developer_uid: ebony59
submission_id: chaiml-ezstorytellingedi_7170_v2
model_name: chaiml-ezstorytellingedi_7170_v2
model_group: ChaiML/EZStorytellingEdi
status: inactive
timestamp: 2024-11-30T03:11:42+00:00
num_battles: 13340
num_wins: 6312
celo_rating: 1243.03
family_friendly_score: 0.5586
family_friendly_standard_error: 0.0070223363633480276
submission_type: basic
model_repo: ChaiML/EZStorytellingEditsSFT_Qi6_71convos_8epoch
model_architecture: MistralForCausalLM
model_num_parameters: 22247282688.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.38929467109198396, 'latency_mean': 2.5686554169654845, 'latency_p50': 2.5796583890914917, 'latency_p90': 2.8380298614501953}, {'batch_size': 3, 'throughput': 0.8137621425601265, 'latency_mean': 3.6719956076145173, 'latency_p50': 3.656232714653015, 'latency_p90': 4.062052369117737}, {'batch_size': 5, 'throughput': 1.0787409019596566, 'latency_mean': 4.609684294462204, 'latency_p50': 4.612231135368347, 'latency_p90': 5.1766541481018065}, {'batch_size': 6, 'throughput': 1.1561508890058083, 'latency_mean': 5.157584685087204, 'latency_p50': 5.152078151702881, 'latency_p90': 5.7867252111434935}, {'batch_size': 10, 'throughput': 1.373016450923169, 'latency_mean': 7.220619006156921, 'latency_p50': 7.150818228721619, 'latency_p90': 8.329883265495301}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: chaiml-ezstorytellingedi_7170_v2
is_internal_developer: True
language_model: ChaiML/EZStorytellingEditsSFT_Qi6_71convos_8epoch
model_size: 22B
ranking_group: single
throughput_3p7s: 0.83
us_pacific_date: 2024-11-29
win_ratio: 0.47316341829085456
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': "{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-ezstorytellingedi-7170-v2-mkmlizer
Waiting for job on chaiml-ezstorytellingedi-7170-v2-mkmlizer to finish
chaiml-ezstorytellingedi-7170-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ezstorytellingedi-7170-v2-mkmlizer: ║ _____ __ __ ║
chaiml-ezstorytellingedi-7170-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-ezstorytellingedi-7170-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-ezstorytellingedi-7170-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-ezstorytellingedi-7170-v2-mkmlizer: ║ /___/ ║
chaiml-ezstorytellingedi-7170-v2-mkmlizer: ║ ║
chaiml-ezstorytellingedi-7170-v2-mkmlizer: ║ Version: 0.11.12 ║
chaiml-ezstorytellingedi-7170-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-ezstorytellingedi-7170-v2-mkmlizer: ║ https://mk1.ai ║
chaiml-ezstorytellingedi-7170-v2-mkmlizer: ║ ║
chaiml-ezstorytellingedi-7170-v2-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-ezstorytellingedi-7170-v2-mkmlizer: ║ belonging to: ║
chaiml-ezstorytellingedi-7170-v2-mkmlizer: ║ ║
chaiml-ezstorytellingedi-7170-v2-mkmlizer: ║ Chai Research Corp. ║
chaiml-ezstorytellingedi-7170-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-ezstorytellingedi-7170-v2-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
chaiml-ezstorytellingedi-7170-v2-mkmlizer: ║ ║
