developer_uid: cloudyu
submission_id: cloudyu-chaiml-nemo-dpo-v6_v6
model_name: cloudyu-chaiml-nemo-dpo-v6_v7
model_group: cloudyu/ChaiML-Nemo-DPO-
status: inactive
timestamp: 2024-11-24T16:28:25+00:00
num_battles: 16821
num_wins: 8422
celo_rating: 1262.23
family_friendly_score: 0.5578000000000001
family_friendly_standard_error: 0.007023662292565041
submission_type: basic
model_repo: cloudyu/ChaiML-Nemo-DPO-V6
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6125085568282336, 'latency_mean': 1.6325326669216156, 'latency_p50': 1.6458669900894165, 'latency_p90': 1.7966217517852783}, {'batch_size': 3, 'throughput': 1.1399984600807964, 'latency_mean': 2.623239872455597, 'latency_p50': 2.6362000703811646, 'latency_p90': 2.865940570831299}, {'batch_size': 5, 'throughput': 1.381889883328499, 'latency_mean': 3.60411954164505, 'latency_p50': 3.597387194633484, 'latency_p90': 4.069917941093444}, {'batch_size': 6, 'throughput': 1.4366815683202903, 'latency_mean': 4.146059725284577, 'latency_p50': 4.126706838607788, 'latency_p90': 4.744708180427551}, {'batch_size': 8, 'throughput': 1.5161000221880736, 'latency_mean': 5.24329824090004, 'latency_p50': 5.231619596481323, 'latency_p90': 5.9302699089050295}, {'batch_size': 10, 'throughput': 1.557205842688816, 'latency_mean': 6.367969716787338, 'latency_p50': 6.371744155883789, 'latency_p90': 7.137459230422974}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: cloudyu-chaiml-nemo-dpo-v6_v7
is_internal_developer: False
language_model: cloudyu/ChaiML-Nemo-DPO-V6
model_size: 13B
ranking_group: single
throughput_3p7s: 1.4
us_pacific_date: 2024-11-24
win_ratio: 0.5006836692229951
generation_params: {'temperature': 1.0, 'top_p': 0.95, 'min_p': 0.05, '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-v6-v6-mkmlizer
Waiting for job on cloudyu-chaiml-nemo-dpo-v6-v6-mkmlizer to finish
cloudyu-chaiml-nemo-dpo-v6-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-chaiml-nemo-dpo-v6-v6-mkmlizer: ║ _____ __ __ ║
cloudyu-chaiml-nemo-dpo-v6-v6-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cloudyu-chaiml-nemo-dpo-v6-v6-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cloudyu-chaiml-nemo-dpo-v6-v6-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cloudyu-chaiml-nemo-dpo-v6-v6-mkmlizer: ║ /___/ ║
cloudyu-chaiml-nemo-dpo-v6-v6-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v6-v6-mkmlizer: ║ Version: 0.11.12 ║
cloudyu-chaiml-nemo-dpo-v6-v6-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cloudyu-chaiml-nemo-dpo-v6-v6-mkmlizer: ║ https://mk1.ai ║
cloudyu-chaiml-nemo-dpo-v6-v6-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v6-v6-mkmlizer: ║ The license key for the current software has been verified as ║
cloudyu-chaiml-nemo-dpo-v6-v6-mkmlizer: ║ belonging to: ║
cloudyu-chaiml-nemo-dpo-v6-v6-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v6-v6-mkmlizer: ║ Chai Research Corp. ║
cloudyu-chaiml-nemo-dpo-v6-v6-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cloudyu-chaiml-nemo-dpo-v6-v6-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
cloudyu-chaiml-nemo-dpo-v6-v6-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v6-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-chaiml-nemo-dpo-v6-v6-mkmlizer: Downloaded to shared memory in 36.429s
cloudyu-chaiml-nemo-dpo-v6-v6-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpxaa9z_jk, device:0
