developer_uid: azuruce
submission_id: chaiml-elo-alignment-run-3_v62
model_name: chaiml-elo-alignment-run-3_v62
model_group: ChaiML/elo_alignment_run
status: inactive
timestamp: 2024-12-14T01:16:10+00:00
num_battles: 11470
num_wins: 6009
celo_rating: 1276.18
family_friendly_score: 0.5908
family_friendly_standard_error: 0.006953493510459329
submission_type: basic
model_repo: ChaiML/elo_alignment_run_3
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.9090032041460077, 'latency_mean': 1.100039724111557, 'latency_p50': 1.094812035560608, 'latency_p90': 1.2343050718307496}, {'batch_size': 4, 'throughput': 1.7576921898620976, 'latency_mean': 2.260327956676483, 'latency_p50': 2.252352714538574, 'latency_p90': 2.5441503524780273}, {'batch_size': 5, 'throughput': 1.8662544545530944, 'latency_mean': 2.6698791193962097, 'latency_p50': 2.688506245613098, 'latency_p90': 2.9622198343276978}, {'batch_size': 8, 'throughput': 2.023625841737663, 'latency_mean': 3.931903909444809, 'latency_p50': 3.9164928197860718, 'latency_p90': 4.379120016098022}, {'batch_size': 10, 'throughput': 2.0293585433004124, 'latency_mean': 4.879048676490783, 'latency_p50': 4.841331720352173, 'latency_p90': 5.627429938316345}, {'batch_size': 12, 'throughput': 1.9948736224770596, 'latency_mean': 5.934371089935302, 'latency_p50': 6.0210654735565186, 'latency_p90': 6.9155114650726315}, {'batch_size': 15, 'throughput': 2.0217296761772787, 'latency_mean': 7.253736027479172, 'latency_p50': 7.3582682609558105, 'latency_p90': 8.130410814285279}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: chaiml-elo-alignment-run-3_v62
is_internal_developer: True
language_model: ChaiML/elo_alignment_run_3
model_size: 8B
ranking_group: single
throughput_3p7s: 2.01
us_pacific_date: 2024-12-13
win_ratio: 0.5238884045335658
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}
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}
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-v62-mkmlizer
Waiting for job on chaiml-elo-alignment-run-3-v62-mkmlizer to finish
chaiml-elo-alignment-run-3-v62-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-elo-alignment-run-3-v62-mkmlizer: ║ _____ __ __ ║
chaiml-elo-alignment-run-3-v62-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-elo-alignment-run-3-v62-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-elo-alignment-run-3-v62-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-elo-alignment-run-3-v62-mkmlizer: ║ /___/ ║
chaiml-elo-alignment-run-3-v62-mkmlizer: ║ ║
chaiml-elo-alignment-run-3-v62-mkmlizer: ║ Version: 0.11.12 ║
chaiml-elo-alignment-run-3-v62-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-elo-alignment-run-3-v62-mkmlizer: ║ https://mk1.ai ║
chaiml-elo-alignment-run-3-v62-mkmlizer: ║ ║
chaiml-elo-alignment-run-3-v62-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-elo-alignment-run-3-v62-mkmlizer: ║ belonging to: ║
chaiml-elo-alignment-run-3-v62-mkmlizer: ║ ║
chaiml-elo-alignment-run-3-v62-mkmlizer: ║ Chai Research Corp. ║
chaiml-elo-alignment-run-3-v62-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-elo-alignment-run-3-v62-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
chaiml-elo-alignment-run-3-v62-mkmlizer: ║ ║
chaiml-elo-alignment-run-3-v62-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-elo-alignment-run-3-v62-mkmlizer: Downloaded to shared memory in 72.993s
