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-5K-32/autotrain-data
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Text Classification
+
+## Validation Metrics
+loss: 0.25288185477256775
+
+f1_macro: 0.9137712253628689
+
+f1_micro: 0.914
+
+f1_weighted: 0.9137712253628689
+
+precision_macro: 0.9140401620479054
+
+precision_micro: 0.914
+
+precision_weighted: 0.9140401620479053
+
+recall_macro: 0.9140000000000001
+
+recall_micro: 0.914
+
+recall_weighted: 0.914
+
+accuracy: 0.914

checkpoint-250/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-250/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ac550315ba901ba111b2561c819cbf1636550eab29c6695b585f0e5b0e5689b
+size 437964800

checkpoint-250/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e85428d82a27a5beefa10bb1b5afa8e5f6c302704cfc33565c8e3ca16806010
+size 876050682

checkpoint-250/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ac869828c5024d4d4a82b7cf859980dc582788f9ad94e39e9adcd052ae285a7
+size 14244

checkpoint-250/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2510bf6ad7c05936779f61e0fa5dbd1a56f64d753f53af2641533f153a76c256
+size 1064

checkpoint-250/trainer_state.json

@@ -0,0 +1,127 @@
+{
+  "best_metric": 0.25288185477256775,
+  "best_model_checkpoint": "few-shot-learning-classification-bert-sm-5K-32/checkpoint-250",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 250,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2,
+      "grad_norm": 4.231257915496826,
+      "learning_rate": 2e-05,
+      "loss": 1.2334,
+      "step": 25
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 2.2730774879455566,
+      "learning_rate": 1.7777777777777777e-05,
+      "loss": 0.6694,
+      "step": 50
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 2.707385778427124,
+      "learning_rate": 1.555555555555556e-05,
+      "loss": 0.3834,
+      "step": 75
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 2.1450345516204834,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.3034,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.1361820697784424,
+      "learning_rate": 1.1111111111111113e-05,
+      "loss": 0.2999,
+      "step": 125
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.904,
+      "eval_f1_macro": 0.9036653728644836,
+      "eval_f1_micro": 0.904,
+      "eval_f1_weighted": 0.9036653728644836,
+      "eval_loss": 0.2839123606681824,
+      "eval_precision_macro": 0.9037858383571149,
+      "eval_precision_micro": 0.904,
+      "eval_precision_weighted": 0.9037858383571149,
+      "eval_recall_macro": 0.904,
+      "eval_recall_micro": 0.904,
+      "eval_recall_weighted": 0.904,
+      "eval_runtime": 9.7499,
+      "eval_samples_per_second": 410.262,
+      "eval_steps_per_second": 6.462,
+      "step": 125
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 3.473186731338501,
+      "learning_rate": 8.888888888888888e-06,
+      "loss": 0.2484,
+      "step": 150
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 3.498867988586426,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.2535,
+      "step": 175
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 3.2598490715026855,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 0.2242,
+      "step": 200
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 2.939223289489746,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 0.2224,
+      "step": 225
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.8699662685394287,
+      "learning_rate": 0.0,
+      "loss": 0.2132,
+      "step": 250
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.914,
+      "eval_f1_macro": 0.9137712253628689,
+      "eval_f1_micro": 0.914,
+      "eval_f1_weighted": 0.9137712253628689,
+      "eval_loss": 0.25288185477256775,
+      "eval_precision_macro": 0.9140401620479054,
+      "eval_precision_micro": 0.914,
+      "eval_precision_weighted": 0.9140401620479053,
+      "eval_recall_macro": 0.9140000000000001,
+      "eval_recall_micro": 0.914,
+      "eval_recall_weighted": 0.914,
+      "eval_runtime": 9.7809,
+      "eval_samples_per_second": 408.961,
+      "eval_steps_per_second": 6.441,
+      "step": 250
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 250,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 8419704963072000.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-250/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8faa3f1dfbabb7fab8de33db0059a4da000d844d786c33151bfd08b4cabd59a
+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 sha256:4ac550315ba901ba111b2561c819cbf1636550eab29c6695b585f0e5b0e5689b
+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:c8faa3f1dfbabb7fab8de33db0059a4da000d844d786c33151bfd08b4cabd59a
+size 5048

training_params.json

@@ -0,0 +1,28 @@
+{
+    "data_path": "few-shot-learning-classification-bert-sm-5K-32/autotrain-data",
+    "model": "google-bert/bert-base-uncased",
+    "lr": 2e-05,
+    "epochs": 2,
+    "max_seq_length": 512,
+    "batch_size": 32,
+    "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-5K-32",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "evaluation_strategy": "epoch",
+    "username": "pravin691983",
+    "log": "none"
+}