Training in progress, epoch 0

eval_job_output.txt

@@ -1,4 +1,4 @@
-slurm submission log: 2024-05-26 22:30:16.881627
+slurm submission log: 2024-05-27 12:34:08.291942
 created following sbatch script: 
 
 ###############################
@@ -7,13 +7,13 @@ created following sbatch script:
 
 #SBATCH --account=nlp
 #SBATCH --cpus-per-task=16
-#SBATCH --dependency=afterok:7653571
+#SBATCH --dependency=afterok:7656663
 #SBATCH --gres=gpu:1
-#SBATCH --job-name=tthrush-job-1485795
+#SBATCH --job-name=tthrush-job-3309802
 #SBATCH --mem=60G
 #SBATCH --nodelist=sphinx1
 #SBATCH --open-mode=append
-#SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/test_ordinal_projection/llms/pythia-70m_sciq_1/eval_job_output.txt
+#SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/test_ordinal_projection_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_projection/llms/pythia-70m_sciq_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/test_ordinal_projection/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_projection_big_diff/llms/pythia-70m_sciq_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/test_ordinal_projection_big_diff/llms/pythia-70m_sciq_1/perf'
 
 ###############################
 
@@ -34,55 +34,67 @@ submission to slurm complete!
 ###############################
 slurm submission output
 
-Submitted batch job 7653572
+Submitted batch job 7656664
 
 
 
 ###############################
 
-slurm submission log: 2024-05-26 22:32:57.780747
-created following sbatch script: 
-
 ###############################
-
-#!/bin/bash
-
-#SBATCH --account=nlp
-#SBATCH --cpus-per-task=16
-#SBATCH --dependency=afterok:7653601
-#SBATCH --gres=gpu:1
-#SBATCH --job-name=tthrush-job-1570626
-#SBATCH --mem=60G
-#SBATCH --nodelist=sphinx1
-#SBATCH --open-mode=append
-#SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/test_ordinal_projection/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
-
-# 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_projection/llms/pythia-70m_sciq_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/test_ordinal_projection/llms/pythia-70m_sciq_1/perf'
-
+start time: 2024-05-27 12:47:58.516681
+machine: sphinx1
+conda env: pretraining-coreset-selection
 ###############################
+running following processes
 
-submission to slurm complete!
+	lm_eval --model hf --model_args pretrained=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/test_ordinal_projection_big_diff/llms/pythia-70m_sciq_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/test_ordinal_projection_big_diff/llms/pythia-70m_sciq_1/perf
 
 
 ###############################
-slurm submission output
-
-Submitted batch job 7653602
-
+command outputs: 
 
 
+2024-05-27:12:48:01,194 INFO     [utils.py:145] Note: detected 255 virtual cores but NumExpr set to maximum of 64, check "NUMEXPR_MAX_THREADS" environment variable.
+2024-05-27:12:48:01,194 INFO     [utils.py:148] Note: NumExpr detected 255 cores but "NUMEXPR_MAX_THREADS" not set, so enforcing safe limit of 8.
+2024-05-27:12:48:01,194 INFO     [utils.py:160] NumExpr defaulting to 8 threads.
+2024-05-27:12:48:01,508 INFO     [config.py:58] PyTorch version 2.2.2 available.
+2024-05-27:12:48:05,349 INFO     [__main__.py:156] Verbosity set to INFO
+2024-05-27:12:48:12,734 WARNING  [__init__.py:194] Some tasks could not be loaded due to missing dependencies. Run with `--verbosity DEBUG` for full details.
+/nlp/scr/tthrush/miniconda3/envs/pretraining-coreset-selection/lib/python3.10/site-packages/datasets/load.py:1429: FutureWarning: The repository for hails/mmlu_no_train contains custom code which must be executed to correctly load the dataset. You can inspect the repository content at https://hf.co/datasets/hails/mmlu_no_train
+You can avoid this message in future by passing the argument `trust_remote_code=True`.
+Passing `trust_remote_code=True` will be mandatory to load this dataset from the next major release of `datasets`.
+  warnings.warn(
+2024-05-27:12:49:29,060 WARNING  [__init__.py:194] Some tasks could not be loaded due to missing dependencies. Run with `--verbosity DEBUG` for full details.
+2024-05-27:12:49:29,064 INFO     [__main__.py:229] Selected Tasks: ['arc_easy', 'lambada', 'piqa', 'sciq', 'xnli_de', 'xnli_en', 'xnli_es', 'xnli_fr']
+2024-05-27:12:49:29,360 INFO     [huggingface.py:148] Using device 'cuda'
+Traceback (most recent call last):
+  File "/nlp/scr/tthrush/miniconda3/envs/pretraining-coreset-selection/bin/lm_eval", line 8, in <module>
+    sys.exit(cli_evaluate())
+  File "/sailhome/tthrush/lm-evaluation-harness/lm_eval/__main__.py", line 231, in cli_evaluate
+    results = evaluator.simple_evaluate(
+  File "/sailhome/tthrush/lm-evaluation-harness/lm_eval/utils.py", line 415, in _wrapper
+    return fn(*args, **kwargs)
+  File "/sailhome/tthrush/lm-evaluation-harness/lm_eval/evaluator.py", line 98, in simple_evaluate
+    lm = lm_eval.api.registry.get_model(model).create_from_arg_string(
+  File "/sailhome/tthrush/lm-evaluation-harness/lm_eval/api/model.py", line 134, in create_from_arg_string
+    return cls(**args, **args2)
+  File "/sailhome/tthrush/lm-evaluation-harness/lm_eval/models/huggingface.py", line 174, in __init__
+    self._get_config(
+  File "/sailhome/tthrush/lm-evaluation-harness/lm_eval/models/huggingface.py", line 420, in _get_config
+    self._config = transformers.AutoConfig.from_pretrained(
+  File "/nlp/scr/tthrush/miniconda3/envs/pretraining-coreset-selection/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py", line 928, in from_pretrained
+    config_dict, unused_kwargs = PretrainedConfig.get_config_dict(pretrained_model_name_or_path, **kwargs)
+  File "/nlp/scr/tthrush/miniconda3/envs/pretraining-coreset-selection/lib/python3.10/site-packages/transformers/configuration_utils.py", line 631, in get_config_dict
+    config_dict, kwargs = cls._get_config_dict(pretrained_model_name_or_path, **kwargs)
+  File "/nlp/scr/tthrush/miniconda3/envs/pretraining-coreset-selection/lib/python3.10/site-packages/transformers/configuration_utils.py", line 686, in _get_config_dict
+    resolved_config_file = cached_file(
+  File "/nlp/scr/tthrush/miniconda3/envs/pretraining-coreset-selection/lib/python3.10/site-packages/transformers/utils/hub.py", line 369, in cached_file
+    raise EnvironmentError(
+OSError: /juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/test_ordinal_projection_big_diff/llms/pythia-70m_sciq_1 does not appear to have a file named config.json. Checkout 'https://huggingface.co//juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/test_ordinal_projection_big_diff/llms/pythia-70m_sciq_1/tree/main' for available files.
 ###############################
-
-slurm submission log: 2024-05-26 22:58:10.061545
+end time: 2024-05-27 12:49:38.627024
+elapsed time: 0:01:40.110343
+slurm submission log: 2024-05-27 23:18:54.461453
 created following sbatch script: 
 
