Model Card for Model ID
Model Details
This Model is designed to explain the intent of shell/bash commands.
Run summary:
eval/accuracy 0.98692
eval/loss 0.03852
eval/runtime 46.3558
eval/samples_per_second 18.142
eval/steps_per_second 4.552
train/epoch 3
train/global_step 2271
train/grad_norm 0.00862
train/learning_rate 0.0
train/loss 0.0014
train/total_flos 1.7588107178855055e+18
train/train_loss 0.07747
train/train_runtime 1614.2767
train/train_samples_per_second 14.057
train/train_steps_per_second 1.407
metrics
learning_rate=2e-5,
per_device_train_batch_size=10,
per_device_eval_batch_size=4,
num_train_epochs=3,
weight_decay=0.01,
load_best_model_at_end=True,
metric_for_best_model="accuracy",
- Downloads last month
- 9
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for KakashiH/BashExplainer_Gemma
Base model
google/codegemma-7b-it