developer_uid: cloudyu
submission_id: cloudyu-chaiml-nemo-dpo-v17_v4
model_name: cloudyu-chaiml-nemo-dpo-v17_v4
model_group: cloudyu/ChaiML-Nemo-DPO-
status: inactive
timestamp: 2024-12-06T07:00:42+00:00
num_battles: 8007
num_wins: 4287
celo_rating: 1280.13
family_friendly_score: 0.5502
family_friendly_standard_error: 0.007035338797812086
submission_type: basic
model_repo: cloudyu/ChaiML-Nemo-DPO-V17
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6142065979486514, 'latency_mean': 1.6280163645744323, 'latency_p50': 1.6293009519577026, 'latency_p90': 1.8110305786132812}, {'batch_size': 3, 'throughput': 1.1293214078025444, 'latency_mean': 2.6512746715545656, 'latency_p50': 2.6391109228134155, 'latency_p90': 2.9527044773101805}, {'batch_size': 5, 'throughput': 1.354180432012946, 'latency_mean': 3.675097118616104, 'latency_p50': 3.6768410205841064, 'latency_p90': 4.1009448051452635}, {'batch_size': 6, 'throughput': 1.4170432863083278, 'latency_mean': 4.21026873588562, 'latency_p50': 4.212448477745056, 'latency_p90': 4.6596764087677}, {'batch_size': 8, 'throughput': 1.4955448091377697, 'latency_mean': 5.324300700426102, 'latency_p50': 5.342507243156433, 'latency_p90': 6.052827167510986}, {'batch_size': 10, 'throughput': 1.5308687361735644, 'latency_mean': 6.467707196474075, 'latency_p50': 6.503702521324158, 'latency_p90': 7.317806529998779}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: cloudyu-chaiml-nemo-dpo-v17_v4
is_internal_developer: False
language_model: cloudyu/ChaiML-Nemo-DPO-V17
model_size: 13B
ranking_group: single
throughput_3p7s: 1.36
us_pacific_date: 2024-12-05
win_ratio: 0.5354065192956163
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-chaiml-nemo-dpo-v17-v4-mkmlizer
Waiting for job on cloudyu-chaiml-nemo-dpo-v17-v4-mkmlizer to finish
cloudyu-chaiml-nemo-dpo-v17-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-chaiml-nemo-dpo-v17-v4-mkmlizer: ║ _____ __ __ ║
cloudyu-chaiml-nemo-dpo-v17-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cloudyu-chaiml-nemo-dpo-v17-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cloudyu-chaiml-nemo-dpo-v17-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cloudyu-chaiml-nemo-dpo-v17-v4-mkmlizer: ║ /___/ ║
cloudyu-chaiml-nemo-dpo-v17-v4-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v17-v4-mkmlizer: ║ Version: 0.11.12 ║
cloudyu-chaiml-nemo-dpo-v17-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cloudyu-chaiml-nemo-dpo-v17-v4-mkmlizer: ║ https://mk1.ai ║
cloudyu-chaiml-nemo-dpo-v17-v4-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v17-v4-mkmlizer: ║ The license key for the current software has been verified as ║
cloudyu-chaiml-nemo-dpo-v17-v4-mkmlizer: ║ belonging to: ║
cloudyu-chaiml-nemo-dpo-v17-v4-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v17-v4-mkmlizer: ║ Chai Research Corp. ║
cloudyu-chaiml-nemo-dpo-v17-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cloudyu-chaiml-nemo-dpo-v17-v4-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
cloudyu-chaiml-nemo-dpo-v17-v4-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v17-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-chaiml-nemo-dpo-v17-v4-mkmlizer: Downloaded to shared memory in 32.230s
cloudyu-chaiml-nemo-dpo-v17-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp8laowaf8, device:0
cloudyu-chaiml-nemo-dpo-v17-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-chaiml-nemo-dpo-v17-v4-mkmlizer: quantized model in 36.786s
cloudyu-chaiml-nemo-dpo-v17-v4-mkmlizer: Processed model cloudyu/ChaiML-Nemo-DPO-V17 in 69.017s
cloudyu-chaiml-nemo-dpo-v17-v4-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-chaiml-nemo-dpo-v17-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-chaiml-nemo-dpo-v17-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v17-v4
cloudyu-chaiml-nemo-dpo-v17-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v17-v4/config.json
cloudyu-chaiml-nemo-dpo-v17-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v17-v4/special_tokens_map.json
cloudyu-chaiml-nemo-dpo-v17-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v17-v4/flywheel_model.0.safetensors
