submission_id: cloudyu-chaiml-nemo-dpo-v1_v2
developer_uid: cloudyu
best_of: 8
celo_rating: 1241.87
display_name: cloudyu-chaiml-nemo-dpo-v1_v2
family_friendly_score: 0.5758
family_friendly_standard_error: 0.006989339882993243
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': 1.0, 'min_p': 0.0, 'top_k': 40, '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-V1
latencies: [{'batch_size': 1, 'throughput': 0.6196802925961399, 'latency_mean': 1.6136688590049744, 'latency_p50': 1.6185362339019775, 'latency_p90': 1.7912901639938354}, {'batch_size': 3, 'throughput': 1.156084557382136, 'latency_mean': 2.5902299320697786, 'latency_p50': 2.595892906188965, 'latency_p90': 2.8685316324234007}, {'batch_size': 5, 'throughput': 1.412152547735335, 'latency_mean': 3.530738208293915, 'latency_p50': 3.5524308681488037, 'latency_p90': 3.941770648956299}, {'batch_size': 6, 'throughput': 1.4732610832521575, 'latency_mean': 4.046972905397415, 'latency_p50': 4.02133321762085, 'latency_p90': 4.628919720649719}, {'batch_size': 8, 'throughput': 1.5307009764954562, 'latency_mean': 5.19165048956871, 'latency_p50': 5.1866607666015625, 'latency_p90': 5.894901967048645}, {'batch_size': 10, 'throughput': 1.5933216323472055, 'latency_mean': 6.223652267456055, 'latency_p50': 6.262577176094055, 'latency_p90': 7.0413020849227905}]
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: cloudyu/ChaiML-Nemo-DPO-
model_name: cloudyu-chaiml-nemo-dpo-v1_v2
model_num_parameters: 12772070400.0
model_repo: cloudyu/ChaiML-Nemo-DPO-V1
model_size: 13B
num_battles: 24494
num_wins: 11549
ranking_group: single
status: inactive
submission_type: basic
throughput_3p7s: 1.44
timestamp: 2024-11-24T03:43:16+00:00
us_pacific_date: 2024-11-23
win_ratio: 0.4715032252796603
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-v1-v2-mkmlizer
Waiting for job on cloudyu-chaiml-nemo-dpo-v1-v2-mkmlizer to finish
cloudyu-chaiml-nemo-dpo-v1-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-chaiml-nemo-dpo-v1-v2-mkmlizer: ║ _____ __ __ ║
cloudyu-chaiml-nemo-dpo-v1-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cloudyu-chaiml-nemo-dpo-v1-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cloudyu-chaiml-nemo-dpo-v1-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cloudyu-chaiml-nemo-dpo-v1-v2-mkmlizer: ║ /___/ ║
cloudyu-chaiml-nemo-dpo-v1-v2-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v1-v2-mkmlizer: ║ Version: 0.11.12 ║
cloudyu-chaiml-nemo-dpo-v1-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cloudyu-chaiml-nemo-dpo-v1-v2-mkmlizer: ║ https://mk1.ai ║
cloudyu-chaiml-nemo-dpo-v1-v2-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v1-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cloudyu-chaiml-nemo-dpo-v1-v2-mkmlizer: ║ belonging to: ║
cloudyu-chaiml-nemo-dpo-v1-v2-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v1-v2-mkmlizer: ║ Chai Research Corp. ║
cloudyu-chaiml-nemo-dpo-v1-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cloudyu-chaiml-nemo-dpo-v1-v2-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
cloudyu-chaiml-nemo-dpo-v1-v2-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v1-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-chaiml-nemo-dpo-v1-v2-mkmlizer: Downloaded to shared memory in 53.418s
cloudyu-chaiml-nemo-dpo-v1-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp75kw14_x, device:0
cloudyu-chaiml-nemo-dpo-v1-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-chaiml-nemo-dpo-v1-v2-mkmlizer: quantized model in 35.931s
cloudyu-chaiml-nemo-dpo-v1-v2-mkmlizer: Processed model cloudyu/ChaiML-Nemo-DPO-V1 in 89.349s
cloudyu-chaiml-nemo-dpo-v1-v2-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-chaiml-nemo-dpo-v1-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-chaiml-nemo-dpo-v1-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v1-v2
cloudyu-chaiml-nemo-dpo-v1-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v1-v2/config.json
cloudyu-chaiml-nemo-dpo-v1-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v1-v2/special_tokens_map.json
cloudyu-chaiml-nemo-dpo-v1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v1-v2/tokenizer_config.json
cloudyu-chaiml-nemo-dpo-v1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v1-v2/tokenizer.json
cloudyu-chaiml-nemo-dpo-v1-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v1-v2/flywheel_model.0.safetensors
