developer_uid: cloudyu
submission_id: cloudyu-nemo-dpo-v16_v1
model_name: cloudyu-nemo-dpo-v16_v1
model_group: cloudyu/Nemo-DPO-V16
status: inactive
timestamp: 2024-12-06T02:54:12+00:00
num_battles: 7502
num_wins: 3897
celo_rating: 1281.17
family_friendly_score: 0.5534
family_friendly_standard_error: 0.007030625007778469
submission_type: basic
model_repo: cloudyu/Nemo-DPO-V16
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6182701709664126, 'latency_mean': 1.6173573780059813, 'latency_p50': 1.6149617433547974, 'latency_p90': 1.7906014680862428}, {'batch_size': 3, 'throughput': 1.130647532098456, 'latency_mean': 2.6419427335262298, 'latency_p50': 2.652755856513977, 'latency_p90': 2.8950092315673825}, {'batch_size': 5, 'throughput': 1.3730358184513753, 'latency_mean': 3.6277972733974457, 'latency_p50': 3.6113513708114624, 'latency_p90': 4.053374481201172}, {'batch_size': 6, 'throughput': 1.4392385564747863, 'latency_mean': 4.141717412471771, 'latency_p50': 4.181608080863953, 'latency_p90': 4.571910500526428}, {'batch_size': 8, 'throughput': 1.5079415853187281, 'latency_mean': 5.273830488920212, 'latency_p50': 5.18919575214386, 'latency_p90': 6.079446697235108}, {'batch_size': 10, 'throughput': 1.5460387227058474, 'latency_mean': 6.425879902839661, 'latency_p50': 6.429694890975952, 'latency_p90': 7.276312041282654}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: cloudyu-nemo-dpo-v16_v1
is_internal_developer: False
language_model: cloudyu/Nemo-DPO-V16
model_size: 13B
ranking_group: single
throughput_3p7s: 1.39
us_pacific_date: 2024-12-05
win_ratio: 0.5194614769394829
generation_params: {'temperature': 1.25, 'top_p': 0.99, 'min_p': 0.01, '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}
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 cloudyu-nemo-dpo-v16-v1-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v16-v1-mkmlizer to finish
cloudyu-nemo-dpo-v16-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v16-v1-mkmlizer: ║ _____ __ __ ║
cloudyu-nemo-dpo-v16-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cloudyu-nemo-dpo-v16-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cloudyu-nemo-dpo-v16-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cloudyu-nemo-dpo-v16-v1-mkmlizer: ║ /___/ ║
cloudyu-nemo-dpo-v16-v1-mkmlizer: ║ ║
cloudyu-nemo-dpo-v16-v1-mkmlizer: ║ Version: 0.11.12 ║
cloudyu-nemo-dpo-v16-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cloudyu-nemo-dpo-v16-v1-mkmlizer: ║ https://mk1.ai ║
cloudyu-nemo-dpo-v16-v1-mkmlizer: ║ ║
cloudyu-nemo-dpo-v16-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cloudyu-nemo-dpo-v16-v1-mkmlizer: ║ belonging to: ║
cloudyu-nemo-dpo-v16-v1-mkmlizer: ║ ║
cloudyu-nemo-dpo-v16-v1-mkmlizer: ║ Chai Research Corp. ║
cloudyu-nemo-dpo-v16-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cloudyu-nemo-dpo-v16-v1-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
cloudyu-nemo-dpo-v16-v1-mkmlizer: ║ ║
cloudyu-nemo-dpo-v16-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-nemo-dpo-v16-v1-mkmlizer: Downloaded to shared memory in 49.599s
cloudyu-nemo-dpo-v16-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmporujwh98, device:0
cloudyu-nemo-dpo-v16-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-nemo-dpo-v16-v1-mkmlizer: quantized model in 37.608s
