Training in progress, epoch 1

eval_job_output.txt

@@ -1,4 +1,4 @@
-slurm submission log: 2024-05-09 15:03:33.472877
+slurm submission log: 2024-05-09 22:15:11.257620
 created following sbatch script: 
 
 ###############################
@@ -7,13 +7,13 @@ created following sbatch script:
 
 #SBATCH --account=nlp
 #SBATCH --cpus-per-task=16
-#SBATCH --dependency=afterok:7592321
+#SBATCH --dependency=afterok:7593072
 #SBATCH --gres=gpu:1
-#SBATCH --job-name=tthrush-job-2121767
+#SBATCH --job-name=tthrush-job-3898793
 #SBATCH --mem=60G
 #SBATCH --nodelist=sphinx2
 #SBATCH --open-mode=append
-#SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/llms_2/pythia-70m_sciq/eval_job_output.txt
+#SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/llms_3/pythia-70m_sciq/eval_job_output.txt
 #SBATCH --partition=sphinx
 #SBATCH --time=14-0
 
@@ -24,7 +24,7 @@ created following sbatch script:
 cd .
 
 # launch commands
-srun --unbuffered run_as_child_processes 'lm_eval --model hf --model_args pretrained=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/llms_2/pythia-70m_sciq,revision=main,dtype=float16,trust_remote_code=True --tasks xnli_en,xnli_fr,sciq,piqa,lambada,arc_easy --device cuda --output_path /juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/llms_2/pythia-70m_sciq/perf'
+srun --unbuffered run_as_child_processes 'lm_eval --model hf --model_args pretrained=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/llms_3/pythia-70m_sciq,revision=main,dtype=float16,trust_remote_code=True --tasks xnli_en,xnli_fr,sciq,piqa,lambada,arc_easy --device cuda --output_path /juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/llms_3/pythia-70m_sciq/perf'
 
 ###############################
 
@@ -34,7 +34,133 @@ submission to slurm complete!
 ###############################
 slurm submission output
 
-Submitted batch job 7592322
+Submitted batch job 7593073
+
+
+
+###############################
+
+slurm submission log: 2024-05-09 23:03:14.163910
+created following sbatch script: 
+
+###############################
+
+#!/bin/bash
+
+#SBATCH --account=nlp
+#SBATCH --cpus-per-task=16
+#SBATCH --dependency=afterok:7593150
+#SBATCH --gres=gpu:1
+#SBATCH --job-name=tthrush-job-4358983
+#SBATCH --mem=60G
+#SBATCH --nodelist=sphinx2
+#SBATCH --open-mode=append
+#SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/llms_3/pythia-70m_sciq/eval_job_output.txt
+#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 'lm_eval --model hf --model_args pretrained=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/llms_3/pythia-70m_sciq,revision=main,dtype=float16,trust_remote_code=True --tasks xnli_en,xnli_fr,sciq,piqa,lambada,arc_easy --device cuda --output_path /juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/llms_3/pythia-70m_sciq/perf'
+
+###############################
+
+submission to slurm complete!
+
+
+###############################
+slurm submission output
+
+Submitted batch job 7593151
+
+
+
+###############################
+
+slurm submission log: 2024-05-10 08:21:53.588187
+created following sbatch script: 
+
+###############################
+
+#!/bin/bash
+
+#SBATCH --account=nlp
+#SBATCH --cpus-per-task=16
+#SBATCH --dependency=afterok:7593609
+#SBATCH --gres=gpu:1
+#SBATCH --job-name=tthrush-job-2971685
+#SBATCH --mem=60G
+#SBATCH --nodelist=sphinx1
+#SBATCH --open-mode=append
+#SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/llms_3/pythia-70m_sciq/eval_job_output.txt
+#SBATCH --partition=sphinx
+#SBATCH --time=14-0
+
+# activate your desired anaconda environment
+. /nlp/scr/tthrush/miniconda3/etc/profile.d/conda.sh ; conda activate pretraining-coreset-selection
+
+# cd to working directory
+cd .
+
+# launch commands
+srun --unbuffered run_as_child_processes 'lm_eval --model hf --model_args pretrained=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/llms_3/pythia-70m_sciq,revision=main,dtype=float16,trust_remote_code=True --tasks xnli_en,xnli_fr,sciq,piqa,lambada,arc_easy --device cuda --output_path /juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/llms_3/pythia-70m_sciq/perf'
+
+###############################
+
+submission to slurm complete!
+
+
+###############################
+slurm submission output
+
+Submitted batch job 7593610
+
+
+
+###############################
+
+slurm submission log: 2024-05-10 08:23:19.697943
+created following sbatch script: 
+
+###############################
+
+#!/bin/bash
+
+#SBATCH --account=nlp
+#SBATCH --cpus-per-task=16
+#SBATCH --dependency=afterok:7593622
+#SBATCH --gres=gpu:1
+#SBATCH --job-name=tthrush-job-3736565
+#SBATCH --mem=60G
+#SBATCH --nodelist=sphinx2
+#SBATCH --open-mode=append
+#SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/llms_3/pythia-70m_sciq/eval_job_output.txt
+#SBATCH --partition=sphinx
+#SBATCH --time=14-0
+
+# activate your desired anaconda environment
+. /nlp/scr/tthrush/miniconda3/etc/profile.d/conda.sh ; conda activate pretraining-coreset-selection
+
+# cd to working directory
+cd .
+
+# launch commands
+srun --unbuffered run_as_child_processes 'lm_eval --model hf --model_args pretrained=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/llms_3/pythia-70m_sciq,revision=main,dtype=float16,trust_remote_code=True --tasks xnli_en,xnli_fr,sciq,piqa,lambada,arc_easy --device cuda --output_path /juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/llms_3/pythia-70m_sciq/perf'
+
+###############################
+
+submission to slurm complete!
+
+
+###############################
+slurm submission output
+
+Submitted batch job 7593623
 
 
 

logs/events.out.tfevents.1715378580.sphinx2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc5ee589231335d27ad6f5b23853eedbfcfede98879160ef7aeba9fe0ce852a8
+size 11509

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:044e607961c73d258eb1029b8abccd40771bbea34d074ff4bb4fc50fe6bd99fb
+oid sha256:553509d9d1ee183f617b165a735939f58c38ab18c3aebe9656e7b5b8291c07eb
 size 281715176

train_job_o

@@ -0,0 +1,84 @@
+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
+
+
+
+###############################
+

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6aaa2fd334b485ddf4113dd54b7b9acb347f131bd2af49a1a9276c1f1bcc363
+oid sha256:18875472afc491b9431a9ba218350700c77cc24cc54e0e61189e595f5b25bb4e
 size 5048