developer_uid: azuruce
submission_id: chaiml-small-story-1119-_1525_v1
model_name: small_story_1129_v3_185
model_group: ChaiML/small_story_1119_
status: inactive
timestamp: 2024-11-20T06:29:18+00:00
num_battles: 12443
num_wins: 6121
celo_rating: 1245.4
family_friendly_score: 0.5756
family_friendly_standard_error: 0.00698977310075227
submission_type: basic
model_repo: ChaiML/small_story_1119_v3_185_albert
model_architecture: MistralForCausalLM
model_num_parameters: 22247282688.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.38801436562635494, 'latency_mean': 2.5771300661563874, 'latency_p50': 2.5829923152923584, 'latency_p90': 2.8344489336013794}, {'batch_size': 3, 'throughput': 0.8284680780525296, 'latency_mean': 3.602289332151413, 'latency_p50': 3.6438790559768677, 'latency_p90': 3.983158183097839}, {'batch_size': 5, 'throughput': 1.102646225911062, 'latency_mean': 4.509491611719131, 'latency_p50': 4.493873953819275, 'latency_p90': 5.12755184173584}, {'batch_size': 6, 'throughput': 1.186972443811378, 'latency_mean': 5.0150122129917145, 'latency_p50': 5.045735239982605, 'latency_p90': 5.663303208351135}, {'batch_size': 10, 'throughput': 1.4119637486774657, 'latency_mean': 7.029199829101563, 'latency_p50': 6.986743450164795, 'latency_p90': 7.971639966964721}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: small_story_1129_v3_185
is_internal_developer: True
language_model: ChaiML/small_story_1119_v3_185_albert
model_size: 22B
ranking_group: single
throughput_3p7s: 0.87
us_pacific_date: 2024-11-19
win_ratio: 0.4919231696536205
generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', '####', 'Bot:', 'User:', 'You:', '<|im_end|>', '<|eot_id|>'], 'max_input_tokens': 1024, 'best_of': 4, 'max_output_tokens': 64}
formatter: {'memory_template': '', 'prompt_template': '', '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-small-story-1119-1525-v1-mkmlizer
Waiting for job on chaiml-small-story-1119-1525-v1-mkmlizer to finish
chaiml-small-story-1119-1525-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-small-story-1119-1525-v1-mkmlizer: ║ _____ __ __ ║
chaiml-small-story-1119-1525-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-small-story-1119-1525-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-small-story-1119-1525-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-small-story-1119-1525-v1-mkmlizer: ║ /___/ ║
chaiml-small-story-1119-1525-v1-mkmlizer: ║ ║
chaiml-small-story-1119-1525-v1-mkmlizer: ║ Version: 0.11.12 ║
chaiml-small-story-1119-1525-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-small-story-1119-1525-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-small-story-1119-1525-v1-mkmlizer: ║ ║
chaiml-small-story-1119-1525-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-small-story-1119-1525-v1-mkmlizer: ║ belonging to: ║
chaiml-small-story-1119-1525-v1-mkmlizer: ║ ║
chaiml-small-story-1119-1525-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-small-story-1119-1525-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-small-story-1119-1525-v1-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
chaiml-small-story-1119-1525-v1-mkmlizer: ║ ║
