ctrltokyo/llm_prompt_mask_fill_model

<!-- This model card has been generated automatically according to the information Keras had access to. You should probably proofread and complete it, then remove this comment. -->

ctrltokyo/llmpromptmaskfillmodel

This model is a fine-tuned version of distilbert-base-uncased on the code_instructions_120k dataset. It achieves the following results on the evaluation set:

• —Train Loss: 2.1215
• —Validation Loss: 1.5672
• —Epoch: 0

Model description

It's just distilbert-base-uncased with some fine tuning.

Intended uses & limitations

This model could be used for live autocompletion of PROMPTS in a coding-specific chatbot. Don't try this on code, because it won't work.

Training and evaluation data

Evaluated on 5% of training data. No further evaluation performed at this point. Trained on NVIDIA V100.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• —optimizer: {'inneroptimizer': {'classname': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learningrate': {'classname': 'WarmUp', 'config': {'initiallearningrate': 2e-05, 'decayschedulefn': {'classname': 'PolynomialDecay', 'config': {'initiallearningrate': 2e-05, 'decaysteps': 108, 'endlearningrate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, '_passiveserialization_': True}, 'warmupsteps': 1000, 'power': 1.0, 'name': None}}, 'decay': 0.0, 'beta1': 0.9, 'beta2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weightdecayrate': 0.01}}, 'dynamic': True, 'initialscale': 32768.0, 'dynamicgrowth_steps': 2000}
• —trainingprecision: mixedfloat16

Training results

Framework versions

• —Transformers 4.31.0
• —TensorFlow 2.12.0
• —Datasets 2.14.1
• —Tokenizers 0.13.3