chaiml-ezstorytellingedi-7170-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ezstorytellingedi-7170-v2-mkmlizer: Downloaded to shared memory in 67.199s
chaiml-ezstorytellingedi-7170-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpft0gyybn, device:0
chaiml-ezstorytellingedi-7170-v2-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-ezstorytellingedi-7170-v2-mkmlizer: quantized model in 42.608s
chaiml-ezstorytellingedi-7170-v2-mkmlizer: Processed model ChaiML/EZStorytellingEditsSFT_Qi6_71convos_8epoch in 109.807s
chaiml-ezstorytellingedi-7170-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ezstorytellingedi-7170-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ezstorytellingedi-7170-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ezstorytellingedi-7170-v2
chaiml-ezstorytellingedi-7170-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ezstorytellingedi-7170-v2/config.json
chaiml-ezstorytellingedi-7170-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ezstorytellingedi-7170-v2/special_tokens_map.json
chaiml-ezstorytellingedi-7170-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ezstorytellingedi-7170-v2/tokenizer_config.json
chaiml-ezstorytellingedi-7170-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ezstorytellingedi-7170-v2/tokenizer.json
chaiml-ezstorytellingedi-7170-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-ezstorytellingedi-7170-v2/flywheel_model.1.safetensors
chaiml-ezstorytellingedi-7170-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ezstorytellingedi-7170-v2/flywheel_model.0.safetensors
chaiml-ezstorytellingedi-7170-v2-mkmlizer: Loading 0: 0%| | 0/507 [00:00<?, ?it/s] Loading 0: 1%| | 5/507 [00:00<00:20, 24.00it/s] Loading 0: 2%|▏ | 12/507 [00:00<00:12, 40.52it/s] Loading 0: 3%|▎ | 17/507 [00:00<00:12, 39.96it/s] Loading 0: 4%|▍ | 22/507 [00:00<00:11, 40.76it/s] Loading 0: 5%|▌ | 27/507 [00:00<00:11, 42.04it/s] Loading 0: 6%|▋ | 32/507 [00:00<00:13, 35.17it/s] Loading 0: 8%|▊ | 39/507 [00:00<00:11, 42.52it/s] Loading 0: 9%|▊ | 44/507 [00:01<00:11, 42.02it/s] Loading 0: 10%|▉ | 49/507 [00:01<00:12, 36.86it/s] Loading 0: 10%|█ | 53/507 [00:01<00:16, 28.31it/s] Loading 0: 11%|█ | 57/507 [00:01<00:16, 27.84it/s] Loading 0: 12%|█▏ | 63/507 [00:01<00:13, 33.37it/s] Loading 0: 13%|█▎ | 67/507 [00:01<00:12, 34.05it/s] Loading 0: 14%|█▍ | 73/507 [00:02<00:11, 36.74it/s] Loading 0: 16%|█▌ | 80/507 [00:02<00:11, 37.80it/s] Loading 0: 17%|█▋ | 87/507 [00:02<00:09, 43.82it/s] Loading 0: 18%|█▊ | 92/507 [00:02<00:09, 42.38it/s] Loading 0: 19%|█▉ | 97/507 [00:02<00:09, 41.56it/s] Loading 0: 20%|██ | 102/507 [00:02<00:09, 43.24it/s] Loading 0: 21%|██ | 107/507 [00:02<00:10, 37.46it/s] Loading 0: 22%|██▏ | 113/507 [00:03<00:11, 32.97it/s] Loading 0: 23%|██▎ | 117/507 [00:03<00:12, 31.20it/s] Loading 0: 24%|██▍ | 122/507 [00:03<00:12, 31.65it/s] Loading 0: 25%|██▌ | 129/507 [00:03<00:09, 38.55it/s] Loading 0: 26%|██▋ | 134/507 [00:03<00:09, 39.24it/s] Loading 0: 27%|██▋ | 139/507 [00:03<00:09, 