submission_id: chaiml-elo-alignment-run-3_v42
developer_uid: robert_irvine
alignment_samples: 756817
alignment_score: 0.2347882216331379
best_of: 16
celo_rating: 1261.96
display_name: chaiml-elo-alignment-run-3_v42
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.08, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
gpu_counts: {'NVIDIA RTX A5000': 1}
is_internal_developer: True
language_model: ChaiML/elo_alignment_run_3
latencies: [{'batch_size': 1, 'throughput': 0.9017464213116528, 'latency_mean': 1.1088656568527222, 'latency_p50': 1.1152373552322388, 'latency_p90': 1.2329012870788574}, {'batch_size': 4, 'throughput': 1.8165891164431105, 'latency_mean': 2.184747577905655, 'latency_p50': 2.188939332962036, 'latency_p90': 2.4059891223907472}, {'batch_size': 5, 'throughput': 1.8860659634067622, 'latency_mean': 2.643401815891266, 'latency_p50': 2.656217336654663, 'latency_p90': 2.9462040424346925}, {'batch_size': 8, 'throughput': 2.0272760566743444, 'latency_mean': 3.9193231856822965, 'latency_p50': 3.940696954727173, 'latency_p90': 4.446785140037536}, {'batch_size': 10, 'throughput': 2.02905747044497, 'latency_mean': 4.88017329454422, 'latency_p50': 4.885567784309387, 'latency_p90': 5.725162172317504}, {'batch_size': 12, 'throughput': 2.043719819021895, 'latency_mean': 5.796779420375824, 'latency_p50': 5.818976283073425, 'latency_p90': 6.693626189231872}, {'batch_size': 15, 'throughput': 2.0240405973233777, 'latency_mean': 7.277918692827225, 'latency_p50': 7.413776636123657, 'latency_p90': 8.082056832313537}]
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: ChaiML/elo_alignment_run
model_name: chaiml-elo-alignment-run-3_v42
model_num_parameters: 8030261248.0
model_repo: ChaiML/elo_alignment_run_3
model_size: 8B
num_battles: 749077
num_wins: 374034
propriety_score: 0.7368255912982414
propriety_total_count: 66929.0
ranking_group: single
status: inactive
submission_type: basic
throughput_3p7s: 2.02
timestamp: 2024-09-11T04:22:07+00:00
us_pacific_date: 2024-09-10
win_ratio: 0.4993265044848527
Download Preference Data
Resubmit model
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name chaiml-elo-alignment-run-3-v42-mkmlizer
Waiting for job on chaiml-elo-alignment-run-3-v42-mkmlizer to finish
chaiml-elo-alignment-run-3-v42-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-elo-alignment-run-3-v42-mkmlizer: ║ _____ __ __ ║
chaiml-elo-alignment-run-3-v42-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-elo-alignment-run-3-v42-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-elo-alignment-run-3-v42-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-elo-alignment-run-3-v42-mkmlizer: ║ /___/ ║
chaiml-elo-alignment-run-3-v42-mkmlizer: ║ ║
chaiml-elo-alignment-run-3-v42-mkmlizer: ║ Version: 0.10.1 ║
chaiml-elo-alignment-run-3-v42-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-elo-alignment-run-3-v42-mkmlizer: ║ https://mk1.ai ║
chaiml-elo-alignment-run-3-v42-mkmlizer: ║ ║
chaiml-elo-alignment-run-3-v42-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-elo-alignment-run-3-v42-mkmlizer: ║ belonging to: ║
chaiml-elo-alignment-run-3-v42-mkmlizer: ║ ║
chaiml-elo-alignment-run-3-v42-mkmlizer: ║ Chai Research Corp. ║
chaiml-elo-alignment-run-3-v42-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-elo-alignment-run-3-v42-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-elo-alignment-run-3-v42-mkmlizer: ║ ║
chaiml-elo-alignment-run-3-v42-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-elo-alignment-run-3-v42-mkmlizer: Downloaded to shared memory in 37.048s
chaiml-elo-alignment-run-3-v42-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpfj6g6v6r, device:0
