End of training

README.md

@@ -0,0 +1,67 @@
+---
+license: bsd-3-clause
+base_model: Salesforce/blip-image-captioning-base
+tags:
+- generated_from_trainer
+model-index:
+- name: blip-image-captioning-base-kag100
+  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. -->
+
+# blip-image-captioning-base-kag100
+
+This model is a fine-tuned version of [Salesforce/blip-image-captioning-base](https://huggingface.co/Salesforce/blip-image-captioning-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1348
+- Wer Score: 0.6810
+
+## 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: 10
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Wer Score |
+|:-------------:|:------:|:----:|:---------------:|:---------:|
+| 0.8536        | 0.9259 | 500  | 0.1085          | 0.6764    |
+| 0.0769        | 1.8519 | 1000 | 0.1131          | 0.6641    |
+| 0.0536        | 2.7778 | 1500 | 0.1201          | 0.6949    |
+| 0.0384        | 3.7037 | 2000 | 0.1268          | 0.6687    |
+| 0.0265        | 4.6296 | 2500 | 0.1289          | 0.6934    |
+| 0.0194        | 5.5556 | 3000 | 0.1319          | 0.6810    |
+| 0.0161        | 6.4815 | 3500 | 0.1332          | 0.6749    |
+| 0.0139        | 7.4074 | 4000 | 0.1342          | 0.6656    |
+| 0.0124        | 8.3333 | 4500 | 0.1352          | 0.6795    |
+| 0.0108        | 9.2593 | 5000 | 0.1348          | 0.6810    |
+
+
+### Framework versions
+
+- Transformers 4.40.1
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 30522,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.40.1"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb51641506ec6fce6f5e3e1edafbef881d791dec6e31a40e1edbd733b40d601a
+oid sha256:28b19c0b96ca26611d15eabf896831cca2d010a8fa13ceabbd035647eb37f146
 size 989717056

runs/May08_13-18-37_9f38360247bf/events.out.tfevents.1715174318.9f38360247bf.6087.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ae79a624cbacf663ff171acf79e364ad7ec12439d30acf361ce0666c9c759d6
-size 10123
+oid sha256:6fd643b02fee428d86ed1f96b968a9facc33a2b82e5367f126870d9f89559d79
+size 10477