lc_cate

README.md

@@ -0,0 +1,73 @@
+---
+license: mit
+base_model: microsoft/deberta-v3-small
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+- precision
+- recall
+model-index:
+- name: lc_cate
+  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. -->
+
+# lc_cate
+
+This model is a fine-tuned version of [microsoft/deberta-v3-small](https://huggingface.co/microsoft/deberta-v3-small) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2644
+- Accuracy: 0.7455
+- F1: 0.7666
+- Precision: 0.7883
+- Recall: 0.7460
+
+## 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: 64
+- eval_batch_size: 128
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 8
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
+| No log        | 1.0   | 32   | 0.3856          | 0.5792   | 0.6540 | 0.7474    | 0.5813 |
+| No log        | 2.0   | 64   | 0.3258          | 0.6733   | 0.6918 | 0.7098    | 0.6746 |
+| No log        | 3.0   | 96   | 0.3051          | 0.6713   | 0.7070 | 0.7451    | 0.6726 |
+| No log        | 4.0   | 128  | 0.3030          | 0.7154   | 0.7345 | 0.7537    | 0.7163 |
+| No log        | 5.0   | 160  | 0.2689          | 0.7335   | 0.7637 | 0.7957    | 0.7341 |
+| No log        | 6.0   | 192  | 0.2712          | 0.7355   | 0.7626 | 0.7910    | 0.7361 |
+| No log        | 7.0   | 224  | 0.2645          | 0.7455   | 0.7673 | 0.7899    | 0.7460 |
+| No log        | 8.0   | 256  | 0.2644          | 0.7455   | 0.7666 | 0.7883    | 0.7460 |
+
+
+### Framework versions
+
+- Transformers 4.42.4
+- Pytorch 2.3.1+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "microsoft/deberta-v3-small",
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LEGAL & COMPLIANCE (INTERNAL)",
+    "1": "L&C ADVISORY/INQUIRIES",
+    "2": "L&C PROCESSING REQUEST",
+    "3": "L&C REQUEST FOR DOCUMENTS"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "L&C ADVISORY/INQUIRIES": 1,
+    "L&C PROCESSING REQUEST": 2,
+    "L&C REQUEST FOR DOCUMENTS": 3,
+    "LEGAL & COMPLIANCE (INTERNAL)": 0
+  },
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "problem_type": "multi_label_classification",
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:087bd30aa9a73538c6066999145f28cdc5655b9c0f37b978249c2199dca94d63
+size 567604704

runs/Jul30_02-52-31_c55f04552318/events.out.tfevents.1722307957.c55f04552318.3104.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d55d703721e851ee6c341a4941cd26de296c60151a94690658b45c3765e644ff
+size 9437

runs/Jul30_02-52-31_c55f04552318/events.out.tfevents.1722308242.c55f04552318.3104.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d1ad98fc7bde1941ab5aa6f88cc736e265ee121387bd4cd4da7aa1fbe95ee62
+size 560

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:148e25d56e77ade2b238617d9801d5bdefdac5c3fe88693e3ae6585f5189b57b
+size 5112