chaiml-elo-alignment-run-3

developer_uid: chai_backend_admin

submission_id: chaiml-elo-alignment-run-3_v59

model_name: chaiml-elo-alignment-run-3_v59

model_group: ChaiML/elo_alignment_run

status: inactive

timestamp: 2024-11-25T19:56:45+00:00

num_battles: 18538

num_wins: 9062

celo_rating: 1254.02

family_friendly_score: 0.5856

family_friendly_standard_error: 0.006966672663474293

submission_type: basic

model_repo: ChaiML/elo_alignment_run_3

model_architecture: LlamaForCausalLM

model_num_parameters: 8030261248.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.8704319391782096, 'latency_mean': 1.1487855422496795, 'latency_p50': 1.148659586906433, 'latency_p90': 1.2600082874298095}, {'batch_size': 4, 'throughput': 2.0280145258462876, 'latency_mean': 1.962155236005783, 'latency_p50': 1.9616193771362305, 'latency_p90': 2.1806528329849244}, {'batch_size': 5, 'throughput': 2.2425907250807056, 'latency_mean': 2.221148872375488, 'latency_p50': 2.2162368297576904, 'latency_p90': 2.496480846405029}, {'batch_size': 8, 'throughput': 2.5945944929436444, 'latency_mean': 3.0592149090766907, 'latency_p50': 3.081373453140259, 'latency_p90': 3.456972599029541}, {'batch_size': 10, 'throughput': 2.7326465544906, 'latency_mean': 3.6313631093502043, 'latency_p50': 3.639788031578064, 'latency_p90': 4.048809123039246}, {'batch_size': 12, 'throughput': 2.8019809678582033, 'latency_mean': 4.231464397907257, 'latency_p50': 4.203374266624451, 'latency_p90': 4.780753421783447}, {'batch_size': 15, 'throughput': 2.9055913026451745, 'latency_mean': 5.101455315351486, 'latency_p50': 5.0967549085617065, 'latency_p90': 5.7674377918243405}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-elo-alignment-run-3_v59

