developer_uid: rirv938
submission_id: chaiml-0sw-95p-5ff-rine_63828_v4
model_name: chaiml-0sw-95p-5ff-rine_63828_v4
model_group: ChaiML/0sw_95p_5ff_rinen
status: torndown
timestamp: 2025-05-15T15:54:47+00:00
num_battles: 8158
num_wins: 4360
celo_rating: 1312.14
family_friendly_score: 0.5506
family_friendly_standard_error: 0.007034765667739047
submission_type: basic
model_repo: ChaiML/0sw_95p_5ff_rinen0721_dpo_0130_cp3000_v8_merged
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.6002566058406885, 'latency_mean': 1.6658819544315338, 'latency_p50': 1.6791819334030151, 'latency_p90': 1.8231863737106322}, {'batch_size': 3, 'throughput': 1.1087412991577805, 'latency_mean': 2.699716856479645, 'latency_p50': 2.691431164741516, 'latency_p90': 2.9783509969711304}, {'batch_size': 5, 'throughput': 1.3464958022705145, 'latency_mean': 3.706268494129181, 'latency_p50': 3.701534628868103, 'latency_p90': 4.126373958587647}, {'batch_size': 6, 'throughput': 1.4229328225566993, 'latency_mean': 4.194993062019348, 'latency_p50': 4.197802782058716, 'latency_p90': 4.725729203224182}, {'batch_size': 8, 'throughput': 1.4928205509774624, 'latency_mean': 5.324260747432708, 'latency_p50': 5.351892709732056, 'latency_p90': 5.986011934280396}, {'batch_size': 10, 'throughput': 1.5214244795478085, 'latency_mean': 6.520083626508713, 'latency_p50': 6.531911015510559, 'latency_p90': 7.3483415126800535}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: chaiml-0sw-95p-5ff-rine_63828_v4
is_internal_developer: True
language_model: ChaiML/0sw_95p_5ff_rinen0721_dpo_0130_cp3000_v8_merged
model_size: 13B
ranking_group: single
throughput_3p7s: 1.35
us_pacific_date: 2025-05-15
win_ratio: 0.5344447168423633
generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['<|im_end|>', '</s>', '\n', '<|eot_id|>', 'You:', 'Bot:', 'User:', '####'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': True}
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-0sw-95p-5ff-rine-63828-v4-mkmlizer
Waiting for job on chaiml-0sw-95p-5ff-rine-63828-v4-mkmlizer to finish
chaiml-0sw-95p-5ff-rine-63828-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-0sw-95p-5ff-rine-63828-v4-mkmlizer: ║ _____ __ __ ║
chaiml-0sw-95p-5ff-rine-63828-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-0sw-95p-5ff-rine-63828-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-0sw-95p-5ff-rine-63828-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-0sw-95p-5ff-rine-63828-v4-mkmlizer: ║ /___/ ║
chaiml-0sw-95p-5ff-rine-63828-v4-mkmlizer: ║ ║
chaiml-0sw-95p-5ff-rine-63828-v4-mkmlizer: ║ Version: 0.12.8 ║
chaiml-0sw-95p-5ff-rine-63828-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-0sw-95p-5ff-rine-63828-v4-mkmlizer: ║ https://mk1.ai ║
chaiml-0sw-95p-5ff-rine-63828-v4-mkmlizer: ║ ║
chaiml-0sw-95p-5ff-rine-63828-v4-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-0sw-95p-5ff-rine-63828-v4-mkmlizer: ║ belonging to: ║
chaiml-0sw-95p-5ff-rine-63828-v4-mkmlizer: ║ ║
chaiml-0sw-95p-5ff-rine-63828-v4-mkmlizer: ║ Chai Research Corp. ║
chaiml-0sw-95p-5ff-rine-63828-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-0sw-95p-5ff-rine-63828-v4-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-0sw-95p-5ff-rine-63828-v4-mkmlizer: ║ ║
chaiml-0sw-95p-5ff-rine-63828-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-0sw-95p-5ff-rine-63828-v4-mkmlizer: Downloaded to shared memory in 79.677s
chaiml-0sw-95p-5ff-rine-63828-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpe5ssghpj, device:0
chaiml-0sw-95p-5ff-rine-63828-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-0sw-95p-5ff-rine-63828-v4-mkmlizer: quantized model in 42.260s
chaiml-0sw-95p-5ff-rine-63828-v4-mkmlizer: Processed model ChaiML/0sw_95p_5ff_rinen0721_dpo_0130_cp3000_v8_merged in 121.938s
