chaiml-small-q-story-tel_5523

developer_uid: azuruce

submission_id: chaiml-small-q-story-tel_5523_v1

model_name: small-story-albert-q

model_group: ChaiML/small_q_story_tel

status: inactive

timestamp: 2024-11-19T16:20:11+00:00

num_battles: 16991

num_wins: 8084

celo_rating: 1232.56

family_friendly_score: 0.5662

family_friendly_standard_error: 0.007008816733229655

submission_type: basic

model_repo: ChaiML/small_q_story_telling_241119_albert_v1

model_architecture: MistralForCausalLM

model_num_parameters: 22247282688.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.3860593505926081, 'latency_mean': 2.590177586078644, 'latency_p50': 2.603103518486023, 'latency_p90': 2.846583437919617}, {'batch_size': 3, 'throughput': 0.8215002745754766, 'latency_mean': 3.634649647474289, 'latency_p50': 3.636966347694397, 'latency_p90': 3.9895514488220214}, {'batch_size': 5, 'throughput': 1.0987301398504945, 'latency_mean': 4.5230488717556, 'latency_p50': 4.493950843811035, 'latency_p90': 5.073752379417419}, {'batch_size': 6, 'throughput': 1.1812929169784523, 'latency_mean': 5.041334787607193, 'latency_p50': 5.031894564628601, 'latency_p90': 5.710828948020935}, {'batch_size': 10, 'throughput': 1.397017696974507, 'latency_mean': 7.093444907665253, 'latency_p50': 7.116755843162537, 'latency_p90': 8.075355076789856}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: small-story-albert-q

