Skip to main content
l2hmc-qcd
Projects
Megatron-DS-Benchmarking
Project
Workspace
Runs
Automat.
Sweeps
Reports
Artifacts

Saforem2's workspace

Showing first 10 groups
204060Time (minutes)020406080100
MODEL_SIZE: GPT33B, machine: ThetaGPU, world_size: 32, env.SP_TYPE: megatron, micro_batch_size: 1, seq_length: 300000, env.GAS: 1, global_batch_size: 1, zero_stage: 1, env.MPSIZE: 32, env.PPSIZE: 1, env.SPSIZE: 1, use_flash_attn: true GPU 0 Utilization (%)
MODEL_SIZE: GPT33B, machine: ThetaGPU, world_size: 32, env.SP_TYPE: megatron, micro_batch_size: 1, seq_length: 288000, env.GAS: 1, global_batch_size: 1, zero_stage: 1, env.MPSIZE: 32, env.PPSIZE: 1, env.SPSIZE: 1, use_flash_attn: true GPU 0 Utilization (%)
MODEL_SIZE: GPT33B, machine: ThetaGPU, world_size: 32, env.SP_TYPE: megatron, micro_batch_size: 1, seq_length: 200000, env.GAS: 1, global_batch_size: 1, zero_stage: 1, env.MPSIZE: 32, env.PPSIZE: 1, env.SPSIZE: 1, use_flash_attn: true GPU 0 Utilization (%)
MODEL_SIZE: GPT33B, machine: ThetaGPU, world_size: 32, env.SP_TYPE: megatron, micro_batch_size: 1, seq_length: 192000, env.GAS: 1, global_batch_size: 1, zero_stage: 1, env.MPSIZE: 32, env.PPSIZE: 1, env.SPSIZE: 1, use_flash_attn: true GPU 0 Utilization (%)
MODEL_SIZE: GPT33B, machine: ThetaGPU, world_size: 32, env.SP_TYPE: megatron, micro_batch_size: 1, seq_length: 300000, env.GAS: 1, global_batch_size: 1, zero_stage: 1, env.MPSIZE: 32, env.PPSIZE: 1, env.SPSIZE: 1, use_flash_attn: true GPU 1 Utilization (%)
MODEL_SIZE: GPT33B, machine: ThetaGPU, world_size: 32, env.SP_TYPE: megatron, micro_batch_size: 1, seq_length: 288000, env.GAS: 1, global_batch_size: 1, zero_stage: 1, env.MPSIZE: 32, env.PPSIZE: 1, env.SPSIZE: 1, use_flash_attn: true GPU 1 Utilization (%)
MODEL_SIZE: GPT33B, machine: ThetaGPU, world_size: 32, env.SP_TYPE: megatron, micro_batch_size: 1, seq_length: 200000, env.GAS: 1, global_batch_size: 1, zero_stage: 1, env.MPSIZE: 32, env.PPSIZE: 1, env.SPSIZE: 1, use_flash_attn: true GPU 1 Utilization (%)
MODEL_SIZE: GPT33B, machine: ThetaGPU, world_size: 32, env.SP_TYPE: megatron, micro_batch_size: 1, seq_length: 192000, env.GAS: 1, global_batch_size: 1, zero_stage: 1, env.MPSIZE: 32, env.PPSIZE: 1, env.SPSIZE: 1, use_flash_attn: true GPU 1 Utilization (%)
MODEL_SIZE: GPT33B, machine: ThetaGPU, world_size: 32, env.SP_TYPE: megatron, micro_batch_size: 1, seq_length: 300000, env.GAS: 1, global_batch_size: 1, zero_stage: 1, env.MPSIZE: 32, env.PPSIZE: 1, env.SPSIZE: 1, use_flash_attn: true GPU 2 Utilization (%)
MODEL_SIZE: GPT33B, machine: ThetaGPU, world_size: 32, env.SP_TYPE: megatron, micro_batch_size: 1, seq_length: 288000, env.GAS: 1, global_batch_size: 1, zero_stage: 1, env.MPSIZE: 32, env.PPSIZE: 1, env.SPSIZE: 1, use_flash_attn: true GPU 2 Utilization (%)
