change number minimums to 0

gradio calculates 'step' relative to the minimum, so at '1' the step values were all offset awkwardly. 0 isn't valid, but, uh, just don't slam the slider to the left.

modules/training.py

@@ -27,18 +27,18 @@ def create_train_interface():
         with gr.Row():
             # TODO: Implement multi-device support.
             micro_batch_size = gr.Slider(label='Micro Batch Size', value=4, minimum=1, maximum=128, step=1, info='Per-device batch size (NOTE: multiple devices not yet implemented). Increasing this will increase VRAM usage.')
-            batch_size = gr.Slider(label='Batch Size', value=128, minimum=1, maximum=1024, step=4, info='Global batch size. The two batch sizes together determine gradient accumulation (gradientAccum = batch / microBatch). Higher gradient accum values lead to better quality training.')
+            batch_size = gr.Slider(label='Batch Size', value=128, minimum=0, maximum=1024, step=4, info='Global batch size. The two batch sizes together determine gradient accumulation (gradientAccum = batch / microBatch). Higher gradient accum values lead to better quality training.')
 
         with gr.Row():
             epochs = gr.Number(label='Epochs', value=3, info='Number of times every entry in the dataset should be fed into training. So 1 means feed each item in once, 5 means feed it in five times, etc.')
             learning_rate = gr.Textbox(label='Learning Rate', value='3e-4', info='Learning rate, in scientific notation. 3e-4 is a good starting base point. 1e-2 is extremely high, 1e-6 is extremely low.')
 
         # TODO: What is the actual maximum rank? Likely distinct per model. This might be better to somehow be on a log scale.
-        lora_rank = gr.Slider(label='LoRA Rank', value=8, minimum=1, maximum=1024, step=4, info='LoRA Rank, or dimension count. Higher values produce a larger file with better control over the model\'s content. Smaller values produce a smaller file with less overall control. Small values like 4 or 8 are great for stylistic guidance, high values like 128 or 256 are good for teaching content upgrades. Higher ranks also require higher VRAM.')
+        lora_rank = gr.Slider(label='LoRA Rank', value=8, minimum=0, maximum=1024, step=4, info='LoRA Rank, or dimension count. Higher values produce a larger file with better control over the model\'s content. Smaller values produce a smaller file with less overall control. Small values like 4 or 8 are great for stylistic guidance, high values like 128 or 256 are good for teaching content upgrades. Higher ranks also require higher VRAM.')
-        lora_alpha = gr.Slider(label='LoRA Alpha', value=16, minimum=1, maximum=2048, step=4, info='LoRA Alpha. This divided by the rank becomes the scaling of the LoRA. Higher means stronger. A good standard value is twice your Rank.')
+        lora_alpha = gr.Slider(label='LoRA Alpha', value=16, minimum=0, maximum=2048, step=4, info='LoRA Alpha. This divided by the rank becomes the scaling of the LoRA. Higher means stronger. A good standard value is twice your Rank.')
         # TODO: Better explain what this does, in terms of real world effect especially.
         lora_dropout = gr.Slider(label='LoRA Dropout', minimum=0.0, maximum=1.0, step=0.025, value=0.05, info='Percentage probability for dropout of LoRA layers.')
-        cutoff_len = gr.Slider(label='Cutoff Length', minimum=1,maximum=2048, value=256, step=32, info='Cutoff length for text input. Essentially, how long of a line of text to feed in at a time. Higher values require drastically more VRAM.')
+        cutoff_len = gr.Slider(label='Cutoff Length', minimum=0, maximum=2048, value=256, step=32, info='Cutoff length for text input. Essentially, how long of a line of text to feed in at a time. Higher values require drastically more VRAM.')
 
         with gr.Row():
             dataset = gr.Dropdown(choices=get_json_dataset('training/datasets'), value='None', label='Dataset', info='The dataset file to use for training.')