cloudyu-nemo-dpo-v16-v1-mkmlizer: Processed model cloudyu/Nemo-DPO-V16 in 87.207s
cloudyu-nemo-dpo-v16-v1-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-nemo-dpo-v16-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v16-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v16-v1
cloudyu-nemo-dpo-v16-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v16-v1/config.json
cloudyu-nemo-dpo-v16-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v16-v1/special_tokens_map.json
cloudyu-nemo-dpo-v16-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v16-v1/tokenizer_config.json
cloudyu-nemo-dpo-v16-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v16-v1/tokenizer.json
cloudyu-nemo-dpo-v16-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-nemo-dpo-v16-v1/flywheel_model.0.safetensors
cloudyu-nemo-dpo-v16-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:14, 24.20it/s] Loading 0: 3%|▎ | 12/363 [00:00<00:08, 39.39it/s] Loading 0: 5%|▍ | 17/363 [00:00<00:09, 38.26it/s] Loading 0: 6%|▌ | 22/363 [00:00<00:09, 37.42it/s] Loading 0: 7%|▋ | 26/363 [00:00<00:09, 36.91it/s] Loading 0: 8%|▊ | 30/363 [00:00<00:08, 37.40it/s] Loading 0: 9%|▉ | 34/363 [00:00<00:09, 35.67it/s] Loading 0: 11%|█ | 39/363 [00:01<00:08, 37.74it/s] Loading 0: 12%|█▏ | 43/363 [00:01<00:08, 36.59it/s] Loading 0: 13%|█▎ | 48/363 [00:01<00:08, 39.03it/s] Loading 0: 14%|█▍ | 52/363 [00:01<00:08, 35.01it/s] Loading 0: 16%|█▌ | 57/363 [00:01<00:07, 38.66it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:11, 25.87it/s] Loading 0: 18%|█▊ | 65/363 [00:01<00:11, 25.78it/s] Loading 0: 20%|█▉ | 71/363 [00:02<00:09, 31.82it/s] Loading 0: 21%|██ | 75/363 [00:02<00:08, 32.03it/s] Loading 0: 22%|██▏ | 80/363 [00:02<00:07, 35.70it/s] Loading 0: 23%|██▎ | 84/363 [00:02<00:08, 34.56it/s] Loading 0: 25%|██▍ | 89/363 [00:02<00:07, 37.54it/s] Loading 0: 26%|██▌ | 93/363 [00:02<00:07, 35.82it/s] Loading 0: 27%|██▋ | 98/363 [00:02<00:06, 38.11it/s] Loading 0: 28%|██▊ | 102/363 [00:02<00:07, 36.93it/s] Loading 0: 30%|██▉ | 108/363 [00:03<00:06, 42.45it/s] Loading 0: 31%|███ | 113/363 [00:03<00:06, 37.69it/s] Loading 0: 33%|███▎ | 118/363 [00:03<00:06, 38.80it/s] Loading 0: 35%|███▍ | 126/363 [00:03<00:04, 47.72it/s] Loading 0: 36%|███▋ | 132/363 [00:03<00:04, 46.49it/s] Loading 0: 38%|███▊ | 137/363 [00:03<00:05, 44.90it/s] Loading 0: 39%|███▉ | 142/363 [00:03<00:06, 34.12it/s] Loading 0: 40%|████ | 146/363 [00:04<00:06, 34.74it/s] Loading 0: 41%|████▏ | 150/363 [00:04<00:06, 34.41it/s] Loading 0: 43%|████▎ | 157/363 [00:04<00:04, 41.61it/s] Loading 0: 45%|████▍ | 163/363 [00:04<00:04, 42.07it/s] Loading 0: 46%|████▋ | 168/363 [00:04<00:04, 42.71it/s] Loading 0: 48%|████▊ | 175/363 [00:04<00:03, 47.86it/s] Loading 0: 50%|████▉ | 181/363 [00:04<00:04, 44.59it/s] Loading 0: 51%|█████ | 186/363 [00:04<00:04, 41.19it/s] Loading 0: 53%|█████▎ | 192/363 [00:05<00:03, 44.93it/s] Loading 0: 54%|█████▍ | 197/363 [00:05<00:03, 43.26it/s] Loading 0: 56%|█████▌ | 202/363 [00:05<00:03, 42.02it/s] Loading 0: 57%|█████▋ | 207/363 [00:05<00:03, 43.78it/s] Loading 0: 58%|█████▊ | 212/363 [00:05<00:03, 38.02it/s] Loading 0: 60%|██████ | 218/363 [00:05<00:03, 43.13it/s] Loading 0: 61%|██████▏ | 223/363 [00:05<00:04, 33.04it/s] Loading 0: 63%|██████▎ | 227/363 [00:06<00:04, 31.87it/s] Loading 0: 64%|██████▎ | 231/363 [00:06<00:04, 