MODEL_SIZE: GPT33B, machine: ThetaGPU, world_size: 32, env.SP_TYPE: megatron, micro_batch_size: 1, seq_length: 200000, env.GAS: 1, global_batch_size: 1, zero_stage: 1, env.MPSIZE: 32, env.PPSIZE: 1, env.SPSIZE: 1, use_flash_attn: true GPU 2 Utilization (%)
MODEL_SIZE: GPT33B, machine: ThetaGPU, world_size: 32, env.SP_TYPE: megatron, micro_batch_size: 1, seq_length: 192000, env.GAS: 1, global_batch_size: 1, zero_stage: 1, env.MPSIZE: 32, env.PPSIZE: 1, env.SPSIZE: 1, use_flash_attn: true GPU 2 Utilization (%)
MODEL_SIZE: GPT33B, machine: ThetaGPU, world_size: 32, env.SP_TYPE: megatron, micro_batch_size: 1, seq_length: 300000, env.GAS: 1, global_batch_size: 1, zero_stage: 1, env.MPSIZE: 32, env.PPSIZE: 1, env.SPSIZE: 1, use_flash_attn: true GPU 3 Utilization (%)
MODEL_SIZE: GPT33B, machine: ThetaGPU, world_size: 32, env.SP_TYPE: megatron, micro_batch_size: 1, seq_length: 288000, env.GAS: 1, global_batch_size: 1, zero_stage: 1, env.MPSIZE: 32, env.PPSIZE: 1, env.SPSIZE: 1, use_flash_attn: true GPU 3 Utilization (%)
MODEL_SIZE: GPT33B, machine: ThetaGPU, world_size: 32, env.SP_TYPE: megatron, micro_batch_size: 1, seq_length: 200000, env.GAS: 1, global_batch_size: 1, zero_stage: 1, env.MPSIZE: 32, env.PPSIZE: 1, env.SPSIZE: 1, use_flash_attn: true GPU 3 Utilization (%)
MODEL_SIZE: GPT33B, machine: ThetaGPU, world_size: 32, env.SP_TYPE: megatron, micro_batch_size: 1, seq_length: 192000, env.GAS: 1, global_batch_size: 1, zero_stage: 1, env.MPSIZE: 32, env.PPSIZE: 1, env.SPSIZE: 1, use_flash_attn: true GPU 3 Utilization (%)
MODEL_SIZE: GPT33B, machine: ThetaGPU, world_size: 32, env.SP_TYPE: megatron, micro_batch_size: 1, seq_length: 300000, env.GAS: 1, global_batch_size: 1, zero_stage: 1, env.MPSIZE: 32, env.PPSIZE: 1, env.SPSIZE: 1, use_flash_attn: true GPU 4 Utilization (%)
MODEL_SIZE: GPT33B, machine: ThetaGPU, world_size: 32, env.SP_TYPE: megatron, micro_batch_size: 1, seq_length: 288000, env.GAS: 1, global_batch_size: 1, zero_stage: 1, env.MPSIZE: 32, env.PPSIZE: 1, env.SPSIZE: 1, use_flash_attn: true GPU 4 Utilization (%)
MODEL_SIZE: GPT33B, machine: ThetaGPU, world_size: 32, env.SP_TYPE: megatron, micro_batch_size: 1, seq_length: 200000, env.GAS: 1, global_batch_size: 1, zero_stage: 1, env.MPSIZE: 32, env.PPSIZE: 1, env.SPSIZE: 1, use_flash_attn: true GPU 4 Utilization (%)
MODEL_SIZE: GPT33B, machine: ThetaGPU, world_size: 32, env.SP_TYPE: megatron, micro_batch_size: 1, seq_length: 192000, env.GAS: 1, global_batch_size: 1, zero_stage: 1, env.MPSIZE: 32, env.PPSIZE: 1, env.SPSIZE: 1, use_flash_attn: true GPU 4 Utilization (%)
MODEL_SIZE: GPT33B, machine: ThetaGPU, world_size: 32, env.SP_TYPE: megatron, micro_batch_size: 1, seq_length: 300000, env.GAS: 1, global_batch_size: 1, zero_stage: 1, env.MPSIZE: 32, env.PPSIZE: 1, env.SPSIZE: 1, use_flash_attn: true GPU 5 Utilization (%)
