developer_uid: cloudyu
submission_id: cloudyu-chaiml-nemo-dpo-v7_v11
model_name: cloudyu-chaiml-nemo-dpo-v7_v7
model_group: cloudyu/ChaiML-Nemo-DPO-
status: inactive
timestamp: 2024-12-04T12:00:49+00:00
num_battles: 14880
num_wins: 7414
celo_rating: 1260.95
family_friendly_score: 0.558
family_friendly_standard_error: 0.007023332542319209
submission_type: basic
model_repo: cloudyu/ChaiML-Nemo-DPO-V7
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6125552900431344, 'latency_mean': 1.6324433040618898, 'latency_p50': 1.6378822326660156, 'latency_p90': 1.7945361852645874}, {'batch_size': 3, 'throughput': 1.1451988317869066, 'latency_mean': 2.607183141708374, 'latency_p50': 2.596332311630249, 'latency_p90': 2.8811851024627684}, {'batch_size': 5, 'throughput': 1.3799912595372665, 'latency_mean': 3.606778223514557, 'latency_p50': 3.602297782897949, 'latency_p90': 4.03004150390625}, {'batch_size': 6, 'throughput': 1.449854137754215, 'latency_mean': 4.109832447767258, 'latency_p50': 4.1049357652664185, 'latency_p90': 4.552670001983643}, {'batch_size': 8, 'throughput': 1.5073077303615376, 'latency_mean': 5.271982254981995, 'latency_p50': 5.282505750656128, 'latency_p90': 5.825343942642212}, {'batch_size': 10, 'throughput': 1.5589058029678895, 'latency_mean': 6.36499220252037, 'latency_p50': 6.267449975013733, 'latency_p90': 7.281465029716491}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: cloudyu-chaiml-nemo-dpo-v7_v7
is_internal_developer: False
language_model: cloudyu/ChaiML-Nemo-DPO-V7
model_size: 13B
ranking_group: single
throughput_3p7s: 1.4
us_pacific_date: 2024-12-04
win_ratio: 0.498252688172043
generation_params: {'temperature': 1.5, '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-chaiml-nemo-dpo-v7-v11-mkmlizer
Waiting for job on cloudyu-chaiml-nemo-dpo-v7-v11-mkmlizer to finish
cloudyu-chaiml-nemo-dpo-v7-v11-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-chaiml-nemo-dpo-v7-v11-mkmlizer: ║ _____ __ __ ║
cloudyu-chaiml-nemo-dpo-v7-v11-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cloudyu-chaiml-nemo-dpo-v7-v11-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cloudyu-chaiml-nemo-dpo-v7-v11-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cloudyu-chaiml-nemo-dpo-v7-v11-mkmlizer: ║ /___/ ║
cloudyu-chaiml-nemo-dpo-v7-v11-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v7-v11-mkmlizer: ║ Version: 0.11.12 ║
cloudyu-chaiml-nemo-dpo-v7-v11-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cloudyu-chaiml-nemo-dpo-v7-v11-mkmlizer: ║ https://mk1.ai ║
cloudyu-chaiml-nemo-dpo-v7-v11-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v7-v11-mkmlizer: ║ The license key for the current software has been verified as ║
cloudyu-chaiml-nemo-dpo-v7-v11-mkmlizer: ║ belonging to: ║
cloudyu-chaiml-nemo-dpo-v7-v11-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v7-v11-mkmlizer: ║ Chai Research Corp. ║
cloudyu-chaiml-nemo-dpo-v7-v11-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cloudyu-chaiml-nemo-dpo-v7-v11-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
cloudyu-chaiml-nemo-dpo-v7-v11-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v7-v11-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-chaiml-nemo-dpo-v7-v11-mkmlizer: Downloaded to shared memory in 32.638s
