submission_id: cloudyu-chaiml-nemo-dpo-v7_v3
developer_uid: cloudyu
best_of: 8
celo_rating: 1265.44
display_name: cloudyu-chaiml-nemo-dpo-v7_v5
family_friendly_score: 0.5509999999999999
family_friendly_standard_error: 0.007034187941759872
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': 1.0, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
gpu_counts: {'NVIDIA RTX A5000': 1}
is_internal_developer: False
language_model: cloudyu/ChaiML-Nemo-DPO-V7
latencies: [{'batch_size': 1, 'throughput': 0.6239155042821484, 'latency_mean': 1.602720522880554, 'latency_p50': 1.6088128089904785, 'latency_p90': 1.7692702770233153}, {'batch_size': 3, 'throughput': 1.141686469809735, 'latency_mean': 2.622961745262146, 'latency_p50': 2.636076331138611, 'latency_p90': 2.8233505487442017}, {'batch_size': 5, 'throughput': 1.3984066987427821, 'latency_mean': 3.5575602996349334, 'latency_p50': 3.558700203895569, 'latency_p90': 3.9843263149261476}, {'batch_size': 6, 'throughput': 1.4656487021694518, 'latency_mean': 4.072129106521606, 'latency_p50': 4.055487275123596, 'latency_p90': 4.537995529174805}, {'batch_size': 8, 'throughput': 1.5378216635201964, 'latency_mean': 5.167537167072296, 'latency_p50': 5.220924139022827, 'latency_p90': 5.8235663890838625}, {'batch_size': 10, 'throughput': 1.5826668236565407, 'latency_mean': 6.278056719303131, 'latency_p50': 6.289407968521118, 'latency_p90': 7.110556960105896}]
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: cloudyu/ChaiML-Nemo-DPO-
model_name: cloudyu-chaiml-nemo-dpo-v7_v5
model_num_parameters: 12772070400.0
model_repo: cloudyu/ChaiML-Nemo-DPO-V7
model_size: 13B
num_battles: 34294
num_wins: 17356
ranking_group: single
status: inactive
submission_type: basic
throughput_3p7s: 1.43
timestamp: 2024-11-24T16:29:56+00:00
us_pacific_date: 2024-11-24
win_ratio: 0.5060943605295387
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 cloudyu-chaiml-nemo-dpo-v7-v3-mkmlizer
Waiting for job on cloudyu-chaiml-nemo-dpo-v7-v3-mkmlizer to finish
cloudyu-chaiml-nemo-dpo-v7-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-chaiml-nemo-dpo-v7-v3-mkmlizer: ║ _____ __ __ ║
cloudyu-chaiml-nemo-dpo-v7-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cloudyu-chaiml-nemo-dpo-v7-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cloudyu-chaiml-nemo-dpo-v7-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cloudyu-chaiml-nemo-dpo-v7-v3-mkmlizer: ║ /___/ ║
cloudyu-chaiml-nemo-dpo-v7-v3-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v7-v3-mkmlizer: ║ Version: 0.11.12 ║
cloudyu-chaiml-nemo-dpo-v7-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cloudyu-chaiml-nemo-dpo-v7-v3-mkmlizer: ║ https://mk1.ai ║
cloudyu-chaiml-nemo-dpo-v7-v3-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v7-v3-mkmlizer: ║ The license key for the current software has been verified as ║
cloudyu-chaiml-nemo-dpo-v7-v3-mkmlizer: ║ belonging to: ║
cloudyu-chaiml-nemo-dpo-v7-v3-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v7-v3-mkmlizer: ║ Chai Research Corp. ║
cloudyu-chaiml-nemo-dpo-v7-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cloudyu-chaiml-nemo-dpo-v7-v3-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
cloudyu-chaiml-nemo-dpo-v7-v3-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v7-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