is_internal_developer: True

language_model: ChaiML/small_q_story_telling_241119_albert_v1

model_size: 22B

ranking_group: single

throughput_3p7s: 0.85

us_pacific_date: 2024-11-19

win_ratio: 0.47578129598022484

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|>'], '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
Starting job with name chaiml-small-q-story-tel-5523-v1-mkmlizer
Waiting for job on chaiml-small-q-story-tel-5523-v1-mkmlizer to finish
chaiml-small-q-story-tel-5523-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-small-q-story-tel-5523-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-small-q-story-tel-5523-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-small-q-story-tel-5523-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-small-q-story-tel-5523-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-small-q-story-tel-5523-v1-mkmlizer: ║       /___/                                                         ║
chaiml-small-q-story-tel-5523-v1-mkmlizer: ║                                                                     ║
chaiml-small-q-story-tel-5523-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-small-q-story-tel-5523-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-small-q-story-tel-5523-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-small-q-story-tel-5523-v1-mkmlizer: ║                                                                     ║
chaiml-small-q-story-tel-5523-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-small-q-story-tel-5523-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-small-q-story-tel-5523-v1-mkmlizer: ║                                                                     ║
chaiml-small-q-story-tel-5523-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-small-q-story-tel-5523-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-small-q-story-tel-5523-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-small-q-story-tel-5523-v1-mkmlizer: ║                                                                     ║
chaiml-small-q-story-tel-5523-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-small-q-story-tel-5523-v1-mkmlizer: Downloaded to shared memory in 86.855s
chaiml-small-q-story-tel-5523-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpouqiirw_, device:0
chaiml-small-q-story-tel-5523-v1-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-small-q-story-tel-5523-v1-mkmlizer: quantized model in 43.999s
chaiml-small-q-story-tel-5523-v1-mkmlizer: Processed model ChaiML/small_q_story_telling_241119_albert_v1 in 130.854s
chaiml-small-q-story-tel-5523-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-small-q-story-tel-5523-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-small-q-story-tel-5523-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-small-q-story-tel-5523-v1
chaiml-small-q-story-tel-5523-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-small-q-story-tel-5523-v1/config.json
chaiml-small-q-story-tel-5523-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-small-q-story-tel-5523-v1/special_tokens_map.json
chaiml-small-q-story-tel-5523-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-small-q-story-tel-5523-v1/tokenizer_config.json
chaiml-small-q-story-tel-5523-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-small-q-story-tel-5523-v1/tokenizer.json
chaiml-small-q-story-tel-5523-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-small-q-story-tel-5523-v1/flywheel_model.1.safetensors
chaiml-small-q-story-tel-5523-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-small-q-story-tel-5523-v1/flywheel_model.0.safetensors
chaiml-small-q-story-tel-5523-v1-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:21, 23.80it/s]
Loading 0:   2%|▏         | 12/507 [00:00<00:12, 38.60it/s]
Loading 0:   3%|▎         | 17/507 [00:00<00:13, 36.76it/s]
Loading 0:   4%|▍         | 21/507 [00:00<00:13, 37.21it/s]
Loading 0:   5%|▍         | 25/507 [00:00<00:13, 35.05it/s]
Loading 0:   6%|▌         | 30/507 [00:00<00:12, 37.05it/s]
Loading 0:   7%|▋         | 34/507 [00:00<00:13, 34.26it/s]
Loading 0:   8%|▊         | 39/507 [00:01<00:12, 36.36it/s]
Loading 0:   8%|▊         | 43/507 [00:01<00:13, 35.32it/s]
Loading 0:   9%|▉         | 47/507 [00:01<00:13, 34.68it/s]
Loading 0:  10%|█         | 51/507 [00:01<00:13, 34.28it/s]
Loading 0:  11%|█         | 55/507 [00:01<00:19, 23.28it/s]
Loading 0:  11%|█▏        | 58/507 [00:01<00:18, 24.57it/s]
Loading 0:  12%|█▏        | 63/507 [00:01<00:15, 28.54it/s]
Loading 0:  13%|█▎        | 67/507 [00:02<00:15, 28.84it/s]
Loading 0:  14%|█▍        | 71/507 [00:02<00:14, 30.72it/s]
Loading 0:  15%|█▍        | 75/507 [00:02<00:13, 31.11it/s]
Loading 0:  16%|█▌        | 80/507 [00:02<00:13, 31.71it/s]
Loading 0:  17%|█▋        | 85/507 [00:02<00:11, 35.81it/s]
Loading 0:  18%|█▊        | 89/507 [00:02<00:13, 30.45it/s]
Loading 0:  19%|█▉        | 96/507 [00:02<00:11, 36.98it/s]
Loading 0:  20%|█▉        | 100/507 [00:03<00:11, 35.27it/s]
Loading 0:  21%|██        | 105/507 [00:03<00:10, 36.70it/s]
Loading 0:  21%|██▏       | 109/507 [00:03<00:11, 34.99it/s]
Loading 0:  22%|██▏       | 113/507 [00:03<00:15, 25.22it/s]
Loading 0:  23%|██▎       | 116/507 [00:03<00:16, 23.53it/s]
Loading 0:  24%|██▍       | 122/507 [00:03<00:14, 26.76it/s]
