chaiml-ezstorytellingsft_7824

submission_id: chaiml-ezstorytellingsft_7824_v1

developer_uid: chai_backend_admin

best_of: 4

celo_rating: 1244.45

display_name: EZ-storytelling-SFT-150-sample2

family_friendly_score: 0.5704

family_friendly_standard_error: 0.007000626257700092

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-sample2

latencies: [{'batch_size': 1, 'throughput': 0.3873171074396648, 'latency_mean': 2.5817874109745027, 'latency_p50': 2.5727694034576416, 'latency_p90': 2.8398867368698117}, {'batch_size': 3, 'throughput': 0.8109739200960744, 'latency_mean': 3.6725941038131715, 'latency_p50': 3.6754719018936157, 'latency_p90': 4.108427262306213}, {'batch_size': 5, 'throughput': 1.0802789907527814, 'latency_mean': 4.595749661922455, 'latency_p50': 4.592572331428528, 'latency_p90': 5.234958076477051}, {'batch_size': 6, 'throughput': 1.1679196553797422, 'latency_mean': 5.102569237947464, 'latency_p50': 5.098196864128113, 'latency_p90': 5.727403140068054}, {'batch_size': 10, 'throughput': 1.3876369755695714, 'latency_mean': 7.131739107370376, 'latency_p50': 7.115227580070496, 'latency_p90': 7.965423822402954}]

