Upload folder using huggingface_hub

README.md

@@ -0,0 +1,27 @@
+
+---
+library_name: transformers
+tags:
+- autotrain
+- text-classification
+base_model: PhaseTechnologies/RoBERTo
+widget:
+- text: "I love AutoTrain"
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Text Classification
+
+## Validation Metrics
+loss: 0.6174320578575134
+
+f1: 0.7039106145251397
+
+precision: 0.5625
+
+recall: 0.9402985074626866
+
+auc: 0.6388059701492537
+
+accuracy: 0.5826771653543307

checkpoint-192/config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "PhaseTechnologies/RoBERTo",
+  "_num_labels": 2,
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "negative",
+    "1": "positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "negative": 0,
+    "positive": 1
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "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,
+  "vocab_size": 50265
+}

checkpoint-192/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80587731ab8e5b200a0728a5733b2a1b8923e0126144d73de0789a50435c83c1
+size 498612824

checkpoint-192/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90a5bc84dbfbbe560c44e89209eb668df77aed4f4bd316bf35fa7b037a41b49d
+size 997339898

checkpoint-192/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dae0a712aab025231b6917338ad8b187ca1612891f36edbbc1a378c77b1d1327
+size 13990

checkpoint-192/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1dbcbdddd816590a07c0eb69151a7b1b1e0691c09b77d885ff9b903c65bb5bf
+size 1064