Loading 0:  25%|██▌       | 129/507 [00:04<00:11, 32.92it/s]
Loading 0:  26%|██▌       | 133/507 [00:04<00:11, 31.85it/s]
Loading 0:  27%|██▋       | 138/507 [00:04<00:10, 34.35it/s]
Loading 0:  28%|██▊       | 142/507 [00:04<00:10, 33.56it/s]
Loading 0:  29%|██▉       | 147/507 [00:04<00:10, 35.85it/s]
Loading 0:  30%|██▉       | 151/507 [00:04<00:10, 34.19it/s]
Loading 0:  31%|███       | 156/507 [00:04<00:09, 36.37it/s]
Loading 0:  32%|███▏      | 160/507 [00:04<00:09, 34.79it/s]
Loading 0:  32%|███▏      | 164/507 [00:05<00:10, 33.23it/s]
Loading 0:  33%|███▎      | 169/507 [00:05<00:13, 25.28it/s]
Loading 0:  34%|███▍      | 172/507 [00:05<00:13, 25.08it/s]
Loading 0:  35%|███▍      | 176/507 [00:05<00:13, 24.80it/s]
Loading 0:  36%|███▌      | 183/507 [00:05<00:10, 32.39it/s]
Loading 0:  37%|███▋      | 187/507 [00:05<00:09, 32.07it/s]
Loading 0:  38%|███▊      | 192/507 [00:06<00:09, 34.76it/s]
Loading 0:  39%|███▊      | 196/507 [00:06<00:09, 33.76it/s]
Loading 0:  40%|███▉      | 201/507 [00:06<00:08, 36.44it/s]
Loading 0:  40%|████      | 205/507 [00:06<00:08, 34.53it/s]
Loading 0:  41%|████▏     | 210/507 [00:06<00:08, 37.02it/s]
Loading 0:  42%|████▏     | 214/507 [00:06<00:08, 36.15it/s]
Loading 0:  43%|████▎     | 218/507 [00:06<00:08, 36.04it/s]
Loading 0:  44%|████▍     | 222/507 [00:06<00:08, 35.19it/s]
Loading 0:  45%|████▍     | 226/507 [00:07<00:11, 25.38it/s]
Loading 0:  45%|████▌     | 230/507 [00:07<00:10, 25.44it/s]
Loading 0:  46%|████▋     | 235/507 [00:07<00:09, 29.94it/s]
Loading 0:  47%|████▋     | 239/507 [00:07<00:09, 28.10it/s]
Loading 0:  49%|████▊     | 246/507 [00:07<00:07, 34.83it/s]
Loading 0:  49%|████▉     | 250/507 [00:07<00:07, 34.06it/s]
Loading 0:  50%|█████     | 255/507 [00:07<00:06, 36.12it/s]
Loading 0:  51%|█████     | 259/507 [00:08<00:07, 35.16it/s]
Loading 0:  52%|█████▏    | 264/507 [00:08<00:06, 36.45it/s]
Loading 0:  53%|█████▎    | 268/507 [00:08<00:06, 34.42it/s]
Loading 0:  54%|█████▍    | 273/507 [00:08<00:06, 36.38it/s]
Loading 0:  55%|█████▍    | 277/507 [00:08<00:06, 35.39it/s]
Loading 0:  56%|█████▌    | 282/507 [00:08<00:05, 38.88it/s]
Loading 0:  56%|█████▋    | 286/507 [00:08<00:08, 25.97it/s]
Loading 0:  57%|█████▋    | 290/507 [00:09<00:07, 28.30it/s]
Loading 0:  58%|█████▊    | 294/507 [00:09<00:07, 27.96it/s]
Loading 0:  59%|█████▉    | 299/507 [00:23<00:07, 27.96it/s]
Loading 0:  59%|█████▉    | 300/507 [00:23<03:13,  1.07it/s]
Loading 0:  60%|█████▉    | 302/507 [00:23<02:43,  1.25it/s]
Loading 0:  61%|██████    | 307/507 [00:23<01:45,  1.89it/s]
Loading 0:  61%|██████    | 310/507 [00:24<01:22,  2.40it/s]
Loading 0:  62%|██████▏   | 314/507 [00:24<00:57,  3.36it/s]
Loading 0:  63%|██████▎   | 319/507 [00:24<00:37,  4.97it/s]
Loading 0:  64%|██████▍   | 324/507 [00:24<00:25,  7.10it/s]
Loading 0:  65%|██████▍   | 328/507 [00:24<00:19,  9.12it/s]
Loading 0:  65%|██████▌   | 332/507 [00:24<00:15, 11.57it/s]
Loading 0:  66%|██████▋   | 336/507 [00:24<00:11, 14.49it/s]
Loading 0:  67%|██████▋   | 340/507 [00:24<00:11, 14.85it/s]
Loading 0:  68%|██████▊   | 344/507 [00:25<00:09, 17.74it/s]
Loading 0:  69%|██████▊   | 348/507 [00:25<00:08, 19.43it/s]
Loading 0:  70%|██████▉   | 354/507 [00:25<00:06, 25.09it/s]
Loading 0:  71%|███████   | 358/507 [00:25<00:05, 26.54it/s]
Loading 0:  72%|███████▏  | 363/507 [00:25<00:04, 30.77it/s]
Loading 0:  72%|███████▏  | 367/507 [00:25<00:04, 31.48it/s]
Loading 0:  73%|███████▎  | 372/507 [00:25<00:03, 35.22it/s]
Loading 0:  74%|███████▍  | 376/507 [00:25<00:03, 35.28it/s]
Loading 0:  75%|███████▌  | 381/507 [00:26<00:03, 38.58it/s]
Loading 0:  76%|███████▌  | 386/507 [00:26<00:03, 38.02it/s]
Loading 0:  77%|███████▋  | 390/507 [00:26<00:03, 30.80it/s]
Loading 0:  78%|███████▊  | 395/507 [00:26<00:04, 26.45it/s]
Loading 0:  79%|███████▉  | 401/507 [00:26<00:03, 28.70it/s]
Loading 0:  80%|████████  | 408/507 [00:26<00:02, 34.92it/s]
Loading 0:  81%|████████▏ | 412/507 [00:27<00:02, 34.37it/s]
Loading 0:  82%|████████▏ | 417/507 [00:27<00:02, 36.73it/s]
Loading 0:  83%|████████▎ | 421/507 [00:27<00:02, 36.02it/s]
Loading 0:  84%|████████▍ | 426/507 [00:27<00:02, 38.53it/s]
Loading 0:  85%|████████▍ | 430/507 [00:27<00:02, 36.55it/s]
Loading 0:  86%|████████▌ | 435/507 [00:27<00:01, 38.63it/s]
Loading 0:  87%|████████▋ | 439/507 [00:27<00:01, 36.85it/s]
Loading 0:  88%|████████▊ | 444/507 [00:27<00:01, 39.06it/s]
Loading 0:  88%|████████▊ | 448/507 [00:28<00:01, 37.00it/s]
Loading 0:  90%|████████▉ | 454/507 [00:28<00:01, 37.97it/s]
Loading 0:  90%|█████████ | 458/507 [00:30<00:08,  6.08it/s]
Loading 0:  91%|█████████ | 461/507 [00:30<00:06,  7.26it/s]
Loading 0:  92%|█████████▏| 465/507 [00:30<00:04,  9.21it/s]
Loading 0:  93%|█████████▎| 472/507 [00:30<00:02, 14.14it/s]
Loading 0:  94%|█████████▍| 476/507 [00:30<00:01, 16.47it/s]
Loading 0:  95%|█████████▍| 481/507 [00:31<00:01, 20.40it/s]
Loading 0:  96%|█████████▌| 485/507 [00:31<00:00, 22.24it/s]
Loading 0:  97%|█████████▋| 490/507 [00:31<00:00, 25.64it/s]
Loading 0:  97%|█████████▋| 494/507 [00:31<00:00, 27.33it/s]
Loading 0:  98%|█████████▊| 499/507 [00:31<00:00, 30.57it/s]
Loading 0:  99%|█████████▉| 503/507 [00:31<00:00, 30.85it/s]
                                                            