cloudyu-chaiml-nemo-dpo-v7-v3-mkmlizer: Downloaded to shared memory in 49.536s
cloudyu-chaiml-nemo-dpo-v7-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpi8zxu33s, device:0
cloudyu-chaiml-nemo-dpo-v7-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-chaiml-nemo-dpo-v7-v3-mkmlizer: quantized model in 35.439s
cloudyu-chaiml-nemo-dpo-v7-v3-mkmlizer: Processed model cloudyu/ChaiML-Nemo-DPO-V7 in 84.975s
cloudyu-chaiml-nemo-dpo-v7-v3-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-chaiml-nemo-dpo-v7-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-chaiml-nemo-dpo-v7-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v7-v3
cloudyu-chaiml-nemo-dpo-v7-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v7-v3/special_tokens_map.json
cloudyu-chaiml-nemo-dpo-v7-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v7-v3/config.json
cloudyu-chaiml-nemo-dpo-v7-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v7-v3/tokenizer_config.json
cloudyu-chaiml-nemo-dpo-v7-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v7-v3/tokenizer.json
cloudyu-chaiml-nemo-dpo-v7-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v7-v3/flywheel_model.0.safetensors
cloudyu-chaiml-nemo-dpo-v7-v3-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:12, 28.37it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:07, 49.79it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:07, 46.34it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:07, 44.31it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 50.84it/s] Loading 0: 10%|█ | 37/363 [00:00<00:06, 46.90it/s] Loading 0: 12%|█▏ | 42/363 [00:00<00:07, 45.48it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:06, 50.84it/s] Loading 0: 15%|█▌ | 55/363 [00:01<00:06, 46.45it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:08, 34.43it/s] Loading 0: 18%|█▊ | 65/363 [00:01<00:08, 33.61it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:07, 40.16it/s] Loading 0: 21%|██▏ | 78/363 [00:01<00:07, 39.95it/s] Loading 0: 23%|██▎ | 83/363 [00:01<00:07, 39.60it/s] Loading 0: 25%|██▍ | 90/363 [00:02<00:06, 44.98it/s] Loading 0: 26%|██▋ | 96/363 [00:02<00:06, 43.77it/s] Loading 0: 28%|██▊ | 101/363 [00:02<00:06, 43.23it/s] Loading 0: 30%|██▉ | 108/363 [00:02<00:05, 49.56it/s] Loading 0: 31%|███▏ | 114/363 [00:02<00:05, 44.83it/s] Loading 0: 33%|███▎ | 119/363 [00:02<00:05, 42.71it/s] Loading 0: 35%|███▍ | 126/363 [00:02<00:04, 48.02it/s] Loading 0: 36%|███▋ | 132/363 [00:03<00:04, 46.60it/s] Loading 0: 38%|███▊ | 137/363 [00:03<00:04, 46.13it/s] Loading 0: 39%|███▉ | 142/363 [00:03<00:06, 35.66it/s] Loading 0: 40%|████ | 146/363 [00:03<00:05, 36.45it/s] Loading 0: 41%|████▏ | 150/363 [00:03<00:06, 35.41it/s] Loading 0: 43%|████▎ | 157/363 [00:03<00:04, 42.81it/s] Loading 0: 45%|████▍ | 163/363 [00:03<00:04, 42.80it/s] Loading 0: 46%|████▋ | 168/363 [00:03<00:04, 43.10it/s] Loading 0: 48%|████▊ | 175/363 [00:04<00:03, 48.79it/s] Loading 0: 50%|████▉ | 181/363 [00:04<00:03, 46.93it/s] Loading 0: 51%|█████ | 186/363 [00:04<00:03, 44.99it/s] Loading 0: 53%|█████▎ | 193/363 [00:04<00:03, 50.19it/s] Loading 0: 55%|█████▍ | 199/363 [00:04<00:03, 47.54it/s] Loading 0: 56%|█████▌ | 204/363 [00:04<00:03, 44.71it/s] Loading 0: 58%|█████▊ | 211/363 [00:04<00:03, 49.42it/s] Loading 0: 60%|█████▉ | 217/363 [00:04<00:03, 46.98it/s] Loading 0: 61%|██████▏ | 223/363 [00:05<00:03, 36.62it/s] Loading 