chaiml-ezstorytellingsft

submission_id: chaiml-ezstorytellingsft_v2

developer_uid: chai_backend_admin

best_of: 4

celo_rating: 1249.56

display_name: EZ-storytelling-SFT-150

family_friendly_score: 0.5691999999999999

family_friendly_standard_error: 0.0070030187776415394

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}

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}

gpu_counts: {'NVIDIA RTX A6000': 1}

is_internal_developer: True

language_model: ChaiML/EZStorytellingSFT

latencies: [{'batch_size': 1, 'throughput': 0.38487189293000595, 'latency_mean': 2.5981692278385164, 'latency_p50': 2.622052788734436, 'latency_p90': 2.8465918779373167}, {'batch_size': 3, 'throughput': 0.8220787576413802, 'latency_mean': 3.6274514842033385, 'latency_p50': 3.623952865600586, 'latency_p90': 4.088440537452698}, {'batch_size': 5, 'throughput': 1.0776026235065497, 'latency_mean': 4.60190336227417, 'latency_p50': 4.645808815956116, 'latency_p90': 5.101010155677796}, {'batch_size': 6, 'throughput': 1.172784960266764, 'latency_mean': 5.080621597766876, 'latency_p50': 5.078444123268127, 'latency_p90': 5.679609775543213}, {'batch_size': 10, 'throughput': 1.388302752664811, 'latency_mean': 7.12950459241867, 'latency_p50': 7.129138827323914, 'latency_p90': 8.004576158523559}]