chaiml-small-story-1119-1525-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Retrying (%r) after connection broken by '%r': %s
chaiml-small-story-1119-1525-v1-mkmlizer: Downloaded to shared memory in 77.407s
chaiml-small-story-1119-1525-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_0c_694t, device:0
chaiml-small-story-1119-1525-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-small-story-1119-1525-v1-mkmlizer: quantized model in 43.154s
chaiml-small-story-1119-1525-v1-mkmlizer: Processed model ChaiML/small_story_1119_v3_185_albert in 120.561s
chaiml-small-story-1119-1525-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-small-story-1119-1525-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-small-story-1119-1525-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-small-story-1119-1525-v1
chaiml-small-story-1119-1525-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-small-story-1119-1525-v1/config.json
chaiml-small-story-1119-1525-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-small-story-1119-1525-v1/special_tokens_map.json
chaiml-small-story-1119-1525-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-small-story-1119-1525-v1/tokenizer_config.json
chaiml-small-story-1119-1525-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-small-story-1119-1525-v1/tokenizer.json
chaiml-small-story-1119-1525-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-small-story-1119-1525-v1/flywheel_model.1.safetensors
chaiml-small-story-1119-1525-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-small-story-1119-1525-v1/flywheel_model.0.safetensors
chaiml-small-story-1119-1525-v1-mkmlizer: Loading 0: 0%| | 0/507 [00:00<?, ?it/s] Loading 0: 1%| | 5/507 [00:00<00:21, 23.43it/s] Loading 0: 2%|▏ | 12/507 [00:00<00:12, 38.16it/s] Loading 0: 3%|▎ | 17/507 [00:00<00:13, 36.56it/s] Loading 0: 4%|▍ | 22/507 [00:00<00:12, 37.43it/s] Loading 0: 5%|▌ | 26/507 [00:00<00:12, 37.36it/s] Loading 0: 6%|▌ | 30/507 [00:00<00:12, 37.71it/s] Loading 0: 7%|▋ | 34/507 [00:00<00:13, 34.90it/s] Loading 0: 8%|▊ | 39/507 [00:01<00:12, 37.41it/s] Loading 0: 8%|▊ | 43/507 [00:01<00:13, 34.84it/s] Loading 0: 9%|▉ | 47/507 [00:01<00:13, 34.36it/s] Loading 0: 10%|█ | 51/507 [00:01<00:13, 33.20it/s] Loading 0: 11%|█ | 55/507 [00:01<00:19, 23.79it/s] Loading 0: 11%|█▏ | 58/507 [00:01<00:17, 25.03it/s] Loading 0: 12%|█▏ | 63/507 [00:01<00:15, 29.49it/s] Loading 0: 13%|█▎ | 67/507 [00:02<00:14, 30.64it/s] Loading 0: 14%|█▍ | 73/507 [00:02<00:12, 33.50it/s] Loading 0: 16%|█▌ | 80/507 [00:02<00:12, 35.41it/s] Loading 0: 17%|█▋ | 87/507 [00:02<00:10, 40.73it/s] Loading 0: 18%|█▊ | 92/507 [00:02<00:10, 39.31it/s] Loading 0: 19%|█▉ | 97/507 [00:02<00:11, 36.75it/s] Loading 0: 20%|█▉ | 101/507 [00:02<00:11, 36.77it/s] Loading 0: 21%|██ | 106/507 [00:03<00:10, 37.82it/s] Loading 0: 22%|██▏ | 110/507 [00:03<00:11, 35.97it/s] Loading 0: 22%|██▏ | 114/507 [00:03<00:14, 26.69it/s] Loading 0: 23%|██▎ | 118/507 [00:03<00:14, 26.70it/s] Loading 0: 24%|██▍ | 122/507 [00:03<00:14, 27.08it/s] Loading 0: 25%|██▌ | 129/507 [00:03<00:11, 33.64it/s] Loading 0: 26%|██▌ | 133/507 [00:04<00:11, 33.17it/s] Loading 0: 27%|██▋ | 138/507 [00:04<00:10, 36.57it/s] Loading 0: 28%|██▊ | 142/507 [00:04<00:10, 35.85it/s] Loading 0: 29%|██▉ | 147/507 [00:04<00:09, 39.00it/s] Loading 0: 30%|██▉ | 152/507 [00:04<00:09, 38.74it/s] Loading 0: 31%|███ | 157/507 [00:04<00:08, 40.05it/s] Loading 0: 32%|███▏ | 163/507 [00:04<00:08, 40.44it/s] Loading 0: 33%|███▎ | 168/507 [00:04<00:08, 42.27it/s] Loading 0: 34%|███▍ | 173/507 [00:05<00:11, 29.89it/s] Loading 0: 35%|███▍ | 177/507 [00:05<00:11, 28.80it/s] Loading 0: 36%|███▌ | 183/507 [00:05<00:09, 33.49it/s] Loading 0: 37%|███▋ | 187/507 [00:05<00:09, 33.17it/s] Loading 0: 38%|███▊ | 192/507 [00:05<00:08, 36.89it/s] Loading 0: 39%|███▊ | 196/507 [00:05<00:08, 36.54it/s] Loading 0: 40%|███▉ | 201/507 [00:05<00:07, 39.88it/s] Loading 0: 41%|████ | 206/507 [00:05<00:07, 40.33it/s] Loading 0: 42%|████▏ | 211/507 [00:06<00:07, 40.86it/s] Loading 0: 43%|████▎ | 216/507 [00:06<00:06, 42.69it/s] Loading 0: 44%|████▎ | 221/507 [00:06<00:08, 35.74it/s] Loading 0: 44%|████▍ | 225/507 [00:06<00:10, 27.20it/s] Loading 0: 45%|████▌ | 230/507 [00:06<00:09, 28.74it/s] Loading 0: 47%|████▋ | 237/507 [00:06<00:07, 35.80it/s] Loading 0: 48%|████▊ | 241/507 [00:07<00:07, 35.22it/s] Loading 0: 49%|████▊ | 246/507 [00:07<00:06, 37.72it/s] Loading 0: 50%|████▉ | 251/507 [00:07<00:06, 37.39it/s] Loading 0: 50%|█████ | 255/507 [00:07<00:06, 37.99it/s] Loading 0: 51%|█████ | 259/507 [00:07<00:06, 36.72it/s] Loading 0: 52%|█████▏ | 264/507 [00:07<00:06, 39.33it/s] Loading 0: 53%|█████▎ | 269/507 [00:07<00:06, 37.61it/s] Loading 0: 54%|█████▍ | 273/507 [00:07<00:06, 38.03it/s] Loading 0: 55%|█████▍ | 277/507 [00:07<00:06, 35.96it/s] Loading 0: 56%|█████▌ | 283/507 [00:08<00:05, 38.32it/s] Loading 0: 57%|█████▋ | 287/507 [00:08<00:08, 25.26it/s] Loading 0: 58%|█████▊ | 293/507 [00:08<00:07, 28.04it/s] Loading 0: 59%|█████▉ | 299/507 [00:23<00:07, 28.04it/s] Loading 0: 59%|█████▉ | 300/507 [00:23<02:45, 1.25it/s] Loading 0: 60%|█████▉ | 302/507 [00:23<02:24, 1.42it/s] Loading 0: 61%|██████ | 307/507 [00:23<01:37, 2.05it/s] Loading 0: 61%|██████ | 310/507 [00:23<01:17, 2.55it/s] Loading 0: 62%|██████▏ | 314/507 [00:23<00:55, 3.49it/s] Loading 0: 63%|██████▎ | 319/507 [00:23<00:36, 5.09it/s] Loading 0: 64%|██████▍ | 324/507 [00:23<00:25, 7.18it/s] Loading 0: 65%|██████▍ | 328/507 [00:24<00:19, 9.20it/s] Loading 0: 65%|██████▌ | 332/507 [00:24<00:14, 11.71it/s] Loading 0: 66%|██████▋ | 337/507 [00:24<00:10, 15.70it/s] Loading 0: 67%|██████▋ | 342/507 [00:24<00:10, 15.25it/s] Loading 0: 68%|██████▊ | 347/507 [00:24<00:08, 18.40it/s] Loading 0: 70%|██████▉ | 354/507 [00:24<00:06, 25.17it/s] Loading 0: 71%|███████ | 359/507 [00:24<00:05, 27.61it/s] Loading 0: 72%|███████▏ | 364/507 [00:25<00:04, 30.39it/s] Loading 0: 73%|███████▎ | 369/507 [00:25<00:04, 32.97it/s] Loading 0: 74%|███████▍ | 374/507 [00:25<00:04, 29.34it/s] Loading 0: 75%|███████▌ | 381/507 [00:25<00:03, 37.02it/s] Loading 0: 76%|███████▌ | 386/507 [00:25<00:03, 37.93it/s] Loading 0: 77%|███████▋ | 391/507 [00:25<00:03, 34.74it/s] Loading 0: 78%|███████▊ | 395/507 [00:26<00:04, 27.60it/s] Loading 0: 79%|███████▉ | 401/507 [00:26<00:03, 28.94it/s] Loading 0: 80%|████████ | 408/507 [00:26<00:02, 35.49it/s] Loading 0: 81%|████████▏ | 413/507 [00:26<00:02, 36.48it/s] Loading 0: 82%|████████▏ | 418/507 [00:26<00:02, 37.57it/s] Loading 0: 