Model save

README.md

@@ -0,0 +1,60 @@
+---
+base_model: tiagoblima/gun-nlth-base
+tags:
+- generated_from_trainer
+model-index:
+- name: t2t-gun-nlth-from-base-ft
+  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. -->
+
+# t2t-gun-nlth-from-base-ft
+
+This model is a fine-tuned version of [tiagoblima/gun-nlth-base](https://huggingface.co/tiagoblima/gun-nlth-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 5.9197
+
+## 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: 5e-05
+- train_batch_size: 2
+- eval_batch_size: 1
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 6.4914        | 0.55  | 4000  | 6.6892          |
+| 6.2748        | 1.1   | 8000  | 8.6345          |
+| 6.0827        | 1.65  | 12000 | 7.7299          |
+| 5.8924        | 2.2   | 16000 | 6.0179          |
+| 5.8561        | 2.74  | 20000 | 5.9197          |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.2+cu121
+- Datasets 2.15.0
+- Tokenizers 0.15.1

generation_config.json

@@ -0,0 +1,16 @@
+{
+  "_from_model_config": true,
+  "bad_words_ids": [
+    [
+      6637
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 6637,
+  "eos_token_id": 2701,
+  "forced_eos_token_id": 2701,
+  "max_length": 512,
+  "num_beams": 2,
+  "pad_token_id": 6637,
+  "transformers_version": "4.35.2"
+}