 ###############################
@@ -91,13 +103,13 @@ created following sbatch script:
 
 #SBATCH --account=nlp
 #SBATCH --cpus-per-task=16
-#SBATCH --dependency=afterok:7653656
+#SBATCH --dependency=afterok:7659769
 #SBATCH --gres=gpu:1
-#SBATCH --job-name=tthrush-job-2260487
+#SBATCH --job-name=tthrush-job-2147042
 #SBATCH --mem=60G
 #SBATCH --nodelist=sphinx1
 #SBATCH --open-mode=append
-#SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/test_ordinal_projection/llms/pythia-70m_sciq_1/eval_job_output.txt
+#SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/test_ordinal_projection_big_diff/llms/pythia-70m_sciq_1/eval_job_output.txt
 #SBATCH --partition=sphinx
 #SBATCH --time=14-0
 
@@ -108,7 +120,7 @@ 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_projection/llms/pythia-70m_sciq_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/test_ordinal_projection/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_projection_big_diff/llms/pythia-70m_sciq_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/test_ordinal_projection_big_diff/llms/pythia-70m_sciq_1/perf'
 
 ###############################
 
@@ -118,13 +130,13 @@ submission to slurm complete!
 ###############################
 slurm submission output
 
-Submitted batch job 7653657
+Submitted batch job 7659770
 
 
 
 ###############################
 
-slurm submission log: 2024-05-26 23:16:43.694904
+slurm submission log: 2024-05-27 23:24:16.563525
 created following sbatch script: 
 
 ###############################
@@ -133,13 +145,13 @@ created following sbatch script:
 
 #SBATCH --account=nlp
 #SBATCH --cpus-per-task=16
-#SBATCH --dependency=afterok:7653713
+#SBATCH --dependency=afterok:7659811
 #SBATCH --gres=gpu:1
-#SBATCH --job-name=tthrush-job-1947317
+#SBATCH --job-name=tthrush-job-2456365
 #SBATCH --mem=60G
 #SBATCH --nodelist=sphinx1
 #SBATCH --open-mode=append
-#SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/test_ordinal_projection/llms/pythia-70m_sciq_1/eval_job_output.txt
+#SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/test_ordinal_projection_big_diff/llms/pythia-70m_sciq_1/eval_job_output.txt
 #SBATCH --partition=sphinx
 #SBATCH --time=14-0
 
@@ -150,7 +162,7 @@ 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_projection/llms/pythia-70m_sciq_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/test_ordinal_projection/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_projection_big_diff/llms/pythia-70m_sciq_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/test_ordinal_projection_big_diff/llms/pythia-70m_sciq_1/perf'
 
 ###############################
 
@@ -160,7 +172,7 @@ submission to slurm complete!
 ###############################
 slurm submission output
 
-Submitted batch job 7653714
+Submitted batch job 7659812
 
 
 

logs/events.out.tfevents.1716911271.sphinx2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4de90193dc0724c97d17ad167ffe10e7294fb99fce2623f40f81de90401dd6e0
+size 11121

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f97eeaa124523f4dbf33c42f1b330e4f59310ede161bb1e410a0b9dd0d11762
+oid sha256:9db3478d5d4b71d3020b911fdba8acdf616efc73e782aad3c13ed3579f2d5633
 size 281715176

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04627cb5fbe82be9fcc5f4e83b525aa07f866ab882c470a7103ad6fc1b58ed72
-size 5176
+oid sha256:1c742f4f4757649b6669d2c7a37926b33e976e9d67c8f290e013c6f1820c0d79
+size 5240