End of training

README.md

@@ -0,0 +1,69 @@
+---
+license: mit
+base_model: microsoft/git-base
+tags:
+- generated_from_trainer
+metrics:
+- rouge
+model-index:
+- name: GIT_inf_w_caption_blur_ep5_eval
+  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_inf_w_caption_blur_ep5_eval
+
+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: 7.4017
+- Rouge1: 3.8217
+- Rouge2: 0.8923
+- Rougel: 3.3753
+- Rougelsum: 3.3525
+- Gen Len: 705.87
+
+## 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: 16
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
+| No log        | 1.0   | 7    | 8.7893          | 1.8363 | 0.4191 | 1.6897 | 1.7007    | 709.0   |
+| No log        | 2.0   | 14   | 8.1101          | 3.079  | 0.6324 | 2.663  | 2.6628    | 709.0   |
+| No log        | 3.0   | 21   | 7.7192          | 3.4348 | 0.8294 | 3.05   | 3.0533    | 708.99  |
+| No log        | 4.0   | 28   | 7.4875          | 3.6579 | 0.8584 | 3.2341 | 3.2327    | 707.9   |
+| No log        | 5.0   | 35   | 7.4017          | 3.8217 | 0.8923 | 3.3753 | 3.3525    | 705.87  |
+
+
+### Framework versions
+
+- Transformers 4.38.1
+- Pytorch 2.2.1+cu121
+- Datasets 2.17.1
+- Tokenizers 0.15.2

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": "4.38.1"
+}