submission_id: chaiml-elo-alignment-run-3_v41
developer_uid: robert_irvine
alignment_samples: 1110888
alignment_score: -0.10002934259516728
best_of: 16
celo_rating: 1262.62
display_name: chaiml-elo-alignment-run-3_v41
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': 0.9119871568465144, 'latency_mean': 1.0964141011238098, 'latency_p50': 1.0969023704528809, 'latency_p90': 1.2179331302642822}, {'batch_size': 4, 'throughput': 1.772915357731385, 'latency_mean': 2.250381056070328, 'latency_p50': 2.240592360496521, 'latency_p90': 2.513550806045532}, {'batch_size': 5, 'throughput': 1.8508812915669717, 'latency_mean': 2.687029730081558, 'latency_p50': 2.6946868896484375, 'latency_p90': 3.029735803604126}, {'batch_size': 8, 'throughput': 1.979408335200181, 'latency_mean': 4.021452668905258, 'latency_p50': 3.966391682624817, 'latency_p90': 4.542020726203918}, {'batch_size': 10, 'throughput': 2.0028744561305443, 'latency_mean': 4.940836870670319, 'latency_p50': 4.9122960567474365, 'latency_p90': 5.730645370483399}, {'batch_size': 12, 'throughput': 2.0223058731654437, 'latency_mean': 5.846102821826935, 'latency_p50': 5.923716068267822, 'latency_p90': 6.695776081085205}, {'batch_size': 15, 'throughput': 2.0060756585669566, 'latency_mean': 7.34603964805603, 'latency_p50': 7.446773052215576, 'latency_p90': 8.18900556564331}]
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: ChaiML/elo_alignment_run
model_name: chaiml-elo-alignment-run-3_v41
model_num_parameters: 8030261248.0
model_repo: ChaiML/elo_alignment_run_3
model_size: 8B
num_battles: 1098266
num_wins: 583017
propriety_score: 0.7387488864085524
propriety_total_count: 97657.0
ranking_group: single
status: inactive
submission_type: basic
throughput_3p7s: 1.97
timestamp: 2024-09-11T04:16:57+00:00
us_pacific_date: 2024-09-10
win_ratio: 0.5308522707613639
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-v41-mkmlizer
Waiting for job on chaiml-elo-alignment-run-3-v41-mkmlizer to finish
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-elo-alignment-run-3-v41-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-elo-alignment-run-3-v41-mkmlizer: ║ _____ __ __ ║
chaiml-elo-alignment-run-3-v41-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-elo-alignment-run-3-v41-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-elo-alignment-run-3-v41-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-elo-alignment-run-3-v41-mkmlizer: ║ /___/ ║
chaiml-elo-alignment-run-3-v41-mkmlizer: ║ ║
chaiml-elo-alignment-run-3-v41-mkmlizer: ║ Version: 0.10.1 ║
chaiml-elo-alignment-run-3-v41-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-elo-alignment-run-3-v41-mkmlizer: ║ https://mk1.ai ║
chaiml-elo-alignment-run-3-v41-mkmlizer: ║ ║
chaiml-elo-alignment-run-3-v41-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-elo-alignment-run-3-v41-mkmlizer: ║ belonging to: ║
chaiml-elo-alignment-run-3-v41-mkmlizer: ║ ║
chaiml-elo-alignment-run-3-v41-mkmlizer: ║ Chai Research Corp. ║
chaiml-elo-alignment-run-3-v41-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-elo-alignment-run-3-v41-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-elo-alignment-run-3-v41-mkmlizer: ║ ║
chaiml-elo-alignment-run-3-v41-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-elo-alignment-run-3-v41-mkmlizer: Downloaded to shared memory in 39.274s
chaiml-elo-alignment-run-3-v41-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpvzskkxxd, device:0
chaiml-elo-alignment-run-3-v41-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-elo-alignment-run-3-v41-mkmlizer: quantized model in 28.457s
