End of training

README.md

@@ -3,8 +3,6 @@ license: mit
 base_model: microsoft/git-base
 tags:
 - generated_from_trainer
-datasets:
-- imagefolder
 model-index:
 - name: isl-img2text
   results: []
@@ -13,15 +11,17 @@ model-index:
 <!-- 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. -->
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/sigurdurhaukur-team/huggingface/runs/wdrysu9g)
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/sigurdurhaukur-team/huggingface/runs/wdrysu9g)
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/sigurdurhaukur-team/huggingface/runs/wdrysu9g)
 # isl-img2text
 
-This model is a fine-tuned version of [microsoft/git-base](https://huggingface.co/microsoft/git-base) on the imagefolder dataset.
+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: 4.0588
-- Wer Score: 37.0
+- eval_loss: 0.0983
+- eval_wer_score: 0.7295
+- eval_runtime: 20.5346
+- eval_samples_per_second: 7.792
+- eval_steps_per_second: 0.974
+- epoch: 15.0
+- step: 150
 
 ## Model description
 
@@ -41,27 +41,19 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 2
-- eval_batch_size: 2
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 2
-- total_train_batch_size: 4
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 50
 - mixed_precision_training: Native AMP
 
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss | Wer Score |
-|:-------------:|:-----:|:----:|:---------------:|:---------:|
-| 7.786         | 25.0  | 50   | 5.6066          | 38.2222   |
-| 4.6043        | 50.0  | 100  | 4.0588          | 37.0      |
-
-
 ### Framework versions
 
 - Transformers 4.42.3
-- Pytorch 2.1.2+cu118
+- Pytorch 2.0.1
 - Datasets 2.20.0
 - Tokenizers 0.19.1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7c9ecd9c1e598c736442d7b70583fe64abb36e489fbf827b0a2c6994f977a9b
+oid sha256:553b20d245a2ce0c07eb766a38b61a703629021705026ded86a3933d9ec373fe
 size 706516040

runs/Jun29_16-00-09_129-213-21-28/events.out.tfevents.1719676810.129-213-21-28.6668.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d488660387379d4ca155064978d8cbbe9fe5345a65d6a05883f1362e68929cf7
-size 12620
+oid sha256:c26e62963a85a964481dde43ed8a0fe8bd9c1f9d1476086daf5ef70dc5b1c5fb
+size 12944