Training in progress, epoch 1

eval_job_output.txt

@@ -1,4 +1,4 @@
-slurm submission log: 2024-05-23 14:58:56.198008
+slurm submission log: 2024-05-24 11:42:13.480511
 created following sbatch script: 
 
 ###############################
@@ -7,24 +7,24 @@ created following sbatch script:
 
 #SBATCH --account=nlp
 #SBATCH --cpus-per-task=16
-#SBATCH --dependency=afterok:7645750
+#SBATCH --dependency=afterok:7648458
 #SBATCH --gres=gpu:1
-#SBATCH --job-name=tthrush-job-1922680
+#SBATCH --job-name=tthrush-job-4938142
 #SBATCH --mem=60G
 #SBATCH --nodelist=sphinx1
 #SBATCH --open-mode=append
-#SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/test_ordinal_constrained_initial_init/llms/pythia-70m_arc_easy_1/eval_job_output.txt
+#SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/test_ordinal_constrained_initial_init_min_threshold/llms/pythia-70m_arc_easy_1/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
+. /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/test_ordinal_constrained_initial_init/llms/pythia-70m_arc_easy_1,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/test_ordinal_constrained_initial_init/llms/pythia-70m_arc_easy_1/perf'
+srun --unbuffered run_as_child_processes 'lm_eval --model hf --model_args pretrained=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/test_ordinal_constrained_initial_init_min_threshold/llms/pythia-70m_arc_easy_1,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/test_ordinal_constrained_initial_init_min_threshold/llms/pythia-70m_arc_easy_1/perf'
 
 ###############################
 
@@ -34,7 +34,49 @@ submission to slurm complete!
 ###############################
 slurm submission output
 
-Submitted batch job 7645751
+Submitted batch job 7648459
+
+
+
+###############################
+
+slurm submission log: 2024-05-24 11:46:19.053627
+created following sbatch script: 
+
+###############################
+
+#!/bin/bash
+
+#SBATCH --account=nlp
+#SBATCH --cpus-per-task=16
+#SBATCH --dependency=afterok:7648490
+#SBATCH --gres=gpu:1
+#SBATCH --job-name=tthrush-job-4800860
+#SBATCH --mem=60G
+#SBATCH --nodelist=sphinx1
+#SBATCH --open-mode=append
+#SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/test_ordinal_constrained_initial_init_min_threshold/llms/pythia-70m_arc_easy_1/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/test_ordinal_constrained_initial_init_min_threshold/llms/pythia-70m_arc_easy_1,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/test_ordinal_constrained_initial_init_min_threshold/llms/pythia-70m_arc_easy_1/perf'
+
+###############################
+
+submission to slurm complete!
+
+
+###############################
+slurm submission output
+
+Submitted batch job 7648491
 
 
 

logs/events.out.tfevents.1716583460.sphinx2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05a62d74c1d341b7b95c3a16fc5d318187f8a52ec6506418faccd7f4d3ec5d69
+size 11405

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c25e236991445412ac4d7e4e6c86be63833105cc77aaf725dafb3ef7bf52ea4
+oid sha256:74c2dbf816959e018ebb29ae62e302dbfb7e750616d2b4490507552ff91a5d1a
 size 281715176

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2e0f1b64453deb57b4585bb9d2662803227b4afe9fdc4394afb17c8c31abf8e
+oid sha256:99ad8e550105f83ddb54bb1711a3ce2eaa655a4b53cd3d5d0a45eb3e3555ddc0
 size 5240