checkpoint-192/trainer_state.json

@@ -0,0 +1,529 @@
+{
+  "best_metric": 0.6174320578575134,
+  "best_model_checkpoint": "autotrain-dtpk3-gqgvr/checkpoint-192",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 192,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.046875,
+      "grad_norm": 44.394126892089844,
+      "learning_rate": 7.5e-06,
+      "loss": 1.503,
+      "step": 3
+    },
+    {
+      "epoch": 0.09375,
+      "grad_norm": 13.359213829040527,
+      "learning_rate": 1.5e-05,
+      "loss": 1.0466,
+      "step": 6
+    },
+    {
+      "epoch": 0.140625,
+      "grad_norm": 15.327120780944824,
+      "learning_rate": 2.25e-05,
+      "loss": 0.7621,
+      "step": 9
+    },
+    {
+      "epoch": 0.1875,
+      "grad_norm": 17.224138259887695,
+      "learning_rate": 3e-05,
+      "loss": 0.8117,
+      "step": 12
+    },
+    {
+      "epoch": 0.234375,
+      "grad_norm": 5.552957534790039,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.7111,
+      "step": 15
+    },
+    {
+      "epoch": 0.28125,
+      "grad_norm": 2.9177513122558594,
+      "learning_rate": 4.5e-05,
+      "loss": 0.6722,
+      "step": 18
+    },
+    {
+      "epoch": 0.328125,
+      "grad_norm": 3.265030860900879,
+      "learning_rate": 4.97093023255814e-05,
+      "loss": 0.685,
+      "step": 21
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 5.11839485168457,
+      "learning_rate": 4.883720930232558e-05,
+      "loss": 0.6925,
+      "step": 24
+    },
+    {
+      "epoch": 0.421875,
+      "grad_norm": 8.2102632522583,
+      "learning_rate": 4.796511627906977e-05,
+      "loss": 0.7709,
+      "step": 27
+    },
+    {
+      "epoch": 0.46875,
+      "grad_norm": 1.8216426372528076,
+      "learning_rate": 4.709302325581396e-05,
+      "loss": 0.637,
+      "step": 30
+    },
+    {
+      "epoch": 0.515625,
+      "grad_norm": 2.6032655239105225,
+      "learning_rate": 4.622093023255814e-05,
+      "loss": 0.6599,
+      "step": 33
+    },
+    {
+      "epoch": 0.5625,
+      "grad_norm": 3.79473614692688,
+      "learning_rate": 4.5348837209302326e-05,
+      "loss": 0.644,
+      "step": 36
+    },
+    {
+      "epoch": 0.609375,
+      "grad_norm": 7.0303730964660645,
+      "learning_rate": 4.447674418604651e-05,
+      "loss": 0.6299,
+      "step": 39
+    },
+    {
+      "epoch": 0.65625,
+      "grad_norm": 4.775753498077393,
+      "learning_rate": 4.36046511627907e-05,
+      "loss": 0.6821,
+      "step": 42
+    },
+    {
+      "epoch": 0.703125,
+      "grad_norm": 7.69596004486084,
+      "learning_rate": 4.2732558139534885e-05,
+      "loss": 0.6634,
+      "step": 45
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 4.036675453186035,
+      "learning_rate": 4.186046511627907e-05,
+      "loss": 0.7426,
+      "step": 48
+    },
+    {
+      "epoch": 0.796875,
+      "grad_norm": 3.5866127014160156,
+      "learning_rate": 4.098837209302326e-05,
+      "loss": 0.7704,
+      "step": 51
+    },
+    {
+      "epoch": 0.84375,
+      "grad_norm": 5.381412506103516,
+      "learning_rate": 4.0116279069767444e-05,
+      "loss": 0.6672,
+      "step": 54
+    },
+    {
+      "epoch": 0.890625,
+      "grad_norm": 1.6377614736557007,
+      "learning_rate": 3.924418604651163e-05,
+      "loss": 0.6648,
+      "step": 57
+    },
+    {
+      "epoch": 0.9375,
+      "grad_norm": 1.5304895639419556,
+      "learning_rate": 3.837209302325582e-05,
+      "loss": 0.5987,
+      "step": 60
+    },
+    {
+      "epoch": 0.984375,
+      "grad_norm": 1.769390344619751,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.6857,
+      "step": 63
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5905511811023622,
+      "eval_auc": 0.6097014925373134,
+      "eval_f1": 0.4222222222222222,
+      "eval_loss": 0.6238564848899841,
+      "eval_precision": 0.8260869565217391,
+      "eval_recall": 0.2835820895522388,
+      "eval_runtime": 22.6769,
+      "eval_samples_per_second": 5.6,
+      "eval_steps_per_second": 0.353,
+      "step": 64
+    },
+    {
+      "epoch": 1.03125,
+      "grad_norm": 4.968754291534424,
+      "learning_rate": 3.662790697674418e-05,
+      "loss": 0.7279,
+      "step": 66
+    },
+    {
+      "epoch": 1.078125,
+      "grad_norm": 1.7518460750579834,
+      "learning_rate": 3.5755813953488376e-05,
+      "loss": 0.6384,
+      "step": 69
+    },
+    {
+      "epoch": 1.125,
+      "grad_norm": 5.8542799949646,
+      "learning_rate": 3.488372093023256e-05,
+      "loss": 0.5118,
+      "step": 72
+    },
+    {
+      "epoch": 1.171875,
+      "grad_norm": 13.197107315063477,
+      "learning_rate": 3.401162790697674e-05,
+      "loss": 0.6106,
+      "step": 75
+    },
+    {
+      "epoch": 1.21875,
+      "grad_norm": 5.81817102432251,
+      "learning_rate": 3.313953488372093e-05,
+      "loss": 0.6194,
+      "step": 78
+    },
+    {
+      "epoch": 1.265625,
+      "grad_norm": 2.4604616165161133,
+      "learning_rate": 3.226744186046512e-05,
+      "loss": 0.576,
+      "step": 81
+    },
+    {
+      "epoch": 1.3125,
+      "grad_norm": 3.2092373371124268,
+      "learning_rate": 3.13953488372093e-05,
+      "loss": 0.5786,
+      "step": 84
+    },
+    {
+      "epoch": 1.359375,
+      "grad_norm": 2.21498441696167,
+      "learning_rate": 3.052325581395349e-05,
+      "loss": 0.4971,
+      "step": 87
+    },
+    {
+      "epoch": 1.40625,
+      "grad_norm": 1.9152885675430298,
+      "learning_rate": 2.9651162790697678e-05,
+      "loss": 0.6565,
+      "step": 90
+    },
+    {
+      "epoch": 1.453125,
+      "grad_norm": 22.123859405517578,
+      "learning_rate": 2.8779069767441864e-05,
+      "loss": 0.6366,
+      "step": 93
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 1.3859971761703491,
+      "learning_rate": 2.7906976744186048e-05,
+      "loss": 0.5938,
+      "step": 96
+    },
+    {
+      "epoch": 1.546875,
+      "grad_norm": 2.3298566341400146,
+      "learning_rate": 2.703488372093023e-05,
+      "loss": 0.6305,
+      "step": 99
+    },
+    {
+      "epoch": 1.59375,
+      "grad_norm": 1.73346745967865,
+      "learning_rate": 2.616279069767442e-05,
+      "loss": 0.5451,