chaiml-elo-alignment-run-3-v42-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-elo-alignment-run-3-v42-mkmlizer: creating bucket guanaco-mkml-models
chaiml-elo-alignment-run-3-v42-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-elo-alignment-run-3-v42-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v42
chaiml-elo-alignment-run-3-v42-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v42/config.json
chaiml-elo-alignment-run-3-v42-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v42/tokenizer_config.json
chaiml-elo-alignment-run-3-v42-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v42/special_tokens_map.json
chaiml-elo-alignment-run-3-v42-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v42/tokenizer.json
chaiml-elo-alignment-run-3-v42-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v42/flywheel_model.0.safetensors
chaiml-elo-alignment-run-3-v42-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:10, 26.68it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:06, 44.79it/s] Loading 0: 6%|▌ | 18/291 [00:00<00:06, 43.76it/s] Loading 0: 8%|▊ | 23/291 [00:00<00:07, 34.19it/s] Loading 0: 11%|█ | 32/291 [00:00<00:05, 43.65it/s] Loading 0: 13%|█▎ | 37/291 [00:01<00:08, 28.23it/s] Loading 0: 14%|█▍ | 41/291 [00:01<00:08, 28.02it/s] Loading 0: 16%|█▋ | 48/291 [00:01<00:06, 36.09it/s] Loading 0: 18%|█▊ | 53/291 [00:01<00:06, 36.11it/s] Loading 0: 20%|█▉ | 58/291 [00:01<00:06, 37.56it/s] Loading 0: 22%|██▏ | 63/291 [00:01<00:05, 40.36it/s] Loading 0: 23%|██▎ | 68/291 [00:01<00:06, 34.67it/s] Loading 0: 26%|██▌ | 75/291 [00:02<00:05, 36.44it/s] Loading 0: 27%|██▋ | 80/291 [00:02<00:06, 30.78it/s] Loading 0: 29%|██▉ | 84/291 [00:02<00:07, 29.39it/s] Loading 0: 31%|███ | 90/291 [00:02<00:05, 35.37it/s] Loading 0: 32%|███▏ | 94/291 [00:02<00:05, 34.56it/s] Loading 0: 34%|███▍ | 100/291 [00:02<00:05, 37.97it/s] Loading 0: 36%|███▋ | 106/291 [00:02<00:04, 39.21it/s] Loading 0: 38%|███▊ | 111/291 [00:03<00:04, 37.09it/s] Loading 0: 40%|███▉ | 116/291 [00:03<00:04, 39.05it/s] Loading 0: 42%|████▏ | 122/291 [00:03<00:03, 43.08it/s] Loading 0: 44%|████▎ | 127/291 [00:03<00:04, 38.98it/s] Loading 0: 46%|████▌ | 133/291 [00:03<00:04, 32.94it/s] Loading 0: 47%|████▋ | 137/291 [00:03<00:04, 32.78it/s] Loading 0: 48%|████▊ | 141/291 [00:04<00:04, 31.24it/s] Loading 0: 51%|█████ | 147/291 [00:04<00:03, 36.38it/s] Loading 0: 52%|█████▏ | 151/291 [00:04<00:04, 34.35it/s] Loading 0: 54%|█████▎ | 156/291 [00:04<00:03, 36.97it/s] Loading 0: 55%|█████▍ | 160/291 [00:04<00:03, 34.80it/s] Loading 0: 57%|█████▋ | 165/291 [00:04<00:03, 37.86it/s] Loading 0: 58%|█████▊ | 169/291 [00:04<00:03, 36.44it/s] Loading 0: 60%|█████▉ | 174/291 [00:04<00:03, 38.20it/s] Loading 0: 61%|██████ | 178/291 [00:04<00:03, 35.87it/s] Loading 0: 64%|██████▎ | 185/291 [00:05<00:02, 40.44it/s] Loading 0: 65%|██████▌ | 190/291 [00:05<00:03, 27.43it/s] Loading 0: 67%|██████▋ | 194/291 [00:05<00:03, 26.54it/s] Loading 0: 69%|██████▉ | 201/291 [00:05<00:02, 34.02it/s] Loading 0: 70%|███████ | 205/291 [00:05<00:02, 33.50it/s] Loading 0: 72%|███████▏ | 210/291 [00:05<00:02, 36.57it/s] Loading 0: 74%|███████▍ | 215/291 [00:06<00:02, 37.05it/s] Loading 0: 76%|███████▌ | 220/291 [00:06<00:01, 37.67it/s] Loading 0: 77%|███████▋ | 224/291 [00:06<00:01, 37.77it/s] Loading 0: 78%|███████▊ | 228/291 [00:06<00:01, 31.98it/s] Loading 0: 80%|████████ | 233/291 [00:06<00:02, 27.88it/s] Loading 0: 82%|████████▏ | 238/291 [00:06<00:01, 31.30it/s] Loading 0: 83%|████████▎ | 242/291 [00:06<00:01, 32.70it/s] Loading 0: 85%|████████▍ | 246/291 [00:07<00:01, 34.05it/s] Loading 0: 86%|████████▌ | 250/291 [00:07<00:01, 33.96it/s] Loading 0: 88%|████████▊ | 255/291 [00:07<00:00, 36.77it/s] Loading 0: 89%|████████▉ | 259/291 [00:07<00:00, 35.98it/s] Loading 0: 91%|█████████ | 264/291 [00:07<00:00, 39.36it/s] Loading 0: 92%|█████████▏| 269/291 [00:07<00:00, 39.57it/s] Loading 0: 94%|█████████▍| 274/291 [00:07<00:00, 39.00it/s] Loading 0: 96%|█████████▌| 279/291 [00:07<00:00, 41.62it/s] Loading 0: 98%|█████████▊| 284/291 [00:07<00:00, 42.98it/s] Loading 0: 99%|█████████▉| 289/291 [00:13<00:00, 2.78it/s]