cloudyu-chaiml-nemo-dpo-v1-v2-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:12, 28.08it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:07, 48.68it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:07, 46.44it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:07, 45.30it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 51.47it/s] Loading 0: 10%|█ | 37/363 [00:00<00:06, 47.34it/s] Loading 0: 12%|█▏ | 42/363 [00:00<00:07, 43.46it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:06, 48.32it/s] Loading 0: 15%|█▌ | 55/363 [00:01<00:06, 46.39it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:08, 33.75it/s] Loading 0: 18%|█▊ | 65/363 [00:01<00:09, 32.91it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:07, 39.73it/s] Loading 0: 21%|██▏ | 78/363 [00:01<00:06, 41.61it/s] Loading 0: 23%|██▎ | 83/363 [00:01<00:06, 42.34it/s] Loading 0: 25%|██▍ | 90/363 [00:02<00:05, 46.76it/s] Loading 0: 26%|██▋ | 96/363 [00:02<00:05, 45.54it/s] Loading 0: 28%|██▊ | 101/363 [00:02<00:05, 44.16it/s] Loading 0: 30%|██▉ | 108/363 [00:02<00:05, 50.31it/s] Loading 0: 31%|███▏ | 114/363 [00:02<00:05, 45.69it/s] Loading 0: 33%|███▎ | 119/363 [00:02<00:05, 44.44it/s] Loading 0: 35%|███▍ | 126/363 [00:02<00:04, 49.31it/s] Loading 0: 36%|███▋ | 132/363 [00:02<00:04, 46.86it/s] Loading 0: 38%|███▊ | 137/363 [00:03<00:04, 45.75it/s] Loading 0: 39%|███▉ | 142/363 [00:03<00:06, 34.43it/s] Loading 0: 40%|████ | 146/363 [00:03<00:06, 35.05it/s] Loading 0: 41%|████▏ | 150/363 [00:03<00:06, 33.04it/s] Loading 0: 43%|████▎ | 156/363 [00:03<00:05, 38.86it/s] Loading 0: 44%|████▍ | 161/363 [00:03<00:05, 40.17it/s] Loading 0: 46%|████▌ | 167/363 [00:03<00:05, 37.83it/s] Loading 0: 48%|████▊ | 175/363 [00:04<00:04, 46.22it/s] Loading 0: 50%|████▉ | 181/363 [00:04<00:04, 43.56it/s] Loading 0: 51%|█████ | 186/363 [00:04<00:04, 41.57it/s] Loading 0: 53%|█████▎ | 193/363 [00:04<00:03, 46.21it/s] Loading 0: 55%|█████▍ | 199/363 [00:04<00:03, 43.87it/s] Loading 0: 56%|█████▌ | 204/363 [00:04<00:03, 41.81it/s] Loading 0: 58%|█████▊ | 211/363 [00:04<00:03, 47.03it/s] Loading 0: 60%|█████▉ | 216/363 [00:05<00:03, 46.95it/s] Loading 0: 61%|██████ | 221/363 [00:05<00:03, 46.98it/s] Loading 0: 62%|██████▏ | 226/363 [00:05<00:04, 28.12it/s] Loading 0: 63%|██████▎ | 230/363 [00:05<00:04, 28.91it/s] Loading 0: 66%|██████▌ | 238/363 [00:05<00:03, 38.07it/s] Loading 0: 67%|██████▋ | 244/363 [00:05<00:03, 38.39it/s] Loading 0: 69%|██████▊ | 249/363 [00:06<00:03, 37.86it/s] Loading 0: 70%|███████ | 255/363 [00:06<00:02, 42.75it/s] Loading 0: 72%|███████▏ | 260/363 [00:06<00:02, 42.84it/s] Loading 0: 73%|███████▎ | 265/363 [00:06<00:02, 42.21it/s] Loading 0: 74%|███████▍ | 270/363 [00:06<00:02, 43.92it/s] Loading 0: 76%|███████▌ | 275/363 [00:06<00:02, 37.58it/s] Loading 0: 78%|███████▊ | 283/363 [00:06<00:01, 45.95it/s] Loading 0: 80%|███████▉ | 289/363 [00:06<00:01, 44.00it/s] Loading 0: 81%|████████ | 294/363 [00:07<00:01, 42.61it/s] Loading 0: 83%|████████▎ | 301/363 [00:07<00:01, 48.74it/s] Loading 0: 85%|████████▍ | 307/363 [00:14<00:20, 2.79it/s] Loading 0: 86%|████████▌ | 312/363 [00:14<00:13, 3.70it/s] Loading 0: 88%|████████▊ | 320/363 [00:14<00:07, 5.74it/s] Loading 0: 90%|████████▉ | 326/363 [00:14<00:04, 7.63it/s] Loading 0: 91%|█████████ | 331/363 [00:14<00:03, 9.67it/s] Loading 0: 93%|█████████▎| 338/363 [00:14<00:01, 13.61it/s] Loading 0: 95%|█████████▍| 344/363 [00:14<00:01, 17.09it/s] Loading 0: 96%|█████████▋| 350/363 [00:14<00:00, 21.31it/s] Loading 0: 98%|█████████▊| 356/363 [00:15<00:00, 26.26it/s] Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 29.93it/s]
Job cloudyu-chaiml-nemo-dpo-v1-v2-mkmlizer completed after 114.53s with status: succeeded
Stopping job with name cloudyu-chaiml-nemo-dpo-v1-v2-mkmlizer
Pipeline stage MKMLizer completed in 115.04s
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-v1-v2
Waiting for inference service cloudyu-chaiml-nemo-dpo-v1-v2 to be ready
Inference service cloudyu-chaiml-nemo-dpo-v1-v2 ready after 121.16824054718018s
Pipeline stage MKMLDeployer completed in 121.70s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.100048065185547s
Received healthy response to inference request in 1.7084853649139404s
Received healthy response to inference request in 1.612428903579712s
Received healthy response to inference request in 1.264467716217041s
Received healthy response to inference request in 0.9131467342376709s
5 requests
0 failed requests
5th percentile: 0.9834109306335449
10th percentile: 1.053675127029419
20th percentile: 1.194203519821167
30th percentile: 1.3340599536895752
40th percentile: 1.4732444286346436
50th percentile: 1.612428903579712
60th percentile: 1.6508514881134033
70th percentile: 1.6892740726470947
80th percentile: 1.7867979049682619
90th percentile: 1.9434229850769043
95th percentile: 2.0217355251312257
99th percentile: 2.0843855571746825
mean time: 1.5197153568267823
Pipeline stage StressChecker completed in 8.91s
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 2.11s
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 2.10s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v1_v2 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 2724.08s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v1_v2 status is now inactive due to auto deactivation removed underperforming models