Upload folder using huggingface_hub

README.md

@@ -0,0 +1,37 @@
+
+---
+tags:
+- autotrain
+- text-classification
+widget:
+- text: "I love AutoTrain"
+datasets:
+- fewshotlearning-text-classification-bert-sm/autotrain-data
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Text Classification
+
+## Validation Metrics
+loss: 0.6685735583305359
+
+f1_macro: 0.8364860941080454
+
+f1_micro: 0.8375
+
+f1_weighted: 0.8364860941080453
+
+precision_macro: 0.8393652915711738
+
+precision_micro: 0.8375
+
+precision_weighted: 0.8393652915711739
+
+recall_macro: 0.8375
+
+recall_micro: 0.8375
+
+recall_weighted: 0.8375
+
+accuracy: 0.8375

checkpoint-80/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-80/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b9e5f7981fe0600bb883464aab6535c7d5105404505bbc8abcea7b3fe7cafd4
+size 437964800

checkpoint-80/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed390a00ce31d13cecc2937782cc0fbb81a22436344730d81515bd50eee69224
+size 876050682

checkpoint-80/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3f2727cd53009085422f7629014b2b1a60fb0a9a84270b29bf3ab246e78b008
+size 14244

checkpoint-80/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00fec0e6b72b9853d4c3f9ba6a59185c8a6f09cf774763b098645bb9a99d9442
+size 1064

checkpoint-80/trainer_state.json

@@ -0,0 +1,74 @@
+{
+  "best_metric": 0.6685735583305359,
+  "best_model_checkpoint": "fewshotlearning-text-classification-bert-sm/checkpoint-80",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 80,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2,
+      "grad_norm": 16.075746536254883,
+      "learning_rate": 0.00018055555555555557,
+      "loss": 1.4192,
+      "step": 16
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 6.529771327972412,
+      "learning_rate": 0.0001388888888888889,
+      "loss": 1.2799,
+      "step": 32
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 27.337310791015625,
+      "learning_rate": 9.444444444444444e-05,
+      "loss": 0.9263,
+      "step": 48
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.956445574760437,
+      "learning_rate": 5.2777777777777784e-05,
+      "loss": 0.4822,
+      "step": 64
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 8.860248565673828,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.6073,
+      "step": 80
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8375,
+      "eval_f1_macro": 0.8364860941080454,
+      "eval_f1_micro": 0.8375,
+      "eval_f1_weighted": 0.8364860941080453,
+      "eval_loss": 0.6685735583305359,
+      "eval_precision_macro": 0.8393652915711738,
+      "eval_precision_micro": 0.8375,
+      "eval_precision_weighted": 0.8393652915711739,
+      "eval_recall_macro": 0.8375,
+      "eval_recall_micro": 0.8375,
+      "eval_recall_weighted": 0.8375,
+      "eval_runtime": 1.1304,
+      "eval_samples_per_second": 70.773,
+      "eval_steps_per_second": 35.387,
+      "step": 80
+    }
+  ],
+  "logging_steps": 16,
+  "max_steps": 80,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 84197049630720.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-80/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd6bf47baf73ff903c6a06ed0fa0b9b3224ae196f25546edfb7dc2191e45162e
+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 sha256:5b9e5f7981fe0600bb883464aab6535c7d5105404505bbc8abcea7b3fe7cafd4
+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:fd6bf47baf73ff903c6a06ed0fa0b9b3224ae196f25546edfb7dc2191e45162e
+size 5048

training_params.json

@@ -0,0 +1,28 @@
+{
+    "data_path": "fewshotlearning-text-classification-bert-sm/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": "fewshotlearning-text-classification-bert-sm",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "evaluation_strategy": "epoch",
+    "username": "pravin691983",
+    "log": "none"
+}