cloudyu-nemo-dpo-v22

developer_uid: cloudyu

submission_id: cloudyu-nemo-dpo-v22_v14

model_name: cloudyu-nemo-dpo-v22_v1

model_group: cloudyu/Nemo-DPO-V22

status: inactive

timestamp: 2024-12-20T14:35:40+00:00

num_battles: 20667

num_wins: 10795

celo_rating: 1277.9

family_friendly_score: 0.5626

family_friendly_standard_error: 0.0070154292812343285

submission_type: basic

model_repo: cloudyu/Nemo-DPO-V22

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6166680401630661, 'latency_mean': 1.6215519070625306, 'latency_p50': 1.6205886602401733, 'latency_p90': 1.7989367723464966}, {'batch_size': 3, 'throughput': 1.1381943082965826, 'latency_mean': 2.6229578709602355, 'latency_p50': 2.611403703689575, 'latency_p90': 2.9097063302993775}, {'batch_size': 5, 'throughput': 1.385766610872293, 'latency_mean': 3.590540361404419, 'latency_p50': 3.555959939956665, 'latency_p90': 4.039305353164673}, {'batch_size': 6, 'throughput': 1.4639870404163877, 'latency_mean': 4.075132840871811, 'latency_p50': 4.078590035438538, 'latency_p90': 4.595408391952515}, {'batch_size': 8, 'throughput': 1.5297099129460654, 'latency_mean': 5.191468042135239, 'latency_p50': 5.203554272651672, 'latency_p90': 5.781757402420044}, {'batch_size': 10, 'throughput': 1.5663746693194291, 'latency_mean': 6.337042205333709, 'latency_p50': 6.3215988874435425, 'latency_p90': 7.173766851425171}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: cloudyu-nemo-dpo-v22_v1