is_internal_developer: True

language_model: ChaiML/elo_alignment_run_3

model_size: 8B

ranking_group: single

throughput_3p7s: 2.76

us_pacific_date: 2024-11-25

win_ratio: 0.48883374689826303

generation_params: {'temperature': 0.9, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.5, 'frequency_penalty': 0.5, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 4, '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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Starting job with name chaiml-elo-alignment-run-3-v59-mkmlizer
Waiting for job on chaiml-elo-alignment-run-3-v59-mkmlizer to finish
chaiml-elo-alignment-run-3-v59-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-elo-alignment-run-3-v59-mkmlizer: ║     _____            __           __                                ║
chaiml-elo-alignment-run-3-v59-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-elo-alignment-run-3-v59-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-elo-alignment-run-3-v59-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-elo-alignment-run-3-v59-mkmlizer: ║       /___/                                                         ║
chaiml-elo-alignment-run-3-v59-mkmlizer: ║                                                                     ║
chaiml-elo-alignment-run-3-v59-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-elo-alignment-run-3-v59-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-elo-alignment-run-3-v59-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-elo-alignment-run-3-v59-mkmlizer: ║                                                                     ║
chaiml-elo-alignment-run-3-v59-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-elo-alignment-run-3-v59-mkmlizer: ║  belonging to:                                                      ║
chaiml-elo-alignment-run-3-v59-mkmlizer: ║                                                                     ║
chaiml-elo-alignment-run-3-v59-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-elo-alignment-run-3-v59-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-elo-alignment-run-3-v59-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-elo-alignment-run-3-v59-mkmlizer: ║                                                                     ║
chaiml-elo-alignment-run-3-v59-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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
chaiml-elo-alignment-run-3-v59-mkmlizer: Downloaded to shared memory in 67.357s
chaiml-elo-alignment-run-3-v59-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpg4l2xqlk, device:0
chaiml-elo-alignment-run-3-v59-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-elo-alignment-run-3-v59-mkmlizer: quantized model in 29.734s
chaiml-elo-alignment-run-3-v59-mkmlizer: Processed model ChaiML/elo_alignment_run_3 in 97.092s
chaiml-elo-alignment-run-3-v59-mkmlizer: creating bucket guanaco-mkml-models
chaiml-elo-alignment-run-3-v59-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-elo-alignment-run-3-v59-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v59
chaiml-elo-alignment-run-3-v59-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v59/config.json
chaiml-elo-alignment-run-3-v59-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v59/special_tokens_map.json
chaiml-elo-alignment-run-3-v59-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v59/tokenizer_config.json
chaiml-elo-alignment-run-3-v59-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v59/tokenizer.json
chaiml-elo-alignment-run-3-v59-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v59/flywheel_model.0.safetensors
chaiml-elo-alignment-run-3-v59-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:12, 23.31it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:08, 33.98it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:08, 32.50it/s]
Loading 0:   7%|▋         | 21/291 [00:00<00:07, 36.19it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:08, 32.77it/s]
Loading 0:  10%|█         | 30/291 [00:00<00:07, 37.28it/s]
Loading 0:  12%|█▏        | 34/291 [00:01<00:11, 23.16it/s]
Loading 0:  13%|█▎        | 38/291 [00:01<00:10, 24.66it/s]
Loading 0:  14%|█▍        | 41/291 [00:01<00:11, 22.25it/s]
Loading 0:  16%|█▋        | 48/291 [00:01<00:07, 30.58it/s]
Loading 0:  18%|█▊        | 52/291 [00:01<00:07, 30.78it/s]
Loading 0:  20%|█▉        | 57/291 [00:01<00:06, 34.05it/s]
Loading 0:  21%|██        | 61/291 [00:02<00:06, 33.01it/s]
Loading 0:  23%|██▎       | 66/291 [00:02<00:06, 36.16it/s]
Loading 0:  24%|██▍       | 70/291 [00:02<00:06, 34.92it/s]
Loading 0:  25%|██▌       | 74/291 [00:02<00:06, 34.67it/s]