max_input_tokens: 1024

max_output_tokens: 64

model_architecture: MistralForCausalLM

model_group: ChaiML/EZStorytellingSFT

model_name: EZ-storytelling-SFT-150

model_num_parameters: 22247282688.0

model_repo: ChaiML/EZStorytellingSFT

model_size: 22B

num_battles: 13693

num_wins: 6895

ranking_group: single

status: inactive

submission_type: basic

throughput_3p7s: 0.85

timestamp: 2024-11-19T18:05:00+00:00

us_pacific_date: 2024-11-19

win_ratio: 0.5035419557438107

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-ezstorytellingsft-v2-mkmlizer
Waiting for job on chaiml-ezstorytellingsft-v2-mkmlizer to finish
chaiml-ezstorytellingsft-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ezstorytellingsft-v2-mkmlizer: ║     _____            __           __                                ║
chaiml-ezstorytellingsft-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-ezstorytellingsft-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-ezstorytellingsft-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-ezstorytellingsft-v2-mkmlizer: ║       /___/                                                         ║
chaiml-ezstorytellingsft-v2-mkmlizer: ║                                                                     ║
chaiml-ezstorytellingsft-v2-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-ezstorytellingsft-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-ezstorytellingsft-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ezstorytellingsft-v2-mkmlizer: ║                                                                     ║
chaiml-ezstorytellingsft-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ezstorytellingsft-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-ezstorytellingsft-v2-mkmlizer: ║                                                                     ║
chaiml-ezstorytellingsft-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ezstorytellingsft-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ezstorytellingsft-v2-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-ezstorytellingsft-v2-mkmlizer: ║                                                                     ║
chaiml-ezstorytellingsft-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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', '')
chaiml-ezstorytellingsft-v2-mkmlizer: Downloaded to shared memory in 56.332s
chaiml-ezstorytellingsft-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpuy3x02bp, device:0
chaiml-ezstorytellingsft-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ezstorytellingsft-v2-mkmlizer: quantized model in 43.492s
chaiml-ezstorytellingsft-v2-mkmlizer: Processed model ChaiML/EZStorytellingSFT in 99.824s
chaiml-ezstorytellingsft-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ezstorytellingsft-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ezstorytellingsft-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ezstorytellingsft-v2
chaiml-ezstorytellingsft-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ezstorytellingsft-v2/config.json
chaiml-ezstorytellingsft-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ezstorytellingsft-v2/special_tokens_map.json
chaiml-ezstorytellingsft-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ezstorytellingsft-v2/tokenizer_config.json
chaiml-ezstorytellingsft-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ezstorytellingsft-v2/tokenizer.json
chaiml-ezstorytellingsft-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-ezstorytellingsft-v2/flywheel_model.1.safetensors
chaiml-ezstorytellingsft-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ezstorytellingsft-v2/flywheel_model.0.safetensors
chaiml-ezstorytellingsft-v2-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:20, 24.67it/s]
Loading 0:   2%|▏         | 12/507 [00:00<00:12, 40.82it/s]
Loading 0:   3%|▎         | 17/507 [00:00<00:12, 39.43it/s]
Loading 0:   4%|▍         | 22/507 [00:00<00:12, 37.82it/s]
Loading 0:   5%|▌         | 26/507 [00:00<00:12, 37.22it/s]
Loading 0:   6%|▌         | 31/507 [00:00<00:12, 38.47it/s]
Loading 0:   7%|▋         | 35/507 [00:00<00:12, 36.89it/s]
Loading 0:   8%|▊         | 39/507 [00:01<00:12, 36.33it/s]
Loading 0:   8%|▊         | 43/507 [00:01<00:13, 34.12it/s]
Loading 0:   9%|▉         | 47/507 [00:01<00:13, 33.45it/s]
Loading 0:  10%|█         | 51/507 [00:01<00:14, 32.30it/s]
Loading 0:  11%|█         | 55/507 [00:01<00:19, 23.33it/s]
Loading 0:  11%|█▏        | 58/507 [00:01<00:18, 24.64it/s]
Loading 0:  12%|█▏        | 63/507 [00:01<00:15, 29.38it/s]
Loading 0:  13%|█▎        | 67/507 [00:02<00:14, 30.75it/s]
Loading 0:  14%|█▍        | 73/507 [00:02<00:12, 33.83it/s]
Loading 0:  16%|█▌        | 80/507 [00:02<00:11, 36.30it/s]
Loading 0:  17%|█▋        | 87/507 [00:02<00:09, 42.34it/s]
Loading 0:  18%|█▊        | 92/507 [00:02<00:10, 41.40it/s]
Loading 0:  19%|█▉        | 97/507 [00:02<00:10, 40.82it/s]
Loading 0:  20%|██        | 102/507 [00:02<00:09, 41.21it/s]
Loading 0:  21%|██        | 107/507 [00:03<00:12, 32.63it/s]
Loading 0:  22%|██▏       | 113/507 [00:03<00:13, 29.87it/s]
Loading 0:  23%|██▎       | 117/507 [00:03<00:13, 29.05it/s]