is_internal_developer: False

language_model: cloudyu/Nemo-DPO-V22

model_size: 13B

ranking_group: single

throughput_3p7s: 1.41

us_pacific_date: 2024-12-20

win_ratio: 0.5223302849954033

generation_params: {'temperature': 0.99, '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-v22-v14-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v22-v14-mkmlizer to finish
cloudyu-nemo-dpo-v22-v14-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v22-v14-mkmlizer: ║     _____            __           __                                ║
cloudyu-nemo-dpo-v22-v14-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cloudyu-nemo-dpo-v22-v14-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cloudyu-nemo-dpo-v22-v14-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cloudyu-nemo-dpo-v22-v14-mkmlizer: ║       /___/                                                         ║
cloudyu-nemo-dpo-v22-v14-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v22-v14-mkmlizer: ║  Version: 0.11.12                                                   ║
cloudyu-nemo-dpo-v22-v14-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cloudyu-nemo-dpo-v22-v14-mkmlizer: ║  https://mk1.ai                                                     ║
cloudyu-nemo-dpo-v22-v14-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v22-v14-mkmlizer: ║  The license key for the current software has been verified as      ║
cloudyu-nemo-dpo-v22-v14-mkmlizer: ║  belonging to:                                                      ║
cloudyu-nemo-dpo-v22-v14-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v22-v14-mkmlizer: ║  Chai Research Corp.                                                ║
cloudyu-nemo-dpo-v22-v14-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cloudyu-nemo-dpo-v22-v14-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
cloudyu-nemo-dpo-v22-v14-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v22-v14-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-nemo-dpo-v22-v14-mkmlizer: Downloaded to shared memory in 32.879s
cloudyu-nemo-dpo-v22-v14-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp2k71dhbr, device:0
cloudyu-nemo-dpo-v22-v14-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-nemo-dpo-v22-v14-mkmlizer: quantized model in 36.387s
cloudyu-nemo-dpo-v22-v14-mkmlizer: Processed model cloudyu/Nemo-DPO-V22 in 69.266s
cloudyu-nemo-dpo-v22-v14-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-nemo-dpo-v22-v14-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v22-v14-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v14
cloudyu-nemo-dpo-v22-v14-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v14/special_tokens_map.json
cloudyu-nemo-dpo-v22-v14-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v14/config.json
cloudyu-nemo-dpo-v22-v14-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v14/tokenizer_config.json
cloudyu-nemo-dpo-v22-v14-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v14/tokenizer.json
cloudyu-nemo-dpo-v22-v14-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v14/flywheel_model.0.safetensors
cloudyu-nemo-dpo-v22-v14-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 28.92it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:07, 47.45it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:07, 47.94it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:08, 40.51it/s]
Loading 0:   8%|▊         | 30/363 [00:00<00:07, 45.04it/s]
Loading 0:  10%|▉         | 35/363 [00:00<00:07, 43.87it/s]
Loading 0:  11%|█         | 40/363 [00:00<00:07, 43.10it/s]
Loading 0:  12%|█▏        | 45/363 [00:01<00:07, 43.84it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:08, 36.71it/s]
Loading 0:  15%|█▌        | 56/363 [00:01<00:07, 41.68it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:10, 29.93it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:09, 29.87it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:08, 35.85it/s]
Loading 0:  21%|██        | 76/363 [00:01<00:07, 37.42it/s]
Loading 0:  22%|██▏       | 81/363 [00:02<00:07, 39.31it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:06, 41.84it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:07, 35.56it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:06, 42.90it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:06, 42.32it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:05, 43.06it/s]
Loading 0:  31%|███       | 113/363 [00:02<00:06, 36.50it/s]
Loading 0:  33%|███▎      | 118/363 [00:03<00:06, 36.95it/s]
Loading 0:  35%|███▍      | 126/363 [00:03<00:05, 45.05it/s]
Loading 0:  36%|███▋      | 132/363 [00:03<00:05, 42.83it/s]
Loading 0:  38%|███▊      | 137/363 [00:03<00:05, 41.88it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:06, 33.22it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 34.30it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 32.87it/s]
Loading 0:  42%|████▏     | 154/363 [00:04<00:06, 34.13it/s]
Loading 0:  44%|████▎     | 158/363 [00:04<00:06, 33.06it/s]
Loading 0:  45%|████▌     | 165/363 [00:04<00:04, 41.87it/s]
Loading 0:  47%|████▋     | 170/363 [00:04<00:04, 42.69it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:04, 44.03it/s]
Loading 0:  50%|████▉     | 181/363 [00:04<00:04, 41.92it/s]
Loading 0:  51%|█████     | 186/363 [00:04<00:04, 41.51it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 46.89it/s]
Loading 0:  55%|█████▍    | 199/363 [00:05<00:03, 43.62it/s]
Loading 0:  56%|█████▌    | 204/363 [00:05<00:03, 42.60it/s]
Loading 0:  58%|█████▊    | 211/363 [00:05<00:03, 47.25it/s]
Loading 0:  60%|█████▉    | 216/363 [00:05<00:03, 47.73it/s]
Loading 0:  61%|██████    | 221/363 [00:05<00:02, 47.66it/s]
Loading 0:  62%|██████▏   | 226/363 [00:05<00:04, 29.30it/s]
Loading 0:  63%|██████▎   | 230/363 [00:05<00:04, 29.26it/s]
Loading 0:  66%|██████▌   | 238/363 [00:06<00:03, 38.08it/s]
Loading 0:  67%|██████▋   | 244/363 [00:06<00:03, 37.94it/s]
Loading 0:  69%|██████▊   | 249/363 [00:06<00:03, 37.61it/s]
Loading 0:  70%|███████   | 255/363 [00:06<00:02, 41.97it/s]
Loading 0:  72%|███████▏  | 260/363 [00:06<00:02, 42.60it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:02, 44.07it/s]
Loading 0:  75%|███████▍  | 271/363 [00:06<00:02, 42.30it/s]
Loading 0:  76%|███████▌  | 276/363 [00:06<00:02, 41.16it/s]
Loading 0:  78%|███████▊  | 282/363 [00:07<00:01, 45.37it/s]
Loading 0:  79%|███████▉  | 287/363 [00:07<00:01, 42.98it/s]
Loading 0:  80%|████████  | 292/363 [00:07<00:01, 42.01it/s]
Loading 0:  82%|████████▏ | 297/363 [00:07<00:01, 42.84it/s]
Loading 0:  83%|████████▎ | 303/363 [00:07<00:01, 41.49it/s]
Loading 0:  85%|████████▍ | 308/363 [00:14<00:22,  2.50it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:15,  3.23it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:08,  5.31it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:05,  7.23it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:03,  9.23it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 13.12it/s]
Loading 0:  95%|█████████▍| 344/363 [00:15<00:01, 16.33it/s]
Loading 0:  96%|█████████▌| 349/363 [00:15<00:00, 19.37it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 25.17it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 27.99it/s]
                                                            
Job cloudyu-nemo-dpo-v22-v14-mkmlizer completed after 94.75s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v22-v14-mkmlizer
Pipeline stage MKMLizer completed in 95.25s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cloudyu-nemo-dpo-v22-v14
Waiting for inference service cloudyu-nemo-dpo-v22-v14 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
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-nemo-dpo-v22-v14 ready after 260.8806200027466s
Pipeline stage MKMLDeployer completed in 261.50s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0342957973480225s
Received healthy response to inference request in 2.0982131958007812s
Received healthy response to inference request in 2.135403633117676s
Received healthy response to inference request in 1.8705530166625977s
Received healthy response to inference request in 2.0036818981170654s
5 requests
0 failed requests
5th percentile: 1.8971787929534911
10th percentile: 1.9238045692443848
20th percentile: 1.977056121826172
30th percentile: 2.009804677963257
40th percentile: 2.0220502376556397
50th percentile: 2.0342957973480225
60th percentile: 2.059862756729126
70th percentile: 2.0854297161102293
80th percentile: 2.10565128326416
90th percentile: 2.120527458190918
95th percentile: 2.127965545654297
99th percentile: 2.133916015625
mean time: 2.0284295082092285
Pipeline stage StressChecker completed in 11.69s
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 0.83s
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 0.70s
Shutdown handler de-registered
cloudyu-nemo-dpo-v22_v14 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 0.09s
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-nemo-dpo-v22-v14-profiler
Waiting for inference service cloudyu-nemo-dpo-v22-v14-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 2748.08s
Shutdown handler de-registered
cloudyu-nemo-dpo-v22_v14 status is now inactive due to auto deactivation removed underperforming models