chaiml-elo-alignment-run-3-v62-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp0exocgvc, device:0
chaiml-elo-alignment-run-3-v62-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-elo-alignment-run-3-v62-mkmlizer: quantized model in 30.964s
chaiml-elo-alignment-run-3-v62-mkmlizer: Processed model ChaiML/elo_alignment_run_3 in 103.958s
chaiml-elo-alignment-run-3-v62-mkmlizer: creating bucket guanaco-mkml-models
chaiml-elo-alignment-run-3-v62-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-elo-alignment-run-3-v62-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v62
chaiml-elo-alignment-run-3-v62-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v62/config.json
chaiml-elo-alignment-run-3-v62-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v62/special_tokens_map.json
chaiml-elo-alignment-run-3-v62-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v62/tokenizer_config.json
chaiml-elo-alignment-run-3-v62-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v62/tokenizer.json
chaiml-elo-alignment-run-3-v62-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v62/flywheel_model.0.safetensors
chaiml-elo-alignment-run-3-v62-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:12, 23.00it/s] Loading 0: 3%|▎ | 10/291 [00:00<00:08, 33.29it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:11, 24.32it/s] Loading 0: 7%|▋ | 19/291 [00:00<00:09, 30.21it/s] Loading 0: 8%|▊ | 23/291 [00:00<00:10, 26.35it/s] Loading 0: 10%|▉ | 28/291 [00:00<00:08, 31.24it/s] Loading 0: 11%|█ | 32/291 [00:01<00:08, 32.26it/s] Loading 0: 12%|█▏ | 36/291 [00:01<00:12, 19.62it/s] Loading 0: 14%|█▍ | 41/291 [00:01<00:11, 21.39it/s] Loading 0: 16%|█▌ | 46/291 [00:01<00:09, 25.90it/s] Loading 0: 17%|█▋ | 50/291 [00:01<00:09, 24.56it/s] Loading 0: 19%|█▉ | 55/291 [00:02<00:08, 29.44it/s] Loading 0: 20%|██ | 59/291 [00:02<00:08, 26.54it/s] Loading 0: 23%|██▎ | 66/291 [00:02<00:06, 34.00it/s] Loading 0: 24%|██▍ | 70/291 [00:02<00:06, 33.31it/s] Loading 0: 25%|██▌ | 74/291 [00:02<00:06, 33.14it/s] Loading 0: 27%|██▋ | 78/291 [00:02<00:06, 33.51it/s] Loading 0: 28%|██▊ | 82/291 [00:03<00:08, 23.98it/s] Loading 0: 29%|██▉ | 85/291 [00:03<00:08, 24.92it/s] Loading 0: 31%|███ | 90/291 [00:03<00:06, 28.92it/s] Loading 0: 32%|███▏ | 94/291 [00:03<00:06, 29.22it/s] Loading 0: 34%|███▍ | 99/291 [00:03<00:05, 32.61it/s] Loading 0: 35%|███▌ | 103/291 [00:03<00:05, 31.67it/s] Loading 0: 37%|███▋ | 108/291 [00:03<00:05, 33.80it/s] Loading 0: 38%|███▊ | 112/291 [00:03<00:05, 32.74it/s] Loading 0: 40%|███▉ | 116/291 [00:04<00:05, 32.57it/s] Loading 0: 41%|████ | 120/291 [00:04<00:05, 33.82it/s] Loading 0: 43%|████▎ | 126/291 [00:04<00:04, 37.92it/s] Loading 0: 45%|████▍ | 130/291 [00:04<00:04, 36.45it/s] Loading 0: 46%|████▌ | 134/291 [00:04<00:06, 24.38it/s] Loading 0: 47%|████▋ | 137/291 [00:04<00:06, 25.19it/s] Loading 0: 48%|████▊ | 140/291 [00:04<00:06, 22.38it/s] Loading 0: 50%|████▉ | 145/291 [00:05<00:05, 27.91it/s] Loading 0: 51%|█████ | 149/291 [00:05<00:05, 25.71it/s] Loading 0: 54%|█████▎ | 156/291 [00:05<00:04, 32.61it/s] Loading 0: 55%|█████▍ | 160/291 [00:05<00:04, 31.04it/s] Loading 0: 57%|█████▋ | 165/291 [00:05<00:03, 32.14it/s] Loading 0: 58%|█████▊ | 169/291 [00:05<00:03, 30.86it/s] Loading 0: 60%|█████▉ | 