chaiml-small-story-885-e_9360

developer_uid: azuruce

submission_id: chaiml-small-story-885-e_9360_v1

model_name: chaiml-small-story-885-e_9360_v1

model_group: ChaiML/small_story_885-e

status: inactive

timestamp: 2024-11-27T18:54:50+00:00

num_battles: 13399

num_wins: 6509

celo_rating: 1248.6

family_friendly_score: 0.5866

family_friendly_standard_error: 0.0069642004566209895

submission_type: basic

model_repo: ChaiML/small_story_885-ed10-100_true_rpg_sft

model_architecture: MistralForCausalLM

model_num_parameters: 22247282688.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.3849679358375307, 'latency_mean': 2.5975402653217317, 'latency_p50': 2.5995630025863647, 'latency_p90': 2.8741355419158934}, {'batch_size': 3, 'throughput': 0.8235469955020992, 'latency_mean': 3.6244915783405305, 'latency_p50': 3.601521611213684, 'latency_p90': 3.961702251434326}, {'batch_size': 5, 'throughput': 1.0730137719662844, 'latency_mean': 4.6347396171092985, 'latency_p50': 4.601974725723267, 'latency_p90': 5.174263763427734}, {'batch_size': 6, 'throughput': 1.1676655513062721, 'latency_mean': 5.103147161006928, 'latency_p50': 5.117982625961304, 'latency_p90': 5.721600770950317}, {'batch_size': 10, 'throughput': 1.3952862735122087, 'latency_mean': 7.105243295431137, 'latency_p50': 7.115852952003479, 'latency_p90': 7.9839293479919435}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-small-story-885-e_9360_v1

