Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,27 @@
+
+---
+tags:
+- autotrain
+- text-classification
+widget:
+- text: "I love AutoTrain"
+datasets:
+- autotrain-28eqp-t2e16/autotrain-data
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Text Classification
+
+## Validation Metrics
+loss: 0.18809613585472107
+
+f1: 0.967032967032967
+
+precision: 0.9617486338797814
+
+recall: 0.9723756906077348
+
+auc: 0.9890489344909235
+
+accuracy: 0.9656160458452722

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 250101
+}

checkpoint-150/config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "microsoft/mdeberta-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": "Ignore",
+    "1": "Send"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Ignore": 0,
+    "Send": 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": "4.40.1",
+  "type_vocab_size": 0,
+  "vocab_size": 251000
+}

checkpoint-150/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f6da20fbe96eb9d7dfa752660db3fc987bc5fce57b78cfc86544c050a700127
+size 1115268200

checkpoint-150/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6307db414c109df437af0f42ddd0051dc7a9bf47793848059c62360e58427a6d
+size 2230650362

checkpoint-150/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c90fc564078dcefc97b989732602b57b8021e70c05441e5a4c1e939d4aa51e6
+size 13990

checkpoint-150/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1320cc0c91c904e1b37627facbc7bdd09ad072c5e9a4fe376e5569a5cdf3a73
+size 1064

checkpoint-150/trainer_state.json

@@ -0,0 +1,186 @@
+{
+  "best_metric": 0.18809613585472107,
+  "best_model_checkpoint": "autotrain-28eqp-t2e16/checkpoint-150",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 150,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "grad_norm": 2.269129753112793,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 0.6984,
+      "step": 8
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 4.074235916137695,
+      "learning_rate": 4.962962962962963e-05,
+      "loss": 0.6593,
+      "step": 16
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 5.697342395782471,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 0.4673,
+      "step": 24
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 5.995659351348877,
+      "learning_rate": 4.3703703703703705e-05,
+      "loss": 0.226,
+      "step": 32
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 6.6095428466796875,
+      "learning_rate": 4.074074074074074e-05,
+      "loss": 0.1767,
+      "step": 40
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.2729267477989197,
+      "learning_rate": 3.777777777777778e-05,
+      "loss": 0.4345,
+      "step": 48
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8968481375358166,
+      "eval_auc": 0.9792817679558011,
+      "eval_f1": 0.8902439024390244,
+      "eval_loss": 0.45533695816993713,
+      "eval_precision": 0.9931972789115646,
+      "eval_recall": 0.8066298342541437,
+      "eval_runtime": 76.2971,
+      "eval_samples_per_second": 4.574,
+      "eval_steps_per_second": 0.288,
+      "step": 50
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.21169081330299377,
+      "learning_rate": 3.481481481481482e-05,
+      "loss": 0.3073,
+      "step": 56
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 8.168057441711426,
+      "learning_rate": 3.185185185185185e-05,
+      "loss": 0.1746,
+      "step": 64
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 1.0985065698623657,
+      "learning_rate": 2.8888888888888888e-05,
+      "loss": 0.118,
+      "step": 72
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.13789577782154083,
+      "learning_rate": 2.5925925925925925e-05,
+      "loss": 0.0233,
+      "step": 80
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 1.7061790227890015,
+      "learning_rate": 2.2962962962962965e-05,
+      "loss": 0.2002,
+      "step": 88
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 6.507961750030518,
+      "learning_rate": 2e-05,
+      "loss": 0.0259,
+      "step": 96
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9484240687679083,
+      "eval_auc": 0.9819126545645883,
+      "eval_f1": 0.9516129032258065,
+      "eval_loss": 0.2552463114261627,
+      "eval_precision": 0.9267015706806283,
+      "eval_recall": 0.9779005524861878,
+      "eval_runtime": 75.7963,
+      "eval_samples_per_second": 4.604,
+      "eval_steps_per_second": 0.29,
+      "step": 100
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 0.1205369234085083,
+      "learning_rate": 1.7037037037037038e-05,
+      "loss": 0.0081,
+      "step": 104
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 0.08243238925933838,
+      "learning_rate": 1.4074074074074075e-05,
+      "loss": 0.0458,
+      "step": 112
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 54.06669998168945,
+      "learning_rate": 1.1111111111111112e-05,
+      "loss": 0.1301,
+      "step": 120
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 0.08115862309932709,
+      "learning_rate": 8.14814814814815e-06,
+      "loss": 0.0053,
+      "step": 128
+    },
+    {
+      "epoch": 2.7199999999999998,
+      "grad_norm": 0.06672395765781403,
+      "learning_rate": 5.185185185185185e-06,
+      "loss": 0.0075,
+      "step": 136
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 0.0613614059984684,
+      "learning_rate": 2.2222222222222225e-06,
+      "loss": 0.0871,
+      "step": 144
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9656160458452722,
+      "eval_auc": 0.9890489344909235,
+      "eval_f1": 0.967032967032967,
+      "eval_loss": 0.18809613585472107,
+      "eval_precision": 0.9617486338797814,
+      "eval_recall": 0.9723756906077348,
+      "eval_runtime": 75.8185,
+      "eval_samples_per_second": 4.603,
+      "eval_steps_per_second": 0.29,
+      "step": 150
+    }
+  ],
+  "logging_steps": 8,
+  "max_steps": 150,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 77750711202816.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-150/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17fb05e59f14858484cc922f527ea9a95cff88d40cb4a23183db0bc980d1795c
+size 5048

config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "microsoft/mdeberta-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": "Ignore",
+    "1": "Send"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Ignore": 0,
+    "Send": 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": "4.40.1",
+  "type_vocab_size": 0,
+  "vocab_size": 251000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f6da20fbe96eb9d7dfa752660db3fc987bc5fce57b78cfc86544c050a700127
+size 1115268200

runs/May08_09-35-21_r-kaludi-autotrain-advanced-rlss2ebc-b05d6-mdz05/events.out.tfevents.1715160922.r-kaludi-autotrain-advanced-rlss2ebc-b05d6-mdz05.86.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2042639da7e2f0b6b7499d3798bf9f9facc1f9cca1a4ad20787ca24a1f30b9c
-size 9323
+oid sha256:bf86c2f4b42b70cb75648392deac1a7ee3e2fbddb8352b9b7ddc3e3e1722d3a1
+size 10618

runs/May08_09-35-21_r-kaludi-autotrain-advanced-rlss2ebc-b05d6-mdz05/events.out.tfevents.1715162474.r-kaludi-autotrain-advanced-rlss2ebc-b05d6-mdz05.86.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7b6815dce1c89603efa91c5d0d71d5c3c561e9e3f9650a0aed078897e334371
+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 sha256:13c8d666d62a7bc4ac8f040aab68e942c861f93303156cc28f5c7e885d86d6e3
+size 4305025

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92a8c99428011732bf63f86cfedf2c5ecd30da100e094f3baf15075880258495
+size 16331639

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
+    },
+    "250101": {
+      "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 sha256:17fb05e59f14858484cc922f527ea9a95cff88d40cb4a23183db0bc980d1795c
+size 5048

training_params.json

@@ -0,0 +1,28 @@
+{
+    "data_path": "autotrain-28eqp-t2e16/autotrain-data",
+    "model": "microsoft/mdeberta-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-28eqp-t2e16",
+    "auto_find_batch_size": false,
+    "mixed_precision": "none",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "evaluation_strategy": "epoch",
+    "username": "Kaludi",
+    "log": "tensorboard"
+}