chaiml-0sw-95p-5ff-rine-63828-v4-mkmlizer: creating bucket guanaco-mkml-models
chaiml-0sw-95p-5ff-rine-63828-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-0sw-95p-5ff-rine-63828-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-0sw-95p-5ff-rine-63828-v4
chaiml-0sw-95p-5ff-rine-63828-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-0sw-95p-5ff-rine-63828-v4/special_tokens_map.json
chaiml-0sw-95p-5ff-rine-63828-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-0sw-95p-5ff-rine-63828-v4/config.json
chaiml-0sw-95p-5ff-rine-63828-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-0sw-95p-5ff-rine-63828-v4/tokenizer_config.json
chaiml-0sw-95p-5ff-rine-63828-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-0sw-95p-5ff-rine-63828-v4/tokenizer.json
chaiml-0sw-95p-5ff-rine-63828-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-0sw-95p-5ff-rine-63828-v4/flywheel_model.0.safetensors
chaiml-0sw-95p-5ff-rine-63828-v4-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:16, 21.09it/s] Loading 0: 3%|▎ | 10/363 [00:00<00:13, 26.03it/s] Loading 0: 4%|▍ | 14/363 [00:00<00:14, 23.57it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:11, 29.56it/s] Loading 0: 6%|▋ | 23/363 [00:00<00:15, 21.77it/s] Loading 0: 7%|▋ | 26/363 [00:01<00:17, 19.79it/s] Loading 0: 9%|▉ | 32/363 [00:01<00:14, 22.68it/s] Loading 0: 10%|█ | 37/363 [00:01<00:11, 27.27it/s] Loading 0: 11%|█▏ | 41/363 [00:01<00:13, 24.38it/s] Loading 0: 13%|█▎ | 46/363 [00:01<00:11, 28.68it/s] Loading 0: 14%|█▍ | 50/363 [00:02<00:12, 25.28it/s] Loading 0: 15%|█▌ | 55/363 [00:02<00:10, 29.77it/s] Loading 0: 17%|█▋ | 60/363 [00:02<00:09, 30.88it/s] Loading 0: 18%|█▊ | 64/363 [00:02<00:14, 20.56it/s] Loading 0: 19%|█▉ | 69/363 [00:02<00:11, 25.14it/s] Loading 0: 20%|██ | 73/363 [00:02<00:11, 24.94it/s] Loading 0: 21%|██ | 77/363 [00:03<00:12, 22.84it/s] Loading 0: 23%|██▎ | 82/363 [00:03<00:10, 27.29it/s] Loading 0: 24%|██▎ | 86/363 [00:03<00:11, 24.69it/s] Loading 0: 25%|██▌ | 91/363 [00:03<00:09, 29.18it/s] Loading 0: 26%|██▌ | 95/363 [00:03<00:10, 25.86it/s] Loading 0: 28%|██▊ | 100/363 [00:03<00:08, 30.29it/s] Loading 0: 29%|██▊ | 104/363 [00:04<00:12, 20.09it/s] Loading 0: 30%|███ | 109/363 [00:04<00:10, 24.63it/s] Loading 0: 31%|███ | 113/363 [00:04<00:10, 23.12it/s] Loading 0: 33%|███▎ | 118/363 [00:04<00:08, 27.58it/s] Loading 0: 34%|███▎ | 122/363 [00:04<00:09, 24.53it/s] Loading 0: 35%|███▍ | 127/363 [00:04<00:08, 28.98it/s] Loading 0: 36%|███▌ | 131/363 [00:05<00:09, 25.58it/s] Loading 0: 37%|███▋ | 136/363 [00:05<00:07, 29.95it/s] Loading 0: 39%|███▉ | 141/363 [00:05<00:07, 31.08it/s] Loading 0: 40%|███▉ | 145/363 [00:05<00:10, 21.63it/s] Loading 0: 41%|████ | 149/363 [00:05<00:10, 21.26it/s] Loading 0: 42%|████▏ | 154/363 [00:06<00:08, 25.81it/s] Loading 0: 44%|████▎ | 158/363 [00:06<00:08, 23.70it/s] Loading 0: 45%|████▍ | 163/363 [00:06<00:07, 28.21it/s] Loading 0: 46%|████▌ | 167/363 [00:06<00:07, 24.99it/s] Loading 0: 47%|████▋ | 172/363 [00:06<00:06, 29.60it/s] Loading 0: 48%|████▊ | 176/363 [00:06<00:07, 26.13it/s] Loading 0: 50%|████▉ | 181/363 [00:07<00:05, 30.45it/s] Loading 0: 51%|█████ | 185/363 [00:07<00:08, 20.08it/s] Loading 0: 52%|█████▏ | 190/363 [00:07<00:06, 24.75it/s] Loading 0: 53%|█████▎ | 194/363 [00:07<00:07, 23.24it/s] Loading 0: 55%|█████▍ | 199/363 [00:07<00:05, 27.70it/s] Loading 0: 56%|█████▌ | 203/363 [00:08<00:06, 24.05it/s] Loading 0: 57%|█████▋ | 208/363 [00:08<00:05, 28.56it/s] Loading 0: 58%|█████▊ | 212/363 [00:08<00:05, 25.42it/s] Loading 0: 60%|█████▉ | 217/363 [00:08<00:04, 29.84it/s] Loading 0: 61%|██████ | 222/363 [00:08<00:04, 30.76it/s] Loading 0: 62%|██████▏ | 226/363 [00:08<00:06, 21.33it/s] Loading 0: 63%|██████▎ | 230/363 [00:09<00:06, 20.90it/s] Loading 0: 65%|██████▍ | 235/363 [00:09<00:05, 25.32it/s] Loading 0: 66%|██████▌ | 239/363 [00:09<00:05, 23.19it/s] Loading 0: 67%|██████▋ | 244/363 [00:09<00:04, 27.44it/s] Loading 0: 68%|██████▊ | 248/363 [00:09<00:04, 25.17it/s] Loading 0: 70%|██████▉ | 253/363 [00:09<00:03, 29.97it/s] Loading 0: 71%|███████ | 257/363 [00:10<00:03, 26.54it/s] Loading 0: 72%|███████▏ | 263/363 [00:10<00:03, 25.28it/s] Loading 0: 73%|███████▎ | 266/363 [00:10<00:04, 20.58it/s] Loading 0: 75%|███████▍ | 271/363 [00:10<00:03, 25.50it/s] Loading 0: 76%|███████▌ | 275/363 [00:10<00:03, 24.01it/s] Loading 0: 78%|███████▊ | 282/363 [00:11<00:02, 30.18it/s] Loading 0: 79%|███████▉ | 286/363 [00:11<00:02, 29.11it/s] Loading 0: 80%|████████ | 291/363 [00:11<00:02, 30.89it/s] Loading 0: 81%|████████▏ | 295/363 [00:11<00:02, 29.60it/s] Loading 0: 82%|████████▏ | 299/363 [00:11<00:02, 29.96it/s] Loading 0: 84%|████████▎ | 304/363 [00:11<00:02, 25.77it/s] Loading 0: 85%|████████▍ | 307/363 [00:12<00:02, 24.47it/s] Loading 0: 86%|████████▌ | 311/363 [00:12<00:02, 23.47it/s] Loading 0: 88%|████████▊ | 318/363 [00:12<00:01, 29.91it/s] Loading 0: 89%|████████▊ | 322/363 [00:12<00:01, 29.05it/s] Loading 0: 90%|█████████ | 327/363 [00:12<00:01, 31.21it/s] Loading 0: 91%|█████████ | 331/363 [00:12<00:01, 29.77it/s] Loading 0: 93%|█████████▎| 336/363 [00:12<00:00, 31.93it/s] Loading 0: 94%|█████████▎| 340/363 [00:13<00:00, 30.14it/s] Loading 0: 95%|█████████▍| 344/363 [00:19<00:09, 2.03it/s] Loading 0: 96%|█████████▌| 348/363 [00:20<00:05, 2.73it/s] Loading 0: 97%|█████████▋| 353/363 [00:20<00:02, 3.94it/s] Loading 0: 98%|█████████▊| 357/363 [00:20<00:01, 5.10it/s]
Job chaiml-0sw-95p-5ff-rine-63828-v4-mkmlizer completed after 155.52s with status: succeeded
Stopping job with name chaiml-0sw-95p-5ff-rine-63828-v4-mkmlizer
Pipeline stage MKMLizer completed in 155.97s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.20s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-0sw-95p-5ff-rine-63828-v4
Waiting for inference service chaiml-0sw-95p-5ff-rine-63828-v4 to be ready
Inference service chaiml-0sw-95p-5ff-rine-63828-v4 ready after 140.60537958145142s
Pipeline stage MKMLDeployer completed in 141.10s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4823460578918457s
Received healthy response to inference request in 2.085310697555542s
Received healthy response to inference request in 1.6097548007965088s
Received healthy response to inference request in 1.6900222301483154s
Received healthy response to inference request in 1.7261371612548828s
5 requests
0 failed requests
5th percentile: 1.6258082866668702
10th percentile: 1.6418617725372315
20th percentile: 1.673968744277954
30th percentile: 1.697245216369629
40th percentile: 1.711691188812256
50th percentile: 1.7261371612548828
60th percentile: 1.8698065757751465
70th percentile: 2.0134759902954102
80th percentile: 2.164717769622803
90th percentile: 2.323531913757324
95th percentile: 2.402938985824585
99th percentile: 2.4664646434783934
mean time: 1.9187141895294189
Pipeline stage StressChecker completed in 10.68s
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 0.64s
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 0.67s
Shutdown handler de-registered
chaiml-0sw-95p-5ff-rine_63828_v4 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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5199.35s
Shutdown handler de-registered
chaiml-0sw-95p-5ff-rine_63828_v4 status is now inactive due to auto deactivation removed underperforming models
chaiml-0sw-95p-5ff-rine_63828_v4 status is now torndown due to DeploymentManager action