chaiml-elo-alignment-run-3

developer_uid: azuruce

submission_id: chaiml-elo-alignment-run-3_v57

model_name: chaiml-elo-alignment-run-3_v57

model_group: ChaiML/elo_alignment_run

status: torndown

timestamp: 2024-11-13T21:59:26+00:00

num_battles: 8488

num_wins: 4510

celo_rating: 1268.81

family_friendly_score: 0.5786

family_friendly_standard_error: 0.006983151723971061

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': 0.9166383364942972, 'latency_mean': 1.0908751821517944, 'latency_p50': 1.0806859731674194, 'latency_p90': 1.2347088575363159}, {'batch_size': 4, 'throughput': 1.8428031373176148, 'latency_mean': 2.166396951675415, 'latency_p50': 2.171288013458252, 'latency_p90': 2.43685622215271}, {'batch_size': 5, 'throughput': 1.9274558035030924, 'latency_mean': 2.5766099071502686, 'latency_p50': 2.586063265800476, 'latency_p90': 2.8479179859161374}, {'batch_size': 8, 'throughput': 2.0712307184353165, 'latency_mean': 3.8400680005550383, 'latency_p50': 3.8402193784713745, 'latency_p90': 4.372087788581848}, {'batch_size': 10, 'throughput': 2.0771035473089485, 'latency_mean': 4.7731023287773136, 'latency_p50': 4.796338319778442, 'latency_p90': 5.3586921930313105}, {'batch_size': 12, 'throughput': 2.070465577651583, 'latency_mean': 5.712437930107117, 'latency_p50': 5.762474775314331, 'latency_p90': 6.559087967872619}, {'batch_size': 15, 'throughput': 2.0932351070691255, 'latency_mean': 7.027527190446854, 'latency_p50': 7.144982933998108, 'latency_p90': 7.810072827339172}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-elo-alignment-run-3_v57

