mirror of
https://github.com/acon96/home-llm.git
synced 2026-01-08 21:28:05 -05:00
add gemma 270 to training notebook
This commit is contained in:
31
train.ipynb
31
train.ipynb
@@ -168,7 +168,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "21865d91",
|
||||
"id": "a4297f4e",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Gemma 3 1B"
|
||||
@@ -194,6 +194,35 @@
|
||||
" save_steps=200, save_total_limit=1, eval_steps=200, logging_steps=2,\n",
|
||||
"))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "21865d91",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Gemma 3 270m"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "2c6e8bea",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# HYPERPARAMETERS ARE NOT TUNED YET\n",
|
||||
"do_training_run(TrainingRunArguments(\n",
|
||||
" run_name=get_next_run_name(\"Home-Gemma-3-270m\"),\n",
|
||||
" base_model=\"google/gemma-3-270m\",\n",
|
||||
" bf16=True,\n",
|
||||
" train_dataset=\"data/home_assistant_train.jsonl\",\n",
|
||||
" test_dataset=\"data/home_assistant_test.jsonl\",\n",
|
||||
" learning_rate=2e-5, learning_rate_warmup=0.03, \n",
|
||||
" batch_size=64, micro_batch_size=2, epochs=1,\n",
|
||||
" ctx_size=8192,\n",
|
||||
" save_steps=200, save_total_limit=1, eval_steps=200, logging_steps=2,\n",
|
||||
"))"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
|
||||
Reference in New Issue
Block a user