kosm-checkpoint / README.md
MoonstoneF's picture
Actually updated text prompt to Q-A
40ffd3e verified
|
raw
history blame
1.62 kB
metadata
license: mit
base_model: microsoft/kosmos-2-patch14-224
tags:
  - generated_from_trainer
model-index:
  - name: kosm-checkpoint
    results: []

kosm-checkpoint

This model is a fine-tuned version of microsoft/kosmos-2-patch14-224 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0420

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: 1e-05
  • train_batch_size: 2
  • eval_batch_size: 2
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 8
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • training_steps: 1000

Training results

Training Loss Epoch Step Validation Loss
No log 0.0497 200 0.0700
0.0802 0.0993 400 0.0581
0.0676 0.1490 600 0.0496
0.0584 0.1986 800 0.0450
0.0525 0.2483 1000 0.0420

Framework versions

  • Transformers 4.42.4
  • Pytorch 2.1.2+cu121
  • Datasets 2.15.0
  • Tokenizers 0.19.1