gpt4all/gpt4all-training/configs/deepspeed/ds_config_mpt.json
Zach Nussbaum 6c4f449b7a
fix: update train scripts and configs for other models (#1164)
* feat: falcon config

* feat: mpt config

* chore: gitignore

* refactor: step calculation

* fix: attention mask + shuffle on epoch end

* fix: return tensors

* fix: wait for everyone

* chore: config

* chore: ds config

* fix: remove ccols

* fix: logging and saving

* chore: add einops
2023-07-12 15:18:24 -04:00

49 lines
899 B
JSON

{
"train_batch_size": "auto",
"gradient_accumulation_steps": "auto",
"train_micro_batch_size_per_gpu": "auto",
"fp16": {
"enabled": "auto",
"min_loss_scale": 1,
"loss_scale_window": 1000,
"hysteresis": 2,
"initial_scale_power": 32
},
"bf16": {
"enabled": "auto"
},
"gradient_clipping": 1.0,
"zero_optimization": {
"stage": 1,
"offload_param": {
"device": "none"
},
"offload_optimizer": {
"device": "none"
},
"allgather_partitions": true,
"allgather_bucket_size": 5e8,
"contiguous_gradients": true
},
"optimizer": {
"type": "AdamW",
"params": {
"lr": "auto",
"betas": [
0.9,
0.999
],
"eps": 1e-08
}
},
"scheduler": {
"type": "WarmupDecayLR",
"params": {
"warmup_min_lr": 0,
"warmup_max_lr": "auto",
"warmup_num_steps": "auto",
"warmup_type": "linear",
"total_num_steps": "auto"
}
}
}