+      "step": 102
+    },
+    {
+      "epoch": 1.640625,
+      "grad_norm": 21.07562255859375,
+      "learning_rate": 2.5290697674418607e-05,
+      "loss": 0.692,
+      "step": 105
+    },
+    {
+      "epoch": 1.6875,
+      "grad_norm": 1.426858901977539,
+      "learning_rate": 2.441860465116279e-05,
+      "loss": 0.611,
+      "step": 108
+    },
+    {
+      "epoch": 1.734375,
+      "grad_norm": 1.2272080183029175,
+      "learning_rate": 2.354651162790698e-05,
+      "loss": 0.5374,
+      "step": 111
+    },
+    {
+      "epoch": 1.78125,
+      "grad_norm": 4.342379093170166,
+      "learning_rate": 2.2674418604651163e-05,
+      "loss": 0.5966,
+      "step": 114
+    },
+    {
+      "epoch": 1.828125,
+      "grad_norm": 1.1373143196105957,
+      "learning_rate": 2.180232558139535e-05,
+      "loss": 0.5905,
+      "step": 117
+    },
+    {
+      "epoch": 1.875,
+      "grad_norm": 1.238311529159546,
+      "learning_rate": 2.0930232558139536e-05,
+      "loss": 0.4506,
+      "step": 120
+    },
+    {
+      "epoch": 1.921875,
+      "grad_norm": 3.4101076126098633,
+      "learning_rate": 2.0058139534883722e-05,
+      "loss": 0.5693,
+      "step": 123
+    },
+    {
+      "epoch": 1.96875,
+      "grad_norm": 4.670176982879639,
+      "learning_rate": 1.918604651162791e-05,
+      "loss": 0.6634,
+      "step": 126
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5984251968503937,
+      "eval_auc": 0.6345771144278607,
+      "eval_f1": 0.4,
+      "eval_loss": 0.6221936941146851,
+      "eval_precision": 0.9444444444444444,
+      "eval_recall": 0.2537313432835821,
+      "eval_runtime": 22.0553,
+      "eval_samples_per_second": 5.758,
+      "eval_steps_per_second": 0.363,
+      "step": 128
+    },
+    {
+      "epoch": 2.015625,
+      "grad_norm": 2.3907852172851562,
+      "learning_rate": 1.831395348837209e-05,
+      "loss": 0.6309,
+      "step": 129
+    },
+    {
+      "epoch": 2.0625,
+      "grad_norm": 0.948510468006134,
+      "learning_rate": 1.744186046511628e-05,
+      "loss": 0.5528,
+      "step": 132
+    },
+    {
+      "epoch": 2.109375,
+      "grad_norm": 1.6974962949752808,
+      "learning_rate": 1.6569767441860464e-05,
+      "loss": 0.4577,
+      "step": 135
+    },
+    {
+      "epoch": 2.15625,
+      "grad_norm": 1.3852076530456543,
+      "learning_rate": 1.569767441860465e-05,
+      "loss": 0.6234,
+      "step": 138
+    },
+    {
+      "epoch": 2.203125,
+      "grad_norm": 3.273153066635132,
+      "learning_rate": 1.4825581395348839e-05,
+      "loss": 0.5546,
+      "step": 141
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 2.748469591140747,
+      "learning_rate": 1.3953488372093024e-05,
+      "loss": 0.4984,
+      "step": 144
+    },
+    {
+      "epoch": 2.296875,
+      "grad_norm": 2.883350372314453,
+      "learning_rate": 1.308139534883721e-05,
+      "loss": 0.4304,
+      "step": 147
+    },
+    {
+      "epoch": 2.34375,
+      "grad_norm": 2.3603620529174805,
+      "learning_rate": 1.2209302325581395e-05,
+      "loss": 0.5716,
+      "step": 150
+    },
+    {
+      "epoch": 2.390625,
+      "grad_norm": 1.320438265800476,
+      "learning_rate": 1.1337209302325581e-05,
+      "loss": 0.5482,
+      "step": 153
+    },
+    {
+      "epoch": 2.4375,
+      "grad_norm": 1.0259778499603271,
+      "learning_rate": 1.0465116279069768e-05,
+      "loss": 0.5973,
+      "step": 156
+    },
+    {
+      "epoch": 2.484375,
+      "grad_norm": 1.2649555206298828,
+      "learning_rate": 9.593023255813954e-06,
+      "loss": 0.5215,
+      "step": 159
+    },
+    {
+      "epoch": 2.53125,
+      "grad_norm": 1.8391621112823486,
+      "learning_rate": 8.72093023255814e-06,
+      "loss": 0.6134,
+      "step": 162
+    },
+    {
+      "epoch": 2.578125,
+      "grad_norm": 3.4416086673736572,
+      "learning_rate": 7.848837209302325e-06,
+      "loss": 0.611,
+      "step": 165
+    },
+    {
+      "epoch": 2.625,
+      "grad_norm": 5.348316669464111,
+      "learning_rate": 6.976744186046512e-06,
+      "loss": 0.6286,
+      "step": 168
+    },
+    {
+      "epoch": 2.671875,
+      "grad_norm": 1.5112167596817017,
+      "learning_rate": 6.1046511627906975e-06,
+      "loss": 0.5942,
+      "step": 171
+    },
+    {
+      "epoch": 2.71875,
+      "grad_norm": 0.7739925980567932,
+      "learning_rate": 5.232558139534884e-06,
+      "loss": 0.6334,
+      "step": 174
+    },
+    {
+      "epoch": 2.765625,
+      "grad_norm": 2.106109857559204,
+      "learning_rate": 4.36046511627907e-06,
+      "loss": 0.5809,
+      "step": 177
+    },
+    {
+      "epoch": 2.8125,
+      "grad_norm": 2.3415915966033936,
+      "learning_rate": 3.488372093023256e-06,
+      "loss": 0.5762,
+      "step": 180
+    },
+    {
+      "epoch": 2.859375,
+      "grad_norm": 1.3243408203125,
+      "learning_rate": 2.616279069767442e-06,
+      "loss": 0.527,
+      "step": 183
+    },
+    {
+      "epoch": 2.90625,
+      "grad_norm": 0.7959187030792236,
+      "learning_rate": 1.744186046511628e-06,
+      "loss": 0.5249,
+      "step": 186
+    },
+    {
+      "epoch": 2.953125,
+      "grad_norm": 1.6207215785980225,
+      "learning_rate": 8.72093023255814e-07,
+      "loss": 0.5213,
+      "step": 189
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.1129848957061768,
+      "learning_rate": 0.0,
+      "loss": 0.5843,
+      "step": 192
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5826771653543307,
+      "eval_auc": 0.6388059701492537,
+      "eval_f1": 0.7039106145251397,
+      "eval_loss": 0.6174320578575134,
+      "eval_precision": 0.5625,
+      "eval_recall": 0.9402985074626866,
+      "eval_runtime": 23.4686,
+      "eval_samples_per_second": 5.411,
+      "eval_steps_per_second": 0.341,
+      "step": 192
+    }
+  ],
+  "logging_steps": 3,
+  "max_steps": 192,
+  "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": 2
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 100047978800640.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-192/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2724b4aa4988df7aa7f9e44f30a9fe7c0cf4b6276ffcff99d06297fa4cdbaac8
+size 5368