is_internal_developer: True

language_model: ChaiML/small_story_885-ed10-100_true_rpg_sft

model_size: 22B

ranking_group: single

throughput_3p7s: 0.85

us_pacific_date: 2024-11-27

win_ratio: 0.48578252108366293

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}

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-885-e-9360-v1-mkmlizer
Waiting for job on chaiml-small-story-885-e-9360-v1-mkmlizer to finish
chaiml-small-story-885-e-9360-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-small-story-885-e-9360-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-small-story-885-e-9360-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-small-story-885-e-9360-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-small-story-885-e-9360-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-small-story-885-e-9360-v1-mkmlizer: ║       /___/                                                         ║
chaiml-small-story-885-e-9360-v1-mkmlizer: ║                                                                     ║
chaiml-small-story-885-e-9360-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-small-story-885-e-9360-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-small-story-885-e-9360-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-small-story-885-e-9360-v1-mkmlizer: ║                                                                     ║
chaiml-small-story-885-e-9360-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-small-story-885-e-9360-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-small-story-885-e-9360-v1-mkmlizer: ║                                                                     ║
chaiml-small-story-885-e-9360-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-small-story-885-e-9360-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-small-story-885-e-9360-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-small-story-885-e-9360-v1-mkmlizer: ║                                                                     ║
chaiml-small-story-885-e-9360-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-small-story-885-e-9360-v1-mkmlizer: Downloaded to shared memory in 87.192s
chaiml-small-story-885-e-9360-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpw5fje5ln, device:0
chaiml-small-story-885-e-9360-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
chaiml-small-story-885-e-9360-v1-mkmlizer: quantized model in 43.797s
chaiml-small-story-885-e-9360-v1-mkmlizer: Processed model ChaiML/small_story_885-ed10-100_true_rpg_sft in 130.989s
chaiml-small-story-885-e-9360-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-small-story-885-e-9360-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-small-story-885-e-9360-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-small-story-885-e-9360-v1
chaiml-small-story-885-e-9360-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-small-story-885-e-9360-v1/config.json
chaiml-small-story-885-e-9360-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-small-story-885-e-9360-v1/special_tokens_map.json
chaiml-small-story-885-e-9360-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-small-story-885-e-9360-v1/tokenizer_config.json
chaiml-small-story-885-e-9360-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-small-story-885-e-9360-v1/tokenizer.json
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-small-story-885-e-9360-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-small-story-885-e-9360-v1/flywheel_model.1.safetensors
chaiml-small-story-885-e-9360-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-small-story-885-e-9360-v1/flywheel_model.0.safetensors
chaiml-small-story-885-e-9360-v1-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:21, 23.55it/s]
Loading 0:   2%|▏         | 12/507 [00:00<00:12, 38.48it/s]
Loading 0:   3%|▎         | 17/507 [00:00<00:13, 35.98it/s]
Loading 0:   4%|▍         | 21/507 [00:00<00:13, 35.37it/s]
Loading 0:   5%|▍         | 25/507 [00:00<00:14, 32.57it/s]
Loading 0:   6%|▌         | 29/507 [00:00<00:13, 34.48it/s]
Loading 0:   7%|▋         | 33/507 [00:01<00:15, 30.09it/s]
Loading 0:   7%|▋         | 37/507 [00:01<00:14, 31.98it/s]
Loading 0:   8%|▊         | 41/507 [00:01<00:15, 29.81it/s]
Loading 0:   9%|▉         | 47/507 [00:01<00:12, 36.51it/s]
Loading 0:  10%|█         | 51/507 [00:01<00:12, 36.43it/s]
Loading 0:  11%|█         | 55/507 [00:01<00:18, 24.58it/s]
Loading 0:  12%|█▏        | 59/507 [00:01<00:16, 26.57it/s]
Loading 0:  12%|█▏        | 63/507 [00:02<00:15, 28.63it/s]
Loading 0:  13%|█▎        | 67/507 [00:02<00:15, 29.17it/s]
Loading 0:  14%|█▍        | 73/507 [00:02<00:13, 32.62it/s]
Loading 0:  16%|█▌        | 80/507 [00:02<00:12, 34.93it/s]
Loading 0:  17%|█▋        | 87/507 [00:02<00:10, 40.44it/s]
Loading 0:  18%|█▊        | 92/507 [00:02<00:10, 39.37it/s]
Loading 0:  19%|█▉        | 97/507 [00:02<00:10, 39.19it/s]
Loading 0:  20%|█▉        | 101/507 [00:02<00:10, 38.99it/s]
Loading 0:  21%|██        | 106/507 [00:03<00:10, 38.96it/s]
Loading 0:  22%|██▏       | 110/507 [00:03<00:10, 38.32it/s]
Loading 0:  22%|██▏       | 114/507 [00:03<00:14, 27.03it/s]
Loading 0:  23%|██▎       | 118/507 [00:03<00:14, 26.36it/s]