max_input_tokens: 1024

max_output_tokens: 64

model_architecture: MistralForCausalLM

model_group: ChaiML/EZStorytellingSFT

model_name: EZ-storytelling-SFT-150-sample2

model_num_parameters: 22247282688.0

model_repo: ChaiML/EZStorytellingSFT-sample2

model_size: 22B

num_battles: 9123

num_wins: 4411

ranking_group: single

status: inactive

submission_type: basic

throughput_3p7s: 0.83

timestamp: 2024-11-19T21:14:36+00:00

us_pacific_date: 2024-11-19

win_ratio: 0.4835032335854434

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-7824-v1-mkmlizer
Waiting for job on chaiml-ezstorytellingsft-7824-v1-mkmlizer to finish
chaiml-ezstorytellingsft-7824-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ezstorytellingsft-7824-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-ezstorytellingsft-7824-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-ezstorytellingsft-7824-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-ezstorytellingsft-7824-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-ezstorytellingsft-7824-v1-mkmlizer: ║       /___/                                                         ║
chaiml-ezstorytellingsft-7824-v1-mkmlizer: ║                                                                     ║
chaiml-ezstorytellingsft-7824-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-ezstorytellingsft-7824-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-ezstorytellingsft-7824-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ezstorytellingsft-7824-v1-mkmlizer: ║                                                                     ║
chaiml-ezstorytellingsft-7824-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ezstorytellingsft-7824-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ezstorytellingsft-7824-v1-mkmlizer: ║                                                                     ║
chaiml-ezstorytellingsft-7824-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ezstorytellingsft-7824-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ezstorytellingsft-7824-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-ezstorytellingsft-7824-v1-mkmlizer: ║                                                                     ║
chaiml-ezstorytellingsft-7824-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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
chaiml-ezstorytellingsft-7824-v1-mkmlizer: Downloaded to shared memory in 105.932s
chaiml-ezstorytellingsft-7824-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmprz9yqu77, device:0
chaiml-ezstorytellingsft-7824-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
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
chaiml-ezstorytellingsft-7824-v1-mkmlizer: quantized model in 43.996s
chaiml-ezstorytellingsft-7824-v1-mkmlizer: Processed model ChaiML/EZStorytellingSFT-sample2 in 149.929s
chaiml-ezstorytellingsft-7824-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ezstorytellingsft-7824-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ezstorytellingsft-7824-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ezstorytellingsft-7824-v1
chaiml-ezstorytellingsft-7824-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ezstorytellingsft-7824-v1/special_tokens_map.json
chaiml-ezstorytellingsft-7824-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ezstorytellingsft-7824-v1/config.json
chaiml-ezstorytellingsft-7824-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ezstorytellingsft-7824-v1/tokenizer_config.json
chaiml-ezstorytellingsft-7824-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ezstorytellingsft-7824-v1/tokenizer.json
chaiml-ezstorytellingsft-7824-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-ezstorytellingsft-7824-v1/flywheel_model.1.safetensors
chaiml-ezstorytellingsft-7824-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ezstorytellingsft-7824-v1/flywheel_model.0.safetensors
chaiml-ezstorytellingsft-7824-v1-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:20, 24.54it/s]
Loading 0:   2%|▏         | 12/507 [00:00<00:12, 39.96it/s]
Loading 0:   3%|▎         | 17/507 [00:00<00:13, 36.78it/s]
Loading 0:   4%|▍         | 21/507 [00:00<00:13, 37.00it/s]
Loading 0:   5%|▍         | 25/507 [00:00<00:13, 34.45it/s]
Loading 0:   6%|▌         | 30/507 [00:00<00:12, 37.43it/s]
Loading 0:   7%|▋         | 34/507 [00:00<00:13, 35.84it/s]
Loading 0:   8%|▊         | 39/507 [00:01<00:12, 37.88it/s]
Loading 0:   8%|▊         | 43/507 [00:01<00:12, 36.19it/s]
Loading 0:   9%|▉         | 47/507 [00:01<00:12, 35.92it/s]
Loading 0:  10%|█         | 51/507 [00:01<00:12, 35.29it/s]
Loading 0:  11%|█         | 55/507 [00:01<00:19, 23.58it/s]
Loading 0:  12%|█▏        | 59/507 [00:01<00:17, 26.27it/s]
Loading 0:  12%|█▏        | 63/507 [00:01<00:15, 28.72it/s]
Loading 0:  13%|█▎        | 67/507 [00:02<00:14, 29.53it/s]
Loading 0:  14%|█▍        | 71/507 [00:02<00:13, 31.88it/s]
Loading 0:  15%|█▍        | 75/507 [00:02<00:12, 33.62it/s]
Loading 0:  16%|█▌        | 80/507 [00:02<00:12, 33.31it/s]
Loading 0:  17%|█▋        | 87/507 [00:02<00:10, 39.89it/s]
Loading 0:  18%|█▊        | 92/507 [00:02<00:10, 38.61it/s]
Loading 0:  19%|█▉        | 96/507 [00:02<00:10, 38.41it/s]
Loading 0:  20%|█▉        | 100/507 [00:02<00:11, 36.77it/s]
Loading 0:  21%|██        | 105/507 [00:03<00:10, 38.71it/s]
Loading 0:  21%|██▏       | 109/507 [00:03<00:11, 36.06it/s]