Loading 0:  24%|██▍       | 122/507 [00:03<00:12, 29.94it/s]
Loading 0:  25%|██▌       | 129/507 [00:03<00:10, 36.88it/s]
Loading 0:  26%|██▌       | 133/507 [00:03<00:10, 36.53it/s]
Loading 0:  27%|██▋       | 138/507 [00:03<00:09, 39.60it/s]
Loading 0:  28%|██▊       | 143/507 [00:04<00:09, 39.05it/s]
Loading 0:  29%|██▉       | 148/507 [00:04<00:08, 40.27it/s]
Loading 0:  30%|███       | 153/507 [00:04<00:08, 41.46it/s]
Loading 0:  31%|███       | 158/507 [00:04<00:09, 35.70it/s]
Loading 0:  32%|███▏      | 164/507 [00:04<00:08, 41.21it/s]
Loading 0:  33%|███▎      | 169/507 [00:04<00:10, 33.34it/s]
Loading 0:  34%|███▍      | 173/507 [00:04<00:10, 33.23it/s]
Loading 0:  35%|███▍      | 177/507 [00:05<00:10, 30.95it/s]
Loading 0:  36%|███▌      | 183/507 [00:05<00:08, 36.08it/s]
Loading 0:  37%|███▋      | 187/507 [00:05<00:08, 35.90it/s]
Loading 0:  38%|███▊      | 192/507 [00:05<00:08, 39.05it/s]
Loading 0:  39%|███▉      | 197/507 [00:05<00:08, 38.41it/s]
Loading 0:  40%|███▉      | 202/507 [00:05<00:07, 39.28it/s]
Loading 0:  41%|████      | 207/507 [00:05<00:07, 40.91it/s]
Loading 0:  42%|████▏     | 212/507 [00:06<00:08, 35.38it/s]
Loading 0:  43%|████▎     | 218/507 [00:06<00:07, 41.13it/s]
Loading 0:  44%|████▍     | 223/507 [00:06<00:07, 36.24it/s]
Loading 0:  45%|████▍     | 227/507 [00:06<00:09, 29.76it/s]
Loading 0:  46%|████▌     | 231/507 [00:06<00:09, 28.68it/s]
Loading 0:  47%|████▋     | 237/507 [00:06<00:07, 33.95it/s]
Loading 0:  48%|████▊     | 241/507 [00:06<00:07, 33.38it/s]
Loading 0:  49%|████▊     | 246/507 [00:07<00:07, 36.05it/s]
Loading 0:  49%|████▉     | 250/507 [00:07<00:07, 35.89it/s]
Loading 0:  50%|█████     | 255/507 [00:07<00:06, 38.66it/s]
Loading 0:  51%|█████     | 259/507 [00:07<00:06, 38.35it/s]
Loading 0:  52%|█████▏    | 264/507 [00:07<00:06, 40.46it/s]
Loading 0:  53%|█████▎    | 269/507 [00:07<00:06, 39.64it/s]
Loading 0:  54%|█████▍    | 274/507 [00:07<00:05, 39.82it/s]
Loading 0:  55%|█████▌    | 279/507 [00:07<00:05, 39.82it/s]
Loading 0:  56%|█████▌    | 284/507 [00:08<00:07, 30.04it/s]
Loading 0:  57%|█████▋    | 288/507 [00:08<00:07, 28.00it/s]
Loading 0:  58%|█████▊    | 293/507 [00:08<00:07, 29.20it/s]
Loading 0:  59%|█████▉    | 299/507 [00:22<00:07, 29.20it/s]
Loading 0:  59%|█████▉    | 300/507 [00:22<02:50,  1.22it/s]
Loading 0:  60%|█████▉    | 302/507 [00:23<02:27,  1.39it/s]
Loading 0:  61%|██████    | 307/507 [00:23<01:38,  2.03it/s]
Loading 0:  61%|██████    | 310/507 [00:23<01:18,  2.52it/s]
Loading 0:  62%|██████▏   | 314/507 [00:23<00:55,  3.47it/s]
Loading 0:  63%|██████▎   | 319/507 [00:23<00:36,  5.09it/s]
Loading 0:  64%|██████▎   | 323/507 [00:23<00:27,  6.73it/s]
Loading 0:  65%|██████▍   | 328/507 [00:23<00:19,  9.35it/s]
Loading 0:  65%|██████▌   | 332/507 [00:23<00:15, 11.64it/s]
Loading 0:  66%|██████▋   | 337/507 [00:24<00:10, 15.54it/s]
Loading 0:  67%|██████▋   | 341/507 [00:24<00:10, 15.90it/s]
Loading 0:  68%|██████▊   | 345/507 [00:24<00:08, 18.49it/s]
Loading 0:  69%|██████▉   | 349/507 [00:24<00:07, 21.32it/s]
Loading 0:  70%|██████▉   | 354/507 [00:24<00:05, 26.45it/s]
Loading 0:  71%|███████   | 358/507 [00:24<00:05, 28.29it/s]
Loading 0:  72%|███████▏  | 363/507 [00:24<00:04, 33.06it/s]
Loading 0:  73%|███████▎  | 368/507 [00:24<00:04, 33.84it/s]
Loading 0:  73%|███████▎  | 372/507 [00:25<00:03, 35.08it/s]
Loading 0:  74%|███████▍  | 376/507 [00:25<00:03, 33.74it/s]
Loading 0:  75%|███████▌  | 381/507 [00:25<00:03, 37.07it/s]
Loading 0:  76%|███████▌  | 385/507 [00:25<00:03, 34.74it/s]
Loading 0:  77%|███████▋  | 389/507 [00:25<00:03, 35.09it/s]
Loading 0:  78%|███████▊  | 393/507 [00:25<00:03, 34.54it/s]
Loading 0:  78%|███████▊  | 397/507 [00:25<00:04, 25.50it/s]
Loading 0:  79%|███████▉  | 401/507 [00:26<00:04, 25.63it/s]
Loading 0:  80%|████████  | 408/507 [00:26<00:03, 32.86it/s]
Loading 0:  81%|████████▏ | 412/507 [00:26<00:02, 32.42it/s]
Loading 0:  82%|████████▏ | 417/507 [00:26<00:02, 34.66it/s]
Loading 0:  83%|████████▎ | 421/507 [00:26<00:02, 33.57it/s]
Loading 0:  84%|████████▍ | 426/507 [00:26<00:02, 36.13it/s]
Loading 0:  85%|████████▍ | 430/507 [00:26<00:02, 34.01it/s]
Loading 0:  86%|████████▌ | 435/507 [00:26<00:01, 37.15it/s]
Loading 0:  87%|████████▋ | 439/507 [00:27<00:01, 36.16it/s]
Loading 0:  88%|████████▊ | 444/507 [00:27<00:01, 39.65it/s]
Loading 0:  89%|████████▊ | 449/507 [00:27<00:01, 40.47it/s]
Loading 0:  90%|████████▉ | 454/507 [00:27<00:01, 41.02it/s]
Loading 0:  91%|█████████ | 459/507 [00:29<00:07,  6.31it/s]
Loading 0:  92%|█████████▏| 465/507 [00:29<00:04,  8.80it/s]
Loading 0:  93%|█████████▎| 472/507 [00:30<00:02, 12.65it/s]
Loading 0:  94%|█████████▍| 476/507 [00:30<00:02, 14.62it/s]
Loading 0:  95%|█████████▍| 481/507 [00:30<00:01, 18.09it/s]
Loading 0:  96%|█████████▌| 485/507 [00:30<00:01, 20.39it/s]
Loading 0:  97%|█████████▋| 490/507 [00:30<00:00, 24.13it/s]
Loading 0:  97%|█████████▋| 494/507 [00:30<00:00, 25.73it/s]
Loading 0:  98%|█████████▊| 499/507 [00:30<00:00, 29.60it/s]
Loading 0:  99%|█████████▉| 503/507 [00:30<00:00, 30.48it/s]
                                                            
