| slurm submission log: 2024-05-09 22:15:10.985393 | |
| created following sbatch script: | |
| ############################### | |
| #!/bin/bash | |
| #SBATCH --account=nlp | |
| #SBATCH --cpus-per-task=16 | |
| #SBATCH --dependency=afterok:7593071 | |
| #SBATCH --gres=gpu:2 | |
| #SBATCH --job-name=tthrush-job-2376031 | |
| #SBATCH --mem=400G | |
| #SBATCH --nodelist=sphinx2 | |
| #SBATCH --open-mode=append | |
| #SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/llms_3/pythia-70m_sciq/train_job_o | |
| #SBATCH --partition=sphinx | |
| #SBATCH --time=14-0 | |
| # activate your desired anaconda environment | |
| . /nlp/scr/tthrush/miniconda3/envs/pretraining-coreset-selection/etc/profile.d/conda.sh ; conda activate pretraining-coreset-selection | |
| # cd to working directory | |
| cd . | |
| # launch commands | |
| srun --unbuffered run_as_child_processes 'utput.txt' 'torchrun --master_port 29502 --nproc_per_node=2 train_llm.py --dataset_id /juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/train_data_3/sciq --output_dir /juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/llms_3/pythia-70m_sciq --o utput_hub_id pythia-70m_sciq --model_id EleutherAI/pythia-70m --num_train_epochs 1 --learning_rate 1e-3 --warmup_ratio=0.1 --gradient_accumulation_steps 2' | |
| ############################### | |
| submission to slurm complete! | |
| ############################### | |
| slurm submission output | |
| Submitted batch job 7593072 | |
| ############################### | |
| slurm submission log: 2024-05-09 23:03:13.895695 | |
| created following sbatch script: | |
| ############################### | |
| #!/bin/bash | |
| #SBATCH --account=nlp | |
| #SBATCH --cpus-per-task=16 | |
| #SBATCH --dependency=afterok:7593149 | |
| #SBATCH --gres=gpu:2 | |
| #SBATCH --job-name=tthrush-job-3384549 | |
| #SBATCH --mem=400G | |
| #SBATCH --nodelist=sphinx2 | |
| #SBATCH --open-mode=append | |
| #SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/llms_3/pythia-70m_sciq/train_job_o | |
| #SBATCH --partition=sphinx | |
| #SBATCH --time=14-0 | |
| # activate your desired anaconda environment | |
| . /nlp/scr/tthrush/miniconda3/envs/pretraining-coreset-selection/etc/profile.d/conda.sh ; conda activate pretraining-coreset-selection | |
| # cd to working directory | |
| cd . | |
| # launch commands | |
| srun --unbuffered run_as_child_processes 'utput.txt' 'torchrun --master_port 29502 --nproc_per_node=2 train_llm.py --dataset_id /juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/train_data_3/sciq --output_dir /juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/llms_3/pythia-70m_sciq --o utput_hub_id pythia-70m_sciq --model_id EleutherAI/pythia-70m --num_train_epochs 1 --learning_rate 1e-3 --warmup_ratio=0.1 --gradient_accumulation_steps 2' | |
| ############################### | |
| submission to slurm complete! | |
| ############################### | |
| slurm submission output | |
| Submitted batch job 7593150 | |
| ############################### | |