0: 63%|██████▎ | 228/363 [00:05<00:03, 36.68it/s] Loading 0: 64%|██████▍ | 232/363 [00:05<00:03, 37.32it/s] Loading 0: 66%|██████▌ | 238/363 [00:05<00:02, 41.82it/s] Loading 0: 67%|██████▋ | 244/363 [00:05<00:02, 40.91it/s] Loading 0: 69%|██████▊ | 249/363 [00:05<00:02, 41.23it/s] Loading 0: 71%|███████ | 256/363 [00:05<00:02, 46.70it/s] Loading 0: 72%|███████▏ | 262/363 [00:06<00:02, 45.33it/s] Loading 0: 74%|███████▎ | 267/363 [00:06<00:02, 45.13it/s] Loading 0: 75%|███████▌ | 274/363 [00:06<00:01, 49.51it/s] Loading 0: 77%|███████▋ | 280/363 [00:06<00:01, 45.58it/s] Loading 0: 79%|███████▊ | 285/363 [00:06<00:01, 44.49it/s] Loading 0: 80%|████████ | 292/363 [00:06<00:01, 48.53it/s] Loading 0: 82%|████████▏ | 298/363 [00:06<00:01, 45.71it/s] Loading 0: 84%|████████▎ | 304/363 [00:13<00:20, 2.85it/s] Loading 0: 85%|████████▍ | 308/363 [00:13<00:15, 3.56it/s] Loading 0: 86%|████████▌ | 312/363 [00:13<00:11, 4.54it/s] Loading 0: 88%|████████▊ | 321/363 [00:14<00:05, 7.54it/s] Loading 0: 91%|█████████ | 329/363 [00:14<00:03, 11.11it/s] Loading 0: 92%|█████████▏| 335/363 [00:14<00:01, 14.05it/s] Loading 0: 94%|█████████▎| 340/363 [00:14<00:01, 16.90it/s] Loading 0: 96%|█████████▌| 347/363 [00:14<00:00, 22.34it/s] Loading 0: 97%|█████████▋| 353/363 [00:14<00:00, 25.96it/s] Loading 0: 99%|█████████▊| 358/363 [00:14<00:00, 28.95it/s]
Job cloudyu-chaiml-nemo-dpo-v7-v3-mkmlizer completed after 114.29s with status: succeeded
Stopping job with name cloudyu-chaiml-nemo-dpo-v7-v3-mkmlizer
Pipeline stage MKMLizer completed in 114.78s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cloudyu-chaiml-nemo-dpo-v7-v3
Waiting for inference service cloudyu-chaiml-nemo-dpo-v7-v3 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 cloudyu-chaiml-nemo-dpo-v7-v3 ready after 110.92650318145752s
Pipeline stage MKMLDeployer completed in 111.43s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2222487926483154s
Received healthy response to inference request in 1.826432704925537s
Received healthy response to inference request in 2.1103289127349854s
Received healthy response to inference request in 1.786712408065796s
Received healthy response to inference request in 1.830392599105835s
5 requests
0 failed requests
5th percentile: 1.794656467437744
10th percentile: 1.8026005268096923
20th percentile: 1.818488645553589
30th percentile: 1.8272246837615966
40th percentile: 1.828808641433716
50th percentile: 1.830392599105835
60th percentile: 1.9423671245574952
70th percentile: 2.0543416500091554
80th percentile: 2.132712888717651
90th percentile: 2.1774808406829833
95th percentile: 2.1998648166656496
99th percentile: 2.2177719974517824
mean time: 1.9552230834960938
Pipeline stage StressChecker completed in 11.09s
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 2.17s
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 2.17s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v7_v3 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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service cloudyu-chaiml-nemo-dpo-v7-v3-profiler
Waiting for inference service cloudyu-chaiml-nemo-dpo-v7-v3-profiler to be ready
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 3181.24s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v7_v3 status is now inactive due to auto deactivation removed underperforming models