Training in progress, epoch 0

eval_job_output.txt

@@ -1,4 +1,4 @@
-slurm submission log: 2024-05-23 14:58:53.803713
+slurm submission log: 2024-05-24 11:42:10.904769
 created following sbatch script: 
 
 ###############################
@@ -7,24 +7,24 @@ created following sbatch script:
 
 #SBATCH --account=nlp
 #SBATCH --cpus-per-task=16
-#SBATCH --dependency=afterok:7645740
+#SBATCH --dependency=afterok:7648449
 #SBATCH --gres=gpu:1
-#SBATCH --job-name=tthrush-job-1104501
+#SBATCH --job-name=tthrush-job-2437039
 #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_sciq_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_sciq_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_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/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_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'
 
 ###############################
 
@@ -34,7 +34,93 @@ submission to slurm complete!
 ###############################
 slurm submission output
 
-Submitted batch job 7645741
+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
 
 
 

logs/events.out.tfevents.1716583437.sphinx2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:336fed18b51c59a42c4e0d7ddbe7e2af3bb2466de4f4bc2de3567ac400e4b03d
+size 11389

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72d975c1a09895fb677a80c6976a87b7c0c808aff25c8bd8eea46a1f10e6607c
+oid sha256:61a4bebdc413eda50b1afca4b1f85d8e92dd18b3e3aac55c140d076328279ef9
 size 281715176

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e5ec4dcc9a1a5c561e3555297a62670552352ebb9dca8bbc21575d63cf52a8c
+oid sha256:89a0a13e12ab5a5a74f69ba2b98abcee0b13224c17dc16f245d07203c86eba98
 size 5240