chaiml-ezstorytellingsft-1k

submission_id: chaiml-ezstorytellingsft-1k_v1

developer_uid: chai_backend_admin

best_of: 4

celo_rating: 1248.69

display_name: EZ-storytelling-SFT-1k

family_friendly_score: 0.5726

family_friendly_standard_error: 0.006996130930735931

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-1k

latencies: [{'batch_size': 1, 'throughput': 0.38692641261758054, 'latency_mean': 2.5844007611274717, 'latency_p50': 2.58172869682312, 'latency_p90': 2.855293130874634}, {'batch_size': 3, 'throughput': 0.8184422080361752, 'latency_mean': 3.6548400175571443, 'latency_p50': 3.6507729291915894, 'latency_p90': 4.023816108703613}, {'batch_size': 5, 'throughput': 1.094185927196541, 'latency_mean': 4.540359808206558, 'latency_p50': 4.533253073692322, 'latency_p90': 5.057183003425598}, {'batch_size': 6, 'throughput': 1.1806139717107, 'latency_mean': 5.044674191474915, 'latency_p50': 5.05730926990509, 'latency_p90': 5.700486135482788}, {'batch_size': 10, 'throughput': 1.3975629455012948, 'latency_mean': 7.098721677064896, 'latency_p50': 7.089284420013428, 'latency_p90': 7.986619329452514}]

