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: 2024-05-13 22:25:17.263290
+slurm submission log: 2024-05-17 11:42:20.756255
 created following sbatch script: 
 
 ###############################
@@ -7,24 +7,24 @@ created following sbatch script:
 
 #SBATCH --account=nlp
 #SBATCH --cpus-per-task=16
-#SBATCH --dependency=afterok:7608407
+#SBATCH --dependency=afterok:7625432
 #SBATCH --gres=gpu:1
-#SBATCH --job-name=tthrush-job-3643749
+#SBATCH --job-name=tthrush-job-3302314
 #SBATCH --mem=60G
 #SBATCH --nodelist=sphinx2
 #SBATCH --open-mode=append
-#SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/llms_basic/pythia-70m_lambada/eval_job_output.txt
+#SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/llms_more_data/pythia-70m_lambada/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_basic/pythia-70m_lambada,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_basic/pythia-70m_lambada/perf'
+srun --unbuffered run_as_child_processes 'lm_eval --model hf --model_args pretrained=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/llms_more_data/pythia-70m_lambada,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_more_data/pythia-70m_lambada/perf'
 
 ###############################
 
@@ -34,7 +34,7 @@ submission to slurm complete!
 ###############################
 slurm submission output
 
-Submitted batch job 7608408
+Submitted batch job 7625433
 
 
 

logs/events.out.tfevents.1716016566.sphinx2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c0c5cbc403d05124430c09eb05a24b9bf5cd463abb495b41656209a90601d8c
+size 95388

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19ac02d05a3b11b674725d9b436d078d38256332843dcd05c4302be70450e335
+oid sha256:400e6a9da0b2fb613f98becd6b9c2cc247d19568a6fa32867c8ae1eaa8dc00b7
 size 281715176

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d23c36ce5b084128790b26ccc616e7a9cd0fd35093c93895ed9a1a7f724a468
-size 5112
+oid sha256:a03974bd8bb5f7f1ffa8ec352d4140d9d9425c0ed4c66e8186db2265cfa6cc99
+size 5176