cloudyu-chaiml-nemo-dpo-v6-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-chaiml-nemo-dpo-v6-v6-mkmlizer: quantized model in 35.688s
cloudyu-chaiml-nemo-dpo-v6-v6-mkmlizer: Processed model cloudyu/ChaiML-Nemo-DPO-V6 in 72.117s
cloudyu-chaiml-nemo-dpo-v6-v6-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-chaiml-nemo-dpo-v6-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-chaiml-nemo-dpo-v6-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v6-v6
cloudyu-chaiml-nemo-dpo-v6-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v6-v6/config.json
cloudyu-chaiml-nemo-dpo-v6-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v6-v6/special_tokens_map.json
cloudyu-chaiml-nemo-dpo-v6-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v6-v6/tokenizer_config.json
cloudyu-chaiml-nemo-dpo-v6-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v6-v6/tokenizer.json
cloudyu-chaiml-nemo-dpo-v6-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v6-v6/flywheel_model.0.safetensors
cloudyu-chaiml-nemo-dpo-v6-v6-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:12, 27.93it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:07, 49.30it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:07, 46.62it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:07, 45.08it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 51.58it/s] Loading 0: 10%|█ | 37/363 [00:00<00:06, 47.96it/s] Loading 0: 12%|█▏ | 42/363 [00:00<00:07, 44.75it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:06, 48.81it/s] Loading 0: 15%|█▍ | 54/363 [00:01<00:06, 48.56it/s] Loading 0: 17%|█▋ | 60/363 [00:01<00:06, 45.37it/s] Loading 0: 18%|█▊ | 65/363 [00:01<00:09, 30.63it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:07, 37.33it/s] Loading 0: 21%|██▏ | 78/363 [00:01<00:07, 38.19it/s] Loading 0: 23%|██▎ | 83/363 [00:01<00:07, 39.42it/s] Loading 0: 25%|██▍ | 89/363 [00:02<00:06, 42.34it/s] Loading 0: 26%|██▌ | 94/363 [00:02<00:06, 42.26it/s] Loading 0: 27%|██▋ | 99/363 [00:02<00:06, 42.08it/s] Loading 0: 29%|██▉ | 105/363 [00:02<00:06, 40.72it/s] Loading 0: 31%|███ | 112/363 [00:02<00:05, 46.08it/s] Loading 0: 32%|███▏ | 117/363 [00:02<00:05, 45.03it/s] Loading 0: 34%|███▎ | 122/363 [00:02<00:05, 45.93it/s] Loading 0: 35%|███▍ | 127/363 [00:03<00:06, 39.06it/s] Loading 0: 37%|███▋ | 135/363 [00:03<00:04, 47.51it/s] Loading 0: 39%|███▉ | 141/363 [00:03<00:04, 46.48it/s] Loading 0: 40%|████ | 146/363 [00:03<00:06, 34.07it/s] Loading 0: 41%|████▏ | 150/363 [00:03<00:06, 33.53it/s] Loading 0: 43%|████▎ | 157/363 [00:03<00:05, 39.54it/s] Loading 0: 45%|████▍ | 163/363 [00:03<00:05, 39.02it/s] Loading 0: 46%|████▋ | 168/363 [00:04<00:04, 40.69it/s] Loading 0: 48%|████▊ | 175/363 [00:04<00:04, 46.57it/s] Loading 0: 50%|████▉ | 181/363 [00:04<00:04, 44.92it/s] Loading 0: 51%|█████ | 186/363 [00:04<00:04, 43.14it/s] Loading 0: 53%|█████▎ | 193/363 [00:04<00:03, 47.64it/s] Loading 0: 55%|█████▍ | 198/363 [00:04<00:03, 47.73it/s] Loading 0: 56%|█████▌ | 203/363 [00:04<00:04, 39.47it/s] Loading 0: 58%|█████▊ | 211/363 [00:04<00:03, 46.60it/s] Loading 0: 60%|█████▉ | 217/363 [00:05<00:03, 44.83it/s] Loading 0: 61%|██████▏ | 223/363 [00:05<00:04, 34.54it/s] Loading 0: 63%|██████▎ | 227/363 [00:05<00:03, 34.60it/s] Loading 0: 64%|██████▎ | 231/363 [00:05<00:03, 