Upload TFPegasusForConditionalGeneration

README.md

@@ -0,0 +1,56 @@
+---
+tags:
+- generated_from_keras_callback
+model-index:
+- name: pegasus-indonesian-base_finetune
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information Keras had access to. You should
+probably proofread and complete it, then remove this comment. -->
+
+# pegasus-indonesian-base_finetune
+
+This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 1.6196
+- Train Accuracy: 0.1079
+- Validation Loss: 1.4097
+- Validation Accuracy: 0.1153
+- Train Lr: 0.00013661868
+- Epoch: 1
+
+## 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:
+- optimizer: {'name': 'Adafactor', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': False, 'is_legacy_optimizer': False, 'learning_rate': 0.00013661868, 'beta_2_decay': -0.8, 'epsilon_1': 1e-30, 'epsilon_2': 0.001, 'clip_threshold': 1.0, 'relative_step': True}
+- training_precision: float32
+
+### Training results
+
+| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Train Lr      | Epoch |
+|:----------:|:--------------:|:---------------:|:-------------------:|:-------------:|:-----:|
+| 2.3484     | 0.0859         | 1.6304          | 0.1080              | 0.00013661868 | 0     |
+| 1.6196     | 0.1079         | 1.4097          | 0.1153              | 0.00013661868 | 1     |
+
+
+### Framework versions
+
+- Transformers 4.30.2
+- TensorFlow 2.12.0
+- Datasets 2.13.1
+- Tokenizers 0.13.3

config.json

@@ -0,0 +1,31 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "architectures": [
+    "PegasusForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "d_model": 512,
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 0,
+  "dropout": 0.15,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 1,
+  "forced_eos_token_id": 1,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "max_position_embeddings": 1024,
+  "model_type": "pegasus",
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "scale_embedding": false,
+  "transformers_version": "4.30.2",
+  "use_cache": true,
+  "vocab_size": 32103
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "forced_eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.30.2"
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:040db8a62c549588552ed971e84938c3a50fd8969c4c7f8e0163d7046c930a21
+size 524505948