submission_id: chaiml-ezstorytellingsft_5389_v1
developer_uid: chai_backend_admin
best_of: 4
celo_rating: 1250.14
display_name: EZ-storytelling-SFT-150-sample3
family_friendly_score: 0.573
family_friendly_standard_error: 0.006995298421082549
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-sample3
latencies: [{'batch_size': 1, 'throughput': 0.39132216519803903, 'latency_mean': 2.5553479278087616, 'latency_p50': 2.5523393154144287, 'latency_p90': 2.8336650371551513}, {'batch_size': 3, 'throughput': 0.8216148238550135, 'latency_mean': 3.6372650980949404, 'latency_p50': 3.6337591409683228, 'latency_p90': 3.998223161697388}, {'batch_size': 5, 'throughput': 1.1021052564380929, 'latency_mean': 4.512493419647217, 'latency_p50': 4.496743679046631, 'latency_p90': 4.9173133850097654}, {'batch_size': 6, 'throughput': 1.1836213905615747, 'latency_mean': 5.045857059955597, 'latency_p50': 5.0258588790893555, 'latency_p90': 5.67396490573883}, {'batch_size': 10, 'throughput': 1.3898827527667532, 'latency_mean': 7.128813695907593, 'latency_p50': 7.062600374221802, 'latency_p90': 8.104539775848389}]
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: ChaiML/EZStorytellingSFT
model_name: EZ-storytelling-SFT-150-sample3
model_num_parameters: 22247282688.0
model_repo: ChaiML/EZStorytellingSFT-sample3
model_size: 22B
num_battles: 9197
num_wins: 4535
ranking_group: single
status: inactive
submission_type: basic
throughput_3p7s: 0.85
timestamp: 2024-11-19T21:30:42+00:00
us_pacific_date: 2024-11-19
win_ratio: 0.49309557464390563
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-5389-v1-mkmlizer
Waiting for job on chaiml-ezstorytellingsft-5389-v1-mkmlizer to finish
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-ezstorytellingsft-5389-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ezstorytellingsft-5389-v1-mkmlizer: ║ _____ __ __ ║
chaiml-ezstorytellingsft-5389-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-ezstorytellingsft-5389-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-ezstorytellingsft-5389-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-ezstorytellingsft-5389-v1-mkmlizer: ║ /___/ ║
chaiml-ezstorytellingsft-5389-v1-mkmlizer: ║ ║
chaiml-ezstorytellingsft-5389-v1-mkmlizer: ║ Version: 0.11.12 ║
chaiml-ezstorytellingsft-5389-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-ezstorytellingsft-5389-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-ezstorytellingsft-5389-v1-mkmlizer: ║ ║
chaiml-ezstorytellingsft-5389-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-ezstorytellingsft-5389-v1-mkmlizer: ║ belonging to: ║
chaiml-ezstorytellingsft-5389-v1-mkmlizer: ║ ║
chaiml-ezstorytellingsft-5389-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-ezstorytellingsft-5389-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-ezstorytellingsft-5389-v1-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
chaiml-ezstorytellingsft-5389-v1-mkmlizer: ║ ║
chaiml-ezstorytellingsft-5389-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
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