Job chaiml-small-q-story-tel-5523-v1-mkmlizer completed after 167.78s with status: succeeded
Stopping job with name chaiml-small-q-story-tel-5523-v1-mkmlizer
Pipeline stage MKMLizer completed in 168.45s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.24s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-small-q-story-tel-5523-v1
Waiting for inference service chaiml-small-q-story-tel-5523-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Failed to get response for submission bbchicago-nana-nemo-12b-v1-0_v8: ('http://bbchicago-nana-nemo-12b-v1-0-v8-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
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-small-q-story-tel-5523-v1 ready after 210.72884345054626s
Pipeline stage MKMLDeployer completed in 211.38s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.1761314868927s
Received healthy response to inference request in 3.1424896717071533s
Received healthy response to inference request in 1.0900545120239258s
Received healthy response to inference request in 2.621117353439331s
Received healthy response to inference request in 3.2307209968566895s
5 requests
0 failed requests
5th percentile: 1.3962670803070067
10th percentile: 1.702479648590088
20th percentile: 2.31490478515625
30th percentile: 2.7253918170928957
40th percentile: 2.9339407444000245
50th percentile: 3.1424896717071533
60th percentile: 3.155946397781372
70th percentile: 3.1694031238555906
80th percentile: 3.187049388885498
90th percentile: 3.2088851928710938
95th percentile: 3.2198030948638916
99th percentile: 3.22853741645813
mean time: 2.65210280418396
Pipeline stage StressChecker completed in 14.88s
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 5.80s
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 2.34s
Shutdown handler de-registered
chaiml-small-q-story-tel_5523_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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-small-q-story-tel-5523-v1-profiler
Waiting for inference service chaiml-small-q-story-tel-5523-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 3326.74s
Shutdown handler de-registered
chaiml-small-q-story-tel_5523_v1 status is now inactive due to auto deactivation removed underperforming models