Upload folder using huggingface_hub

README.md

@@ -0,0 +1,37 @@
+
+---
+tags:
+- autotrain
+- text-classification
+widget:
+- text: "I love AutoTrain"
+datasets:
+- few-shot-learning-classification-bert-sm-500/autotrain-data
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Text Classification
+
+## Validation Metrics
+loss: 0.5352076888084412
+
+f1_macro: 0.8831874792383778
+
+f1_micro: 0.8825
+
+f1_weighted: 0.8831874792383778
+
+precision_macro: 0.8856660322436862
+
+precision_micro: 0.8825
+
+precision_weighted: 0.885666032243686
+
+recall_macro: 0.8825
+
+recall_micro: 0.8825
+
+recall_weighted: 0.8825
+
+accuracy: 0.8825

checkpoint-400/config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "google-bert/bert-base-uncased",
+  "_num_labels": 4,
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "0",
+    "1": "1",
+    "2": "2",
+    "3": "3"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "0": 0,
+    "1": 1,
+    "2": 2,
+    "3": 3
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

checkpoint-400/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d5824a3bf72608b7e7c80ca953a3bf10e43aeda0a0e1702717fa5afe981cdf2
+size 437964800

checkpoint-400/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db9dfe50f16181f614502284e52de8b9962dadef43947922cc0659b6cf45b034
+size 876050682

checkpoint-400/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8e9cd4d67ba129479ee5268ec98eac2f774257312bf19ef9e96feb27cfe5d40
+size 14244

checkpoint-400/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3da4d5f597bd82767814dfef236ca8b63acb0fb2697d9ac551fad9a989b42463
+size 1064

checkpoint-400/trainer_state.json

@@ -0,0 +1,151 @@
+{
+  "best_metric": 0.5352076888084412,
+  "best_model_checkpoint": "few-shot-learning-classification-bert-sm-500/checkpoint-400",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0625,
+      "grad_norm": 10.746420860290527,
+      "learning_rate": 0.00012,
+      "loss": 1.3515,
+      "step": 25
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 13.11999225616455,
+      "learning_rate": 0.000195,
+      "loss": 0.8696,
+      "step": 50
+    },
+    {
+      "epoch": 0.1875,
+      "grad_norm": 0.8173635005950928,
+      "learning_rate": 0.00018222222222222224,
+      "loss": 0.6066,
+      "step": 75
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 18.56312370300293,
+      "learning_rate": 0.00016833333333333335,
+      "loss": 0.7135,
+      "step": 100
+    },
+    {
+      "epoch": 0.3125,
+      "grad_norm": 25.261268615722656,
+      "learning_rate": 0.00015444444444444446,
+      "loss": 0.8303,
+      "step": 125
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 8.452961921691895,
+      "learning_rate": 0.00014055555555555555,
+      "loss": 0.623,
+      "step": 150
+    },
+    {
+      "epoch": 0.4375,
+      "grad_norm": 23.321823120117188,
+      "learning_rate": 0.00012722222222222223,
+      "loss": 1.0241,
+      "step": 175
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 7.1832356452941895,
+      "learning_rate": 0.00011333333333333334,
+      "loss": 0.9929,
+      "step": 200
+    },
+    {
+      "epoch": 0.5625,
+      "grad_norm": 4.93562126159668,
+      "learning_rate": 9.944444444444446e-05,
+      "loss": 0.5292,
+      "step": 225
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 1.7682493925094604,
+      "learning_rate": 8.555555555555556e-05,
+      "loss": 0.7429,
+      "step": 250
+    },
+    {
+      "epoch": 0.6875,
+      "grad_norm": 0.14674201607704163,
+      "learning_rate": 7.166666666666667e-05,
+      "loss": 0.643,
+      "step": 275
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 306.0769958496094,
+      "learning_rate": 5.7777777777777776e-05,
+      "loss": 0.3974,
+      "step": 300
+    },
+    {
+      "epoch": 0.8125,
+      "grad_norm": 0.12910698354244232,
+      "learning_rate": 4.388888888888889e-05,
+      "loss": 0.3826,
+      "step": 325
+    },
+    {
+      "epoch": 0.875,
+      "grad_norm": 0.1545443832874298,
+      "learning_rate": 3e-05,
+      "loss": 0.8772,
+      "step": 350
+    },
+    {
+      "epoch": 0.9375,
+      "grad_norm": 0.5163759589195251,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.6603,
+      "step": 375
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 16.037109375,
+      "learning_rate": 2.777777777777778e-06,
+      "loss": 0.3469,
+      "step": 400
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8825,
+      "eval_f1_macro": 0.8831874792383778,
+      "eval_f1_micro": 0.8825,
+      "eval_f1_weighted": 0.8831874792383778,
+      "eval_loss": 0.5352076888084412,
+      "eval_precision_macro": 0.8856660322436862,
+      "eval_precision_micro": 0.8825,
+      "eval_precision_weighted": 0.885666032243686,
+      "eval_recall_macro": 0.8825,
+      "eval_recall_micro": 0.8825,
+      "eval_recall_weighted": 0.8825,
+      "eval_runtime": 3.0412,
+      "eval_samples_per_second": 131.529,
+      "eval_steps_per_second": 65.765,
+      "step": 400
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 400,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 420985248153600.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-400/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f26afbf2fe7b443868647b47d0159bc5a8ba9b57b7b86a63261c895eb1c0b943
+size 5048

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "google-bert/bert-base-uncased",
+  "_num_labels": 4,
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "0",
+    "1": "1",
+    "2": "2",
+    "3": "3"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "0": 0,
+    "1": 1,
+    "2": 2,
+    "3": 3
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d5824a3bf72608b7e7c80ca953a3bf10e43aeda0a0e1702717fa5afe981cdf2
+size 437964800

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 +1,55 @@
+{
+  "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_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f26afbf2fe7b443868647b47d0159bc5a8ba9b57b7b86a63261c895eb1c0b943
+size 5048

training_params.json

@@ -0,0 +1,28 @@
+{
+    "data_path": "few-shot-learning-classification-bert-sm-500/autotrain-data",
+    "model": "google-bert/bert-base-uncased",
+    "lr": 0.0002,
+    "epochs": 1,
+    "max_seq_length": 512,
+    "batch_size": 1,
+    "warmup_ratio": 0.1,
+    "gradient_accumulation": 4,
+    "optimizer": "adamw_torch",
+    "scheduler": "linear",
+    "weight_decay": 0.01,
+    "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": "few-shot-learning-classification-bert-sm-500",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "evaluation_strategy": "epoch",
+    "username": "pravin691983",
+    "log": "none"
+}