Loading 0:  22%|██▏       | 113/507 [00:03<00:15, 25.63it/s]
Loading 0:  23%|██▎       | 116/507 [00:03<00:16, 24.04it/s]
Loading 0:  24%|██▍       | 122/507 [00:03<00:13, 27.84it/s]
Loading 0:  25%|██▌       | 129/507 [00:03<00:10, 34.83it/s]
Loading 0:  26%|██▌       | 133/507 [00:04<00:10, 34.05it/s]
Loading 0:  27%|██▋       | 138/507 [00:04<00:10, 36.48it/s]
Loading 0:  28%|██▊       | 142/507 [00:04<00:10, 35.50it/s]
Loading 0:  29%|██▉       | 147/507 [00:04<00:09, 38.43it/s]
Loading 0:  30%|██▉       | 151/507 [00:04<00:09, 35.71it/s]
Loading 0:  31%|███       | 156/507 [00:04<00:09, 37.48it/s]
Loading 0:  32%|███▏      | 160/507 [00:04<00:09, 36.25it/s]
Loading 0:  32%|███▏      | 164/507 [00:04<00:09, 36.38it/s]
Loading 0:  33%|███▎      | 169/507 [00:05<00:12, 27.80it/s]
Loading 0:  34%|███▍      | 173/507 [00:05<00:11, 28.74it/s]
Loading 0:  35%|███▍      | 177/507 [00:05<00:12, 27.42it/s]
Loading 0:  36%|███▌      | 181/507 [00:05<00:11, 29.36it/s]
Loading 0:  36%|███▋      | 185/507 [00:05<00:11, 28.43it/s]
Loading 0:  38%|███▊      | 191/507 [00:05<00:08, 35.60it/s]
Loading 0:  38%|███▊      | 195/507 [00:05<00:09, 32.32it/s]
Loading 0:  40%|███▉      | 201/507 [00:06<00:08, 36.65it/s]
Loading 0:  40%|████      | 205/507 [00:06<00:08, 35.71it/s]
Loading 0:  41%|████▏     | 210/507 [00:06<00:07, 37.34it/s]
Loading 0:  42%|████▏     | 214/507 [00:06<00:08, 35.88it/s]
Loading 0:  43%|████▎     | 218/507 [00:06<00:08, 35.49it/s]
Loading 0:  44%|████▍     | 222/507 [00:06<00:08, 34.55it/s]
Loading 0:  45%|████▍     | 226/507 [00:06<00:10, 25.77it/s]
Loading 0:  45%|████▌     | 230/507 [00:07<00:10, 26.13it/s]
Loading 0:  47%|████▋     | 237/507 [00:07<00:08, 33.64it/s]
Loading 0:  48%|████▊     | 241/507 [00:07<00:08, 33.14it/s]
Loading 0:  49%|████▊     | 246/507 [00:07<00:07, 35.13it/s]
Loading 0:  49%|████▉     | 250/507 [00:07<00:07, 34.42it/s]
Loading 0:  50%|█████     | 255/507 [00:07<00:06, 36.23it/s]
Loading 0:  51%|█████     | 259/507 [00:07<00:07, 34.56it/s]
Loading 0:  52%|█████▏    | 263/507 [00:07<00:06, 35.39it/s]
Loading 0:  53%|█████▎    | 267/507 [00:08<00:07, 32.27it/s]
Loading 0:  54%|█████▍    | 273/507 [00:08<00:06, 36.66it/s]
Loading 0:  55%|█████▍    | 277/507 [00:08<00:06, 35.22it/s]
Loading 0:  56%|█████▌    | 283/507 [00:08<00:06, 36.06it/s]
Loading 0:  57%|█████▋    | 287/507 [00:08<00:09, 24.39it/s]
Loading 0:  58%|█████▊    | 293/507 [00:08<00:07, 26.99it/s]
Loading 0:  59%|█████▉    | 299/507 [00:23<00:07, 26.99it/s]
Loading 0:  59%|█████▉    | 300/507 [00:23<02:45,  1.25it/s]
Loading 0:  60%|█████▉    | 302/507 [00:23<02:23,  1.43it/s]
Loading 0:  61%|██████    | 307/507 [00:23<01:37,  2.05it/s]
Loading 0:  61%|██████    | 310/507 [00:24<01:17,  2.54it/s]
Loading 0:  62%|██████▏   | 314/507 [00:24<00:55,  3.48it/s]
Loading 0:  63%|██████▎   | 319/507 [00:24<00:37,  5.07it/s]
Loading 0:  64%|██████▍   | 324/507 [00:24<00:25,  7.17it/s]
Loading 0:  65%|██████▍   | 328/507 [00:24<00:19,  9.06it/s]
Loading 0:  65%|██████▌   | 332/507 [00:24<00:15, 11.50it/s]
Loading 0:  66%|██████▋   | 337/507 [00:24<00:11, 15.32it/s]
Loading 0:  67%|██████▋   | 341/507 [00:24<00:10, 15.49it/s]
Loading 0:  68%|██████▊   | 345/507 [00:25<00:08, 18.06it/s]
Loading 0:  69%|██████▉   | 349/507 [00:25<00:07, 20.77it/s]
Loading 0:  70%|██████▉   | 354/507 [00:25<00:05, 25.50it/s]
Loading 0:  71%|███████   | 358/507 [00:25<00:05, 27.18it/s]
Loading 0:  72%|███████▏  | 363/507 [00:25<00:04, 31.30it/s]
Loading 0:  72%|███████▏  | 367/507 [00:25<00:04, 31.34it/s]
Loading 0:  73%|███████▎  | 372/507 [00:25<00:03, 34.96it/s]
Loading 0:  74%|███████▍  | 376/507 [00:25<00:03, 34.20it/s]
Loading 0:  75%|███████▌  | 381/507 [00:26<00:03, 36.45it/s]
Loading 0:  76%|███████▌  | 385/507 [00:26<00:03, 35.72it/s]
Loading 0:  77%|███████▋  | 389/507 [00:26<00:03, 36.24it/s]
Loading 0:  78%|███████▊  | 393/507 [00:26<00:03, 35.80it/s]
Loading 0:  78%|███████▊  | 397/507 [00:26<00:04, 26.44it/s]
Loading 0:  79%|███████▉  | 401/507 [00:26<00:03, 26.79it/s]
Loading 0:  80%|████████  | 408/507 [00:26<00:02, 34.39it/s]
Loading 0:  81%|████████▏ | 412/507 [00:26<00:02, 34.09it/s]
Loading 0:  82%|████████▏ | 417/507 [00:27<00:02, 36.50it/s]
Loading 0:  83%|████████▎ | 421/507 [00:27<00:02, 35.35it/s]
Loading 0:  84%|████████▍ | 426/507 [00:27<00:02, 37.93it/s]
Loading 0:  85%|████████▍ | 430/507 [00:27<00:02, 36.36it/s]
Loading 0:  86%|████████▌ | 435/507 [00:27<00:01, 37.71it/s]
Loading 0:  87%|████████▋ | 439/507 [00:27<00:01, 36.55it/s]
Loading 0:  88%|████████▊ | 444/507 [00:27<00:01, 39.17it/s]
Loading 0:  88%|████████▊ | 448/507 [00:27<00:01, 37.72it/s]
Loading 0:  90%|████████▉ | 454/507 [00:28<00:01, 38.69it/s]
Loading 0:  90%|█████████ | 458/507 [00:30<00:07,  6.17it/s]
Loading 0:  91%|█████████ | 461/507 [00:30<00:06,  7.43it/s]
Loading 0:  92%|█████████▏| 465/507 [00:30<00:04,  9.47it/s]
Loading 0:  93%|█████████▎| 472/507 [00:30<00:02, 14.59it/s]
Loading 0:  94%|█████████▍| 476/507 [00:30<00:01, 17.06it/s]
Loading 0:  95%|█████████▍| 481/507 [00:30<00:01, 21.11it/s]
Loading 0:  96%|█████████▌| 485/507 [00:31<00:00, 23.04it/s]
Loading 0:  97%|█████████▋| 490/507 [00:31<00:00, 26.93it/s]
Loading 0:  97%|█████████▋| 494/507 [00:31<00:00, 27.93it/s]
Loading 0:  98%|█████████▊| 499/507 [00:31<00:00, 30.92it/s]
Loading 0:  99%|█████████▉| 503/507 [00:31<00:00, 30.75it/s]
                                                            