max_input_tokens: 1024

max_output_tokens: 64

model_architecture: MistralForCausalLM

model_group: ChaiML/EZStorytellingSFT

model_name: EZ-storytelling-SFT-1k

model_num_parameters: 22247282688.0

model_repo: ChaiML/EZStorytellingSFT-1k

model_size: 22B

num_battles: 9774

num_wins: 4852

ranking_group: single

status: inactive

submission_type: basic

throughput_3p7s: 0.84

timestamp: 2024-11-19T23:33:00+00:00

us_pacific_date: 2024-11-19

win_ratio: 0.4964190710047064

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-1k-v1-mkmlizer
Waiting for job on chaiml-ezstorytellingsft-1k-v1-mkmlizer to finish
chaiml-ezstorytellingsft-1k-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ezstorytellingsft-1k-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-ezstorytellingsft-1k-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-ezstorytellingsft-1k-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-ezstorytellingsft-1k-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-ezstorytellingsft-1k-v1-mkmlizer: ║       /___/                                                         ║
chaiml-ezstorytellingsft-1k-v1-mkmlizer: ║                                                                     ║
chaiml-ezstorytellingsft-1k-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-ezstorytellingsft-1k-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-ezstorytellingsft-1k-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ezstorytellingsft-1k-v1-mkmlizer: ║                                                                     ║
chaiml-ezstorytellingsft-1k-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ezstorytellingsft-1k-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ezstorytellingsft-1k-v1-mkmlizer: ║                                                                     ║
chaiml-ezstorytellingsft-1k-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ezstorytellingsft-1k-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ezstorytellingsft-1k-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-ezstorytellingsft-1k-v1-mkmlizer: ║                                                                     ║
chaiml-ezstorytellingsft-1k-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ezstorytellingsft-1k-v1-mkmlizer: Downloaded to shared memory in 76.036s
chaiml-ezstorytellingsft-1k-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp6ieoevjq, device:0
chaiml-ezstorytellingsft-1k-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ezstorytellingsft-1k-v1-mkmlizer: quantized model in 43.354s
chaiml-ezstorytellingsft-1k-v1-mkmlizer: Processed model ChaiML/EZStorytellingSFT-1k in 119.391s
chaiml-ezstorytellingsft-1k-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ezstorytellingsft-1k-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ezstorytellingsft-1k-v1
chaiml-ezstorytellingsft-1k-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ezstorytellingsft-1k-v1/special_tokens_map.json
chaiml-ezstorytellingsft-1k-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ezstorytellingsft-1k-v1/config.json
chaiml-ezstorytellingsft-1k-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ezstorytellingsft-1k-v1/tokenizer_config.json
chaiml-ezstorytellingsft-1k-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ezstorytellingsft-1k-v1/tokenizer.json
chaiml-ezstorytellingsft-1k-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-ezstorytellingsft-1k-v1/flywheel_model.1.safetensors
chaiml-ezstorytellingsft-1k-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ezstorytellingsft-1k-v1/flywheel_model.0.safetensors
chaiml-ezstorytellingsft-1k-v1-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:20, 24.81it/s]
Loading 0:   2%|▏         | 12/507 [00:00<00:12, 39.24it/s]
Loading 0:   3%|▎         | 17/507 [00:00<00:13, 37.27it/s]
Loading 0:   4%|▍         | 22/507 [00:00<00:12, 38.82it/s]
Loading 0:   5%|▌         | 27/507 [00:00<00:11, 40.65it/s]
Loading 0:   6%|▋         | 32/507 [00:00<00:13, 34.87it/s]
Loading 0:   8%|▊         | 39/507 [00:01<00:11, 42.10it/s]
Loading 0:   9%|▊         | 44/507 [00:01<00:11, 41.81it/s]
Loading 0:  10%|▉         | 49/507 [00:01<00:12, 35.95it/s]
Loading 0:  10%|█         | 53/507 [00:01<00:16, 27.45it/s]
Loading 0:  11%|█         | 57/507 [00:01<00:16, 27.05it/s]
Loading 0:  12%|█▏        | 63/507 [00:01<00:13, 32.05it/s]
Loading 0:  13%|█▎        | 67/507 [00:01<00:13, 32.12it/s]
Loading 0:  14%|█▍        | 72/507 [00:02<00:12, 36.12it/s]
Loading 0:  15%|█▍        | 76/507 [00:02<00:11, 36.76it/s]
Loading 0:  16%|█▌        | 80/507 [00:02<00:13, 32.37it/s]
Loading 0:  17%|█▋        | 87/507 [00:02<00:10, 40.22it/s]
Loading 0:  18%|█▊        | 92/507 [00:02<00:10, 39.50it/s]
Loading 0:  19%|█▉        | 97/507 [00:02<00:10, 40.22it/s]
Loading 0:  20%|██        | 102/507 [00:02<00:09, 41.46it/s]
Loading 0:  21%|██        | 107/507 [00:03<00:11, 34.96it/s]
Loading 0:  22%|██▏       | 113/507 [00:03<00:13, 30.14it/s]
Loading 0:  23%|██▎       | 117/507 [00:03<00:13, 29.03it/s]