Loading 0:  27%|██▋       | 78/291 [00:02<00:06, 34.80it/s]
Loading 0:  28%|██▊       | 82/291 [00:02<00:09, 22.55it/s]
Loading 0:  29%|██▉       | 85/291 [00:02<00:08, 23.80it/s]
Loading 0:  31%|███       | 90/291 [00:03<00:07, 28.38it/s]
Loading 0:  32%|███▏      | 94/291 [00:03<00:06, 28.20it/s]
Loading 0:  34%|███▍      | 99/291 [00:03<00:06, 31.58it/s]
Loading 0:  35%|███▌      | 103/291 [00:03<00:06, 30.42it/s]
Loading 0:  37%|███▋      | 108/291 [00:03<00:05, 33.00it/s]
Loading 0:  38%|███▊      | 112/291 [00:03<00:05, 31.23it/s]
Loading 0:  40%|███▉      | 116/291 [00:03<00:05, 31.78it/s]
Loading 0:  42%|████▏     | 122/291 [00:03<00:04, 36.27it/s]
Loading 0:  44%|████▎     | 127/291 [00:04<00:04, 33.48it/s]
Loading 0:  46%|████▌     | 133/291 [00:04<00:05, 28.16it/s]
Loading 0:  47%|████▋     | 137/291 [00:04<00:05, 28.14it/s]
Loading 0:  48%|████▊     | 140/291 [00:04<00:06, 23.97it/s]
Loading 0:  51%|█████     | 147/291 [00:04<00:04, 31.05it/s]
Loading 0:  52%|█████▏    | 151/291 [00:05<00:04, 30.09it/s]
Loading 0:  54%|█████▎    | 156/291 [00:05<00:04, 33.00it/s]
Loading 0:  55%|█████▍    | 160/291 [00:05<00:04, 31.68it/s]
Loading 0:  57%|█████▋    | 165/291 [00:05<00:03, 34.61it/s]
Loading 0:  58%|█████▊    | 169/291 [00:05<00:03, 32.99it/s]
Loading 0:  60%|█████▉    | 174/291 [00:05<00:03, 35.68it/s]
Loading 0:  61%|██████    | 178/291 [00:05<00:03, 34.06it/s]
Loading 0:  64%|██████▎   | 185/291 [00:05<00:02, 37.87it/s]
Loading 0:  65%|██████▍   | 189/291 [00:06<00:04, 24.29it/s]
Loading 0:  67%|██████▋   | 194/291 [00:06<00:03, 25.59it/s]
Loading 0:  69%|██████▉   | 201/291 [00:06<00:02, 32.52it/s]
Loading 0:  70%|███████   | 205/291 [00:06<00:02, 32.06it/s]
Loading 0:  72%|███████▏  | 210/291 [00:06<00:02, 34.97it/s]
Loading 0:  74%|███████▎  | 214/291 [00:06<00:02, 33.46it/s]
Loading 0:  75%|███████▌  | 219/291 [00:07<00:01, 36.28it/s]
Loading 0:  77%|███████▋  | 223/291 [00:07<00:01, 34.70it/s]
Loading 0:  78%|███████▊  | 227/291 [00:07<00:01, 34.63it/s]
Loading 0:  79%|███████▉  | 231/291 [00:07<00:01, 34.43it/s]
Loading 0:  81%|████████  | 235/291 [00:07<00:02, 24.46it/s]
Loading 0:  82%|████████▏ | 239/291 [00:07<00:02, 23.98it/s]
Loading 0:  85%|████████▍ | 246/291 [00:08<00:01, 31.77it/s]
Loading 0:  86%|████████▌ | 250/291 [00:08<00:01, 31.58it/s]
Loading 0:  88%|████████▊ | 255/291 [00:08<00:01, 34.06it/s]
Loading 0:  89%|████████▉ | 259/291 [00:08<00:00, 33.06it/s]
Loading 0:  91%|█████████ | 264/291 [00:08<00:00, 35.53it/s]
Loading 0:  92%|█████████▏| 268/291 [00:08<00:00, 34.69it/s]
Loading 0:  94%|█████████▍| 273/291 [00:08<00:00, 37.06it/s]
Loading 0:  95%|█████████▌| 277/291 [00:08<00:00, 34.99it/s]
Loading 0:  97%|█████████▋| 281/291 [00:08<00:00, 35.32it/s]
Loading 0:  98%|█████████▊| 286/291 [00:14<00:01,  2.53it/s]
Loading 0:  99%|█████████▉| 289/291 [00:14<00:00,  3.14it/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
Job chaiml-elo-alignment-run-3-v59-mkmlizer completed after 124.63s with status: succeeded
Stopping job with name chaiml-elo-alignment-run-3-v59-mkmlizer
Pipeline stage MKMLizer completed in 125.14s
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-v59
Waiting for inference service chaiml-elo-alignment-run-3-v59 to be ready
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-v59 ready after 130.50349760055542s
Pipeline stage MKMLDeployer completed in 131.03s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.7833247184753418s
Received healthy response to inference request in 1.7244410514831543s
Received healthy response to inference request in 1.3447799682617188s
Received healthy response to inference request in 1.2625632286071777s
Received healthy response to inference request in 1.2309668064117432s
5 requests
0 failed requests
5th percentile: 1.23728609085083
10th percentile: 1.243605375289917
20th percentile: 1.2562439441680908
30th percentile: 1.279006576538086
40th percentile: 1.3118932723999024
50th percentile: 1.3447799682617188
60th percentile: 1.4966444015502929
70th percentile: 1.648508834838867
80th percentile: 1.7362177848815918
90th percentile: 1.7597712516784667
95th percentile: 1.7715479850769043
99th percentile: 1.7809693717956543
mean time: 1.4692151546478271
Pipeline stage StressChecker completed in 8.74s
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 2.28s
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 2.10s
Shutdown handler de-registered
chaiml-elo-alignment-run-3_v59 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 2202.15s
Shutdown handler de-registered
chaiml-elo-alignment-run-3_v59 status is now inactive due to auto deactivation removed underperforming models