End of training

README.md

@@ -0,0 +1,93 @@
+---
+library_name: transformers
+license: mit
+base_model: microsoft/git-base
+tags:
+- generated_from_trainer
+model-index:
+- name: git-base-500
+  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-500
+
+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: 0.4821
+- Wer Score: 9.2017
+
+## 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: 2
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 16
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 50
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Wer Score |
+|:-------------:|:------:|:----:|:---------------:|:---------:|
+| 3.581         | 1.576  | 50   | 4.4228          | 7.6017    |
+| 1.1579        | 3.128  | 100  | 0.6864          | 1.0293    |
+| 0.2423        | 4.704  | 150  | 0.4391          | 1.3034    |
+| 0.1852        | 6.256  | 200  | 0.4293          | 7.6948    |
+| 0.1384        | 7.832  | 250  | 0.4313          | 4.6155    |
+| 0.1293        | 9.384  | 300  | 0.4316          | 8.5241    |
+| 0.115         | 10.96  | 350  | 0.4312          | 9.1914    |
+| 0.0914        | 12.512 | 400  | 0.4347          | 3.3466    |
+| 0.0927        | 14.064 | 450  | 0.4401          | 8.8345    |
+| 0.0783        | 15.64  | 500  | 0.4409          | 9.2147    |
+| 0.0735        | 17.192 | 550  | 0.4455          | 9.2448    |
+| 0.0616        | 18.768 | 600  | 0.4476          | 9.2526    |
+| 0.0552        | 20.32  | 650  | 0.4498          | 9.2328    |
+| 0.0493        | 21.896 | 700  | 0.4544          | 9.2190    |
+| 0.0457        | 23.448 | 750  | 0.4581          | 9.1862    |
+| 0.0399        | 25.0   | 800  | 0.4583          | 9.2302    |
+| 0.0353        | 26.576 | 850  | 0.4616          | 9.1871    |
+| 0.0348        | 28.128 | 900  | 0.4659          | 9.1733    |
+| 0.0311        | 29.704 | 950  | 0.4694          | 9.2198    |
+| 0.0305        | 31.256 | 1000 | 0.4698          | 9.2379    |
+| 0.0277        | 32.832 | 1050 | 0.4733          | 9.2129    |
+| 0.0253        | 34.384 | 1100 | 0.4740          | 9.2302    |
+| 0.0244        | 35.96  | 1150 | 0.4735          | 9.2043    |
+| 0.0223        | 37.512 | 1200 | 0.4758          | 9.1871    |
+| 0.0223        | 39.064 | 1250 | 0.4779          | 9.2078    |
+| 0.0219        | 40.64  | 1300 | 0.4795          | 9.2078    |
+| 0.0215        | 42.192 | 1350 | 0.4792          | 9.2095    |
+| 0.0202        | 43.768 | 1400 | 0.4797          | 9.2241    |
+| 0.0189        | 45.32  | 1450 | 0.4812          | 9.2034    |
+| 0.019         | 46.896 | 1500 | 0.4818          | 9.2017    |
+| 0.0187        | 48.448 | 1550 | 0.4819          | 9.1853    |
+| 0.0186        | 50.0   | 1600 | 0.4821          | 9.2017    |
+
+
+### Framework versions
+
+- Transformers 4.52.4
+- Pytorch 2.6.0+cu124
+- Datasets 3.6.0
+- Tokenizers 0.21.2

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": "4.52.4"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea3266ac9fda9d06f6cc2702b85e78e1a1436689d449e3848fc4605ec305326e
+oid sha256:18435b53634fd2aa73ca78a29700fa2f73f95ef16201d20d1ac92e01d6a3f04f
 size 706516040