Upload folder using huggingface_hub

README.md

@@ -0,0 +1,36 @@
+
+---
+tags:
+- autotrain
+- text-classification
+base_model: cross-encoder/nli-roberta-base
+widget:
+- text: "I love AutoTrain"
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Text Classification
+
+## Validation Metrics
+loss: 1.3794080018997192
+
+f1_macro: 0.21842933805832918
+
+f1_micro: 0.4551574223406493
+
+f1_weighted: 0.306703002026862
+
+precision_macro: 0.19546905037281545
+
+precision_micro: 0.4551574223406493
+
+precision_weighted: 0.2510467302490216
+
+recall_macro: 0.2811753463927377
+
+recall_micro: 0.4551574223406493
+
+recall_weighted: 0.4551574223406493
+
+accuracy: 0.4551574223406493

checkpoint-85566/config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "cross-encoder/nli-roberta-base",
+  "_num_labels": 7,
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "College;School;Institute",
+    "1": "Department;Branch",
+    "2": "District;University",
+    "3": "Laboratory;Institute",
+    "4": "Polytechnic;Academy",
+    "5": "School;Institute",
+    "6": "State;Country"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "College;School;Institute": 0,
+    "Department;Branch": 1,
+    "District;University": 2,
+    "Laboratory;Institute": 3,
+    "Polytechnic;Academy": 4,
+    "School;Institute": 5,
+    "State;Country": 6
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

checkpoint-85566/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe5a29d98c1c700db364b57e461500b8136e7fa090f3d47bcf0a2aeffe6ac287
+size 498628204

checkpoint-85566/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f1ac457545db1f44ff3ea44ea8d5b477777ad7694b5cacb76e008fb3a2cc07f
+size 997370618

checkpoint-85566/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b86b46cebe9b9051da88047a07a1f71867f3e1b764e83a5201ed1f892831b761
+size 13990

checkpoint-85566/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2da9d9c3d6898bea5f868ba74168d890d8ea10748b8b08ec89fc4269c633b04
+size 1064

checkpoint-85566/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60879ecc88370920ef972a33f6418ee76aca5b8ae0c0138fd88d52b0728c09f4
+size 5240

config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "cross-encoder/nli-roberta-base",
+  "_num_labels": 7,
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "College;School;Institute",
+    "1": "Department;Branch",
+    "2": "District;University",
+    "3": "Laboratory;Institute",
+    "4": "Polytechnic;Academy",
+    "5": "School;Institute",
+    "6": "State;Country"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "College;School;Institute": 0,
+    "Department;Branch": 1,
+    "District;University": 2,
+    "Laboratory;Institute": 3,
+    "Polytechnic;Academy": 4,
+    "School;Institute": 5,
+    "State;Country": 6
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe5a29d98c1c700db364b57e461500b8136e7fa090f3d47bcf0a2aeffe6ac287
+size 498628204

runs/Sep11_10-55-26_r-5m4ck3r-autotrainers1-nm0vj2jq-600e5-1di1j/events.out.tfevents.1726052127.r-5m4ck3r-autotrainers1-nm0vj2jq-600e5-1di1j.104.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1038ebb4d4779e902e9bea0b36b0f1096e4a89d789f67604110d3f86f6a636f6
-size 739016
+oid sha256:08e0839f15b59f317ceb26d1394c8bd9d3c16c0e05dde7b12707216b8af19b83
+size 741514

runs/Sep11_10-55-26_r-5m4ck3r-autotrainers1-nm0vj2jq-600e5-1di1j/events.out.tfevents.1726309586.r-5m4ck3r-autotrainers1-nm0vj2jq-600e5-1di1j.104.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21ce716cf7ba5aaa817183492db59743b7fb14e3c9bcdf0a347ee2fe93b4b8ca
+size 936

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60879ecc88370920ef972a33f6418ee76aca5b8ae0c0138fd88d52b0728c09f4
+size 5240

training_params.json

@@ -0,0 +1,30 @@
+{
+    "data_path": "address-large-text-classifier/autotrain-data",
+    "model": "cross-encoder/nli-roberta-base",
+    "lr": 5e-05,
+    "epochs": 3,
+    "max_seq_length": 128,
+    "batch_size": 2,
+    "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": "address-large-text-classifier",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "eval_strategy": "epoch",
+    "username": "5m4ck3r",
+    "log": "tensorboard",
+    "early_stopping_patience": 5,
+    "early_stopping_threshold": 0.01
+}