Training in progress, epoch 0

eval_job_output.txt

@@ -1,4 +1,4 @@
-slurm submission log: 2024-05-29 11:13:54.170698
+slurm submission log: 2024-05-30 23:53:13.187539
 created following sbatch script: 
 
 ###############################
@@ -7,24 +7,24 @@ created following sbatch script:
 
 #SBATCH --account=nlp
 #SBATCH --cpus-per-task=16
-#SBATCH --dependency=afterok:7667690
+#SBATCH --dependency=afterok:7673212
 #SBATCH --gres=gpu:1
-#SBATCH --job-name=tthrush-job-3245904
+#SBATCH --job-name=tthrush-job-3043295
 #SBATCH --mem=60G
 #SBATCH --nodelist=sphinx1
 #SBATCH --open-mode=append
-#SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/paper_writeup_tests/ordinal_constrained/llms/pythia-70m_xnli_es_1/eval_job_output.txt
+#SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/paper_writeup_tests/ordinal_ph_proj/llms/pythia-70m_xnli_es_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/paper_writeup_tests/ordinal_constrained/llms/pythia-70m_xnli_es_1,revision=main,dtype=float16,trust_remote_code=True --tasks piqa,arc_easy,xnli_en,xnli_fr,xnli_de,xnli_es,sciq,lambada --device cuda --output_path /juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/paper_writeup_tests/ordinal_constrained/llms/pythia-70m_xnli_es_1/perf'
+srun --unbuffered run_as_child_processes 'lm_eval --model hf --model_args pretrained=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/paper_writeup_tests/ordinal_ph_proj/llms/pythia-70m_xnli_es_1,revision=main,dtype=float16,trust_remote_code=True --tasks piqa,arc_easy,xnli_en,xnli_fr,xnli_de,xnli_es,sciq,lambada --device cuda --output_path /juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/paper_writeup_tests/ordinal_ph_proj/llms/pythia-70m_xnli_es_1/perf'
 
 ###############################
 
@@ -34,49 +34,7 @@ submission to slurm complete!
 ###############################
 slurm submission output
 
-Submitted batch job 7667691
-
-
-
-###############################
-
-slurm submission log: 2024-05-30 08:40:47.901673
-created following sbatch script: 
-
-###############################
-
-#!/bin/bash
-
-#SBATCH --account=nlp
-#SBATCH --cpus-per-task=16
-#SBATCH --dependency=afterok:7670601
-#SBATCH --gres=gpu:1
-#SBATCH --job-name=tthrush-job-3932226
-#SBATCH --mem=60G
-#SBATCH --nodelist=sphinx1
-#SBATCH --open-mode=append
-#SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/paper_writeup_tests/ordinal_constrained/llms/pythia-70m_xnli_es_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
-
-# 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/paper_writeup_tests/ordinal_constrained/llms/pythia-70m_xnli_es_1,revision=main,dtype=float16,trust_remote_code=True --tasks piqa,arc_easy,xnli_en,xnli_fr,xnli_de,xnli_es,sciq,lambada --device cuda --output_path /juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/paper_writeup_tests/ordinal_constrained/llms/pythia-70m_xnli_es_1/perf'
-
-###############################
-
-submission to slurm complete!
-
-
-###############################
-slurm submission output
-
-Submitted batch job 7670602
+Submitted batch job 7673213
 
 
 

logs/events.out.tfevents.1717149472.sphinx2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80914a972e058861c694504deaacbd0a186dce81f43e69f771ba221c5a724134
+size 95473

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b22ed50f878b923ab2f951a1f8c2ed14912ab7096cf360c0d7cf9625063e160
+oid sha256:33b7daad8c5649faddfc0acd06b83621bc09f7bdb5450993e7165d2a8f869129
 size 281715176

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76f67480085d9e95ea411eddaee9e6f57f6b47b34d3b957850248a2137d2ae79
+oid sha256:83c40c597a791fc2785f96d0659a964bef92862718f2c1c0a0f4c83a9d590105
 size 5240