83%|████████▎ | 423/507 [00:26<00:02, 39.82it/s] Loading 0: 84%|████████▍ | 428/507 [00:26<00:02, 35.37it/s] Loading 0: 86%|████████▌ | 435/507 [00:27<00:01, 42.54it/s] Loading 0: 87%|████████▋ | 440/507 [00:27<00:01, 42.63it/s] Loading 0: 88%|████████▊ | 445/507 [00:27<00:01, 42.71it/s] Loading 0: 89%|████████▉ | 451/507 [00:27<00:01, 42.16it/s] Loading 0: 90%|████████▉ | 456/507 [00:29<00:07, 7.11it/s] Loading 0: 91%|█████████ | 460/507 [00:29<00:05, 8.57it/s] Loading 0: 92%|█████████▏| 465/507 [00:29<00:03, 10.91it/s] Loading 0: 93%|█████████▎| 472/507 [00:30<00:02, 15.60it/s] Loading 0: 94%|█████████▍| 476/507 [00:30<00:01, 17.66it/s] Loading 0: 95%|█████████▍| 481/507 [00:30<00:01, 21.56it/s] Loading 0: 96%|█████████▌| 485/507 [00:30<00:00, 23.75it/s] Loading 0: 97%|█████████▋| 490/507 [00:30<00:00, 27.80it/s] Loading 0: 97%|█████████▋| 494/507 [00:30<00:00, 28.66it/s] Loading 0: 98%|█████████▊| 499/507 [00:30<00:00, 31.81it/s] Loading 0: 99%|█████████▉| 503/507 [00:30<00:00, 32.04it/s]
Job chaiml-small-story-1119-1525-v1-mkmlizer completed after 147.74s with status: succeeded
Stopping job with name chaiml-small-story-1119-1525-v1-mkmlizer
Pipeline stage MKMLizer completed in 148.31s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.23s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-small-story-1119-1525-v1
Waiting for inference service chaiml-small-story-1119-1525-v1 to be ready
Retrying (%r) after connection broken by '%r': %s
Failed to get response for submission rica40325-10-14dpo_v2: ('http://rica40325-10-14dpo-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Inference service chaiml-small-story-1119-1525-v1 ready after 201.9974570274353s
Pipeline stage MKMLDeployer completed in 202.65s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.905362367630005s
Received healthy response to inference request in 2.3964638710021973s
Received healthy response to inference request in 2.27295184135437s
Received healthy response to inference request in 2.396350860595703s
Received healthy response to inference request in 2.532802104949951s
5 requests
0 failed requests
5th percentile: 2.2976316452026366
10th percentile: 2.322311449050903
20th percentile: 2.3716710567474366
30th percentile: 2.396373462677002
40th percentile: 2.3964186668395997
50th percentile: 2.3964638710021973
60th percentile: 2.4509991645812987
70th percentile: 2.5055344581604
80th percentile: 2.607314157485962
90th percentile: 2.7563382625579833
95th percentile: 2.830850315093994
99th percentile: 2.8904599571228027
mean time: 2.5007862091064452
Pipeline stage StressChecker completed in 13.96s
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 2.61s
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 3.11s
Shutdown handler de-registered
chaiml-small-story-1119-_1525_v1 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 0.13s
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-small-story-1119-1525-v1-profiler
Waiting for inference service chaiml-small-story-1119-1525-v1-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 3119.41s
Shutdown handler de-registered
chaiml-small-story-1119-_1525_v1 status is now inactive due to auto deactivation removed underperforming models