End of training

README.md

@@ -0,0 +1,69 @@
+---
+license: mit
+base_model: Supabase/gte-small
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: v_best_model
+ 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. -->
+
+# v_best_model
+
+This model is a fine-tuned version of [Supabase/gte-small](https://huggingface.co/Supabase/gte-small) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2700
+- Accuracy: 0.9437
+
+## 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: 0.0001
+- train_batch_size: 64
+- eval_batch_size: 64
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 1.639 | 1.0 | 21 | 1.3351 | 0.7606 |
+| 1.065 | 2.0 | 42 | 0.7793 | 0.8592 |
+| 0.6055 | 3.0 | 63 | 0.5200 | 0.8873 |
+| 0.3519 | 4.0 | 84 | 0.3832 | 0.9014 |
+| 0.2186 | 5.0 | 105 | 0.3277 | 0.9155 |
+| 0.1573 | 6.0 | 126 | 0.2844 | 0.9296 |
+| 0.118 | 7.0 | 147 | 0.3185 | 0.9014 |
+| 0.0948 | 8.0 | 168 | 0.2744 | 0.9437 |
+| 0.0831 | 9.0 | 189 | 0.2746 | 0.9437 |
+| 0.0778 | 10.0 | 210 | 0.2700 | 0.9437 |
+
+
+### Framework versions
+
+- Transformers 4.36.2
+- Pytorch 2.0.1+cu117
+- Datasets 2.16.1
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,42 @@
+{
+ "_name_or_path": "Supabase/gte-small",
+ "architectures": [
+ "BertForSequenceClassification"
+ ],
+ "attention_probs_dropout_prob": 0.1,
+ "classifier_dropout": null,
+ "hidden_act": "gelu",
+ "hidden_dropout_prob": 0.1,
+ "hidden_size": 384,
+ "id2label": {
+ "0": "LABEL_0",
+ "1": "LABEL_1",
+ "2": "LABEL_2",
+ "3": "LABEL_3",
+ "4": "LABEL_4",
+ "5": "LABEL_5"
+ },
+ "initializer_range": 0.02,
+ "intermediate_size": 1536,
+ "label2id": {
+ "LABEL_0": 0,
+ "LABEL_1": 1,
+ "LABEL_2": 2,
+ "LABEL_3": 3,
+ "LABEL_4": 4,
+ "LABEL_5": 5
+ },
+ "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": "4.36.2",
+ "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:fa21c38e01984301408f87509d1656595831c8e8320a986e35fad6ed5ed49ede
+size 133472536

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+ "cls_token": {
+ "content": "[CLS]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "mask_token": {
+ "content": "[MASK]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "[PAD]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "sep_token": {
+ "content": "[SEP]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "unk_token": {
+ "content": "[UNK]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}

tokenizer_config.json

@@ -0,0 +1,64 @@
+{
+ "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]",
+ "max_length": 128,
+ "model_max_length": 512,
+ "never_split": null,
+ "pad_to_multiple_of": null,
+ "pad_token": "[PAD]",
+ "pad_token_type_id": 0,
+ "padding_side": "right",
+ "sep_token": "[SEP]",
+ "stride": 0,
+ "strip_accents": null,
+ "tokenize_chinese_chars": true,
+ "tokenizer_class": "BertTokenizer",
+ "truncation_side": "right",
+ "truncation_strategy": "longest_first",
+ "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86566a9b4698cdecf1573173cb12bd8332b5ba3100f49e9b1d2fa459d7ccdc4e
+size 4219