Loading 0:  24%|██▍       | 122/507 [00:03<00:14, 25.80it/s]
Loading 0:  25%|██▌       | 127/507 [00:03<00:12, 30.14it/s]
Loading 0:  26%|██▌       | 131/507 [00:04<00:13, 28.35it/s]
Loading 0:  27%|██▋       | 138/507 [00:04<00:10, 35.74it/s]
Loading 0:  28%|██▊       | 142/507 [00:04<00:10, 34.70it/s]
Loading 0:  29%|██▉       | 147/507 [00:04<00:09, 37.65it/s]
Loading 0:  30%|██▉       | 151/507 [00:04<00:09, 36.29it/s]
Loading 0:  31%|███       | 156/507 [00:04<00:09, 38.87it/s]
Loading 0:  32%|███▏      | 161/507 [00:04<00:08, 38.65it/s]
Loading 0:  33%|███▎      | 165/507 [00:04<00:08, 38.98it/s]
Loading 0:  33%|███▎      | 169/507 [00:05<00:11, 28.18it/s]
Loading 0:  34%|███▍      | 173/507 [00:05<00:11, 29.05it/s]
Loading 0:  35%|███▍      | 177/507 [00:05<00:11, 28.61it/s]
Loading 0:  36%|███▌      | 183/507 [00:05<00:09, 34.81it/s]
Loading 0:  37%|███▋      | 187/507 [00:05<00:09, 35.07it/s]
Loading 0:  38%|███▊      | 192/507 [00:05<00:08, 38.61it/s]
Loading 0:  39%|███▉      | 197/507 [00:05<00:08, 37.86it/s]
Loading 0:  40%|███▉      | 202/507 [00:06<00:07, 38.78it/s]
Loading 0:  41%|████      | 206/507 [00:06<00:07, 38.85it/s]
Loading 0:  41%|████▏     | 210/507 [00:06<00:07, 38.96it/s]
Loading 0:  42%|████▏     | 214/507 [00:06<00:07, 36.98it/s]
Loading 0:  43%|████▎     | 218/507 [00:06<00:07, 36.59it/s]
Loading 0:  44%|████▍     | 222/507 [00:06<00:07, 35.88it/s]
Loading 0:  45%|████▍     | 226/507 [00:06<00:10, 26.89it/s]
Loading 0:  45%|████▌     | 230/507 [00:06<00:10, 26.57it/s]
Loading 0:  47%|████▋     | 237/507 [00:07<00:07, 33.99it/s]
Loading 0:  48%|████▊     | 241/507 [00:07<00:07, 33.72it/s]
Loading 0:  49%|████▊     | 246/507 [00:07<00:07, 36.74it/s]
Loading 0:  49%|████▉     | 250/507 [00:07<00:07, 36.36it/s]
Loading 0:  50%|█████     | 255/507 [00:07<00:06, 38.87it/s]
Loading 0:  51%|█████     | 259/507 [00:07<00:06, 37.65it/s]
Loading 0:  52%|█████▏    | 264/507 [00:07<00:06, 40.23it/s]
Loading 0:  53%|█████▎    | 269/507 [00:07<00:06, 37.50it/s]
Loading 0:  54%|█████▍    | 273/507 [00:08<00:06, 37.40it/s]
Loading 0:  55%|█████▍    | 277/507 [00:08<00:06, 36.15it/s]
Loading 0:  56%|█████▌    | 283/507 [00:08<00:05, 38.24it/s]
Loading 0:  57%|█████▋    | 287/507 [00:08<00:08, 25.36it/s]
Loading 0:  58%|█████▊    | 293/507 [00:08<00:07, 28.68it/s]
Loading 0:  59%|█████▉    | 299/507 [00:23<00:07, 28.68it/s]
Loading 0:  59%|█████▉    | 300/507 [00:23<02:46,  1.24it/s]
Loading 0:  60%|█████▉    | 302/507 [00:23<02:25,  1.41it/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%|██████▏   | 313/507 [00:23<01:00,  3.22it/s]
Loading 0:  63%|██████▎   | 318/507 [00:24<00:39,  4.83it/s]
Loading 0:  64%|██████▎   | 322/507 [00:24<00:28,  6.46it/s]
Loading 0:  64%|██████▍   | 327/507 [00:24<00:19,  9.19it/s]
Loading 0:  65%|██████▌   | 331/507 [00:24<00:15, 11.58it/s]
Loading 0:  66%|██████▌   | 335/507 [00:24<00:11, 14.44it/s]
Loading 0:  67%|██████▋   | 340/507 [00:24<00:10, 16.22it/s]
Loading 0:  68%|██████▊   | 344/507 [00:24<00:08, 18.83it/s]
Loading 0:  69%|██████▊   | 348/507 [00:25<00:07, 20.39it/s]
Loading 0:  70%|██████▉   | 354/507 [00:25<00:05, 26.31it/s]
Loading 0:  71%|███████   | 358/507 [00:25<00:05, 27.12it/s]
Loading 0:  72%|███████▏  | 363/507 [00:25<00:04, 30.79it/s]
Loading 0:  72%|███████▏  | 367/507 [00:25<00:04, 30.22it/s]
Loading 0:  73%|███████▎  | 372/507 [00:25<00:04, 32.89it/s]
Loading 0:  74%|███████▍  | 376/507 [00:25<00:03, 33.20it/s]
Loading 0:  75%|███████▌  | 381/507 [00:25<00:03, 36.37it/s]
Loading 0:  76%|███████▌  | 385/507 [00:26<00:03, 35.70it/s]
Loading 0:  77%|███████▋  | 389/507 [00:26<00:03, 36.50it/s]
Loading 0:  78%|███████▊  | 393/507 [00:26<00:03, 36.28it/s]
Loading 0:  78%|███████▊  | 397/507 [00:26<00:04, 26.13it/s]
Loading 0:  79%|███████▉  | 401/507 [00:26<00:04, 26.19it/s]
Loading 0:  80%|████████  | 408/507 [00:26<00:02, 33.67it/s]
Loading 0:  81%|████████▏ | 412/507 [00:26<00:02, 33.47it/s]
Loading 0:  82%|████████▏ | 417/507 [00:27<00:02, 36.42it/s]
Loading 0:  83%|████████▎ | 421/507 [00:27<00:02, 35.17it/s]
Loading 0:  84%|████████▍ | 426/507 [00:27<00:02, 37.79it/s]
Loading 0:  85%|████████▍ | 430/507 [00:27<00:02, 35.62it/s]
Loading 0:  86%|████████▌ | 435/507 [00:27<00:01, 38.06it/s]
Loading 0:  87%|████████▋ | 439/507 [00:27<00:01, 36.49it/s]
Loading 0:  88%|████████▊ | 444/507 [00:27<00:01, 39.60it/s]
Loading 0:  89%|████████▊ | 449/507 [00:27<00:01, 37.55it/s]
Loading 0:  90%|████████▉ | 454/507 [00:27<00:01, 37.89it/s]
Loading 0:  90%|█████████ | 458/507 [00:30<00:08,  5.97it/s]
Loading 0:  91%|█████████ | 461/507 [00:30<00:06,  7.15it/s]
Loading 0:  92%|█████████▏| 465/507 [00:30<00:04,  9.13it/s]
Loading 0:  93%|█████████▎| 472/507 [00:30<00:02, 14.12it/s]
Loading 0:  94%|█████████▍| 476/507 [00:30<00:01, 16.55it/s]
Loading 0:  95%|█████████▍| 481/507 [00:30<00:01, 20.61it/s]
Loading 0:  96%|█████████▌| 485/507 [00:31<00:00, 22.55it/s]
Loading 0:  97%|█████████▋| 490/507 [00:31<00:00, 26.34it/s]
Loading 0:  97%|█████████▋| 494/507 [00:31<00:00, 28.12it/s]
Loading 0:  98%|█████████▊| 499/507 [00:31<00:00, 32.16it/s]
Loading 0:  99%|█████████▉| 503/507 [00:31<00:00, 32.90it/s]
                                                            
