Training complete

README.md

@@ -0,0 +1,63 @@
+---
+license: mit
+base_model: microsoft/git-base
+tags:
+- pokemon-git-captions
+- generated_from_trainer
+model-index:
+- name: git-base-pokemon
+  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. -->
+
+# git-base-pokemon
+
+This model is a fine-tuned version of [microsoft/git-base](https://huggingface.co/microsoft/git-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.3390
+- Wer Score: 11.7677
+
+## 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: 128
+- eval_batch_size: 128
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 256
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 50
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Wer Score |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|
+| 7.2428        | 16.67 | 50   | 4.9155          | 21.2828   |
+| 3.5043        | 33.33 | 100  | 2.1489          | 17.5884   |
+| 1.7042        | 50.0  | 150  | 1.3390          | 11.7677   |
+
+
+### Framework versions
+
+- Transformers 4.34.0
+- Pytorch 2.1.0a0+29c30b1
+- Datasets 2.14.5
+- Tokenizers 0.14.1

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 101,
+  "eos_token_id": 102,
+  "pad_token_id": 0,
+  "transformers_version": "4.34.0"
+}