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-abs/autotrain-data
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Text Classification
+
+## Validation Metrics
+loss: 0.25161686539649963
+
+f1_macro: 0.9235095937897977
+
+f1_micro: 0.9235
+
+f1_weighted: 0.9235095937897976
+
+precision_macro: 0.9244227025831069
+
+precision_micro: 0.9235
+
+precision_weighted: 0.9244227025831069
+
+recall_macro: 0.9235
+
+recall_micro: 0.9235
+
+recall_weighted: 0.9235
+
+accuracy: 0.9235

checkpoint-1200/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-1200/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36686d35fac82608880cab4948346080d6a5da14a9af6806ca6aa389c023ac2e
+size 437964800

checkpoint-1200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:833bcc074b0f63b6ce1668818458424daf2e72fa88543967d6656e48c66fef30
+size 876050682

checkpoint-1200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e64bcd3a10dc5b13cfcac8c2570bc3ae91092aee7858cc6ca69843c9a2647db7
+size 14244

checkpoint-1200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc40c362852e8ec8df78c719925dcaed04eed3a2e0fd27b70b4009619b5db562
+size 1064

checkpoint-1200/trainer_state.json

@@ -0,0 +1,411 @@
+{
+  "best_metric": 0.25161686539649963,
+  "best_model_checkpoint": "few-shot-learning-classification-bert-sm-5K-abs/checkpoint-1200",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0625,
+      "grad_norm": 4.01630973815918,
+      "learning_rate": 2.5e-06,
+      "loss": 1.3991,
+      "step": 25
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 3.608208179473877,
+      "learning_rate": 5e-06,
+      "loss": 1.3613,
+      "step": 50
+    },
+    {
+      "epoch": 0.1875,
+      "grad_norm": 7.118488311767578,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 1.2086,
+      "step": 75
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 6.23046350479126,
+      "learning_rate": 1e-05,
+      "loss": 0.9404,
+      "step": 100
+    },
+    {
+      "epoch": 0.3125,
+      "grad_norm": 3.4354333877563477,
+      "learning_rate": 1.25e-05,
+      "loss": 0.6381,
+      "step": 125
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 4.42125940322876,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.4253,
+      "step": 150
+    },
+    {
+      "epoch": 0.4375,
+      "grad_norm": 2.722324848175049,
+      "learning_rate": 1.7500000000000002e-05,
+      "loss": 0.3235,
+      "step": 175
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 3.4759390354156494,
+      "learning_rate": 2e-05,
+      "loss": 0.3575,
+      "step": 200
+    },
+    {
+      "epoch": 0.5625,
+      "grad_norm": 5.411329746246338,
+      "learning_rate": 1.9722222222222224e-05,
+      "loss": 0.3401,
+      "step": 225
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 3.3247408866882324,
+      "learning_rate": 1.9444444444444445e-05,
+      "loss": 0.2746,
+      "step": 250
+    },
+    {
+      "epoch": 0.6875,
+      "grad_norm": 2.7389793395996094,
+      "learning_rate": 1.916666666666667e-05,
+      "loss": 0.2436,
+      "step": 275
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 3.443031072616577,
+      "learning_rate": 1.888888888888889e-05,
+      "loss": 0.293,
+      "step": 300
+    },
+    {
+      "epoch": 0.8125,
+      "grad_norm": 2.7726056575775146,
+      "learning_rate": 1.8611111111111114e-05,
+      "loss": 0.2534,
+      "step": 325
+    },
+    {
+      "epoch": 0.875,
+      "grad_norm": 9.94852066040039,
+      "learning_rate": 1.8333333333333333e-05,
+      "loss": 0.2837,
+      "step": 350
+    },
+    {
+      "epoch": 0.9375,
+      "grad_norm": 4.16672945022583,
+      "learning_rate": 1.8055555555555558e-05,
+      "loss": 0.242,
+      "step": 375
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 8.227896690368652,
+      "learning_rate": 1.7777777777777777e-05,
+      "loss": 0.2517,
+      "step": 400
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.90825,
+      "eval_f1_macro": 0.9079265555064384,
+      "eval_f1_micro": 0.90825,
+      "eval_f1_weighted": 0.9079265555064384,
+      "eval_loss": 0.2762264013290405,
+      "eval_precision_macro": 0.911143490468423,
+      "eval_precision_micro": 0.90825,
+      "eval_precision_weighted": 0.9111434904684229,
+      "eval_recall_macro": 0.90825,
+      "eval_recall_micro": 0.90825,
+      "eval_recall_weighted": 0.90825,
+      "eval_runtime": 33.6206,
+      "eval_samples_per_second": 118.975,
+      "eval_steps_per_second": 7.436,
+      "step": 400
+    },
+    {
+      "epoch": 1.0625,
+      "grad_norm": 4.824068069458008,
+      "learning_rate": 1.7500000000000002e-05,
+      "loss": 0.1968,
+      "step": 425
+    },
+    {
+      "epoch": 1.125,
+      "grad_norm": 5.542304992675781,
+      "learning_rate": 1.7222222222222224e-05,
+      "loss": 0.2139,
+      "step": 450
+    },
+    {
+      "epoch": 1.1875,
+      "grad_norm": 9.050013542175293,
+      "learning_rate": 1.6944444444444446e-05,
+      "loss": 0.2118,
+      "step": 475
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 4.569813251495361,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.186,
+      "step": 500
+    },
+    {
+      "epoch": 1.3125,
+      "grad_norm": 6.071652889251709,
+      "learning_rate": 1.638888888888889e-05,
+      "loss": 0.1712,
+      "step": 525
+    },
+    {
+      "epoch": 1.375,
+      "grad_norm": 3.662824869155884,
+      "learning_rate": 1.6111111111111115e-05,
+      "loss": 0.221,
+      "step": 550
+    },
+    {
+      "epoch": 1.4375,
+      "grad_norm": 9.244938850402832,
+      "learning_rate": 1.5833333333333333e-05,
+      "loss": 0.1875,
+      "step": 575
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 1.5883489847183228,