chaiml-ezstorytellingsft-5389-v1-mkmlizer: Downloaded to shared memory in 112.912s
chaiml-ezstorytellingsft-5389-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp9g6wi0ru, device:0
chaiml-ezstorytellingsft-5389-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ezstorytellingsft-5389-v1-mkmlizer: quantized model in 42.862s
chaiml-ezstorytellingsft-5389-v1-mkmlizer: Processed model ChaiML/EZStorytellingSFT-sample3 in 155.774s
chaiml-ezstorytellingsft-5389-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ezstorytellingsft-5389-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ezstorytellingsft-5389-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ezstorytellingsft-5389-v1
chaiml-ezstorytellingsft-5389-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ezstorytellingsft-5389-v1/config.json
chaiml-ezstorytellingsft-5389-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ezstorytellingsft-5389-v1/special_tokens_map.json
chaiml-ezstorytellingsft-5389-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ezstorytellingsft-5389-v1/tokenizer_config.json
chaiml-ezstorytellingsft-5389-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ezstorytellingsft-5389-v1/tokenizer.json
chaiml-ezstorytellingsft-5389-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-ezstorytellingsft-5389-v1/flywheel_model.1.safetensors
chaiml-ezstorytellingsft-5389-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ezstorytellingsft-5389-v1/flywheel_model.0.safetensors
chaiml-ezstorytellingsft-5389-v1-mkmlizer: Loading 0: 0%| | 0/507 [00:00<?, ?it/s] Loading 0: 1%| | 5/507 [00:00<00:19, 25.30it/s] Loading 0: 2%|▏ | 12/507 [00:00<00:11, 42.30it/s] Loading 0: 3%|▎ | 17/507 [00:00<00:11, 41.09it/s] Loading 0: 4%|▍ | 22/507 [00:00<00:12, 38.82it/s] Loading 0: 5%|▌ | 27/507 [00:00<00:12, 39.07it/s] Loading 0: 6%|▋ | 32/507 [00:00<00:14, 32.45it/s] Loading 0: 8%|▊ | 39/507 [00:01<00:11, 39.13it/s] Loading 0: 9%|▊ | 44/507 [00:01<00:12, 38.45it/s] Loading 0: 10%|▉ | 49/507 [00:01<00:13, 34.41it/s] Loading 0: 10%|█ | 53/507 [00:01<00:16, 26.99it/s] Loading 0: 11%|█ | 57/507 [00:01<00:17, 26.25it/s] Loading 0: 12%|█▏ | 63/507 [00:01<00:14, 31.19it/s] Loading 0: 13%|█▎ | 67/507 [00:02<00:13, 31.56it/s] Loading 0: 14%|█▍ | 73/507 [00:02<00:12, 34.40it/s] Loading 0: 16%|█▌ | 80/507 [00:02<00:12, 35.34it/s] Loading 0: 17%|█▋ | 87/507 [00:02<00:10, 40.95it/s] Loading 0: 18%|█▊ | 92/507 [00:02<00:10, 39.08it/s] Loading 0: 19%|█▉ | 97/507 [00:02<00:10, 39.11it/s] Loading 0: 20%|██ | 102/507 [00:02<00:09, 40.56it/s] Loading 0: 21%|██ | 107/507 [00:03<00:11, 33.34it/s] Loading 0: 22%|██▏ | 112/507 [00:03<00:11, 35.60it/s] Loading 0: 23%|██▎ | 116/507 [00:03<00:15, 24.65it/s] Loading 0: 24%|██▍ | 122/507 [00:03<00:13, 27.71it/s] Loading 0: 25%|██▌ | 129/507 [00:03<00:10, 34.49it/s] Loading 0: 26%|██▋ | 134/507 [00:03<00:10, 35.67it/s] Loading 0: 27%|██▋ | 139/507 [00:04<00:09, 37.20it/s] Loading 0: 28%|██▊ | 144/507 [00:04<00:09, 37.73it/s] Loading 0: 29%|██▉ | 149/507 [00:04<00:11, 32.45it/s] Loading 0: 31%|███ | 156/507 [00:04<00:08, 39.73it/s] Loading 0: 32%|███▏ | 161/507 [00:04<00:09, 38.36it/s] Loading 0: 