End of training

README.md

@@ -0,0 +1,71 @@
+---
+base_model: FPTAI/vibert-base-cased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+model-index:
+- name: vibert-base-cased-ed
+  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. -->
+
+# vibert-base-cased-ed
+
+This model is a fine-tuned version of [FPTAI/vibert-base-cased](https://huggingface.co/FPTAI/vibert-base-cased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0595
+- F1 Micro: 0.7034
+- F1 Macro: 0.0430
+- Accuracy: 0.6374
+- Recall Micro: 0.6094
+- Precision Micro: 0.8317
+- Recall Macro: 0.0392
+- Precision Macro: 0.0621
+- F1: 0.5913
+
+## 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 Micro | F1 Macro | Accuracy | Recall Micro | Precision Micro | Recall Macro | Precision Macro | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:--------:|:------------:|:---------------:|:------------:|:---------------:|:------:|
+| 0.0696        | 1.0   | 1526 | 0.0711          | 0.6892   | 0.0243   | 0.7054   | 0.6737       | 0.7054          | 0.0294       | 0.0207          | 0.5573 |
+| 0.055         | 2.0   | 3052 | 0.0622          | 0.6965   | 0.0252   | 0.6345   | 0.6060       | 0.8187          | 0.0265       | 0.0241          | 0.5775 |
+| 0.0631        | 3.0   | 4578 | 0.0598          | 0.7054   | 0.0255   | 0.6436   | 0.6147       | 0.8274          | 0.0268       | 0.0243          | 0.5847 |
+| 0.0534        | 4.0   | 6104 | 0.0591          | 0.6980   | 0.0260   | 0.6268   | 0.5989       | 0.8362          | 0.0265       | 0.0540          | 0.5809 |
+| 0.0296        | 5.0   | 7630 | 0.0595          | 0.7034   | 0.0430   | 0.6374   | 0.6094       | 0.8317          | 0.0392       | 0.0621          | 0.5913 |
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,106 @@
+{
+  "_name_or_path": "FPTAI/vibert-base-cased",
+  "_num_labels": 2,
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Appeal",
+    "1": "Merge-org",
+    "2": "Sue",
+    "3": "O",
+    "4": "End-position",
+    "5": "Start-position",
+    "6": "Transfer-ownership",
+    "7": "Sentence",
+    "8": "Transfer-money",
+    "9": "Trial-hearing",
+    "10": "Die",
+    "11": "Injure",
+    "12": "Release-parole",
+    "13": "Divorce",
+    "14": "Marry",
+    "15": "Pardon",
+    "16": "Meet",
+    "17": "Convict",
+    "18": "Demonstrate",
+    "19": "Start-org",
+    "20": "Extradite",
+    "21": "Fine",
+    "22": "Execute",
+    "23": "Phone-write",
+    "24": "Arrest-jail",
+    "25": "End-org",
+    "26": "Elect",
+    "27": "Declare-bankruptcy",
+    "28": "Nominate",
+    "29": "Attack",
+    "30": "Be-born",
+    "31": "Arquit",
+    "32": "Transport",
+    "33": "Charge-indict"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Appeal": 0,
+    "Arquit": 31,
+    "Arrest-jail": 24,
+    "Attack": 29,
+    "Be-born": 30,
+    "Charge-indict": 33,
+    "Convict": 17,
+    "Declare-bankruptcy": 27,
+    "Demonstrate": 18,
+    "Die": 10,
+    "Divorce": 13,
+    "Elect": 26,
+    "End-org": 25,
+    "End-position": 4,
+    "Execute": 22,
+    "Extradite": 20,
+    "Fine": 21,
+    "Injure": 11,
+    "Marry": 14,
+    "Meet": 16,
+    "Merge-org": 1,
+    "Nominate": 28,
+    "O": 3,
+    "Pardon": 15,
+    "Phone-write": 23,
+    "Release-parole": 12,
+    "Sentence": 7,
+    "Start-org": 19,
+    "Start-position": 5,
+    "Sue": 2,
+    "Transfer-money": 8,
+    "Transfer-ownership": 6,
+    "Transport": 32,
+    "Trial-hearing": 9
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "problem_type": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 38168
+}

logs/events.out.tfevents.1718452370.1f9650542848.648.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:546429020b90f9ed436582464cc0c4070bebcaec89f0f333631a9384431eab28
+size 171283

logs/events.out.tfevents.1718455960.1f9650542848.648.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e9c0eb7c33f7c67e6e29dd4b4eb7c4e39b7f2904fd5a981be941f3964916fdd
+size 791

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63a644f3eba14ffe91ceeda20a1c3eb52c3c0e49f1a207454bc76ba180bed961
+size 461545600

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e068273df845ce42e6fca7e463207b057a715473e8f34533c824f2f33e83544
+size 5112