submission_id: cloudyu-chaiml-nemo-dpo-v5_v2
developer_uid: cloudyu
best_of: 8
celo_rating: 1261.04
display_name: cloudyu-chaiml-nemo-dpo-v5_v2
family_friendly_score: 0.5676
family_friendly_standard_error: 0.007006143589736082
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': 0.95, '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-V5
latencies: [{'batch_size': 1, 'throughput': 0.6169355011331533, 'latency_mean': 1.6208428716659546, 'latency_p50': 1.6283776760101318, 'latency_p90': 1.7827612161636353}, {'batch_size': 3, 'throughput': 1.1430207108993677, 'latency_mean': 2.6137473678588865, 'latency_p50': 2.617748737335205, 'latency_p90': 2.8827285051345823}, {'batch_size': 5, 'throughput': 1.3872894789065802, 'latency_mean': 3.5900985026359558, 'latency_p50': 3.5866583585739136, 'latency_p90': 4.010787582397461}, {'batch_size': 6, 'throughput': 1.451658103343924, 'latency_mean': 4.1141073036193845, 'latency_p50': 4.121076941490173, 'latency_p90': 4.628178024291992}, {'batch_size': 8, 'throughput': 1.5206356492408857, 'latency_mean': 5.231495833396911, 'latency_p50': 5.203487157821655, 'latency_p90': 5.868678164482117}, {'batch_size': 10, 'throughput': 1.5710136257856266, 'latency_mean': 6.3148924303054805, 'latency_p50': 6.327920436859131, 'latency_p90': 7.183208727836609}]
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: cloudyu/ChaiML-Nemo-DPO-
model_name: cloudyu-chaiml-nemo-dpo-v5_v2
model_num_parameters: 12772070400.0
model_repo: cloudyu/ChaiML-Nemo-DPO-V5
model_size: 13B
num_battles: 23778
num_wins: 11941
ranking_group: single
status: inactive
submission_type: basic
throughput_3p7s: 1.41
timestamp: 2024-11-24T10:02:08+00:00
us_pacific_date: 2024-11-24
win_ratio: 0.5021868954495753
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-v5-v2-mkmlizer
Waiting for job on cloudyu-chaiml-nemo-dpo-v5-v2-mkmlizer to finish
cloudyu-chaiml-nemo-dpo-v5-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-chaiml-nemo-dpo-v5-v2-mkmlizer: ║ _____ __ __ ║
cloudyu-chaiml-nemo-dpo-v5-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cloudyu-chaiml-nemo-dpo-v5-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cloudyu-chaiml-nemo-dpo-v5-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cloudyu-chaiml-nemo-dpo-v5-v2-mkmlizer: ║ /___/ ║
cloudyu-chaiml-nemo-dpo-v5-v2-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v5-v2-mkmlizer: ║ Version: 0.11.12 ║
cloudyu-chaiml-nemo-dpo-v5-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cloudyu-chaiml-nemo-dpo-v5-v2-mkmlizer: ║ https://mk1.ai ║
cloudyu-chaiml-nemo-dpo-v5-v2-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v5-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cloudyu-chaiml-nemo-dpo-v5-v2-mkmlizer: ║ belonging to: ║
cloudyu-chaiml-nemo-dpo-v5-v2-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v5-v2-mkmlizer: ║ Chai Research Corp. ║
cloudyu-chaiml-nemo-dpo-v5-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cloudyu-chaiml-nemo-dpo-v5-v2-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
cloudyu-chaiml-nemo-dpo-v5-v2-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v5-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-chaiml-nemo-dpo-v5-v2-mkmlizer: Downloaded to shared memory in 33.657s
cloudyu-chaiml-nemo-dpo-v5-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_zn57czx, device:0