chaiml-elo-alignment-run-3-v41-mkmlizer: Processed model ChaiML/elo_alignment_run_3 in 67.731s
chaiml-elo-alignment-run-3-v41-mkmlizer: creating bucket guanaco-mkml-models
chaiml-elo-alignment-run-3-v41-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-elo-alignment-run-3-v41-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v41
chaiml-elo-alignment-run-3-v41-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v41/config.json
chaiml-elo-alignment-run-3-v41-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v41/special_tokens_map.json
chaiml-elo-alignment-run-3-v41-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v41/tokenizer_config.json
chaiml-elo-alignment-run-3-v41-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v41/tokenizer.json
chaiml-elo-alignment-run-3-v41-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v41/flywheel_model.0.safetensors
chaiml-elo-alignment-run-3-v41-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:11, 25.69it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:06, 42.29it/s] Loading 0: 6%|▌ | 17/291 [00:00<00:06, 40.40it/s] Loading 0: 8%|▊ | 22/291 [00:00<00:06, 40.21it/s] Loading 0: 9%|▉ | 27/291 [00:00<00:06, 40.01it/s] Loading 0: 11%|█ | 32/291 [00:00<00:06, 41.45it/s] Loading 0: 13%|█▎ | 37/291 [00:01<00:09, 25.88it/s] Loading 0: 14%|█▍ | 41/291 [00:01<00:09, 25.19it/s] Loading 0: 16%|█▋ | 48/291 [00:01<00:07, 32.30it/s] Loading 0: 18%|█▊ | 52/291 [00:01<00:07, 31.37it/s] Loading 0: 20%|█▉ | 58/291 [00:01<00:06, 35.12it/s] Loading 0: 22%|██▏ | 64/291 [00:01<00:06, 36.43it/s] Loading 0: 23%|██▎ | 68/291 [00:02<00:06, 32.85it/s] Loading 0: 25%|██▌ | 74/291 [00:02<00:05, 38.65it/s] Loading 0: 27%|██▋ | 79/291 [00:02<00:05, 37.42it/s] Loading 0: 29%|██▊ | 83/291 [00:02<00:08, 24.61it/s] Loading 0: 31%|███ | 90/291 [00:02<00:06, 32.53it/s] Loading 0: 33%|███▎ | 95/291 [00:02<00:05, 34.12it/s] Loading 0: 34%|███▍ | 100/291 [00:02<00:05, 35.50it/s] Loading 0: 36%|███▌ | 105/291 [00:03<00:05, 36.91it/s] Loading 0: 38%|███▊ | 110/291 [00:03<00:05, 31.89it/s] Loading 0: 40%|███▉ | 116/291 [00:03<00:04, 37.19it/s] Loading 0: 42%|████▏ | 122/291 [00:03<00:04, 41.65it/s] Loading 0: 44%|████▎ | 127/291 [00:03<00:04, 38.27it/s] Loading 0: 46%|████▌ | 133/291 [00:03<00:04, 33.19it/s] Loading 0: 47%|████▋ | 137/291 [00:04<00:04, 32.84it/s] Loading 0: 48%|████▊ | 141/291 [00:04<00:04, 30.94it/s] Loading 0: 51%|█████ | 147/291 [00:04<00:03, 36.21it/s] Loading 0: 52%|█████▏ | 151/291 [00:04<00:04, 34.30it/s] Loading 0: 54%|█████▎ | 156/291 [00:04<00:03, 36.27it/s] Loading 0: 55%|█████▍ | 160/291 [00:04<00:03, 34.35it/s] Loading 0: 57%|█████▋ | 165/291 [00:04<00:03, 37.73it/s] Loading 0: 58%|█████▊ | 169/291 [00:04<00:03, 36.12it/s] Loading 0: 60%|█████▉ | 174/291 [00:05<00:03, 38.75it/s] Loading 0: 61%|██████ | 178/291 [00:05<00:03, 35.75it/s] Loading 0: 64%|██████▎ | 185/291 [00:05<00:02, 40.52it/s] Loading 0: 65%|██████▌ | 190/291 [00:05<00:03, 27.47it/s] Loading 0: 67%|██████▋ | 194/291 [00:05<00:03, 27.09it/s] Loading 0: 69%|██████▉ | 201/291 [00:05<00:02, 34.14it/s] Loading 0: 70%|███████ | 205/291 [00:06<00:02, 33.71it/s] Loading 0: 72%|███████▏ | 210/291 [00:06<00:02, 37.01it/s] Loading 0: 74%|███████▍ | 215/291 [00:06<00:02, 37.71it/s] Loading 0: 76%|███████▌ | 220/291 [00:06<00:01, 37.72it/s] Loading 0: 77%|███████▋ | 224/291 [00:06<00:01, 37.64it/s] Loading 0: 78%|███████▊ | 228/291 [00:06<00:02, 31.19it/s] Loading 0: 80%|████████ | 233/291 [00:06<00:02, 27.46it/s] Loading 0: 82%|████████▏ | 238/291 [00:06<00:01, 31.97it/s] Loading 0: 83%|████████▎ | 242/291 [00:07<00:01, 33.10it/s] Loading 0: 85%|████████▍ | 247/291 [00:07<00:01, 34.68it/s] Loading 0: 87%|████████▋ | 252/291 [00:07<00:01, 38.00it/s] Loading 0: 88%|████████▊ | 257/291 [00:07<00:01, 32.58it/s] Loading 0: 91%|█████████ | 264/291 [00:07<00:00, 39.95it/s] Loading 0: 92%|█████████▏| 269/291 [00:07<00:00, 39.75it/s] Loading 0: 94%|█████████▍| 274/291 [00:07<00:00, 39.72it/s] Loading 0: 96%|█████████▌| 279/291 [00:08<00:00, 40.65it/s] Loading 0: 98%|█████████▊| 284/291 [00:08<00:00, 42.20it/s] Loading 0: 99%|█████████▉| 289/291 [00:13<00:00, 2.87it/s]