39.99it/s] Loading 0: 28%|██▊ | 144/507 [00:03<00:08, 40.88it/s] Loading 0: 29%|██▉ | 149/507 [00:04<00:10, 34.61it/s] Loading 0: 31%|███ | 156/507 [00:04<00:08, 41.68it/s] Loading 0: 32%|███▏ | 161/507 [00:04<00:08, 42.41it/s] Loading 0: 33%|███▎ | 167/507 [00:04<00:07, 45.99it/s] Loading 0: 34%|███▍ | 172/507 [00:04<00:10, 30.56it/s] Loading 0: 35%|███▍ | 176/507 [00:04<00:10, 30.46it/s] Loading 0: 36%|███▌ | 183/507 [00:04<00:08, 38.13it/s] Loading 0: 37%|███▋ | 188/507 [00:05<00:08, 37.94it/s] Loading 0: 38%|███▊ | 193/507 [00:05<00:07, 39.74it/s] Loading 0: 39%|███▉ | 198/507 [00:05<00:07, 41.37it/s] Loading 0: 40%|████ | 203/507 [00:05<00:08, 34.81it/s] Loading 0: 41%|████▏ | 210/507 [00:05<00:07, 41.78it/s] Loading 0: 42%|████▏ | 215/507 [00:05<00:06, 41.78it/s] Loading 0: 43%|████▎ | 220/507 [00:05<00:07, 36.22it/s] Loading 0: 44%|████▍ | 224/507 [00:06<00:09, 28.89it/s] Loading 0: 45%|████▌ | 230/507 [00:06<00:09, 29.87it/s] Loading 0: 47%|████▋ | 237/507 [00:06<00:07, 36.28it/s] Loading 0: 48%|████▊ | 242/507 [00:06<00:07, 36.94it/s] Loading 0: 49%|████▊ | 247/507 [00:06<00:06, 37.82it/s] Loading 0: 50%|████▉ | 251/507 [00:06<00:06, 38.29it/s] Loading 0: 50%|█████ | 256/507 [00:06<00:06, 39.11it/s] Loading 0: 51%|█████▏ | 261/507 [00:07<00:06, 40.37it/s] Loading 0: 52%|█████▏ | 266/507 [00:07<00:07, 33.83it/s] Loading 0: 54%|█████▍ | 273/507 [00:07<00:05, 40.68it/s] Loading 0: 55%|█████▍ | 278/507 [00:07<00:05, 39.93it/s] Loading 0: 56%|█████▌ | 283/507 [00:07<00:05, 39.73it/s] Loading 0: 57%|█████▋ | 288/507 [00:07<00:07, 28.71it/s] Loading 0: 58%|█████▊ | 293/507 [00:08<00:07, 29.22it/s] Loading 0: 59%|█████▉ | 299/507 [00:22<00:07, 29.22it/s] Loading 0: 59%|█████▉ | 300/507 [00:22<02:41, 1.28it/s] Loading 0: 60%|█████▉ | 302/507 [00:22<02:21, 1.45it/s] Loading 0: 61%|██████ | 307/507 [00:22<01:35, 2.08it/s] Loading 0: 61%|██████ | 310/507 [00:22<01:16, 2.58it/s] Loading 0: 62%|██████▏ | 314/507 [00:23<00:54, 3.53it/s] Loading 0: 63%|██████▎ | 319/507 [00:23<00:36, 5.13it/s] Loading 0: 64%|██████▎ | 323/507 [00:23<00:27, 6.78it/s] Loading 0: 65%|██████▍ | 328/507 [00:23<00:19, 9.39it/s] Loading 0: 65%|██████▌ | 332/507 [00:23<00:14, 11.87it/s] Loading 0: 66%|██████▋ | 337/507 [00:23<00:10, 15.73it/s] Loading 0: 67%|██████▋ | 341/507 [00:23<00:10, 15.81it/s] Loading 0: 68%|██████▊ | 345/507 [00:24<00:08, 18.30it/s] Loading 0: 69%|██████▉ | 349/507 [00:24<00:07, 21.03it/s] Loading 0: 70%|██████▉ | 354/507 [00:24<00:05, 26.10it/s] Loading 0: 71%|███████ | 358/507 [00:24<00:05, 28.03it/s] Loading 0: 72%|███████▏ | 364/507 [00:24<00:04, 33.02it/s] Loading 0: 73%|███████▎ | 369/507 [00:24<00:03, 36.22it/s] Loading 0: 74%|███████▍ | 374/507 [00:24<00:04, 33.14it/s] Loading 0: 75%|███████▌ | 381/507 [00:24<00:03, 41.31it/s] Loading 0: 76%|███████▌ | 386/507 [00:24<00:03, 40.21it/s] Loading 0: 77%|███████▋ | 391/507 [00:25<00:03, 35.98it/s] Loading 0: 78%|███████▊ | 395/507 [00:25<00:03, 29.48it/s] Loading 0: 79%|███████▉ | 401/507 [00:25<00:03, 