is_internal_developer: True

language_model: ChaiML/elo_alignment_run_3

model_size: 8B

ranking_group: single

throughput_3p7s: 2.07

us_pacific_date: 2024-11-13

win_ratio: 0.5313383600377003

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-v57-mkmlizer
Waiting for job on chaiml-elo-alignment-run-3-v57-mkmlizer to finish
chaiml-elo-alignment-run-3-v57-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-elo-alignment-run-3-v57-mkmlizer: ║     _____            __           __                                ║
chaiml-elo-alignment-run-3-v57-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-elo-alignment-run-3-v57-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-elo-alignment-run-3-v57-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-elo-alignment-run-3-v57-mkmlizer: ║       /___/                                                         ║
chaiml-elo-alignment-run-3-v57-mkmlizer: ║                                                                     ║
chaiml-elo-alignment-run-3-v57-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-elo-alignment-run-3-v57-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-elo-alignment-run-3-v57-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-elo-alignment-run-3-v57-mkmlizer: ║                                                                     ║
chaiml-elo-alignment-run-3-v57-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-elo-alignment-run-3-v57-mkmlizer: ║  belonging to:                                                      ║
chaiml-elo-alignment-run-3-v57-mkmlizer: ║                                                                     ║
chaiml-elo-alignment-run-3-v57-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-elo-alignment-run-3-v57-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-elo-alignment-run-3-v57-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-elo-alignment-run-3-v57-mkmlizer: ║                                                                     ║
chaiml-elo-alignment-run-3-v57-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-elo-alignment-run-3-v57-mkmlizer: Downloaded to shared memory in 43.479s
chaiml-elo-alignment-run-3-v57-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpbpgdk96r, device:0
chaiml-elo-alignment-run-3-v57-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-elo-alignment-run-3-v57-mkmlizer: quantized model in 30.345s
chaiml-elo-alignment-run-3-v57-mkmlizer: Processed model ChaiML/elo_alignment_run_3 in 73.824s
chaiml-elo-alignment-run-3-v57-mkmlizer: creating bucket guanaco-mkml-models
chaiml-elo-alignment-run-3-v57-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-elo-alignment-run-3-v57-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v57
chaiml-elo-alignment-run-3-v57-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v57/config.json
chaiml-elo-alignment-run-3-v57-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v57/special_tokens_map.json
chaiml-elo-alignment-run-3-v57-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v57/tokenizer_config.json
chaiml-elo-alignment-run-3-v57-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v57/tokenizer.json
chaiml-elo-alignment-run-3-v57-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v57/flywheel_model.0.safetensors
chaiml-elo-alignment-run-3-v57-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:12, 22.77it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:08, 33.29it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:08, 31.04it/s]
Loading 0:   7%|▋         | 20/291 [00:00<00:08, 33.41it/s]
Loading 0:   8%|▊         | 24/291 [00:00<00:09, 27.34it/s]
Loading 0:  10%|█         | 30/291 [00:00<00:07, 34.31it/s]
Loading 0:  12%|█▏        | 34/291 [00:01<00:11, 22.96it/s]
Loading 0:  13%|█▎        | 37/291 [00:01<00:11, 22.51it/s]
Loading 0:  14%|█▍        | 41/291 [00:01<00:11, 22.33it/s]
Loading 0:  16%|█▋        | 48/291 [00:01<00:08, 29.78it/s]
Loading 0:  18%|█▊        | 52/291 [00:01<00:08, 29.23it/s]
Loading 0:  20%|█▉        | 57/291 [00:01<00:07, 31.85it/s]
Loading 0:  21%|██        | 61/291 [00:02<00:07, 30.48it/s]
Loading 0:  23%|██▎       | 66/291 [00:02<00:06, 33.27it/s]
Loading 0:  24%|██▍       | 70/291 [00:02<00:06, 32.75it/s]
Loading 0:  25%|██▌       | 74/291 [00:02<00:06, 32.74it/s]
Loading 0:  27%|██▋       | 78/291 [00:02<00:06, 32.28it/s]
Loading 0:  28%|██▊       | 82/291 [00:02<00:09, 22.11it/s]
Loading 0:  29%|██▉       | 85/291 [00:03<00:09, 22.80it/s]
Loading 0:  31%|███       | 90/291 [00:03<00:07, 26.90it/s]
Loading 0:  32%|███▏      | 94/291 [00:03<00:07, 27.06it/s]
Loading 0:  34%|███▍      | 99/291 [00:03<00:06, 30.16it/s]
Loading 0:  35%|███▌      | 103/291 [00:03<00:06, 29.16it/s]
Loading 0:  37%|███▋      | 108/291 [00:03<00:05, 32.36it/s]
Loading 0:  38%|███▊      | 112/291 [00:03<00:05, 30.14it/s]
Loading 0:  40%|███▉      | 116/291 [00:04<00:05, 30.07it/s]
Loading 0:  42%|████▏     | 122/291 [00:04<00:04, 34.67it/s]
Loading 0:  44%|████▎     | 127/291 [00:04<00:05, 32.03it/s]
Loading 0:  46%|████▌     | 133/291 [00:04<00:05, 27.61it/s]
Loading 0:  47%|████▋     | 136/291 [00:04<00:05, 26.11it/s]
Loading 0:  48%|████▊     | 140/291 [00:04<00:06, 24.68it/s]
Loading 0:  51%|█████     | 147/291 [00:05<00:04, 31.60it/s]
Loading 0:  52%|█████▏    | 151/291 [00:05<00:04, 30.92it/s]
Loading 0:  54%|█████▎    | 156/291 [00:05<00:04, 33.11it/s]
Loading 0:  55%|█████▍    | 160/291 [00:05<00:04, 31.88it/s]
Loading 0:  57%|█████▋    | 165/291 [00:05<00:03, 34.88it/s]
Loading 0:  58%|█████▊    | 169/291 [00:05<00:03, 33.14it/s]
Loading 0:  60%|█████▉    | 174/291 [00:05<00:03, 34.11it/s]
Loading 0:  61%|██████    | 178/291 [00:06<00:03, 32.43it/s]
Loading 0:  63%|██████▎   | 184/291 [00:06<00:02, 38.60it/s]
Loading 0:  65%|██████▍   | 189/291 [00:06<00:04, 23.64it/s]
Loading 0:  67%|██████▋   | 194/291 [00:06<00:03, 24.73it/s]
Loading 0:  69%|██████▉   | 201/291 [00:06<00:02, 30.63it/s]
Loading 0:  70%|███████   | 205/291 [00:06<00:02, 30.13it/s]
Loading 0:  72%|███████▏  | 210/291 [00:07<00:02, 32.29it/s]
Loading 0:  74%|███████▎  | 214/291 [00:07<00:02, 31.66it/s]
Loading 0:  75%|███████▌  | 219/291 [00:07<00:02, 34.53it/s]
Loading 0:  77%|███████▋  | 223/291 [00:07<00:02, 32.28it/s]
Loading 0:  78%|███████▊  | 227/291 [00:07<00:02, 31.70it/s]
Loading 0:  79%|███████▉  | 231/291 [00:07<00:01, 31.79it/s]
Loading 0:  81%|████████  | 235/291 [00:08<00:02, 22.95it/s]
Loading 0:  82%|████████▏ | 239/291 [00:08<00:02, 22.98it/s]
Loading 0:  85%|████████▍ | 246/291 [00:08<00:01, 29.68it/s]
Loading 0:  86%|████████▌ | 250/291 [00:08<00:01, 30.12it/s]
Loading 0:  88%|████████▊ | 255/291 [00:08<00:01, 33.59it/s]
Loading 0:  89%|████████▉ | 259/291 [00:08<00:01, 31.76it/s]
Loading 0:  91%|█████████ | 264/291 [00:08<00:00, 34.40it/s]
Loading 0:  92%|█████████▏| 268/291 [00:09<00:00, 32.51it/s]
Loading 0:  94%|█████████▍| 273/291 [00:09<00:00, 35.29it/s]
Loading 0:  95%|█████████▌| 277/291 [00:09<00:00, 32.99it/s]
Loading 0:  97%|█████████▋| 281/291 [00:09<00:00, 32.97it/s]
Loading 0:  98%|█████████▊| 286/291 [00:15<00:02,  2.47it/s]
Loading 0:  99%|█████████▉| 289/291 [00:15<00:00,  3.07it/s]
                                                            
