Training in progress, epoch 1

eval_job_output.txt

@@ -1,4 +1,4 @@
-slurm submission log: 2024-05-09 15:03:32.459554
+slurm submission log: 2024-05-09 22:15:09.685549
 created following sbatch script: 
 
 ###############################
@@ -7,13 +7,13 @@ created following sbatch script:
 
 #SBATCH --account=nlp
 #SBATCH --cpus-per-task=16
-#SBATCH --dependency=afterok:7592317
+#SBATCH --dependency=afterok:7593066
 #SBATCH --gres=gpu:1
-#SBATCH --job-name=tthrush-job-964700
+#SBATCH --job-name=tthrush-job-4826856
 #SBATCH --mem=60G
 #SBATCH --nodelist=sphinx2
 #SBATCH --open-mode=append
-#SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/llms_2/pythia-70m_xnli_en/eval_job_output.txt
+#SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/llms_3/pythia-70m_xnli_en/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_xnli_en,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_xnli_en/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_xnli_en,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_xnli_en/perf'
 
 ###############################
 
@@ -34,7 +34,133 @@ submission to slurm complete!
 ###############################
 slurm submission output
 
-Submitted batch job 7592318
+Submitted batch job 7593067
+
+
+
+###############################
+
+slurm submission log: 2024-05-09 23:03:12.596676
+created following sbatch script: 
+
+###############################
+
+#!/bin/bash
+
+#SBATCH --account=nlp
+#SBATCH --cpus-per-task=16
+#SBATCH --dependency=afterok:7593144
+#SBATCH --gres=gpu:1
+#SBATCH --job-name=tthrush-job-1449593
+#SBATCH --mem=60G
+#SBATCH --nodelist=sphinx2
+#SBATCH --open-mode=append
+#SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/llms_3/pythia-70m_xnli_en/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_xnli_en,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_xnli_en/perf'
+
+###############################
+
+submission to slurm complete!
+
+
+###############################
+slurm submission output
+
+Submitted batch job 7593145
+
+
+
+###############################
+
+slurm submission log: 2024-05-10 08:21:52.650420
+created following sbatch script: 
+
+###############################
+
+#!/bin/bash
+
+#SBATCH --account=nlp
+#SBATCH --cpus-per-task=16
+#SBATCH --dependency=afterok:7593605
+#SBATCH --gres=gpu:1
+#SBATCH --job-name=tthrush-job-1511651
+#SBATCH --mem=60G
+#SBATCH --nodelist=sphinx1
+#SBATCH --open-mode=append
+#SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/llms_3/pythia-70m_xnli_en/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_xnli_en,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_xnli_en/perf'
+
+###############################
+
+submission to slurm complete!
+
+
+###############################
+slurm submission output
+
+Submitted batch job 7593606
+
+
+
+###############################
+
+slurm submission log: 2024-05-10 08:23:18.600174
+created following sbatch script: 
+
+###############################
+
+#!/bin/bash
+
+#SBATCH --account=nlp
+#SBATCH --cpus-per-task=16
+#SBATCH --dependency=afterok:7593618
+#SBATCH --gres=gpu:1
+#SBATCH --job-name=tthrush-job-2660082
+#SBATCH --mem=60G
+#SBATCH --nodelist=sphinx2
+#SBATCH --open-mode=append
+#SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/llms_3/pythia-70m_xnli_en/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_xnli_en,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_xnli_en/perf'
+
+###############################
+
+submission to slurm complete!
+
+
+###############################
+slurm submission output
+
+Submitted batch job 7593619
 
 
 

logs/events.out.tfevents.1715378050.sphinx2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:367b56a7197e3e691141f03054206d000081646ff06bfbe1388b784a99ac7de9
+size 11521

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b273ff2a9804e3488f6f847e84b099718af578ca28877329de9c2dc7acf7293
+oid sha256:d75ce8b0dffc07c7350558ed3e247117b68570fc0d7d717b2f8906caa9f00f00
 size 281715176

train_job_o

@@ -0,0 +1,84 @@
+slurm submission log: 2024-05-09 22:15:09.451748
+created following sbatch script: 
+
+###############################
+
+#!/bin/bash
+
+#SBATCH --account=nlp
+#SBATCH --cpus-per-task=16
+#SBATCH --dependency=afterok:7593065
+#SBATCH --gres=gpu:2
+#SBATCH --job-name=tthrush-job-3358034
+#SBATCH --mem=400G
+#SBATCH --nodelist=sphinx2
+#SBATCH --open-mode=append
+#SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/llms_3/pythia-70m_xnli_en/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 29500 --nproc_per_node=2 train_llm.py --dataset_id /juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/train_data_3/xnli_en --output_dir /juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/llms_3/pythia-70m_xnli_en --o    utput_hub_id pythia-70m_xnli_en --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 7593066
+
+
+
+###############################
+
+slurm submission log: 2024-05-09 23:03:12.351551
+created following sbatch script: 
+
+###############################
+
+#!/bin/bash
+
+#SBATCH --account=nlp
+#SBATCH --cpus-per-task=16
+#SBATCH --dependency=afterok:7593143
+#SBATCH --gres=gpu:2
+#SBATCH --job-name=tthrush-job-2078504
+#SBATCH --mem=400G
+#SBATCH --nodelist=sphinx2
+#SBATCH --open-mode=append
+#SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/llms_3/pythia-70m_xnli_en/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 29500 --nproc_per_node=2 train_llm.py --dataset_id /juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/train_data_3/xnli_en --output_dir /juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/llms_3/pythia-70m_xnli_en --o    utput_hub_id pythia-70m_xnli_en --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 7593144
+
+
+
+###############################
+

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ff883ad86802128c0aa97e80f71b71c55a94c13a43f3cae8dfab6dfcb3e074d
+oid sha256:4d9e15a46006853a122970f426d6179ad8f955096cd5269037dcc8e49a307e60
 size 5112