Job chaiml-elo-alignment-run-3-v41-mkmlizer completed after 94.59s with status: succeeded
Stopping job with name chaiml-elo-alignment-run-3-v41-mkmlizer
Pipeline stage MKMLizer completed in 95.40s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-elo-alignment-run-3-v41
Waiting for inference service chaiml-elo-alignment-run-3-v41 to be ready
Failed to get response for submission chaiml-llama-8b-pairwis_8189_v19: ('http://chaiml-llama-8b-pairwis-8189-v19-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'readfrom tcp 127.0.0.1:57394->127.0.0.1:8080: write tcp 127.0.0.1:57394->127.0.0.1:8080: use of closed network connection\n')
Inference service chaiml-elo-alignment-run-3-v41 ready after 161.07205533981323s
Pipeline stage MKMLDeployer completed in 161.51s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.8802742958068848s
Received healthy response to inference request in 1.7809429168701172s
Received healthy response to inference request in 2.400972604751587s
Received healthy response to inference request in 2.328819990158081s
Received healthy response to inference request in 1.6851341724395752s
5 requests
0 failed requests
5th percentile: 1.7042959213256836
10th percentile: 1.723457670211792
20th percentile: 1.7617811679840087
30th percentile: 1.8905183315277099
40th percentile: 2.1096691608428957
50th percentile: 2.328819990158081
60th percentile: 2.3576810359954834
70th percentile: 2.3865420818328857
80th percentile: 2.4968329429626466
90th percentile: 2.6885536193847654
95th percentile: 2.784413957595825
99th percentile: 2.8611022281646727
mean time: 2.215228796005249
Pipeline stage StressChecker completed in 12.30s
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 5.62s
Shutdown handler de-registered
chaiml-elo-alignment-run-3_v41 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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-elo-alignment-run-3-v41-profiler
Waiting for inference service chaiml-elo-alignment-run-3-v41-profiler to be ready
Inference service chaiml-elo-alignment-run-3-v41-profiler ready after 160.40181756019592s
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-alignment728fa11ae88f3cda31af6481a458414f-deplo6sgn9:/code/chaiverse_profiler_1726028706 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-elo-alignment728fa11ae88f3cda31af6481a458414f-deplo6sgn9 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726028706 && 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_1726028706/summary.json'
kubectl exec -it chaiml-elo-alignment728fa11ae88f3cda31af6481a458414f-deplo6sgn9 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726028706/summary.json'
Pipeline stage MKMLProfilerRunner completed in 844.27s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-elo-alignment-run-3-v41-profiler is running
Tearing down inference service chaiml-elo-alignment-run-3-v41-profiler
Service chaiml-elo-alignment-run-3-v41-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.74s
Shutdown handler de-registered
chaiml-elo-alignment-run-3_v41 status is now inactive due to auto deactivation removed underperforming models