Training in progress, epoch 1

config.json

@@ -23,7 +23,7 @@
   "rotary_pct": 0.25,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.39.3",
+  "transformers_version": "4.40.2",
   "use_cache": true,
   "use_parallel_residual": true,
   "vocab_size": 50304

eval_job_output.txt

@@ -1,4 +1,4 @@
-slurm submission log: 2024-05-11 22:52:02.402564
+slurm submission log: 2024-05-20 10:11:59.906526
 created following sbatch script: 
 
 ###############################
@@ -7,24 +7,24 @@ created following sbatch script:
 
 #SBATCH --account=nlp
 #SBATCH --cpus-per-task=16
-#SBATCH --dependency=afterok:
+#SBATCH --dependency=afterok:7635790
 #SBATCH --gres=gpu:1
-#SBATCH --job-name=tthrush-job-4888498
+#SBATCH --job-name=tthrush-job-1011450
 #SBATCH --mem=60G
-#SBATCH --nodelist=sphinx2
+#SBATCH --nodelist=sphinx1
 #SBATCH --open-mode=append
-#SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/llms_5/pythia-70m_default/eval_job_output.txt
+#SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/70m_llms_more_data_test_normalized/pythia-70m_default_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/llms_5/pythia-70m_default,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/llms_5/pythia-70m_default/perf'
+srun --unbuffered run_as_child_processes 'lm_eval --model hf --model_args pretrained=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/70m_llms_more_data_test_normalized/pythia-70m_default_1,revision=main,dtype=float16,trust_remote_code=True --tasks xnli_en,xnli_fr,sciq,piqa,lambada,arc_easy,default --device cuda --output_path /juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/70m_llms_more_data_test_normalized/pythia-70m_default_1/perf'
 
 ###############################
 
@@ -34,91 +34,7 @@ submission to slurm complete!
 ###############################
 slurm submission output
 
-
-
-sbatch: error: Batch job submission failed: Job dependency problem
-
-###############################
-
-slurm submission log: 2024-05-11 22:53:20.065335
-created following sbatch script: 
-
-###############################
-
-#!/bin/bash
-
-#SBATCH --account=nlp
-#SBATCH --cpus-per-task=16
-#SBATCH --dependency=afterok:7599822
-#SBATCH --gres=gpu:1
-#SBATCH --job-name=tthrush-job-2562954
-#SBATCH --mem=60G
-#SBATCH --nodelist=sphinx2
-#SBATCH --open-mode=append
-#SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/llms_5/pythia-70m_default/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/llms_5/pythia-70m_default,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/llms_5/pythia-70m_default/perf'
-
-###############################
-
-submission to slurm complete!
-
-
-###############################
-slurm submission output
-
-Submitted batch job 7599823
-
-
-
-###############################
-
-slurm submission log: 2024-05-11 23:09:48.287855
-created following sbatch script: 
-
-###############################
-
-#!/bin/bash
-
-#SBATCH --account=nlp
-#SBATCH --cpus-per-task=16
-#SBATCH --dependency=afterok:7599868
-#SBATCH --gres=gpu:1
-#SBATCH --job-name=tthrush-job-4073620
-#SBATCH --mem=60G
-#SBATCH --nodelist=sphinx2
-#SBATCH --open-mode=append
-#SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/llms_5/pythia-70m_default/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/llms_5/pythia-70m_default,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/llms_5/pythia-70m_default/perf'
-
-###############################
-
-submission to slurm complete!
-
-
-###############################
-slurm submission output
-
-Submitted batch job 7599869
+Submitted batch job 7635791
 
 
 

logs/events.out.tfevents.1716245528.sphinx2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b4de350dcd464831a416cf5a86a0b0f2b7fd0003923c3a64438cc31390713a6
+size 95455

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b951b996bf316cd5f1f805ff62c7a17ff38b1796cef1aa7ed93aab71b0e1ab3
+oid sha256:cf7b47385f852fe85e4a2837781a49a0e236a5e632a260688f4ae5c333f57f3a
 size 281715176

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cf3be7689dc496c68d9042ba7ef79c5166b2cf3d4a5717ebfc52a3a1503f499
-size 5112
+oid sha256:0433006cce1a247878d083c2265b5f8ae1fd4d1878e57fb6a9ba2f55d3ef8231
+size 5240