Job chaiml-ezstorytellingsft-7824-v1-mkmlizer completed after 178.7s with status: succeeded
Stopping job with name chaiml-ezstorytellingsft-7824-v1-mkmlizer
Pipeline stage MKMLizer completed in 179.28s
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-7824-v1
Waiting for inference service chaiml-ezstorytellingsft-7824-v1 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
Inference service chaiml-ezstorytellingsft-7824-v1 ready after 210.83107089996338s
Pipeline stage MKMLDeployer completed in 211.40s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.4325575828552246s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Received healthy response to inference request in 2.6512351036071777s
Received healthy response to inference request in 3.3139352798461914s
Received healthy response to inference request in 2.6119961738586426s
Received healthy response to inference request in 2.587470293045044s
5 requests
0 failed requests
5th percentile: 2.592375469207764
10th percentile: 2.5972806453704833
20th percentile: 2.6070909976959227
30th percentile: 2.6198439598083496
40th percentile: 2.6355395317077637
50th percentile: 2.6512351036071777
60th percentile: 2.9163151741027833
70th percentile: 3.1813952445983884
80th percentile: 3.337659740447998
90th percentile: 3.3851086616516115
95th percentile: 3.408833122253418
99th percentile: 3.4278126907348634
mean time: 2.919438886642456
Pipeline stage StressChecker completed in 16.75s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Failed to get response for submission zonemercy-lexical-viral-_8779_v2: ('http://zonemercy-lexical-viral-8779-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:54368->127.0.0.1:8080: read: connection reset by peer\n')
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 2.29s
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 2.29s
Shutdown handler de-registered
chaiml-ezstorytellingsft_7824_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 3152.75s
Shutdown handler de-registered
chaiml-ezstorytellingsft_7824_v1 status is now inactive due to auto deactivation removed underperforming models