Loading 0:  24%|██▍       | 122/507 [00:03<00:13, 28.99it/s]
Loading 0:  25%|██▌       | 129/507 [00:03<00:10, 35.25it/s]
Loading 0:  26%|██▌       | 133/507 [00:03<00:10, 34.42it/s]
Loading 0:  27%|██▋       | 138/507 [00:03<00:10, 36.46it/s]
Loading 0:  28%|██▊       | 142/507 [00:04<00:10, 35.94it/s]
Loading 0:  29%|██▉       | 147/507 [00:04<00:09, 38.81it/s]
Loading 0:  30%|██▉       | 151/507 [00:04<00:09, 37.97it/s]
Loading 0:  31%|███       | 157/507 [00:04<00:08, 40.74it/s]
Loading 0:  32%|███▏      | 162/507 [00:04<00:08, 41.75it/s]
Loading 0:  33%|███▎      | 167/507 [00:04<00:07, 43.22it/s]
Loading 0:  34%|███▍      | 172/507 [00:04<00:12, 26.69it/s]
Loading 0:  35%|███▍      | 176/507 [00:05<00:12, 26.74it/s]
Loading 0:  36%|███▌      | 183/507 [00:05<00:09, 34.42it/s]
Loading 0:  37%|███▋      | 188/507 [00:05<00:09, 34.62it/s]
Loading 0:  38%|███▊      | 193/507 [00:05<00:08, 36.47it/s]
Loading 0:  39%|███▉      | 198/507 [00:05<00:07, 39.22it/s]
Loading 0:  40%|████      | 203/507 [00:05<00:08, 34.07it/s]
Loading 0:  41%|████▏     | 210/507 [00:05<00:07, 40.57it/s]
Loading 0:  42%|████▏     | 215/507 [00:06<00:07, 37.49it/s]
Loading 0:  43%|████▎     | 220/507 [00:06<00:08, 32.18it/s]
Loading 0:  44%|████▍     | 224/507 [00:06<00:10, 26.12it/s]
Loading 0:  45%|████▌     | 230/507 [00:06<00:09, 27.87it/s]
Loading 0:  47%|████▋     | 237/507 [00:06<00:07, 34.81it/s]
Loading 0:  48%|████▊     | 241/507 [00:06<00:07, 34.82it/s]
Loading 0:  49%|████▊     | 246/507 [00:07<00:06, 38.03it/s]
Loading 0:  50%|████▉     | 251/507 [00:07<00:06, 38.27it/s]
Loading 0:  50%|█████     | 256/507 [00:07<00:06, 38.86it/s]
Loading 0:  51%|█████▏    | 261/507 [00:07<00:06, 40.25it/s]
Loading 0:  52%|█████▏    | 266/507 [00:07<00:07, 34.31it/s]
Loading 0:  54%|█████▍    | 273/507 [00:07<00:05, 42.17it/s]
Loading 0:  55%|█████▍    | 278/507 [00:07<00:05, 40.80it/s]
Loading 0:  56%|█████▌    | 283/507 [00:07<00:05, 40.72it/s]
Loading 0:  57%|█████▋    | 288/507 [00:08<00:07, 27.85it/s]
Loading 0:  58%|█████▊    | 293/507 [00:08<00:07, 28.09it/s]
Loading 0:  59%|█████▉    | 299/507 [00:23<00:07, 28.09it/s]
Loading 0:  59%|█████▉    | 300/507 [00:23<02:43,  1.27it/s]
Loading 0:  60%|█████▉    | 302/507 [00:23<02:22,  1.44it/s]
Loading 0:  61%|██████    | 307/507 [00:23<01:36,  2.07it/s]
Loading 0:  61%|██████    | 310/507 [00:23<01:17,  2.55it/s]
Loading 0:  62%|██████▏   | 313/507 [00:23<00:59,  3.25it/s]
Loading 0:  63%|██████▎   | 318/507 [00:23<00:38,  4.86it/s]
Loading 0:  64%|██████▎   | 322/507 [00:23<00:28,  6.44it/s]
Loading 0:  64%|██████▍   | 327/507 [00:23<00:19,  9.17it/s]
Loading 0:  65%|██████▌   | 331/507 [00:24<00:15, 11.47it/s]
Loading 0:  66%|██████▌   | 335/507 [00:24<00:12, 14.30it/s]
Loading 0:  67%|██████▋   | 340/507 [00:24<00:10, 16.00it/s]
Loading 0:  68%|██████▊   | 344/507 [00:24<00:08, 18.44it/s]
Loading 0:  69%|██████▊   | 348/507 [00:24<00:08, 19.70it/s]
Loading 0:  70%|██████▉   | 354/507 [00:24<00:06, 25.01it/s]
Loading 0:  71%|███████   | 358/507 [00:24<00:05, 26.24it/s]
Loading 0:  72%|███████▏  | 363/507 [00:25<00:04, 29.76it/s]
Loading 0:  72%|███████▏  | 367/507 [00:25<00:04, 30.82it/s]
Loading 0:  73%|███████▎  | 372/507 [00:25<00:03, 34.13it/s]
Loading 0:  74%|███████▍  | 376/507 [00:25<00:04, 32.69it/s]
Loading 0:  75%|███████▌  | 381/507 [00:25<00:03, 35.88it/s]
Loading 0:  76%|███████▌  | 385/507 [00:25<00:03, 34.77it/s]
Loading 0:  77%|███████▋  | 389/507 [00:25<00:03, 35.24it/s]
Loading 0:  78%|███████▊  | 393/507 [00:25<00:03, 35.55it/s]
Loading 0:  78%|███████▊  | 397/507 [00:26<00:04, 26.58it/s]
Loading 0:  79%|███████▉  | 401/507 [00:26<00:04, 26.42it/s]
Loading 0:  80%|████████  | 408/507 [00:26<00:02, 34.64it/s]
Loading 0:  81%|████████▏ | 412/507 [00:26<00:02, 34.37it/s]
Loading 0:  82%|████████▏ | 417/507 [00:26<00:02, 37.47it/s]
Loading 0:  83%|████████▎ | 421/507 [00:26<00:02, 36.18it/s]
Loading 0:  84%|████████▍ | 426/507 [00:26<00:02, 38.77it/s]
Loading 0:  85%|████████▌ | 431/507 [00:27<00:01, 38.67it/s]
Loading 0:  86%|████████▌ | 436/507 [00:27<00:01, 39.77it/s]
Loading 0:  87%|████████▋ | 441/507 [00:27<00:01, 41.04it/s]
Loading 0:  88%|████████▊ | 446/507 [00:27<00:01, 34.35it/s]
Loading 0:  89%|████████▉ | 453/507 [00:27<00:01, 42.18it/s]
Loading 0:  90%|█████████ | 458/507 [00:29<00:07,  6.90it/s]
Loading 0:  91%|█████████ | 462/507 [00:29<00:05,  8.60it/s]
Loading 0:  92%|█████████▏| 466/507 [00:30<00:03, 10.36it/s]
Loading 0:  93%|█████████▎| 472/507 [00:30<00:02, 14.33it/s]
Loading 0:  94%|█████████▍| 476/507 [00:30<00:01, 16.52it/s]
Loading 0:  95%|█████████▍| 481/507 [00:30<00:01, 20.69it/s]
Loading 0:  96%|█████████▌| 485/507 [00:30<00:00, 22.95it/s]
Loading 0:  97%|█████████▋| 490/507 [00:30<00:00, 27.60it/s]
Loading 0:  98%|█████████▊| 495/507 [00:30<00:00, 29.83it/s]
Loading 0:  99%|█████████▊| 500/507 [00:30<00:00, 32.34it/s]
Loading 0:  99%|█████████▉| 504/507 [00:31<00:00, 33.61it/s]
                                                            
