Model save

README.md

@@ -0,0 +1,61 @@
+---
+license: mit
+base_model: microsoft/git-base
+tags:
+- generated_from_trainer
+model-index:
+- name: output_dir
+  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. -->
+
+# output_dir
+
+This model is a fine-tuned version of [microsoft/git-base](https://huggingface.co/microsoft/git-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8219
+- Wer Score: 4.3488
+
+## 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: 1
+- 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
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Wer Score |
+|:-------------:|:------:|:----:|:---------------:|:---------:|
+| 7.5175        | 0.9091 | 50   | 5.0110          | 10.6279   |
+| 3.4896        | 1.8182 | 100  | 1.9416          | 5.2326    |
+| 1.353         | 2.7273 | 150  | 0.8219          | 4.3488    |
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

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": "4.41.2"
+}

runs/Jun24_20-06-00_8e3b1ee642f7/events.out.tfevents.1719259560.8e3b1ee642f7.3835.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66a9c5b720da9576be05cce10f9fcf5a158dc8902603eb44e8a8200a3b326a93
-size 6621
+oid sha256:431b1de741cd6e0b585fd3ff8f7b118d082f52ecc30d418f5635375c1c57a508
+size 6975