cloudyu-chaiml-nemo-dpo-v5-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
cloudyu-chaiml-nemo-dpo-v5-v2-mkmlizer: quantized model in 35.888s
cloudyu-chaiml-nemo-dpo-v5-v2-mkmlizer: Processed model cloudyu/ChaiML-Nemo-DPO-V5 in 69.546s
cloudyu-chaiml-nemo-dpo-v5-v2-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-chaiml-nemo-dpo-v5-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-chaiml-nemo-dpo-v5-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v5-v2
cloudyu-chaiml-nemo-dpo-v5-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v5-v2/config.json
cloudyu-chaiml-nemo-dpo-v5-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v5-v2/special_tokens_map.json
cloudyu-chaiml-nemo-dpo-v5-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v5-v2/tokenizer_config.json
cloudyu-chaiml-nemo-dpo-v5-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v5-v2/tokenizer.json
cloudyu-chaiml-nemo-dpo-v5-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v5-v2/flywheel_model.0.safetensors
cloudyu-chaiml-nemo-dpo-v5-v2-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:12, 27.80it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:07, 49.01it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:07, 46.60it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:07, 45.17it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 51.54it/s] Loading 0: 10%|█ | 37/363 [00:00<00:06, 48.43it/s] Loading 0: 12%|█▏ | 42/363 [00:00<00:07, 45.77it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:06, 50.80it/s] Loading 0: 15%|█▌ | 55/363 [00:01<00:06, 46.53it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:08, 34.06it/s] Loading 0: 18%|█▊ | 65/363 [00:01<00:09, 32.29it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:07, 38.18it/s] Loading 0: 21%|██▏ | 78/363 [00:01<00:07, 39.33it/s] Loading 0: 23%|██▎ | 83/363 [00:02<00:07, 39.21it/s] Loading 0: 25%|██▍ | 90/363 [00:02<00:06, 44.72it/s] Loading 0: 26%|██▋ | 96/363 [00:02<00:06, 43.43it/s] Loading 0: 28%|██▊ | 101/363 [00:02<00:06, 40.83it/s] Loading 0: 29%|██▉ | 106/363 [00:02<00:06, 42.59it/s] Loading 0: 31%|███ | 112/363 [00:02<00:05, 45.64it/s] Loading 0: 32%|███▏ | 117/363 [00:02<00:05, 43.14it/s] Loading 0: 34%|███▍ | 123/363 [00:02<00:05, 42.39it/s] Loading 0: 35%|███▌ | 128/363 [00:03<00:05, 42.67it/s] Loading 0: 37%|███▋ | 135/363 [00:03<00:04, 48.22it/s] Loading 0: 39%|███▉ | 141/363 [00:03<00:04, 46.77it/s] Loading 0: 40%|████ | 146/363 [00:03<00:06, 32.17it/s] Loading 0: 41%|████▏ | 150/363 [00:03<00:06, 31.67it/s] Loading 0: 43%|████▎ | 157/363 [00:03<00:05, 38.48it/s] Loading 0: 45%|████▍ | 163/363 [00:03<00:05, 39.86it/s] Loading 0: 46%|████▋ | 168/363 [00:04<00:04, 41.24it/s] Loading 0: 48%|████▊ | 175/363 [00:04<00:04, 46.89it/s] Loading 0: 50%|████▉ | 181/363 [00:04<00:03, 46.26it/s] Loading 0: 51%|█████ | 186/363 [00:04<00:03, 45.72it/s] Loading 0: 53%|█████▎ | 193/363 [00:04<00:03, 51.06it/s] Loading 0: 55%|█████▍ | 199/363 [00:04<00:03, 45.22it/s] Loading 0: 56%|█████▌ | 204/363 [00:04<00:03, 43.98it/s] Loading 0: 58%|█████▊ | 211/363 [00:04<00:03, 49.63it/s] Loading 0: 60%|█████▉ | 217/363 [00:05<00:03, 48.05it/s] Loading 0: 61%|██████▏ | 223/363 [00:05<00:03, 37.00it/s] Loading 0: 63%|██████▎ | 228/363 [00:05<00:03, 35.99it/s] Loading 0: 64%|██████▍ | 232/363 [00:05<00:03, 36.35it/s] Loading 0: 