+      "learning_rate": 1.555555555555556e-05,
+      "loss": 0.1935,
+      "step": 600
+    },
+    {
+      "epoch": 1.5625,
+      "grad_norm": 1.2358183860778809,
+      "learning_rate": 1.5277777777777777e-05,
+      "loss": 0.1719,
+      "step": 625
+    },
+    {
+      "epoch": 1.625,
+      "grad_norm": 7.782473087310791,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.1872,
+      "step": 650
+    },
+    {
+      "epoch": 1.6875,
+      "grad_norm": 4.7159223556518555,
+      "learning_rate": 1.4722222222222224e-05,
+      "loss": 0.2126,
+      "step": 675
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 6.77329158782959,
+      "learning_rate": 1.4455555555555555e-05,
+      "loss": 0.1599,
+      "step": 700
+    },
+    {
+      "epoch": 1.8125,
+      "grad_norm": 8.043964385986328,
+      "learning_rate": 1.4177777777777779e-05,
+      "loss": 0.1948,
+      "step": 725
+    },
+    {
+      "epoch": 1.875,
+      "grad_norm": 2.504098892211914,
+      "learning_rate": 1.39e-05,
+      "loss": 0.2085,
+      "step": 750
+    },
+    {
+      "epoch": 1.9375,
+      "grad_norm": 5.84541130065918,
+      "learning_rate": 1.3622222222222223e-05,
+      "loss": 0.1747,
+      "step": 775
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 3.1481826305389404,
+      "learning_rate": 1.3344444444444446e-05,
+      "loss": 0.1559,
+      "step": 800
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.91325,
+      "eval_f1_macro": 0.9131506992934328,
+      "eval_f1_micro": 0.91325,
+      "eval_f1_weighted": 0.9131506992934328,
+      "eval_loss": 0.26044753193855286,
+      "eval_precision_macro": 0.9151077674416565,
+      "eval_precision_micro": 0.91325,
+      "eval_precision_weighted": 0.9151077674416563,
+      "eval_recall_macro": 0.9132500000000001,
+      "eval_recall_micro": 0.91325,
+      "eval_recall_weighted": 0.91325,
+      "eval_runtime": 33.6732,
+      "eval_samples_per_second": 118.789,
+      "eval_steps_per_second": 7.424,
+      "step": 800
+    },
+    {
+      "epoch": 2.0625,
+      "grad_norm": 2.6985983848571777,
+      "learning_rate": 1.3066666666666668e-05,
+      "loss": 0.1303,
+      "step": 825
+    },
+    {
+      "epoch": 2.125,
+      "grad_norm": 0.7569481730461121,
+      "learning_rate": 1.278888888888889e-05,
+      "loss": 0.1298,
+      "step": 850
+    },
+    {
+      "epoch": 2.1875,
+      "grad_norm": 8.65732479095459,
+      "learning_rate": 1.2511111111111112e-05,
+      "loss": 0.1157,
+      "step": 875
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 5.493431091308594,
+      "learning_rate": 1.2233333333333335e-05,
+      "loss": 0.1091,
+      "step": 900
+    },
+    {
+      "epoch": 2.3125,
+      "grad_norm": 3.7139196395874023,
+      "learning_rate": 1.1955555555555556e-05,
+      "loss": 0.1311,
+      "step": 925
+    },
+    {
+      "epoch": 2.375,
+      "grad_norm": 5.745367527008057,
+      "learning_rate": 1.1677777777777779e-05,
+      "loss": 0.145,
+      "step": 950
+    },
+    {
+      "epoch": 2.4375,
+      "grad_norm": 4.435564994812012,
+      "learning_rate": 1.14e-05,
+      "loss": 0.1259,
+      "step": 975
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 4.195883274078369,
+      "learning_rate": 1.1122222222222223e-05,
+      "loss": 0.0984,
+      "step": 1000
+    },
+    {
+      "epoch": 2.5625,
+      "grad_norm": 3.7901735305786133,
+      "learning_rate": 1.0844444444444446e-05,
+      "loss": 0.1098,
+      "step": 1025
+    },
+    {
+      "epoch": 2.625,
+      "grad_norm": 1.1230658292770386,
+      "learning_rate": 1.0566666666666667e-05,
+      "loss": 0.1217,
+      "step": 1050
+    },
+    {
+      "epoch": 2.6875,
+      "grad_norm": 6.928635120391846,
+      "learning_rate": 1.028888888888889e-05,
+      "loss": 0.114,
+      "step": 1075
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 3.181431293487549,
+      "learning_rate": 1.0011111111111112e-05,
+      "loss": 0.1066,
+      "step": 1100
+    },
+    {
+      "epoch": 2.8125,
+      "grad_norm": 3.546902656555176,
+      "learning_rate": 9.733333333333334e-06,
+      "loss": 0.1157,
+      "step": 1125
+    },
+    {
+      "epoch": 2.875,
+      "grad_norm": 3.7598774433135986,
+      "learning_rate": 9.455555555555557e-06,
+      "loss": 0.1517,
+      "step": 1150
+    },
+    {
+      "epoch": 2.9375,
+      "grad_norm": 3.6415417194366455,
+      "learning_rate": 9.17777777777778e-06,
+      "loss": 0.1156,
+      "step": 1175
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.1175150871276855,
+      "learning_rate": 8.900000000000001e-06,
+      "loss": 0.0853,
+      "step": 1200
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9235,
+      "eval_f1_macro": 0.9235095937897977,
+      "eval_f1_micro": 0.9235,
+      "eval_f1_weighted": 0.9235095937897976,
+      "eval_loss": 0.25161686539649963,
+      "eval_precision_macro": 0.9244227025831069,
+      "eval_precision_micro": 0.9235,
+      "eval_precision_weighted": 0.9244227025831069,
+      "eval_recall_macro": 0.9235,
+      "eval_recall_micro": 0.9235,
+      "eval_recall_weighted": 0.9235,
+      "eval_runtime": 33.6749,
+      "eval_samples_per_second": 118.783,
+      "eval_steps_per_second": 7.424,
+      "step": 1200
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 2000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 1.2629557444608e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efc92fedf4fc60faa131e95d710b58d08873843b514f0bc6a392a4f504fc19df
+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 sha256:36686d35fac82608880cab4948346080d6a5da14a9af6806ca6aa389c023ac2e
+size 437964800

