mirror of
https://github.com/rasbt/LLMs-from-scratch.git
synced 2026-04-10 12:33:42 +00:00
Add standalone instruction finetuning script (#233)
This commit is contained in:
committed by
GitHub
parent
c595f3da3f
commit
8ccca3a882
@@ -426,7 +426,7 @@
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"train_portion = int(len(data) * 0.85) # 85% for training\n",
|
||||
"test_portion = int(len(data) * 0.1) # 10% for testing\n",
|
||||
"test_portion = int(len(data) * 0.1) # 10% for testing\n",
|
||||
"val_portion = len(data) - train_portion - test_portion # Remaining 5% for validation\n",
|
||||
"\n",
|
||||
"train_data = data[:train_portion]\n",
|
||||
@@ -1166,7 +1166,8 @@
|
||||
" batch_size=batch_size,\n",
|
||||
" collate_fn=customized_collate_fn,\n",
|
||||
" shuffle=True,\n",
|
||||
" drop_last=True\n",
|
||||
" drop_last=True,\n",
|
||||
" num_workers=num_workers\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
@@ -1185,7 +1186,8 @@
|
||||
" batch_size=batch_size,\n",
|
||||
" collate_fn=customized_collate_fn,\n",
|
||||
" shuffle=False,\n",
|
||||
" drop_last=False\n",
|
||||
" drop_last=False,\n",
|
||||
" num_workers=num_workers\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"test_dataset = InstructionDataset(test_data, tokenizer)\n",
|
||||
@@ -1194,7 +1196,8 @@
|
||||
" batch_size=batch_size,\n",
|
||||
" collate_fn=customized_collate_fn,\n",
|
||||
" shuffle=False,\n",
|
||||
" drop_last=False\n",
|
||||
" drop_last=False,\n",
|
||||
" num_workers=num_workers\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
|
||||
Reference in New Issue
Block a user