Job chaiml-ezstorytellingsft-v2-mkmlizer completed after 135.48s with status: succeeded
Stopping job with name chaiml-ezstorytellingsft-v2-mkmlizer
Pipeline stage MKMLizer completed in 136.05s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-ezstorytellingsft-v2
Waiting for inference service chaiml-ezstorytellingsft-v2 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
Inference service chaiml-ezstorytellingsft-v2 ready after 211.37068819999695s
Pipeline stage MKMLDeployer completed in 211.96s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.0654776096343994s
Received healthy response to inference request in 2.6764824390411377s
Received healthy response to inference request in 3.113520383834839s
Received healthy response to inference request in 2.6567280292510986s
Received healthy response to inference request in 2.803701877593994s
5 requests
0 failed requests
5th percentile: 2.6606789112091063
10th percentile: 2.6646297931671143
20th percentile: 2.67253155708313
30th percentile: 2.701926326751709
40th percentile: 2.7528141021728514
50th percentile: 2.803701877593994
60th percentile: 2.9084121704101564
70th percentile: 3.0131224632263183
80th percentile: 3.075086164474487
90th percentile: 3.094303274154663
95th percentile: 3.103911828994751
99th percentile: 3.1115986728668212
mean time: 2.8631820678710938
Pipeline stage StressChecker completed in 15.90s
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 2.68s
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 2.52s
Shutdown handler de-registered
chaiml-ezstorytellingsft_v2 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-ezstorytellingsft-v2-profiler
Waiting for inference service chaiml-ezstorytellingsft-v2-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 3176.94s
Shutdown handler de-registered
chaiml-ezstorytellingsft_v2 status is now inactive due to auto deactivation removed underperforming models