33%|███▎ | 166/507 [00:04<00:08, 39.28it/s] Loading 0: 34%|███▎ | 171/507 [00:05<00:12, 26.76it/s] Loading 0: 35%|███▍ | 176/507 [00:05<00:11, 28.62it/s] Loading 0: 36%|███▌ | 181/507 [00:05<00:10, 32.54it/s] Loading 0: 36%|███▋ | 185/507 [00:05<00:10, 29.92it/s] Loading 0: 37%|███▋ | 190/507 [00:05<00:09, 32.84it/s] Loading 0: 38%|███▊ | 194/507 [00:05<00:10, 30.12it/s] Loading 0: 40%|███▉ | 201/507 [00:05<00:08, 36.55it/s] Loading 0: 40%|████ | 205/507 [00:05<00:08, 36.68it/s] Loading 0: 42%|████▏ | 211/507 [00:06<00:07, 39.75it/s] Loading 0: 43%|████▎ | 216/507 [00:06<00:06, 42.07it/s] Loading 0: 44%|████▎ | 221/507 [00:06<00:07, 36.58it/s] Loading 0: 44%|████▍ | 225/507 [00:06<00:10, 28.10it/s] Loading 0: 45%|████▌ | 230/507 [00:06<00:09, 29.36it/s] Loading 0: 47%|████▋ | 237/507 [00:06<00:07, 36.20it/s] Loading 0: 48%|████▊ | 242/507 [00:07<00:07, 36.94it/s] Loading 0: 49%|████▊ | 247/507 [00:07<00:06, 37.89it/s] Loading 0: 50%|████▉ | 251/507 [00:07<00:06, 38.17it/s] Loading 0: 50%|█████ | 256/507 [00:07<00:06, 38.34it/s] Loading 0: 51%|█████▏ | 260/507 [00:07<00:06, 37.29it/s] Loading 0: 52%|█████▏ | 265/507 [00:07<00:06, 38.07it/s] Loading 0: 53%|█████▎ | 269/507 [00:07<00:06, 38.07it/s] Loading 0: 54%|█████▍ | 274/507 [00:07<00:05, 39.14it/s] Loading 0: 55%|█████▍ | 278/507 [00:07<00:05, 38.52it/s] Loading 0: 56%|█████▌ | 283/507 [00:08<00:05, 38.40it/s] Loading 0: 57%|█████▋ | 287/507 [00:08<00:08, 25.27it/s] Loading 0: 58%|█████▊ | 293/507 [00:08<00:07, 28.67it/s] Loading 0: 59%|█████▉ | 299/507 [00:23<00:07, 28.67it/s] Loading 0: 59%|█████▉ | 300/507 [00:23<02:47, 1.23it/s] Loading 0: 60%|█████▉ | 302/507 [00:23<02:26, 1.40it/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<00:37, 5.05it/s] Loading 0: 64%|██████▍ | 324/507 [00:23<00:25, 7.15it/s] Loading 0: 65%|██████▍ | 328/507 [00:24<00:19, 9.15it/s] Loading 0: 65%|██████▌ | 332/507 [00:24<00:15, 11.62it/s] Loading 0: 66%|██████▋ | 337/507 [00:24<00:10, 15.54it/s] Loading 0: 67%|██████▋ | 341/507 [00:24<00:10, 15.62it/s] Loading 0: 68%|██████▊ | 345/507 [00:24<00:09, 17.34it/s] Loading 0: 69%|██████▉ | 349/507 [00:24<00:07, 19.87it/s] Loading 0: 70%|██████▉ | 354/507 [00:24<00:06, 24.71it/s] Loading 0: 71%|███████ | 358/507 [00:25<00:05, 26.71it/s] Loading 0: 72%|███████▏ | 363/507 [00:25<00:04, 31.25it/s] Loading 0: 72%|███████▏ | 367/507 [00:25<00:04, 31.99it/s] Loading 0: 73%|███████▎ | 372/507 [00:25<00:03, 35.91it/s] Loading 0: 74%|███████▍ | 377/507 [00:25<00:03, 37.35it/s] Loading 0: 75%|███████▌ | 382/507 [00:25<00:03, 38.71it/s] Loading 0: 76%|███████▋ | 387/507 [00:25<00:02, 41.08it/s] Loading 0: 77%|███████▋ | 392/507 [00:25<00:03, 35.66it/s] Loading 0: 78%|███████▊ | 396/507 [00:26<00:04, 27.52it/s] Loading 0: 79%|███████▉ | 401/507 [00:26<00:03, 29.07it/s] Loading 0: 80%|████████ | 408/507 [00:26<00:02, 35.44it/s] Loading 0: 81%|████████▏ | 412/507 [00:26<00:02, 33.84it/s] Loading 0: 82%|████████▏ | 417/507 [00:26<00:02, 35.01it/s] Loading 0: 83%|████████▎ | 421/507 [00:26<00:02, 33.15it/s] Loading 0: 84%|████████▍ | 425/507 [00:26<00:02, 34.65it/s] Loading 0: 