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "PhaseTechnologies/RoBERTo",
+  "_num_labels": 2,
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "negative",
+    "1": "positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "negative": 0,
+    "positive": 1
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "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,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80587731ab8e5b200a0728a5733b2a1b8923e0126144d73de0789a50435c83c1
+size 498612824

runs/Jan30_08-23-42_r-phasetechnologies-robertophyfirsttrain-zizp0wk0-31e16-mpa4x/events.out.tfevents.1738225423.r-phasetechnologies-robertophyfirsttrain-zizp0wk0-31e16-mpa4x.105.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3e5de7eefc7c4960c553a6dc9c5e100e0fa6086c9dcb8f82c6f0b89eca2b9fa
-size 13135
+oid sha256:6633d81869310938348d87fda071d5f0174fb0687c692c34dfc76dd3db903494
+size 20618

runs/Jan30_08-23-42_r-phasetechnologies-robertophyfirsttrain-zizp0wk0-31e16-mpa4x/events.out.tfevents.1738226571.r-phasetechnologies-robertophyfirsttrain-zizp0wk0-31e16-mpa4x.105.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de15b095ded2f334cd13c43b0bb4a2e4013a4d3962c6d96200cc5136b265a76a
+size 607

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "max_length": 128,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2724b4aa4988df7aa7f9e44f30a9fe7c0cf4b6276ffcff99d06297fa4cdbaac8
+size 5368

training_params.json

@@ -0,0 +1,30 @@
+{
+    "data_path": "autotrain-dtpk3-gqgvr/autotrain-data",
+    "model": "PhaseTechnologies/RoBERTo",
+    "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-dtpk3-gqgvr",
+    "auto_find_batch_size": false,
+    "mixed_precision": null,
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "eval_strategy": "epoch",
+    "username": "PhaseTechnologies",
+    "log": "tensorboard",
+    "early_stopping_patience": 5,
+    "early_stopping_threshold": 0.01
+}