Job chaiml-ezstorytellingsft-1k-v1-mkmlizer completed after 147.84s with status: succeeded
Stopping job with name chaiml-ezstorytellingsft-1k-v1-mkmlizer
Pipeline stage MKMLizer completed in 148.44s
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-ezstorytellingsft-1k-v1
Waiting for inference service chaiml-ezstorytellingsft-1k-v1 to be ready
Inference service chaiml-ezstorytellingsft-1k-v1 ready after 221.81556963920593s
Pipeline stage MKMLDeployer completed in 222.50s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.1156504154205322s
Received healthy response to inference request in 2.817631244659424s
Received healthy response to inference request in 2.7456326484680176s
Received healthy response to inference request in 2.6060454845428467s
Received healthy response to inference request in 2.697105884552002s
5 requests
0 failed requests
5th percentile: 2.6242575645446777
10th percentile: 2.642469644546509
20th percentile: 2.678893804550171
30th percentile: 2.706811237335205
40th percentile: 2.7262219429016112
50th percentile: 2.7456326484680176
60th percentile: 2.77443208694458
70th percentile: 2.8032315254211424
80th percentile: 2.8772350788116454
90th percentile: 2.996442747116089
95th percentile: 3.0560465812683106
99th percentile: 3.103729648590088
mean time: 2.7964131355285646
Pipeline stage StressChecker completed in 15.49s
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 3.60s
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 3.15s
Shutdown handler de-registered
chaiml-ezstorytellingsft-1k_v1 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 3105.42s
Shutdown handler de-registered
chaiml-ezstorytellingsft-1k_v1 status is now inactive due to auto deactivation removed underperforming models