31.23it/s] Loading 0: 80%|████████ | 408/507 [00:25<00:02, 37.82it/s] Loading 0: 81%|████████▏ | 413/507 [00:25<00:02, 38.23it/s] Loading 0: 82%|████████▏ | 418/507 [00:25<00:02, 38.85it/s] Loading 0: 83%|████████▎ | 423/507 [00:26<00:02, 40.52it/s] Loading 0: 84%|████████▍ | 428/507 [00:26<00:02, 35.54it/s] Loading 0: 86%|████████▌ | 435/507 [00:26<00:01, 42.66it/s] Loading 0: 87%|████████▋ | 440/507 [00:26<00:01, 42.67it/s] Loading 0: 88%|████████▊ | 445/507 [00:26<00:01, 43.05it/s] Loading 0: 89%|████████▉ | 450/507 [00:26<00:01, 44.61it/s] Loading 0: 90%|████████▉ | 455/507 [00:28<00:07, 6.77it/s] Loading 0: 91%|█████████ | 459/507 [00:29<00:05, 8.27it/s] Loading 0: 92%|█████████▏| 465/507 [00:29<00:03, 11.40it/s] Loading 0: 93%|█████████▎| 472/507 [00:29<00:02, 16.24it/s] Loading 0: 94%|█████████▍| 477/507 [00:29<00:01, 19.03it/s] Loading 0: 95%|█████████▌| 482/507 [00:29<00:01, 22.50it/s] Loading 0: 96%|█████████▌| 487/507 [00:29<00:00, 26.11it/s] Loading 0: 97%|█████████▋| 492/507 [00:29<00:00, 25.76it/s] Loading 0: 98%|█████████▊| 499/507 [00:30<00:00, 32.01it/s] Loading 0: 99%|█████████▉| 504/507 [00:30<00:00, 33.53it/s]
Job chaiml-ezstorytellingedi-7170-v2-mkmlizer completed after 145.42s with status: succeeded
Stopping job with name chaiml-ezstorytellingedi-7170-v2-mkmlizer
Pipeline stage MKMLizer completed in 145.91s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-ezstorytellingedi-7170-v2
Waiting for inference service chaiml-ezstorytellingedi-7170-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
Inference service chaiml-ezstorytellingedi-7170-v2 ready after 130.4595742225647s
Pipeline stage MKMLDeployer completed in 131.02s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.0170023441314697s
Received healthy response to inference request in 2.772212505340576s
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
Received healthy response to inference request in 2.584413528442383s
Received healthy response to inference request in 1.8998591899871826s
Received healthy response to inference request in 1.7691774368286133s
5 requests
0 failed requests
5th percentile: 1.795313787460327
10th percentile: 1.821450138092041
20th percentile: 1.8737228393554688
30th percentile: 2.036770057678223
40th percentile: 2.310591793060303
50th percentile: 2.584413528442383
60th percentile: 2.6595331192016602
70th percentile: 2.7346527099609377
80th percentile: 2.821170473098755
90th percentile: 2.9190864086151125
95th percentile: 2.968044376373291
99th percentile: 3.007210750579834
mean time: 2.408533000946045
Pipeline stage StressChecker completed in 13.40s
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 2.18s
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 2.01s
Shutdown handler de-registered
chaiml-ezstorytellingedi_7170_v2 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 3678.04s
Shutdown handler de-registered
chaiml-ezstorytellingedi_7170_v2 status is now inactive due to auto deactivation removed underperforming models