66%|██████▌ | 238/363 [00:05<00:03, 41.19it/s] Loading 0: 67%|██████▋ | 244/363 [00:05<00:02, 41.69it/s] Loading 0: 69%|██████▊ | 249/363 [00:05<00:02, 41.54it/s] Loading 0: 71%|███████ | 256/363 [00:06<00:02, 46.91it/s] Loading 0: 72%|███████▏ | 262/363 [00:06<00:02, 44.88it/s] Loading 0: 74%|███████▎ | 267/363 [00:06<00:02, 40.63it/s] Loading 0: 75%|███████▍ | 272/363 [00:06<00:02, 41.10it/s] Loading 0: 76%|███████▋ | 277/363 [00:06<00:02, 35.67it/s] Loading 0: 77%|███████▋ | 281/363 [00:06<00:02, 35.53it/s] Loading 0: 79%|███████▊ | 285/363 [00:06<00:02, 30.97it/s] Loading 0: 80%|███████▉ | 289/363 [00:07<00:02, 31.57it/s] Loading 0: 81%|████████ | 293/363 [00:07<00:02, 30.82it/s] Loading 0: 83%|████████▎ | 302/363 [00:07<00:01, 44.15it/s] Loading 0: 85%|████████▍ | 307/363 [00:14<00:21, 2.55it/s] Loading 0: 86%|████████▌ | 312/363 [00:14<00:14, 3.47it/s] Loading 0: 88%|████████▊ | 320/363 [00:14<00:07, 5.53it/s] Loading 0: 90%|████████▉ | 326/363 [00:14<00:04, 7.47it/s] Loading 0: 91%|█████████ | 331/363 [00:14<00:03, 9.55it/s] Loading 0: 93%|█████████▎| 338/363 [00:14<00:01, 13.50it/s] Loading 0: 95%|█████████▍| 344/363 [00:14<00:01, 16.94it/s] Loading 0: 96%|█████████▋| 350/363 [00:15<00:00, 21.06it/s] Loading 0: 98%|█████████▊| 356/363 [00:15<00:00, 25.91it/s] Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 29.34it/s]
Job cloudyu-chaiml-nemo-dpo-v5-v2-mkmlizer completed after 94.12s with status: succeeded
Stopping job with name cloudyu-chaiml-nemo-dpo-v5-v2-mkmlizer
Pipeline stage MKMLizer completed in 94.64s
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 cloudyu-chaiml-nemo-dpo-v5-v2
Waiting for inference service cloudyu-chaiml-nemo-dpo-v5-v2 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service cloudyu-chaiml-nemo-dpo-v5-v2 ready after 120.45659255981445s
Pipeline stage MKMLDeployer completed in 121.00s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6113393306732178s
Received healthy response to inference request in 1.6741750240325928s
Received healthy response to inference request in 1.6909773349761963s
Received healthy response to inference request in 1.9875006675720215s
Received healthy response to inference request in 1.9079210758209229s
5 requests
0 failed requests
5th percentile: 1.6775354862213134
10th percentile: 1.680895948410034
20th percentile: 1.6876168727874756
30th percentile: 1.7343660831451415
40th percentile: 1.8211435794830322
50th percentile: 1.9079210758209229
60th percentile: 1.9397529125213624
70th percentile: 1.9715847492218017
80th percentile: 2.112268400192261
90th percentile: 2.3618038654327393
95th percentile: 2.4865715980529783
99th percentile: 2.58638578414917
mean time: 1.9743826866149903
Pipeline stage StressChecker completed in 11.17s
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 2.14s
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 2.05s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v5_v2 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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service cloudyu-chaiml-nemo-dpo-v5-v2-profiler
Waiting for inference service cloudyu-chaiml-nemo-dpo-v5-v2-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 2934.81s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v5_v2 status is now inactive due to auto deactivation removed underperforming models