Job chaiml-elo-alignment-run-3-v42-mkmlizer completed after 83.95s with status: succeeded
Stopping job with name chaiml-elo-alignment-run-3-v42-mkmlizer
Pipeline stage MKMLizer completed in 84.80s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.73s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-elo-alignment-run-3-v42
Waiting for inference service chaiml-elo-alignment-run-3-v42 to be ready
Failed to get response for submission chaiml-elo-alignment-run-3_v36: ('http://chaiml-llama-8b-pairwis-8189-v19-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:33312->127.0.0.1:8080: read: connection reset by peer\n')
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service chaiml-elo-alignment-run-3-v42 ready after 161.2247416973114s
Pipeline stage MKMLDeployer completed in 161.72s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1431784629821777s
Received healthy response to inference request in 1.6016850471496582s
Received healthy response to inference request in 1.793576717376709s
Received healthy response to inference request in 2.063054084777832s
Received healthy response to inference request in 1.4301998615264893s
5 requests
0 failed requests
5th percentile: 1.464496898651123
10th percentile: 1.498793935775757
20th percentile: 1.5673880100250244
30th percentile: 1.6400633811950684
40th percentile: 1.7168200492858887
50th percentile: 1.793576717376709
60th percentile: 1.9013676643371582
70th percentile: 2.0091586112976074
80th percentile: 2.079078960418701
90th percentile: 2.1111287117004394
95th percentile: 2.1271535873413088
99th percentile: 2.1399734878540038
mean time: 1.8063388347625733
Pipeline stage StressChecker completed in 10.44s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 7.43s
Shutdown handler de-registered
chaiml-elo-alignment-run-3_v42 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-elo-alignment-run-3-v42-profiler
Waiting for inference service chaiml-elo-alignment-run-3-v42-profiler to be ready
Inference service chaiml-elo-alignment-run-3-v42-profiler ready after 160.38072848320007s
Pipeline stage MKMLProfilerDeployer completed in 160.73s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-elo-alignmentbbaaf345b574af97d25843a6a2e22991-deplofvr5b:/code/chaiverse_profiler_1726028993 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-elo-alignmentbbaaf345b574af97d25843a6a2e22991-deplofvr5b --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726028993 && python profiles.py profile --best_of_n 16 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 512 --output_tokens 64 --summary /code/chaiverse_profiler_1726028993/summary.json'
kubectl exec -it chaiml-elo-alignmentbbaaf345b574af97d25843a6a2e22991-deplofvr5b --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726028993/summary.json'
Pipeline stage MKMLProfilerRunner completed in 836.70s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-elo-alignment-run-3-v42-profiler is running
Tearing down inference service chaiml-elo-alignment-run-3-v42-profiler
Service chaiml-elo-alignment-run-3-v42-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.67s
Shutdown handler de-registered
chaiml-elo-alignment-run-3_v42 status is now inactive due to auto deactivation removed underperforming models