Training in progress, epoch 1

eval_job_output.txt

@@ -1,4 +1,4 @@
-slurm submission log: 2024-05-24 11:42:10.904769
+slurm submission log: 2024-05-24 23:54:02.801635
 created following sbatch script: 
 
 ###############################
@@ -7,13 +7,13 @@ created following sbatch script:
 
 #SBATCH --account=nlp
 #SBATCH --cpus-per-task=16
-#SBATCH --dependency=afterok:7648449
+#SBATCH --dependency=afterok:7649441
 #SBATCH --gres=gpu:1
-#SBATCH --job-name=tthrush-job-2437039
+#SBATCH --job-name=tthrush-job-1955160
 #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_sciq_1/eval_job_output.txt
+#SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/test_ordinal_constrained_big_diff/llms/pythia-70m_sciq_1/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/test_ordinal_constrained_initial_init_min_threshold/llms/pythia-70m_sciq_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_sciq_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_big_diff/llms/pythia-70m_sciq_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_big_diff/llms/pythia-70m_sciq_1/perf'
 
 ###############################
 
@@ -34,93 +34,7 @@ submission to slurm complete!
 ###############################
 slurm submission output
 
-Submitted batch job 7648450
-
-
-
-###############################
-
-/var/lib/slurm/slurmd/job7648450/slurm_script: line 16: /nlp/scr/tthrush/miniconda3/envs/pretraining-coreset-selection/etc/profile.d/conda.sh: No such file or directory
-
-CommandNotFoundError: Your shell has not been properly configured to use 'conda activate'.
-To initialize your shell, run
-
-    $ conda init <SHELL_NAME>
-
-Currently supported shells are:
-  - bash
-  - fish
-  - tcsh
-  - xonsh
-  - zsh
-  - powershell
-
-See 'conda init --help' for more information and options.
-
-IMPORTANT: You may need to close and restart your shell after running 'conda init'.
-
-
-###############################
-start time: 2024-05-24 11:44:53.492934
-machine: sphinx1
-conda env: pretraining-coreset-selection
-###############################
-running following 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_sciq_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_sciq_1/perf
-
-
-###############################
-command outputs: 
-
-
-2024-05-24:11:44:56,229 INFO     [utils.py:145] Note: detected 255 virtual cores but NumExpr set to maximum of 64, check "NUMEXPR_MAX_THREADS" environment variable.
-2024-05-24:11:44:56,229 INFO     [utils.py:148] Note: NumExpr detected 255 cores but "NUMEXPR_MAX_THREADS" not set, so enforcing safe limit of 8.
-2024-05-24:11:44:56,229 INFO     [utils.py:160] NumExpr defaulting to 8 threads.
-2024-05-24:11:44:56,591 INFO     [config.py:58] PyTorch version 2.2.2 available.
-2024-05-24:11:45:00,567 INFO     [__main__.py:156] Verbosity set to INFO
-2024-05-24:11:45:07,210 WARNING  [__init__.py:194] Some tasks could not be loaded due to missing dependencies. Run with `--verbosity DEBUG` for full details.
-srun: Job step aborted: Waiting up to 32 seconds for job step to finish.
-slurmstepd: error: *** JOB 7648450 ON sphinx1 CANCELLED AT 2024-05-24T11:45:39 ***
-slurmstepd: error: *** STEP 7648450.0 ON sphinx1 CANCELLED AT 2024-05-24T11:45:39 ***
-Received SIGTERM, job terminating, terminating 1 processes...
-slurm submission log: 2024-05-24 11:46:16.500701
-created following sbatch script: 
-
-###############################
-
-#!/bin/bash
-
-#SBATCH --account=nlp
-#SBATCH --cpus-per-task=16
-#SBATCH --dependency=afterok:7648481
-#SBATCH --gres=gpu:1
-#SBATCH --job-name=tthrush-job-372659
-#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_sciq_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_sciq_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_sciq_1/perf'
-
-###############################
-
-submission to slurm complete!
-
-
-###############################
-slurm submission output
-
-Submitted batch job 7648482
+Submitted batch job 7649442
 
 
 

logs/events.out.tfevents.1716638120.sphinx2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a86e8c9ab98a468226f77dd552822075f74dade9445693350b07056ae1a9622
+size 11757

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16d5d98dfb903310dfa778a7293e779ee9d90710b91997a8a5cbef4beeb71f77
+oid sha256:8f706f76b0bdccb013ae3106ed175517dc612deb4788b18cb357077a34fd0ab4
 size 281715176

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89a0a13e12ab5a5a74f69ba2b98abcee0b13224c17dc16f245d07203c86eba98
+oid sha256:46a1093854b1dc085cb47307a8ccf603f67215e6816d7415bbf2835bd797f3b5
 size 5240