Job chaiml-small-story-885-e-9360-v1-mkmlizer completed after 166.03s with status: succeeded
Stopping job with name chaiml-small-story-885-e-9360-v1-mkmlizer
Pipeline stage MKMLizer completed in 166.54s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Connection pool is full, discarding connection: %s. Connection pool size: %s
Creating inference service chaiml-small-story-885-e-9360-v1
Waiting for inference service chaiml-small-story-885-e-9360-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
Inference service chaiml-small-story-885-e-9360-v1 ready after 120.4195282459259s
Pipeline stage MKMLDeployer completed in 120.95s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.0857315063476562s
Received healthy response to inference request in 2.5213325023651123s
Received healthy response to inference request in 2.3920345306396484s
Received healthy response to inference request in 2.2527949810028076s
Received healthy response to inference request in 2.483729124069214s
5 requests
0 failed requests
5th percentile: 2.2806428909301757
10th percentile: 2.3084908008575438
20th percentile: 2.3641866207122804
30th percentile: 2.4103734493255615
40th percentile: 2.4470512866973877
50th percentile: 2.483729124069214
60th percentile: 2.4987704753875732
70th percentile: 2.5138118267059326
80th percentile: 2.6342123031616214
90th percentile: 2.8599719047546386
95th percentile: 2.972851705551147
99th percentile: 3.0631555461883546
mean time: 2.5471245288848876
Pipeline stage StressChecker completed in 13.98s
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 2.15s
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 2.04s
Shutdown handler de-registered
chaiml-small-story-885-e_9360_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
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 4195.83s
Shutdown handler de-registered
chaiml-small-story-885-e_9360_v1 status is now inactive due to auto deactivation removed underperforming models