cloudyu-chaiml-nemo-dpo-v7-v11-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpcmjgcxns, device:0
cloudyu-chaiml-nemo-dpo-v7-v11-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
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
cloudyu-chaiml-nemo-dpo-v7-v11-mkmlizer: quantized model in 35.489s
cloudyu-chaiml-nemo-dpo-v7-v11-mkmlizer: Processed model cloudyu/ChaiML-Nemo-DPO-V7 in 68.127s
cloudyu-chaiml-nemo-dpo-v7-v11-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-chaiml-nemo-dpo-v7-v11-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-chaiml-nemo-dpo-v7-v11-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v7-v11
cloudyu-chaiml-nemo-dpo-v7-v11-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v7-v11/config.json
cloudyu-chaiml-nemo-dpo-v7-v11-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v7-v11/special_tokens_map.json
cloudyu-chaiml-nemo-dpo-v7-v11-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v7-v11/tokenizer_config.json
cloudyu-chaiml-nemo-dpo-v7-v11-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v7-v11/tokenizer.json
cloudyu-chaiml-nemo-dpo-v7-v11-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:12, 28.59it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:06, 50.89it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:07, 47.85it/s] Loading 0: 7%|▋ | 25/363 [00:00<00:06, 48.83it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 51.64it/s] Loading 0: 10%|█ | 37/363 [00:00<00:06, 48.62it/s] Loading 0: 12%|█▏ | 43/363 [00:00<00:06, 49.22it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:06, 51.13it/s] Loading 0: 15%|█▌ | 55/363 [00:01<00:06, 47.74it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:08, 35.52it/s] Loading 0: 18%|█▊ | 66/363 [00:01<00:08, 35.47it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:07, 39.65it/s] Loading 0: 21%|██▏ | 78/363 [00:01<00:07, 40.22it/s] Loading 0: 23%|██▎ | 83/363 [00:01<00:06, 41.06it/s] Loading 0: 25%|██▍ | 90/363 [00:02<00:05, 46.37it/s] Loading 0: 26%|██▋ | 96/363 [00:02<00:06, 44.04it/s] Loading 0: 28%|██▊ | 101/363 [00:02<00:06, 43.06it/s] Loading 0: 30%|██▉ | 108/363 [00:02<00:05, 49.28it/s] Loading 0: 31%|███▏ | 114/363 [00:02<00:05, 44.67it/s] Loading 0: 33%|███▎ | 119/363 [00:02<00:05, 42.73it/s] Loading 0: 35%|███▍ | 126/363 [00:02<00:04, 48.23it/s] Loading 0: 36%|███▋ | 132/363 [00:02<00:04, 46.43it/s] Loading 0: 38%|███▊ | 137/363 [00:03<00:04, 45.79it/s] Loading 0: 39%|███▉ | 142/363 [00:03<00:06, 35.47it/s] Loading 0: 40%|████ | 146/363 [00:03<00:06, 36.04it/s] Loading 0: 41%|████▏ | 150/363 [00:03<00:06, 34.89it/s] Loading 0: 43%|████▎ | 157/363 [00:03<00:04, 42.03it/s] Loading 0: 45%|████▍ | 163/363 [00:03<00:04, 42.25it/s] Loading 0: 46%|████▋ | 168/363 [00:03<00:04, 42.94it/s] Loading 0: 48%|████▊ | 175/363 [00:04<00:03, 48.34it/s] Loading 0: 50%|████▉ | 181/363 [00:04<00:03, 46.39it/s] Loading 0: 51%|█████ | 186/363 [00:04<00:03, 45.19it/s] Loading 0: 53%|█████▎ | 193/363 [00:04<00:03, 50.17it/s] Loading 0: 55%|█████▍ | 199/363 [00:04<00:03, 47.91it/s] Loading 0: 56%|█████▌ | 204/363 [00:04<00:03, 46.34it/s] Loading 0: 58%|█████▊ | 211/363 [00:04<00:02, 51.49it/s] Loading 0: 60%|█████▉ | 217/363 [00:04<00:02, 49.23it/s] Loading 0: 61%|██████▏ | 223/363 [00:05<00:03, 37.91it/s] Loading 0: 