Upload folder using huggingface_hub

README.md

@@ -0,0 +1,26 @@
+
+---
+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: 0.3079245686531067
+
+f1: 0.9307469180565627
+
+precision: 0.9708774583963692
+
+recall: 0.8938022284122563
+
+auc: 0.9840253557545333
+
+accuracy: 0.9334958217270195

added_tokens.json

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

checkpoint-712/config.json

@@ -0,0 +1,44 @@
+{
+  "_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": "0",
+    "1": "1"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "0": 0,
+    "1": 1
+  },
+  "layer_norm_eps": 1e-07,
+  "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": "4.43.1",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

checkpoint-712/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f9c810e1afb818440210e282c807a8ebc14aeae903baa8022e12a9b5d4ae4b6
+size 737719272

checkpoint-712/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a190e8c7c128b241b654a6c77f52379b61210491a27a8d188da9d31636aa96c
+size 1475558394

checkpoint-712/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf56780eafdcf429915e69dfc871f5e4839b7a0b2b823e519734d57538072f17
+size 14244

checkpoint-712/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2655f44847a1070a830b66c796cc24dc9a9400f72a8da37893d24514e21db6ab
+size 1064

checkpoint-712/trainer_state.json

@@ -0,0 +1,251 @@
+{
+  "best_metric": 0.3079245686531067,
+  "best_model_checkpoint": "autotrain-kcpio-wclqs/checkpoint-712",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 712,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0351123595505618,
+      "grad_norm": 1.9374197721481323,
+      "learning_rate": 1.736111111111111e-05,
+      "loss": 0.6963,
+      "step": 25
+    },
+    {
+      "epoch": 0.0702247191011236,
+      "grad_norm": 3.9908769130706787,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.5465,
+      "step": 50
+    },
+    {
+      "epoch": 0.10533707865168539,
+      "grad_norm": 8.669546127319336,
+      "learning_rate": 4.930555555555556e-05,
+      "loss": 0.4025,
+      "step": 75
+    },
+    {
+      "epoch": 0.1404494382022472,
+      "grad_norm": 0.6609323024749756,
+      "learning_rate": 4.8125000000000004e-05,
+      "loss": 0.338,
+      "step": 100
+    },
+    {
+      "epoch": 0.175561797752809,
+      "grad_norm": 0.6923323273658752,
+      "learning_rate": 4.6171875e-05,
+      "loss": 0.265,
+      "step": 125
+    },
+    {
+      "epoch": 0.21067415730337077,
+      "grad_norm": 0.6821861267089844,
+      "learning_rate": 4.421875e-05,
+      "loss": 0.2498,
+      "step": 150
+    },
+    {
+      "epoch": 0.24578651685393257,
+      "grad_norm": 0.10477828234434128,
+      "learning_rate": 4.2265625000000006e-05,
+      "loss": 0.1785,
+      "step": 175
+    },
+    {
+      "epoch": 0.2808988764044944,
+      "grad_norm": 3.7019550800323486,
+      "learning_rate": 4.0312500000000004e-05,
+      "loss": 0.2335,
+      "step": 200
+    },
+    {
+      "epoch": 0.3160112359550562,
+      "grad_norm": 16.70686912536621,
+      "learning_rate": 3.8359375e-05,
+      "loss": 0.1422,
+      "step": 225
+    },
+    {
+      "epoch": 0.351123595505618,
+      "grad_norm": 0.07099178433418274,
+      "learning_rate": 3.640625e-05,
+      "loss": 0.1525,
+      "step": 250
+    },
+    {
+      "epoch": 0.3862359550561798,
+      "grad_norm": 0.049899421632289886,
+      "learning_rate": 3.4453125000000006e-05,
+      "loss": 0.0916,
+      "step": 275
+    },
+    {
+      "epoch": 0.42134831460674155,
+      "grad_norm": 0.021365324035286903,
+      "learning_rate": 3.2500000000000004e-05,
+      "loss": 0.0504,
+      "step": 300
+    },
+    {
+      "epoch": 0.45646067415730335,
+      "grad_norm": 0.03689989075064659,
+      "learning_rate": 3.0546875e-05,
+      "loss": 0.09,
+      "step": 325
+    },
+    {
+      "epoch": 0.49157303370786515,
+      "grad_norm": 0.24886544048786163,
+      "learning_rate": 2.8593750000000004e-05,
+      "loss": 0.0951,
+      "step": 350
+    },
+    {
+      "epoch": 0.526685393258427,
+      "grad_norm": 0.06867190450429916,
+      "learning_rate": 2.6640625000000002e-05,
+      "loss": 0.0483,
+      "step": 375
+    },
+    {
+      "epoch": 0.5617977528089888,
+      "grad_norm": 0.29167991876602173,
+      "learning_rate": 2.4687500000000004e-05,
+      "loss": 0.1251,
+      "step": 400
+    },
+    {
+      "epoch": 0.5969101123595506,
+      "grad_norm": 0.10820268094539642,
+      "learning_rate": 2.2734375000000002e-05,
+      "loss": 0.1432,
+      "step": 425
+    },
+    {
+      "epoch": 0.6320224719101124,
+      "grad_norm": 0.07357452809810638,
+      "learning_rate": 2.0781250000000004e-05,
+      "loss": 0.0941,
+      "step": 450
+    },
+    {
+      "epoch": 0.6671348314606742,
+      "grad_norm": 0.13083012402057648,
+      "learning_rate": 1.8828125000000002e-05,
+      "loss": 0.1754,
+      "step": 475
+    },
+    {
+      "epoch": 0.702247191011236,
+      "grad_norm": 0.11591902375221252,
+      "learning_rate": 1.6875000000000004e-05,
+      "loss": 0.1484,
+      "step": 500
+    },
+    {
+      "epoch": 0.7373595505617978,
+      "grad_norm": 23.016658782958984,
+      "learning_rate": 1.4921875000000002e-05,
+      "loss": 0.1112,
+      "step": 525
+    },
+    {
+      "epoch": 0.7724719101123596,
+      "grad_norm": 29.17462158203125,
+      "learning_rate": 1.2968750000000002e-05,
+      "loss": 0.0749,
+      "step": 550
+    },
+    {
+      "epoch": 0.8075842696629213,
+      "grad_norm": 0.27380064129829407,
+      "learning_rate": 1.1015625e-05,
+      "loss": 0.1224,
+      "step": 575
+    },
+    {
+      "epoch": 0.8426966292134831,
+      "grad_norm": 0.11491677910089493,
+      "learning_rate": 9.0625e-06,
+      "loss": 0.04,
+      "step": 600
+    },
+    {
+      "epoch": 0.8778089887640449,
+      "grad_norm": 0.04559633880853653,
+      "learning_rate": 7.109375e-06,
+      "loss": 0.032,
+      "step": 625
+    },
+    {
+      "epoch": 0.9129213483146067,
+      "grad_norm": 0.12071628123521805,
+      "learning_rate": 5.15625e-06,
+      "loss": 0.1393,
+      "step": 650
+    },
+    {
+      "epoch": 0.9480337078651685,
+      "grad_norm": 0.14503008127212524,
+      "learning_rate": 3.203125e-06,
+      "loss": 0.0517,
+      "step": 675
+    },
+    {
+      "epoch": 0.9831460674157303,
+      "grad_norm": 0.045122675597667694,
+      "learning_rate": 1.25e-06,
+      "loss": 0.0517,
+      "step": 700
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9334958217270195,
+      "eval_auc": 0.9840253557545333,
+      "eval_f1": 0.9307469180565627,
+      "eval_loss": 0.3079245686531067,
+      "eval_precision": 0.9708774583963692,
+      "eval_recall": 0.8938022284122563,
+      "eval_runtime": 20.2322,
+      "eval_samples_per_second": 283.904,
+      "eval_steps_per_second": 17.744,
+      "step": 712
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 712,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "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": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 374413746333696.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-712/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a39862abc3e24cf38e8b88f4870a2c896765c971e470d14f28780139f321c28a
+size 5240

