,
+      "grad_norm": 5.234611511230469,
+      "learning_rate": 1.5079365079365079e-05,
+      "loss": 0.1346,
+      "step": 765
+    },
+    {
+      "epoch": 2.2342857142857144,
+      "grad_norm": 0.22019706666469574,
+      "learning_rate": 1.4179894179894179e-05,
+      "loss": 0.1516,
+      "step": 782
+    },
+    {
+      "epoch": 2.282857142857143,
+      "grad_norm": 0.05589751526713371,
+      "learning_rate": 1.3280423280423282e-05,
+      "loss": 0.0221,
+      "step": 799
+    },
+    {
+      "epoch": 2.3314285714285714,
+      "grad_norm": 1.0066980123519897,
+      "learning_rate": 1.2380952380952381e-05,
+      "loss": 0.134,
+      "step": 816
+    },
+    {
+      "epoch": 2.38,
+      "grad_norm": 0.26126623153686523,
+      "learning_rate": 1.1481481481481482e-05,
+      "loss": 0.1686,
+      "step": 833
+    },
+    {
+      "epoch": 2.4285714285714284,
+      "grad_norm": 0.10336403548717499,
+      "learning_rate": 1.0582010582010582e-05,
+      "loss": 0.1286,
+      "step": 850
+    },
+    {
+      "epoch": 2.4771428571428573,
+      "grad_norm": 3.996295690536499,
+      "learning_rate": 9.682539682539683e-06,
+      "loss": 0.1906,
+      "step": 867
+    },
+    {
+      "epoch": 2.525714285714286,
+      "grad_norm": 0.06981644779443741,
+      "learning_rate": 8.783068783068783e-06,
+      "loss": 0.3068,
+      "step": 884
+    },
+    {
+      "epoch": 2.5742857142857143,
+      "grad_norm": 50.26215362548828,
+      "learning_rate": 7.883597883597884e-06,
+      "loss": 0.1845,
+      "step": 901
+    },
+    {
+      "epoch": 2.6228571428571428,
+      "grad_norm": 0.20857813954353333,
+      "learning_rate": 6.984126984126985e-06,
+      "loss": 0.1038,
+      "step": 918
+    },
+    {
+      "epoch": 2.6714285714285713,
+      "grad_norm": 24.78173828125,
+      "learning_rate": 6.0846560846560845e-06,
+      "loss": 0.1554,
+      "step": 935
+    },
+    {
+      "epoch": 2.7199999999999998,
+      "grad_norm": 1.273622751235962,
+      "learning_rate": 5.185185185185185e-06,
+      "loss": 0.1497,
+      "step": 952
+    },
+    {
+      "epoch": 2.7685714285714287,
+      "grad_norm": 0.16568787395954132,
+      "learning_rate": 4.285714285714286e-06,
+      "loss": 0.2257,
+      "step": 969
+    },
+    {
+      "epoch": 2.817142857142857,
+      "grad_norm": 0.4252100884914398,
+      "learning_rate": 3.3862433862433868e-06,
+      "loss": 0.0084,
+      "step": 986
+    },
+    {
+      "epoch": 2.8657142857142857,
+      "grad_norm": 0.06408315896987915,
+      "learning_rate": 2.486772486772487e-06,
+      "loss": 0.1151,
+      "step": 1003
+    },
+    {
+      "epoch": 2.914285714285714,
+      "grad_norm": 0.11793053150177002,
+      "learning_rate": 1.5873015873015873e-06,
+      "loss": 0.1673,
+      "step": 1020
+    },
+    {
+      "epoch": 2.9628571428571426,
+      "grad_norm": 0.14011150598526,
+      "learning_rate": 6.878306878306879e-07,
+      "loss": 0.0355,
+      "step": 1037
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8928571428571429,
+      "eval_f1_macro": 0.8585052497990947,
+      "eval_f1_micro": 0.8928571428571429,
+      "eval_f1_weighted": 0.8907561750703225,
+      "eval_loss": 0.47395700216293335,
+      "eval_precision_macro": 0.8764483580832203,
+      "eval_precision_micro": 0.8928571428571429,
+      "eval_precision_weighted": 0.8908864823138299,
+      "eval_recall_macro": 0.8441908044288117,
+      "eval_recall_micro": 0.8928571428571429,
+      "eval_recall_weighted": 0.8928571428571429,
+      "eval_runtime": 66.4114,
+      "eval_samples_per_second": 10.54,
+      "eval_steps_per_second": 0.663,
+      "step": 1050
+    }
+  ],
+  "logging_steps": 17,
+  "max_steps": 1050,
+  "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": 278186498150400.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1050/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ddbcc28b85ff0e9811bc65e60a4362a1609ffc9fcf41ceade79ddce3eada840
+size 5240

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "distilbert/distilbert-base-uncased-finetuned-sst-2-english",
+  "_num_labels": 3,
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "finetuning_task": "sst-2",
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "negative",
+    "1": "neutral",
+    "2": "positive"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "negative": 0,
+    "neutral": 1,
+    "positive": 2
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.0",
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b7ca4ed782ed1f9891987b5bd00feff2452af5f279c0e6a96d7d964a86027eb
+size 267835644

runs/Oct12_06-52-38_r-maheshshastrakar-distilbertsentiment-k6l4djkv-22be7-jojzs/events.out.tfevents.1728715962.r-maheshshastrakar-distilbertsentiment-k6l4djkv-22be7-jojzs.121.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d0973362f98472de952983e18331c4042869dd687ea2efce88f9df09b1a038d
-size 18393
+oid sha256:51b021f0c95a21ec91554246459ffc8fd16e4453ca9aeb15f66bd6ac14e56e78
+size 20846

runs/Oct12_06-52-38_r-maheshshastrakar-distilbertsentiment-k6l4djkv-22be7-jojzs/events.out.tfevents.1728719531.r-maheshshastrakar-distilbertsentiment-k6l4djkv-22be7-jojzs.121.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1bfad7e6c3405ebe4422f94f141815637f93e19daaca12e74ebc27d5603544c
+size 921

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 +1,57 @@
+{
+  "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": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "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 sha256:6ddbcc28b85ff0e9811bc65e60a4362a1609ffc9fcf41ceade79ddce3eada840
+size 5240

training_params.json

@@ -0,0 +1,30 @@
+{
+    "data_path": "autotrain-4d7s5-yxads/autotrain-data",
+    "model": "distilbert/distilbert-base-uncased-finetuned-sst-2-english",
+    "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-4d7s5-yxads",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "eval_strategy": "epoch",
+    "username": "maheshshastrakar",
+    "log": "tensorboard",
+    "early_stopping_patience": 5,
+    "early_stopping_threshold": 0.01
+}