Upload folder using huggingface_hub

README.md

@@ -0,0 +1,27 @@
+
+---
+library_name: transformers
+tags:
+- autotrain
+- text-classification
+base_model: microsoft/deberta-v3-base
+widget:
+- text: "I love AutoTrain"
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Text Classification
+
+## Validation Metrics
+loss: 0.4501543343067169
+
+f1: 0.8251121076233184
+
+precision: 0.7479674796747967
+
+recall: 0.92
+
+auc: 0.9066000000000001
+
+accuracy: 0.805

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

checkpoint-100/config.json

@@ -0,0 +1,45 @@
+{
+  "_name_or_path": "microsoft/deberta-v3-base",
+  "_num_labels": 2,
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "human",
+    "1": "machine"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "human": 0,
+    "machine": 1
+  },
+  "layer_norm_eps": 1e-07,
+  "legacy": true,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.0",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

checkpoint-100/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c22608dc27f11515fb5f82fd9466c5c140f3b042b37e723117ebdfd2507204a
+size 737719272

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:859d504455ce51b512fb4a21e3b326988f1f52027942cf0bcc2ef0287fb4cdca
+size 1475552762

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d8db4e55544cd53d731b105b244ba6e40392c27329a5e11db10ab564baabbbe
+size 13990

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d035e61f1c66cd4befda09e39359b5d11abe5b64d7c41726de679803569f208e
+size 1064

checkpoint-100/trainer_state.json

@@ -0,0 +1,195 @@
+{
+  "best_metric": 0.4501543343067169,
+  "best_model_checkpoint": "autotrain-qkfvr-4yrwe/checkpoint-100",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "grad_norm": 3.2349209785461426,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.6925,
+      "step": 5
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 3.42258358001709,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.6949,
+      "step": 10
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 1.1544133424758911,
+      "learning_rate": 2.5e-05,
+      "loss": 0.7045,
+      "step": 15
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 4.767457962036133,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.6916,
+      "step": 20
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 1.978225588798523,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 0.6937,
+      "step": 25
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 4.386098384857178,
+      "learning_rate": 5e-05,
+      "loss": 0.6817,
+      "step": 30
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 2.616386651992798,
+      "learning_rate": 4.9074074074074075e-05,
+      "loss": 0.6589,
+      "step": 35
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 6.577281951904297,
+      "learning_rate": 4.814814814814815e-05,
+      "loss": 0.6352,
+      "step": 40
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 5.725684642791748,
+      "learning_rate": 4.722222222222222e-05,
+      "loss": 0.6231,
+      "step": 45
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 14.771023750305176,
+      "learning_rate": 4.62962962962963e-05,
+      "loss": 0.6771,
+      "step": 50
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 6.239844799041748,
+      "learning_rate": 4.5370370370370374e-05,
+      "loss": 0.6031,
+      "step": 55
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 5.879209995269775,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.3533,
+      "step": 60
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 6.339338779449463,
+      "learning_rate": 4.351851851851852e-05,
+      "loss": 0.5966,
+      "step": 65
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 16.186792373657227,
+      "learning_rate": 4.259259259259259e-05,
+      "loss": 0.6782,
+      "step": 70
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 9.90497875213623,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 0.6433,
+      "step": 75
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 4.704445838928223,
+      "learning_rate": 4.074074074074074e-05,
+      "loss": 0.4488,
+      "step": 80
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 17.884246826171875,
+      "learning_rate": 3.981481481481482e-05,
+      "loss": 0.618,
+      "step": 85
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 8.23388957977295,
+      "learning_rate": 3.888888888888889e-05,
+      "loss": 0.5853,
+      "step": 90
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 8.233333587646484,
+      "learning_rate": 3.7962962962962964e-05,
+      "loss": 0.4419,
+      "step": 95
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 6.261537075042725,
+      "learning_rate": 3.7037037037037037e-05,
+      "loss": 0.4245,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.805,
+      "eval_auc": 0.9066000000000001,
+      "eval_f1": 0.8251121076233184,
+      "eval_loss": 0.4501543343067169,
+      "eval_precision": 0.7479674796747967,
+      "eval_recall": 0.92,
+      "eval_runtime": 29.3558,
+      "eval_samples_per_second": 6.813,
+      "eval_steps_per_second": 0.443,
+      "step": 100
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 300,
+  "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": 52623154790400.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85e0dc49116122a44683f59f96771186c3c8edae5889f6c271093b4fc954084f
+size 5368

config.json

@@ -0,0 +1,45 @@
+{
+  "_name_or_path": "microsoft/deberta-v3-base",
+  "_num_labels": 2,
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "human",
+    "1": "machine"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "human": 0,
+    "machine": 1
+  },
+  "layer_norm_eps": 1e-07,
+  "legacy": true,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.0",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c22608dc27f11515fb5f82fd9466c5c140f3b042b37e723117ebdfd2507204a
+size 737719272

runs/Aug20_08-43-35_r-motionlabs-autotrain-lbrlx0kx-42d13-svqgo/events.out.tfevents.1755679417.r-motionlabs-autotrain-lbrlx0kx-42d13-svqgo.82.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f09f9de74713a987f7e5982d0648301dc8d51bcf0bf662518284432a10cebe9
-size 17274
+oid sha256:fd0cce176a8aa40912ee14580018190ab4cd03f6f4c858e9a6d4d3f262a336a7
+size 19835

runs/Aug20_08-43-35_r-motionlabs-autotrain-lbrlx0kx-42d13-svqgo/events.out.tfevents.1755680918.r-motionlabs-autotrain-lbrlx0kx-42d13-svqgo.82.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77f741ec8f03b724e18438ec44363d4d879304dde598866190b31151ca45ae81
+size 607

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85e0dc49116122a44683f59f96771186c3c8edae5889f6c271093b4fc954084f
+size 5368

training_params.json

@@ -0,0 +1,30 @@
+{
+    "data_path": "autotrain-qkfvr-4yrwe/autotrain-data",
+    "model": "microsoft/deberta-v3-base",
+    "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-qkfvr-4yrwe",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "eval_strategy": "epoch",
+    "username": "saneowl",
+    "log": "tensorboard",
+    "early_stopping_patience": 5,
+    "early_stopping_threshold": 0.01
+}