runs/May08_09-49-30_a63b8a253cdc/events.out.tfevents.1715161771.a63b8a253cdc.4610.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f6694a8eba853bc52e541fb59bbe18b8fd9e81e7c8421cd36925fb8e7678ddf
-size 21957
+oid sha256:4f2c59c0277cf4e6fc066d72b24a9d0e4082010983349652df840f8c5f6a685b
+size 26309

runs/May08_09-49-30_a63b8a253cdc/events.out.tfevents.1715164079.a63b8a253cdc.4610.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce78b95b19e950d6234454bc7701d2984cf20d7d845799332dce150d9cbb97f3
+size 921

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:efc92fedf4fc60faa131e95d710b58d08873843b514f0bc6a392a4f504fc19df
+size 5048

training_params.json

@@ -0,0 +1,28 @@
+{
+    "data_path": "few-shot-learning-classification-bert-sm-5K-abs/autotrain-data",
+    "model": "google-bert/bert-base-uncased",
+    "lr": 2e-05,
+    "epochs": 5,
+    "max_seq_length": 512,
+    "batch_size": 8,
+    "warmup_ratio": 0.1,
+    "gradient_accumulation": 5,
+    "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-abs",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "evaluation_strategy": "epoch",
+    "username": "pravin691983",
+    "log": "tensorboard"
+}