174/291 [00:05<00:03, 32.56it/s] Loading 0: 61%|██████ | 178/291 [00:06<00:03, 30.92it/s] Loading 0: 63%|██████▎ | 182/291 [00:06<00:03, 32.67it/s] Loading 0: 64%|██████▍ | 186/291 [00:06<00:04, 23.68it/s] Loading 0: 65%|██████▍ | 189/291 [00:06<00:04, 21.49it/s] Loading 0: 67%|██████▋ | 194/291 [00:06<00:04, 22.56it/s] Loading 0: 68%|██████▊ | 199/291 [00:06<00:03, 27.25it/s] Loading 0: 70%|██████▉ | 203/291 [00:07<00:03, 25.29it/s] Loading 0: 71%|███████▏ | 208/291 [00:07<00:02, 29.76it/s] Loading 0: 73%|███████▎ | 212/291 [00:07<00:02, 26.77it/s] Loading 0: 75%|███████▍ | 217/291 [00:07<00:02, 31.34it/s] Loading 0: 76%|███████▌ | 221/291 [00:07<00:02, 27.62it/s] Loading 0: 78%|███████▊ | 226/291 [00:07<00:02, 32.19it/s] Loading 0: 79%|███████▉ | 230/291 [00:08<00:02, 29.36it/s] Loading 0: 80%|████████ | 234/291 [00:08<00:02, 21.38it/s] Loading 0: 82%|████████▏ | 239/291 [00:08<00:02, 23.18it/s] Loading 0: 84%|████████▍ | 244/291 [00:08<00:01, 27.60it/s] Loading 0: 85%|████████▌ | 248/291 [00:08<00:01, 25.82it/s] Loading 0: 87%|████████▋ | 253/291 [00:08<00:01, 30.20it/s] Loading 0: 88%|████████▊ | 257/291 [00:09<00:01, 25.90it/s] Loading 0: 90%|█████████ | 262/291 [00:09<00:00, 30.00it/s] Loading 0: 91%|█████████▏| 266/291 [00:09<00:00, 26.98it/s] Loading 0: 93%|█████████▎| 271/291 [00:09<00:00, 31.07it/s] Loading 0: 95%|█████████▍| 275/291 [00:09<00:00, 27.50it/s] Loading 0: 96%|█████████▌| 280/291 [00:09<00:00, 31.32it/s] Loading 0: 98%|█████████▊| 285/291 [00:10<00:00, 31.44it/s] Loading 0: 99%|█████████▉| 289/291 [00:15<00:00, 2.46it/s]
Job chaiml-elo-alignment-run-3-v62-mkmlizer completed after 134.95s with status: succeeded
Stopping job with name chaiml-elo-alignment-run-3-v62-mkmlizer
Pipeline stage MKMLizer completed in 135.44s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-elo-alignment-run-3-v62
Waiting for inference service chaiml-elo-alignment-run-3-v62 to be ready
Inference service chaiml-elo-alignment-run-3-v62 ready after 201.1383821964264s
Pipeline stage MKMLDeployer completed in 201.70s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8934435844421387s
Received healthy response to inference request in 1.4540636539459229s
Received healthy response to inference request in 1.7021903991699219s
Received healthy response to inference request in 1.4946341514587402s
Received healthy response to inference request in 1.3999500274658203s
5 requests
0 failed requests
5th percentile: 1.4107727527618408
10th percentile: 1.4215954780578612
20th percentile: 1.4432409286499024
30th percentile: 1.4621777534484863
40th percentile: 1.4784059524536133
50th percentile: 1.4946341514587402
60th percentile: 1.5776566505432128
70th percentile: 1.6606791496276856
80th percentile: 1.7404410362243652
90th percentile: 1.816942310333252
95th percentile: 1.8551929473876954
99th percentile: 1.88579345703125
mean time: 1.5888563632965087
Pipeline stage StressChecker completed in 9.24s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 2.24s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 2.02s
Shutdown handler de-registered
chaiml-elo-alignment-run-3_v62 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 2274.05s
Shutdown handler de-registered
chaiml-elo-alignment-run-3_v62 status is now inactive due to auto deactivation removed underperforming models