85%|████████▍ | 429/507 [00:27<00:02, 31.15it/s] Loading 0: 86%|████████▌ | 435/507 [00:27<00:02, 35.86it/s] Loading 0: 87%|████████▋ | 439/507 [00:27<00:01, 36.28it/s] Loading 0: 88%|████████▊ | 444/507 [00:27<00:01, 39.36it/s] Loading 0: 89%|████████▊ | 449/507 [00:27<00:01, 38.87it/s] Loading 0: 90%|████████▉ | 454/507 [00:27<00:01, 36.36it/s] Loading 0: 90%|█████████ | 458/507 [00:29<00:08, 6.08it/s] Loading 0: 91%|█████████ | 461/507 [00:30<00:06, 7.32it/s] Loading 0: 92%|█████████▏| 465/507 [00:30<00:04, 9.38it/s] Loading 0: 93%|█████████▎| 472/507 [00:30<00:02, 14.45it/s] Loading 0: 94%|█████████▍| 476/507 [00:30<00:01, 17.00it/s] Loading 0: 95%|█████████▍| 481/507 [00:30<00:01, 21.19it/s] Loading 0: 96%|█████████▌| 485/507 [00:30<00:00, 22.87it/s] Loading 0: 97%|█████████▋| 490/507 [00:30<00:00, 26.69it/s] Loading 0: 97%|█████████▋| 494/507 [00:30<00:00, 28.02it/s] Loading 0: 98%|█████████▊| 499/507 [00:31<00:00, 31.86it/s] Loading 0: 99%|█████████▉| 503/507 [00:31<00:00, 32.19it/s]
Job chaiml-ezstorytellingsft-5389-v1-mkmlizer completed after 187.1s with status: succeeded
Stopping job with name chaiml-ezstorytellingsft-5389-v1-mkmlizer
Pipeline stage MKMLizer completed in 187.84s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-ezstorytellingsft-5389-v1
Waiting for inference service chaiml-ezstorytellingsft-5389-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
Inference service chaiml-ezstorytellingsft-5389-v1 ready after 210.71897554397583s
Pipeline stage MKMLDeployer completed in 211.26s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.7298879623413086s
Received healthy response to inference request in 2.702707052230835s
Received healthy response to inference request in 2.7681374549865723s
Received healthy response to inference request in 1.634829044342041s
Received healthy response to inference request in 1.313239336013794s
5 requests
0 failed requests
5th percentile: 1.3775572776794434
10th percentile: 1.4418752193450928
20th percentile: 1.5705111026763916
30th percentile: 1.8484046459197998
40th percentile: 2.2755558490753174
50th percentile: 2.702707052230835
60th percentile: 2.7135794162750244
70th percentile: 2.724451780319214
80th percentile: 2.7375378608703613
90th percentile: 2.752837657928467
95th percentile: 2.7604875564575195
99th percentile: 2.766607475280762
mean time: 2.22976016998291
Pipeline stage StressChecker completed in 12.49s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%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
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 6.30s
run pipeline stage %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
Running pipeline stage TriggerMKMLProfilingPipeline
Connection pool is full, discarding connection: %s. Connection pool size: %s
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 3.74s
Shutdown handler de-registered
chaiml-ezstorytellingsft_5389_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 3155.57s
Shutdown handler de-registered
chaiml-ezstorytellingsft_5389_v1 status is now inactive due to auto deactivation removed underperforming models