MODEL_SIZE: GPT33B, machine: ThetaGPU, world_size: 32, env.SP_TYPE: megatron, micro_batch_size: 1, seq_length: 288000, env.GAS: 1, global_batch_size: 1, zero_stage: 1, env.MPSIZE: 32, env.PPSIZE: 1, env.SPSIZE: 1, use_flash_attn: true GPU 5 Utilization (%)
MODEL_SIZE: GPT33B, machine: ThetaGPU, world_size: 32, env.SP_TYPE: megatron, micro_batch_size: 1, seq_length: 200000, env.GAS: 1, global_batch_size: 1, zero_stage: 1, env.MPSIZE: 32, env.PPSIZE: 1, env.SPSIZE: 1, use_flash_attn: true GPU 5 Utilization (%)
MODEL_SIZE: GPT33B, machine: ThetaGPU, world_size: 32, env.SP_TYPE: megatron, micro_batch_size: 1, seq_length: 192000, env.GAS: 1, global_batch_size: 1, zero_stage: 1, env.MPSIZE: 32, env.PPSIZE: 1, env.SPSIZE: 1, use_flash_attn: true GPU 5 Utilization (%)
MODEL_SIZE: GPT33B, machine: ThetaGPU, world_size: 32, env.SP_TYPE: megatron, micro_batch_size: 1, seq_length: 300000, env.GAS: 1, global_batch_size: 1, zero_stage: 1, env.MPSIZE: 32, env.PPSIZE: 1, env.SPSIZE: 1, use_flash_attn: true GPU 6 Utilization (%)
MODEL_SIZE: GPT33B, machine: ThetaGPU, world_size: 32, env.SP_TYPE: megatron, micro_batch_size: 1, seq_length: 288000, env.GAS: 1, global_batch_size: 1, zero_stage: 1, env.MPSIZE: 32, env.PPSIZE: 1, env.SPSIZE: 1, use_flash_attn: true GPU 6 Utilization (%)
MODEL_SIZE: GPT33B, machine: ThetaGPU, world_size: 32, env.SP_TYPE: megatron, micro_batch_size: 1, seq_length: 200000, env.GAS: 1, global_batch_size: 1, zero_stage: 1, env.MPSIZE: 32, env.PPSIZE: 1, env.SPSIZE: 1, use_flash_attn: true GPU 6 Utilization (%)
MODEL_SIZE: GPT33B, machine: ThetaGPU, world_size: 32, env.SP_TYPE: megatron, micro_batch_size: 1, seq_length: 192000, env.GAS: 1, global_batch_size: 1, zero_stage: 1, env.MPSIZE: 32, env.PPSIZE: 1, env.SPSIZE: 1, use_flash_attn: true GPU 6 Utilization (%)
MODEL_SIZE: GPT33B, machine: ThetaGPU, world_size: 32, env.SP_TYPE: megatron, micro_batch_size: 1, seq_length: 300000, env.GAS: 1, global_batch_size: 1, zero_stage: 1, env.MPSIZE: 32, env.PPSIZE: 1, env.SPSIZE: 1, use_flash_attn: true GPU 7 Utilization (%)
MODEL_SIZE: GPT33B, machine: ThetaGPU, world_size: 32, env.SP_TYPE: megatron, micro_batch_size: 1, seq_length: 288000, env.GAS: 1, global_batch_size: 1, zero_stage: 1, env.MPSIZE: 32, env.PPSIZE: 1, env.SPSIZE: 1, use_flash_attn: true GPU 7 Utilization (%)
MODEL_SIZE: GPT33B, machine: ThetaGPU, world_size: 32, env.SP_TYPE: megatron, micro_batch_size: 1, seq_length: 200000, env.GAS: 1, global_batch_size: 1, zero_stage: 1, env.MPSIZE: 32, env.PPSIZE: 1, env.SPSIZE: 1, use_flash_attn: true GPU 7 Utilization (%)
MODEL_SIZE: GPT33B, machine: ThetaGPU, world_size: 32, env.SP_TYPE: megatron, micro_batch_size: 1, seq_length: 192000, env.GAS: 1, global_batch_size: 1, zero_stage: 1, env.MPSIZE: 32, env.PPSIZE: 1, env.SPSIZE: 1, use_flash_attn: true GPU 7 Utilization (%)