33.22it/s] Loading 0: 66%|██████▌ | 238/363 [00:05<00:03, 39.84it/s] Loading 0: 67%|██████▋ | 243/363 [00:05<00:02, 41.41it/s] Loading 0: 68%|██████▊ | 248/363 [00:06<00:03, 34.06it/s] Loading 0: 70%|███████ | 255/363 [00:06<00:02, 39.94it/s] Loading 0: 72%|███████▏ | 260/363 [00:06<00:02, 39.39it/s] Loading 0: 73%|███████▎ | 265/363 [00:06<00:02, 39.80it/s] Loading 0: 75%|███████▍ | 271/363 [00:06<00:02, 38.79it/s] Loading 0: 76%|███████▌ | 276/363 [00:06<00:02, 37.84it/s] Loading 0: 78%|███████▊ | 282/363 [00:06<00:01, 42.75it/s] Loading 0: 79%|███████▉ | 287/363 [00:06<00:01, 43.18it/s] Loading 0: 80%|████████ | 292/363 [00:07<00:01, 43.53it/s] Loading 0: 82%|████████▏ | 298/363 [00:07<00:01, 42.79it/s] Loading 0: 84%|████████▎ | 304/363 [00:13<00:22, 2.67it/s] Loading 0: 85%|████████▍ | 308/363 [00:14<00:16, 3.40it/s] Loading 0: 86%|████████▌ | 312/363 [00:14<00:11, 4.36it/s] Loading 0: 88%|████████▊ | 320/363 [00:14<00:06, 7.17it/s] Loading 0: 90%|████████▉ | 326/363 [00:14<00:03, 9.68it/s] Loading 0: 91%|█████████ | 331/363 [00:14<00:02, 12.22it/s] Loading 0: 93%|█████████▎| 338/363 [00:14<00:01, 17.15it/s] Loading 0: 95%|█████████▍| 344/363 [00:14<00:00, 21.05it/s] Loading 0: 96%|█████████▌| 349/363 [00:14<00:00, 24.47it/s] Loading 0: 98%|█████████▊| 356/363 [00:15<00:00, 31.10it/s] Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 34.21it/s]
Job cloudyu-chaiml-nemo-dpo-v6-v6-mkmlizer completed after 93.99s with status: succeeded
Stopping job with name cloudyu-chaiml-nemo-dpo-v6-v6-mkmlizer
Pipeline stage MKMLizer completed in 94.49s
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-v6-v6
Waiting for inference service cloudyu-chaiml-nemo-dpo-v6-v6 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service cloudyu-chaiml-nemo-dpo-v6-v6 ready after 120.42403721809387s
Pipeline stage MKMLDeployer completed in 121.47s
run pipeline stage %s
Running pipeline stage StressChecker
Failed to get response for submission cloudyu-chaiml-nemo-dpo-v9_v3: ('http://cloudyu-chaiml-nemo-dpo-v9-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:56784->127.0.0.1:8080: read: connection reset by peer\n')
Received healthy response to inference request in 2.3409852981567383s
Received healthy response to inference request in 1.7817621231079102s
Received healthy response to inference request in 1.6874732971191406s
Received healthy response to inference request in 1.6475179195404053s
Received healthy response to inference request in 1.796738624572754s
5 requests
0 failed requests
5th percentile: 1.6555089950561523
10th percentile: 1.6635000705718994
20th percentile: 1.6794822216033936
30th percentile: 1.7063310623168946
40th percentile: 1.7440465927124023
50th percentile: 1.7817621231079102
60th percentile: 1.7877527236938477
70th percentile: 1.7937433242797851
80th percentile: 1.9055879592895508
90th percentile: 2.1232866287231444
95th percentile: 2.232135963439941
99th percentile: 2.319215431213379
mean time: 1.8508954524993897
Pipeline stage StressChecker completed in 10.55s
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 2.34s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v6_v6 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 2947.26s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v6_v6 status is now inactive due to auto deactivation removed underperforming models