Job chaiml-elo-alignment-run-3-v57-mkmlizer completed after 94.07s with status: succeeded
Stopping job with name chaiml-elo-alignment-run-3-v57-mkmlizer
Pipeline stage MKMLizer completed in 95.51s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.22s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-elo-alignment-run-3-v57
Waiting for inference service chaiml-elo-alignment-run-3-v57 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
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
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
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
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
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
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-v57 ready after 190.9108805656433s
Pipeline stage MKMLDeployer completed in 191.53s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2501747608184814s
Received healthy response to inference request in 1.5034699440002441s
Received healthy response to inference request in 1.4025053977966309s
Received healthy response to inference request in 1.4740197658538818s
Received healthy response to inference request in 1.5855991840362549s
5 requests
0 failed requests
5th percentile: 1.416808271408081
10th percentile: 1.4311111450195313
20th percentile: 1.4597168922424317
30th percentile: 1.4799098014831542
40th percentile: 1.4916898727416992
50th percentile: 1.5034699440002441
60th percentile: 1.5363216400146484
70th percentile: 1.5691733360290527
80th percentile: 1.7185142993927003
90th percentile: 1.9843445301055909
95th percentile: 2.117259645462036
99th percentile: 2.2235917377471925
mean time: 1.6431538105010985
Pipeline stage StressChecker completed in 9.84s
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 2.83s
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 3.47s
Shutdown handler de-registered
chaiml-elo-alignment-run-3_v57 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 0.16s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-elo-alignment-run-3-v57-profiler
Waiting for inference service chaiml-elo-alignment-run-3-v57-profiler to be ready
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 2357.93s
Shutdown handler de-registered
chaiml-elo-alignment-run-3_v57 status is now inactive due to auto deactivation removed underperforming models
chaiml-elo-alignment-run-3_v57 status is now torndown due to DeploymentManager action