28.64it/s] Loading 0: 65%|██████▌ | 237/363 [00:06<00:03, 34.11it/s] Loading 0: 66%|██████▋ | 241/363 [00:06<00:03, 33.86it/s] Loading 0: 68%|██████▊ | 246/363 [00:06<00:03, 37.51it/s] Loading 0: 69%|██████▉ | 251/363 [00:06<00:02, 38.25it/s] Loading 0: 71%|███████ | 256/363 [00:06<00:02, 37.56it/s] Loading 0: 72%|███████▏ | 260/363 [00:06<00:02, 36.81it/s] Loading 0: 73%|███████▎ | 264/363 [00:07<00:02, 37.24it/s] Loading 0: 74%|███████▍ | 268/363 [00:07<00:02, 35.72it/s] Loading 0: 75%|███████▌ | 273/363 [00:07<00:02, 37.67it/s] Loading 0: 76%|███████▋ | 277/363 [00:07<00:02, 36.01it/s] Loading 0: 78%|███████▊ | 282/363 [00:07<00:02, 38.59it/s] Loading 0: 79%|███████▉ | 286/363 [00:07<00:02, 36.67it/s] Loading 0: 80%|████████ | 291/363 [00:07<00:01, 38.65it/s] Loading 0: 81%|████████▏ | 295/363 [00:07<00:01, 36.46it/s] Loading 0: 82%|████████▏ | 299/363 [00:08<00:01, 35.86it/s] Loading 0: 84%|████████▎ | 304/363 [00:14<00:28, 2.10it/s] Loading 0: 85%|████████▍ | 307/363 [00:15<00:21, 2.63it/s] Loading 0: 86%|████████▌ | 312/363 [00:15<00:13, 3.88it/s] Loading 0: 88%|████████▊ | 320/363 [00:15<00:06, 6.66it/s] Loading 0: 90%|████████▉ | 325/363 [00:15<00:04, 8.82it/s] Loading 0: 91%|█████████ | 330/363 [00:15<00:03, 10.76it/s] Loading 0: 92%|█████████▏| 335/363 [00:15<00:02, 13.91it/s] Loading 0: 94%|█████████▎| 340/363 [00:15<00:01, 16.86it/s] Loading 0: 95%|█████████▌| 346/363 [00:15<00:00, 21.69it/s] Loading 0: 97%|█████████▋| 351/363 [00:16<00:00, 25.18it/s] Loading 0: 98%|█████████▊| 356/363 [00:16<00:00, 29.15it/s] Loading 0: 99%|█████████▉| 361/363 [00:16<00:00, 32.92it/s]
Job cloudyu-nemo-dpo-v16-v1-mkmlizer completed after 117.15s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v16-v1-mkmlizer
Pipeline stage MKMLizer completed in 119.55s
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-nemo-dpo-v16-v1
Waiting for inference service cloudyu-nemo-dpo-v16-v1 to be ready
Inference service cloudyu-nemo-dpo-v16-v1 ready after 190.53497219085693s
Pipeline stage MKMLDeployer completed in 192.89s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1337389945983887s
Received healthy response to inference request in 2.257830858230591s
Received healthy response to inference request in 1.9188528060913086s
Received healthy response to inference request in 2.164015293121338s
Received healthy response to inference request in 2.1306374073028564s
5 requests
0 failed requests
5th percentile: 1.9612097263336181
10th percentile: 2.0035666465759276
20th percentile: 2.0882804870605467
30th percentile: 2.131257724761963
40th percentile: 2.132498359680176
50th percentile: 2.1337389945983887
60th percentile: 2.145849514007568
70th percentile: 2.157960033416748
80th percentile: 2.1827784061431883
90th percentile: 2.2203046321868896
95th percentile: 2.2390677452087404
99th percentile: 2.2540782356262206
mean time: 2.1210150718688965
Pipeline stage StressChecker completed in 12.04s
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 2.12s
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
cloudyu-nemo-dpo-v16_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
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 2499.29s
Shutdown handler de-registered
cloudyu-nemo-dpo-v16_v1 status is now inactive due to auto deactivation removed underperforming models