Training in progress, epoch 1

eval_job_output.txt

@@ -1,4 +1,4 @@
-slurm submission log: 2024-05-09 15:03:34.997660
+slurm submission log: 2024-05-09 22:15:13.606492
 created following sbatch script: 
 
 ###############################
@@ -7,13 +7,13 @@ created following sbatch script:
 
 #SBATCH --account=nlp
 #SBATCH --cpus-per-task=16
-#SBATCH --dependency=afterok:7592327
+#SBATCH --dependency=afterok:7593081
 #SBATCH --gres=gpu:1
-#SBATCH --job-name=tthrush-job-3419847
+#SBATCH --job-name=tthrush-job-1314089
 #SBATCH --mem=60G
 #SBATCH --nodelist=sphinx2
 #SBATCH --open-mode=append
-#SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/llms_2/pythia-70m_arc_easy/eval_job_output.txt
+#SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/llms_3/pythia-70m_arc_easy/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_arc_easy,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_arc_easy/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_arc_easy,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_arc_easy/perf'
 
 ###############################
 
@@ -34,7 +34,133 @@ submission to slurm complete!
 ###############################
 slurm submission output
 
-Submitted batch job 7592328
+Submitted batch job 7593082
+
+
+
+###############################
+
+slurm submission log: 2024-05-09 23:03:16.593571
+created following sbatch script: 
+
+###############################
+
+#!/bin/bash
+
+#SBATCH --account=nlp
+#SBATCH --cpus-per-task=16
+#SBATCH --dependency=afterok:7593159
+#SBATCH --gres=gpu:1
+#SBATCH --job-name=tthrush-job-1934302
+#SBATCH --mem=60G
+#SBATCH --nodelist=sphinx2
+#SBATCH --open-mode=append
+#SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/llms_3/pythia-70m_arc_easy/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_arc_easy,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_arc_easy/perf'
+
+###############################
+
+submission to slurm complete!
+
+
+###############################
+slurm submission output
+
+Submitted batch job 7593160
+
+
+
+###############################
+
+slurm submission log: 2024-05-10 08:21:55.097144
+created following sbatch script: 
+
+###############################
+
+#!/bin/bash
+
+#SBATCH --account=nlp
+#SBATCH --cpus-per-task=16
+#SBATCH --dependency=afterok:7593615
+#SBATCH --gres=gpu:1
+#SBATCH --job-name=tthrush-job-1652949
+#SBATCH --mem=60G
+#SBATCH --nodelist=sphinx1
+#SBATCH --open-mode=append
+#SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/llms_3/pythia-70m_arc_easy/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_arc_easy,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_arc_easy/perf'
+
+###############################
+
+submission to slurm complete!
+
+
+###############################
+slurm submission output
+
+Submitted batch job 7593616
+
+
+
+###############################
+
+slurm submission log: 2024-05-10 08:23:21.265984
+created following sbatch script: 
+
+###############################
+
+#!/bin/bash
+
+#SBATCH --account=nlp
+#SBATCH --cpus-per-task=16
+#SBATCH --dependency=afterok:7593628
+#SBATCH --gres=gpu:1
+#SBATCH --job-name=tthrush-job-4696529
+#SBATCH --mem=60G
+#SBATCH --nodelist=sphinx2
+#SBATCH --open-mode=append
+#SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/llms_3/pythia-70m_arc_easy/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_arc_easy,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_arc_easy/perf'
+
+###############################
+
+submission to slurm complete!
+
+
+###############################
+slurm submission output
+
+Submitted batch job 7593629
 
 
 

logs/events.out.tfevents.1715379130.sphinx2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64ac36094afdbbec94ef0ccebe19d0ce2c20bed25caee8e4cc3da64caefd3af6
+size 11525

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7983c8343af0c152854a5e7705a951c19f4b0f8e8a8a6387b6abbbca8d3d9e33
+oid sha256:62bc6d540d51bb852727ad007bcbb5e6570a057dd49e748dc87a85855976b878
 size 281715176

train_job_o

@@ -0,0 +1,84 @@
+slurm submission log: 2024-05-09 22:15:13.373799
+created following sbatch script: 
+
+###############################
+
+#!/bin/bash
+
+#SBATCH --account=nlp
+#SBATCH --cpus-per-task=16
+#SBATCH --dependency=afterok:7593080
+#SBATCH --gres=gpu:2
+#SBATCH --job-name=tthrush-job-1909730
+#SBATCH --mem=400G
+#SBATCH --nodelist=sphinx2
+#SBATCH --open-mode=append
+#SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/llms_3/pythia-70m_arc_easy/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 29505 --nproc_per_node=2 train_llm.py --dataset_id /juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/train_data_3/arc_easy --output_dir /juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/llms_3/pythia-70m_arc_easy --o    utput_hub_id pythia-70m_arc_easy --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 7593081
+
+
+
+###############################
+
+slurm submission log: 2024-05-09 23:03:16.360972
+created following sbatch script: 
+
+###############################
+
+#!/bin/bash
+
+#SBATCH --account=nlp
+#SBATCH --cpus-per-task=16
+#SBATCH --dependency=afterok:7593158
+#SBATCH --gres=gpu:2
+#SBATCH --job-name=tthrush-job-1041728
+#SBATCH --mem=400G
+#SBATCH --nodelist=sphinx2
+#SBATCH --open-mode=append
+#SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/llms_3/pythia-70m_arc_easy/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 29505 --nproc_per_node=2 train_llm.py --dataset_id /juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/train_data_3/arc_easy --output_dir /juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/llms_3/pythia-70m_arc_easy --o    utput_hub_id pythia-70m_arc_easy --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 7593159
+
+
+
+###############################
+

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a3e2a60cd14b3dbbaf3d866569ed94ac9b6a79055688c2eb14eeb2de944679d
+oid sha256:fa76f20c5f442a876f1203253c41b87df813ddfe4e21883c4f29a95c52428c94
 size 5112