genta-tech/genta-mix

README.md

@@ -0,0 +1,92 @@
+---
+license: mit
+base_model: ilos-vigil/bigbird-small-indonesian
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: test_trainer
+  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. -->
+
+# test_trainer
+
+This model is a fine-tuned version of [ilos-vigil/bigbird-small-indonesian](https://huggingface.co/ilos-vigil/bigbird-small-indonesian) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2500
+- Accuracy: 0.5
+
+## 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: 0.0005
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- total_train_batch_size: 16
+- total_eval_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 1
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 0.2611        | 0.04  | 500   | 0.2617          | 0.5      |
+| 0.2547        | 0.07  | 1000  | 0.2525          | 0.5      |
+| 0.2527        | 0.11  | 1500  | 0.2500          | 0.5      |
+| 0.2523        | 0.14  | 2000  | 0.2522          | 0.5      |
+| 0.253         | 0.18  | 2500  | 0.2504          | 0.5      |
+| 0.252         | 0.21  | 3000  | 0.2553          | 0.5      |
+| 0.2662        | 0.25  | 3500  | 0.2501          | 0.5      |
+| 0.2869        | 0.29  | 4000  | 0.2705          | 0.5      |
+| 0.2534        | 0.32  | 4500  | 0.2505          | 0.5      |
+| 0.252         | 0.36  | 5000  | 0.2504          | 0.5      |
+| 0.2518        | 0.39  | 5500  | 0.2526          | 0.5      |
+| 0.2508        | 0.43  | 6000  | 0.2501          | 0.5      |
+| 0.2512        | 0.46  | 6500  | 0.2501          | 0.5      |
+| 0.251         | 0.5   | 7000  | 0.2500          | 0.5      |
+| 0.2502        | 0.54  | 7500  | 0.2502          | 0.5      |
+| 0.2507        | 0.57  | 8000  | 0.2545          | 0.5      |
+| 0.2511        | 0.61  | 8500  | 0.2509          | 0.5      |
+| 0.2503        | 0.64  | 9000  | 0.2500          | 0.5      |
+| 0.2506        | 0.68  | 9500  | 0.2501          | 0.5      |
+| 0.2505        | 0.71  | 10000 | 0.2504          | 0.5      |
+| 0.2505        | 0.75  | 10500 | 0.2504          | 0.5      |
+| 0.2504        | 0.79  | 11000 | 0.2501          | 0.5      |
+| 0.2502        | 0.82  | 11500 | 0.2500          | 0.5      |
+| 0.2503        | 0.86  | 12000 | 0.2500          | 0.5      |
+| 0.2501        | 0.89  | 12500 | 0.2500          | 0.5      |
+| 0.2503        | 0.93  | 13000 | 0.2500          | 0.5      |
+| 0.2502        | 0.96  | 13500 | 0.2500          | 0.5      |
+| 0.2502        | 1.0   | 14000 | 0.2500          | 0.5      |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.0.1
+- Datasets 2.15.0
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "ilos-vigil/bigbird-small-indonesian",
+  "architectures": [
+    "BigBirdForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "attention_type": "block_sparse",
+  "block_size": 64,
+  "bos_token_id": 1,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 512,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 4096,
+  "model_type": "big_bird",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 4,
+  "num_random_blocks": 3,
+  "pad_token_id": 0,
+  "problem_type": "regression",
+  "rescale_embeddings": false,
+  "sep_token_id": 66,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 2,
+  "use_bias": true,
+  "use_cache": true,
+  "vocab_size": 30000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:beeebcd4ad2742a40f2368877cb07e1bbe16e6df61caba28afba5a2e169ebf0f
+size 122386804

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5491189832f585cf2d99b4fae594e754df81525f1e06854b88541f1d36578fc
+size 4091