End of training

README.md

@@ -0,0 +1,66 @@
+---
+base_model: SpanBERT/spanbert-large-cased
+tags:
+- generated_from_trainer
+metrics:
+- f1
+- accuracy
+model-index:
+- name: sapect_complaint_spanbert
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# sapect_complaint_spanbert
+
+This model is a fine-tuned version of [SpanBERT/spanbert-large-cased](https://huggingface.co/SpanBERT/spanbert-large-cased) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1905
+- F1: 0.7365
+- Roc Auc: 0.8250
+- Accuracy: 0.5052
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | F1     | Roc Auc | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|
+| 0.284         | 1.0   | 582  | 0.2261          | 0.6543 | 0.7733  | 0.3720   |
+| 0.2063        | 2.0   | 1164 | 0.1965          | 0.7113 | 0.8003  | 0.4338   |
+| 0.1822        | 3.0   | 1746 | 0.1935          | 0.7197 | 0.8062  | 0.4416   |
+| 0.1632        | 4.0   | 2328 | 0.1918          | 0.7325 | 0.8210  | 0.4897   |
+| 0.1408        | 5.0   | 2910 | 0.1905          | 0.7365 | 0.8250  | 0.5052   |
+
+
+### Framework versions
+
+- Transformers 4.41.1
+- Pytorch 1.13.1+cu117
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,53 @@
+{
+  "_name_or_path": "SpanBERT/spanbert-large-cased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "Over-all_Complaint Label",
+    "1": "provider_response",
+    "2": "misc_info",
+    "3": "credential_error",
+    "4": "net_banking_issue",
+    "5": "consumer_safety",
+    "6": "review",
+    "7": "no_aspects",
+    "8": "general_query",
+    "9": "financial_situation",
+    "10": "financial_info"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "Over-all_Complaint Label": 0,
+    "consumer_safety": 5,
+    "credential_error": 3,
+    "financial_info": 10,
+    "financial_situation": 9,
+    "general_query": 8,
+    "misc_info": 2,
+    "net_banking_issue": 4,
+    "no_aspects": 7,
+    "provider_response": 1,
+    "review": 6
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb23dbdadbae0a5d547d440b3debba42f2699621236738090af1f58d0acca3e8
+size 1334409164

runs/Jun14_19-56-47_iit-p/events.out.tfevents.1718375211.iit-p.30207.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03fe02157f994d5180806a596b9231e2b497bfbd42216771c8d90678b3c426f9
+size 5400

runs/Jun14_19-58-04_iit-p/events.out.tfevents.1718375288.iit-p.30516.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f90894541a13b4ccbf8203f63384c0118fc7927c7d34f0ef37df1c58b622f35
+size 4136

runs/Jun14_19-59-46_iit-p/events.out.tfevents.1718375390.iit-p.31148.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ee6f87c900683dfff30d6f98ec3f5c0c7e666b44cb73a7a91caba973e1f9610
+size 4136

runs/Jun14_20-00-44_iit-p/events.out.tfevents.1718375448.iit-p.31454.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9c96265e8c4e42b3e453fc184619dfe4cfd6a53c25c2048913cb5024b1ff3a8
+size 8909

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 +1,57 @@
+{
+  "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_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "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 sha256:8982f2865b57f23bb8e669eac83d989557732de460ecac5e62e98431b6bf68d5
+size 4667