cloudyu-chaiml-nemo-dpo-v17-v4-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:12, 27.76it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:07, 48.42it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:07, 45.40it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:07, 44.61it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 50.69it/s] Loading 0: 10%|█ | 37/363 [00:00<00:06, 48.59it/s] Loading 0: 12%|█▏ | 42/363 [00:00<00:06, 46.58it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:06, 51.62it/s] Loading 0: 15%|█▌ | 55/363 [00:01<00:06, 47.24it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:09, 33.30it/s] Loading 0: 18%|█▊ | 65/363 [00:01<00:09, 32.82it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:07, 39.35it/s] Loading 0: 21%|██▏ | 78/363 [00:01<00:07, 40.60it/s] Loading 0: 23%|██▎ | 83/363 [00:01<00:06, 40.03it/s] Loading 0: 25%|██▍ | 89/363 [00:02<00:06, 44.69it/s] Loading 0: 26%|██▌ | 94/363 [00:02<00:06, 43.36it/s] Loading 0: 27%|██▋ | 99/363 [00:02<00:06, 43.46it/s] Loading 0: 29%|██▉ | 105/363 [00:02<00:05, 43.25it/s] Loading 0: 31%|███ | 112/363 [00:02<00:05, 47.26it/s] Loading 0: 32%|███▏ | 117/363 [00:02<00:05, 44.76it/s] Loading 0: 34%|███▍ | 123/363 [00:02<00:05, 43.80it/s] Loading 0: 35%|███▌ | 128/363 [00:02<00:05, 41.66it/s] Loading 0: 37%|███▋ | 134/363 [00:03<00:05, 45.70it/s] Loading 0: 38%|███▊ | 139/363 [00:03<00:05, 44.62it/s] Loading 0: 40%|███▉ | 144/363 [00:03<00:08, 26.91it/s] Loading 0: 41%|████ | 149/363 [00:03<00:07, 29.42it/s] Loading 0: 43%|████▎ | 157/363 [00:03<00:05, 37.95it/s] Loading 0: 45%|████▍ | 163/363 [00:03<00:05, 38.18it/s] Loading 0: 46%|████▋ | 168/363 [00:04<00:05, 38.65it/s] Loading 0: 48%|████▊ | 174/363 [00:04<00:04, 43.25it/s] Loading 0: 49%|████▉ | 179/363 [00:04<00:04, 40.89it/s] Loading 0: 51%|█████ | 184/363 [00:04<00:04, 40.42it/s] Loading 0: 52%|█████▏ | 189/363 [00:04<00:04, 41.35it/s] Loading 0: 53%|█████▎ | 194/363 [00:04<00:04, 36.66it/s] Loading 0: 55%|█████▌ | 201/363 [00:04<00:03, 44.32it/s] Loading 0: 57%|█████▋ | 206/363 [00:04<00:03, 44.61it/s] Loading 0: 58%|█████▊ | 211/363 [00:05<00:03, 45.93it/s] Loading 0: 60%|█████▉ | 217/363 [00:05<00:03, 44.02it/s] Loading 0: 61%|██████▏ | 223/363 [00:05<00:04, 33.24it/s] Loading 0: 63%|██████▎ | 227/363 [00:05<00:03, 34.08it/s] Loading 0: 64%|██████▎ | 231/363 [00:05<00:04, 32.50it/s] Loading 0: 65%|██████▌ | 237/363 [00:05<00:03, 38.65it/s] Loading 0: 67%|██████▋ | 242/363 [00:05<00:03, 39.31it/s] Loading 0: 68%|██████▊ | 247/363 [00:06<00:02, 41.53it/s] Loading 0: 70%|██████▉ | 253/363 [00:06<00:02, 42.24it/s] Loading 0: 71%|███████ | 258/363 [00:06<00:02, 42.42it/s] Loading 0: 73%|███████▎ | 265/363 [00:06<00:02, 47.36it/s] Loading 0: 75%|███████▍ | 271/363 [00:06<00:01, 46.09it/s] Loading 0: 76%|███████▌ | 276/363 [00:06<00:01, 44.77it/s] Loading 0: 78%|███████▊ | 283/363 [00:06<00:01, 49.52it/s] Loading 0: 80%|███████▉ | 289/363 [00:06<00:01, 44.45it/s] Loading 0: 81%|████████ | 294/363 [00:07<00:01, 42.46it/s] Loading 0: 83%|████████▎ | 300/363 [00:07<00:01, 46.63it/s] Loading 0: 84%|████████▍ | 305/363 [00:14<00:22, 2.58it/s] Loading 0: 85%|████████▌ | 309/363 [00:14<00:16, 3.28it/s] Loading 0: 86%|████████▌ | 313/363 [00:14<00:11, 4.23it/s] Loading 0: 88%|████████▊ | 320/363 [00:14<00:06, 6.60it/s] Loading 0: 90%|████████▉ | 326/363 [00:14<00:04, 9.07it/s] Loading 0: 91%|█████████ | 331/363 [00:14<00:02, 11.59it/s] Loading 0: 93%|█████████▎| 338/363 [00:14<00:01, 16.35it/s] Loading 0: 95%|█████████▍| 344/363 [00:15<00:00, 20.06it/s] Loading 0: 96%|█████████▌| 349/363 [00:15<00:00, 23.31it/s] Loading 0: 98%|█████████▊| 356/363 [00:15<00:00, 29.66it/s] Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 32.52it/s]
Job cloudyu-chaiml-nemo-dpo-v17-v4-mkmlizer completed after 91.38s with status: succeeded
Stopping job with name cloudyu-chaiml-nemo-dpo-v17-v4-mkmlizer
Pipeline stage MKMLizer completed in 93.63s
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-chaiml-nemo-dpo-v17-v4
Waiting for inference service cloudyu-chaiml-nemo-dpo-v17-v4 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
Inference service cloudyu-chaiml-nemo-dpo-v17-v4 ready after 183.78624200820923s
Pipeline stage MKMLDeployer completed in 185.91s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1993966102600098s
Received healthy response to inference request in 2.200786590576172s
Received healthy response to inference request in 1.8871746063232422s
Received healthy response to inference request in 1.8438384532928467s
Received healthy response to inference request in 1.917372226715088s
5 requests
0 failed requests
5th percentile: 1.8525056838989258
10th percentile: 1.8611729145050049
20th percentile: 1.878507375717163
30th percentile: 1.8932141304016112
40th percentile: 1.9052931785583496
50th percentile: 1.917372226715088
60th percentile: 2.0301819801330567
70th percentile: 2.142991733551025
80th percentile: 2.199674606323242
90th percentile: 2.200230598449707
95th percentile: 2.2005085945129395
99th percentile: 2.2007309913635256
mean time: 2.0097136974334715
Pipeline stage StressChecker completed in 11.43s
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 2.43s
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 2.45s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v17_v4 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 2619.84s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v17_v4 status is now inactive due to auto deactivation removed underperforming models