config.json

@@ -0,0 +1,44 @@
+{
+  "_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": "0",
+    "1": "1"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "0": 0,
+    "1": 1
+  },
+  "layer_norm_eps": 1e-07,
+  "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": "4.43.1",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f9c810e1afb818440210e282c807a8ebc14aeae903baa8022e12a9b5d4ae4b6
+size 737719272

runs/Jul25_18-13-12_r-assaflehr-autotrain5-j80r2m81-046a7-kkp2g/events.out.tfevents.1721931193.r-assaflehr-autotrain5-j80r2m81-046a7-kkp2g.74.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56d5da9b36b04899960b1de1a132b4670519464eb7e6fbc0389b144aa6ab7286
-size 5198
+oid sha256:af7be6a9d279411f0061ef5a6676836f7e489ec99937474921fc1ec4929cf72d
+size 11959

runs/Jul25_18-13-12_r-assaflehr-autotrain5-j80r2m81-046a7-kkp2g/events.out.tfevents.1721931362.r-assaflehr-autotrain5-j80r2m81-046a7-kkp2g.74.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91e0d6ca6ae05207ca1eac74df3cb3dc67d0da0fea31dfc2371e88360cda0bc9
+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 +1,58 @@
+{
+  "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": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "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:a39862abc3e24cf38e8b88f4870a2c896765c971e470d14f28780139f321c28a
+size 5240

training_params.json

@@ -0,0 +1,30 @@
+{
+    "data_path": "autotrain-kcpio-wclqs/autotrain-data",
+    "model": "microsoft/deberta-v3-base",
+    "lr": 5e-05,
+    "epochs": 1,
+    "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-kcpio-wclqs",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "eval_strategy": "epoch",
+    "username": "assaflehr",
+    "log": "tensorboard",
+    "early_stopping_patience": 5,
+    "early_stopping_threshold": 0.01
+}