* synced gpus * fix * fix * need to use t5-small for quality tests * notes * complete merge * fix a disappearing std stream problem * start zero3 tests * wip * tune params * sorting out the pre-trained model loading * reworking generate loop wip * wip * style * fix tests * split the tests * refactor tests * wip * parameterized * fix * workout the resume from non-ds checkpoint pass + test * cleanup * remove no longer needed code * split getter/setter functions * complete the docs * suggestions * gpus and their compute capabilities link * Apply suggestions from code review Co-authored-by: Lysandre Debut <lysandre@huggingface.co> * style * remove invalid paramgd * automatically configure zero3 params that rely on hidden size * make _get_resized_embeddings zero3-aware * add test exercising resize_token_embeddings() * add docstring Co-authored-by: Lysandre Debut <lysandre@huggingface.co>
44 lines
943 B
JSON
44 lines
943 B
JSON
{
|
|
"fp16": {
|
|
"enabled": true,
|
|
"loss_scale": 0,
|
|
"loss_scale_window": 1000,
|
|
"initial_scale_power": 16,
|
|
"hysteresis": 2,
|
|
"min_loss_scale": 1
|
|
},
|
|
|
|
"zero_optimization": {
|
|
"stage": 2,
|
|
"allgather_partitions": true,
|
|
"allgather_bucket_size": 2e8,
|
|
"overlap_comm": true,
|
|
"reduce_scatter": true,
|
|
"reduce_bucket_size": 2e8,
|
|
"contiguous_gradients": true,
|
|
"cpu_offload": true
|
|
},
|
|
|
|
"optimizer": {
|
|
"type": "AdamW",
|
|
"params": {
|
|
"lr": 3e-5,
|
|
"betas": [0.8, 0.999],
|
|
"eps": 1e-8,
|
|
"weight_decay": 3e-7
|
|
}
|
|
},
|
|
|
|
"scheduler": {
|
|
"type": "WarmupLR",
|
|
"params": {
|
|
"warmup_min_lr": 0,
|
|
"warmup_max_lr": 3e-5,
|
|
"warmup_num_steps": 500
|
|
}
|
|
},
|
|
|
|
"steps_per_print": 2000,
|
|
"wall_clock_breakdown": false
|
|
}
|