Delete ds_config.json
Browse files- ds_config.json +0 -50
ds_config.json
DELETED
|
@@ -1,50 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"fp16": {
|
| 3 |
-
"enabled": "auto",
|
| 4 |
-
"loss_scale": 0,
|
| 5 |
-
"loss_scale_window": 1000,
|
| 6 |
-
"initial_scale_power": 16,
|
| 7 |
-
"hysteresis": 2,
|
| 8 |
-
"min_loss_scale": 1
|
| 9 |
-
},
|
| 10 |
-
"optimizer": {
|
| 11 |
-
"type": "AdamW",
|
| 12 |
-
"params": {
|
| 13 |
-
"lr": "auto",
|
| 14 |
-
"betas": "auto",
|
| 15 |
-
"eps": "auto",
|
| 16 |
-
"weight_decay": "auto"
|
| 17 |
-
}
|
| 18 |
-
},
|
| 19 |
-
"scheduler": {
|
| 20 |
-
"type": "WarmupLR",
|
| 21 |
-
"params": {
|
| 22 |
-
"warmup_min_lr": "auto",
|
| 23 |
-
"warmup_max_lr": "auto",
|
| 24 |
-
"warmup_num_steps": "auto"
|
| 25 |
-
}
|
| 26 |
-
},
|
| 27 |
-
"zero_optimization": {
|
| 28 |
-
"stage": 3,
|
| 29 |
-
"allgather_partitions": true,
|
| 30 |
-
"allgather_bucket_size": 2e8,
|
| 31 |
-
"overlap_comm": true,
|
| 32 |
-
"reduce_scatter": true,
|
| 33 |
-
"reduce_bucket_size": 2e8,
|
| 34 |
-
"contiguous_gradients": true,
|
| 35 |
-
"offload_optimizer": {
|
| 36 |
-
"device": "cpu"
|
| 37 |
-
},
|
| 38 |
-
"offload_param": {
|
| 39 |
-
"device": "cpu"
|
| 40 |
-
},
|
| 41 |
-
"stage3_gather_16bit_weights_on_model_save": true
|
| 42 |
-
},
|
| 43 |
-
"gradient_accumulation_steps": "auto",
|
| 44 |
-
"gradient_clipping": "auto",
|
| 45 |
-
"communication_data_type": "fp32",
|
| 46 |
-
"steps_per_print": 1000000000000000,
|
| 47 |
-
"train_batch_size": "auto",
|
| 48 |
-
"train_micro_batch_size_per_gpu": "auto",
|
| 49 |
-
"wall_clock_breakdown": false
|
| 50 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|