63%|██████▎ | 228/363 [00:05<00:03, 38.03it/s] Loading 0: 64%|██████▍ | 233/363 [00:05<00:03, 40.41it/s] Loading 0: 66%|██████▌ | 239/363 [00:05<00:03, 37.77it/s] Loading 0: 68%|██████▊ | 247/363 [00:05<00:02, 45.30it/s] Loading 0: 70%|██████▉ | 253/363 [00:05<00:02, 44.26it/s] Loading 0: 71%|███████ | 258/363 [00:05<00:02, 43.93it/s] Loading 0: 73%|███████▎ | 265/363 [00:06<00:02, 48.26it/s] Loading 0: 75%|███████▍ | 271/363 [00:06<00:01, 46.40it/s] Loading 0: 76%|███████▌ | 276/363 [00:06<00:01, 45.15it/s] Loading 0: 78%|███████▊ | 283/363 [00:06<00:01, 49.55it/s] Loading 0: 80%|███████▉ | 289/363 [00:06<00:01, 46.63it/s] Loading 0: 81%|████████ | 294/363 [00:06<00:01, 44.79it/s] Loading 0: 83%|████████▎ | 301/363 [00:06<00:01, 50.85it/s] Loading 0: 85%|████████▍ | 307/363 [00:13<00:19, 2.83it/s] Loading 0: 86%|████████▌ | 312/363 [00:13<00:13, 3.74it/s] Loading 0: 88%|████████▊ | 320/363 [00:13<00:07, 5.80it/s] Loading 0: 90%|████████▉ | 326/363 [00:14<00:04, 7.71it/s] Loading 0: 91%|█████████ | 331/363 [00:14<00:03, 9.79it/s] Loading 0: 93%|█████████▎| 338/363 [00:14<00:01, 13.74it/s] Loading 0: 95%|█████████▍| 344/363 [00:14<00:01, 17.17it/s] Loading 0: 96%|█████████▋| 350/363 [00:14<00:00, 21.33it/s] Loading 0: 98%|█████████▊| 356/363 [00:14<00:00, 26.24it/s] Loading 0: 100%|█████████▉| 362/363 [00:14<00:00, 29.88it/s]
Job cloudyu-chaiml-nemo-dpo-v7-v11-mkmlizer completed after 94.25s with status: succeeded
Stopping job with name cloudyu-chaiml-nemo-dpo-v7-v11-mkmlizer
Pipeline stage MKMLizer completed in 94.76s
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-v7-v11
Waiting for inference service cloudyu-chaiml-nemo-dpo-v7-v11 to be ready
Inference service cloudyu-chaiml-nemo-dpo-v7-v11 ready after 150.5393373966217s
Pipeline stage MKMLDeployer completed in 151.10s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2381887435913086s
Received healthy response to inference request in 1.839259147644043s
Received healthy response to inference request in 1.799867868423462s
Received healthy response to inference request in 2.053647756576538s
Received healthy response to inference request in 1.6904172897338867s
5 requests
0 failed requests
5th percentile: 1.7123074054718017
10th percentile: 1.7341975212097167
20th percentile: 1.777977752685547
30th percentile: 1.807746124267578
40th percentile: 1.8235026359558106
50th percentile: 1.839259147644043
60th percentile: 1.925014591217041
70th percentile: 2.0107700347900392
80th percentile: 2.090555953979492
90th percentile: 2.1643723487854003
95th percentile: 2.2012805461883547
99th percentile: 2.230807104110718
mean time: 1.9242761611938477
Pipeline stage StressChecker completed in 11.18s
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 2.29s
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 2.24s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v7_v11 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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service cloudyu-chaiml-nemo-dpo-v7-v11-profiler
Waiting for inference service cloudyu-chaiml-nemo-dpo-v7-v11-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 2703.23s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v7_v11 status is now inactive due to auto deactivation removed underperforming models