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 22:25:18.110347
+slurm submission log: 2024-05-17 11:42:21.569484
 created following sbatch script: 
 
 ###############################
@@ -7,24 +7,24 @@ created following sbatch script:
 
 #SBATCH --account=nlp
 #SBATCH --cpus-per-task=16
-#SBATCH --dependency=afterok:7608410
+#SBATCH --dependency=afterok:7625435
 #SBATCH --gres=gpu:1
-#SBATCH --job-name=tthrush-job-2687315
+#SBATCH --job-name=tthrush-job-2029793
 #SBATCH --mem=60G
 #SBATCH --nodelist=sphinx2
 #SBATCH --open-mode=append
-#SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/llms_basic/pythia-70m_arc_easy/eval_job_output.txt
+#SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/llms_more_data/pythia-70m_arc_easy/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_arc_easy,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_arc_easy/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_arc_easy,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_arc_easy/perf'
 
 ###############################
 
@@ -34,7 +34,7 @@ submission to slurm complete!
 ###############################
 slurm submission output
 
-Submitted batch job 7608411
+Submitted batch job 7625436
 
 
 

logs/events.out.tfevents.1716022652.sphinx2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a83d861b4fdb307118c91ce356ddd9c77af3b50f8d83c9a4145218c18dfa7ff4
+size 95392

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f139b16d6b9703f2b3b5a7017d4472598e4b772444edbf3b07201a9017ba2758
+oid sha256:aac7930c164962b872a12a11bbc9fe9417fb0a96dcef35b9eb657b763e0d6afa
 size 281715176

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e04c8621a1c09bf776f6dc0f916c6bd551d1ca6898a8c955ec19def07c49b351
-size 5112
+oid sha256:9660a724752170b6549cfdb0321416b703ab249763292c2c4c04b37e54e7435e
+size 5176