developer_uid: cloudyu
submission_id: cloudyu-chaiml-nemo-dpo-v7_v1
model_name: cloudyu-chaiml-nemo-dpo-v7_v1
model_group: cloudyu/ChaiML-Nemo-DPO-
status: inactive
timestamp: 2024-11-24T12:38:38+00:00
num_battles: 25395
num_wins: 12848
celo_rating: 1266.16
family_friendly_score: 0.5532
family_friendly_standard_error: 0.0070309282459715084
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': 0.6168186291213232, 'latency_mean': 1.6211626994609833, 'latency_p50': 1.630225419998169, 'latency_p90': 1.7902255296707152}, {'batch_size': 3, 'throughput': 1.165461833935849, 'latency_mean': 2.5714129388332365, 'latency_p50': 2.560004472732544, 'latency_p90': 2.817251110076904}, {'batch_size': 5, 'throughput': 1.4052665344444897, 'latency_mean': 3.5395164370536802, 'latency_p50': 3.504828929901123, 'latency_p90': 4.004421806335449}, {'batch_size': 6, 'throughput': 1.483884926186949, 'latency_mean': 4.024528188705444, 'latency_p50': 4.004984140396118, 'latency_p90': 4.51999146938324}, {'batch_size': 8, 'throughput': 1.5481492972073103, 'latency_mean': 5.133149086236954, 'latency_p50': 5.128374695777893, 'latency_p90': 5.843901920318603}, {'batch_size': 10, 'throughput': 1.5791049068306782, 'latency_mean': 6.279911555051804, 'latency_p50': 6.305177807807922, 'latency_p90': 7.069473767280578}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: cloudyu-chaiml-nemo-dpo-v7_v1
is_internal_developer: False
language_model: cloudyu/ChaiML-Nemo-DPO-V7
model_size: 13B
ranking_group: single
throughput_3p7s: 1.44
us_pacific_date: 2024-11-24
win_ratio: 0.5059263634573735
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}
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-v1-mkmlizer
Waiting for job on cloudyu-chaiml-nemo-dpo-v7-v1-mkmlizer to finish
cloudyu-chaiml-nemo-dpo-v7-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-chaiml-nemo-dpo-v7-v1-mkmlizer: ║ _____ __ __ ║
cloudyu-chaiml-nemo-dpo-v7-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cloudyu-chaiml-nemo-dpo-v7-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cloudyu-chaiml-nemo-dpo-v7-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cloudyu-chaiml-nemo-dpo-v7-v1-mkmlizer: ║ /___/ ║
cloudyu-chaiml-nemo-dpo-v7-v1-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v7-v1-mkmlizer: ║ Version: 0.11.12 ║
cloudyu-chaiml-nemo-dpo-v7-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cloudyu-chaiml-nemo-dpo-v7-v1-mkmlizer: ║ https://mk1.ai ║
cloudyu-chaiml-nemo-dpo-v7-v1-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v7-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cloudyu-chaiml-nemo-dpo-v7-v1-mkmlizer: ║ belonging to: ║
cloudyu-chaiml-nemo-dpo-v7-v1-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v7-v1-mkmlizer: ║ Chai Research Corp. ║
cloudyu-chaiml-nemo-dpo-v7-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cloudyu-chaiml-nemo-dpo-v7-v1-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
cloudyu-chaiml-nemo-dpo-v7-v1-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v7-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
cloudyu-chaiml-nemo-dpo-v7-v1-mkmlizer: Downloaded to shared memory in 47.314s
cloudyu-chaiml-nemo-dpo-v7-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpdqyqbza_, device:0
cloudyu-chaiml-nemo-dpo-v7-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-chaiml-nemo-dpo-v7-v1-mkmlizer: quantized model in 35.119s
cloudyu-chaiml-nemo-dpo-v7-v1-mkmlizer: Processed model cloudyu/ChaiML-Nemo-DPO-V7 in 82.433s
cloudyu-chaiml-nemo-dpo-v7-v1-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-chaiml-nemo-dpo-v7-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-chaiml-nemo-dpo-v7-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v7-v1
cloudyu-chaiml-nemo-dpo-v7-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v7-v1/config.json
cloudyu-chaiml-nemo-dpo-v7-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v7-v1/special_tokens_map.json
cloudyu-chaiml-nemo-dpo-v7-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v7-v1/tokenizer_config.json
cloudyu-chaiml-nemo-dpo-v7-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v7-v1/tokenizer.json
cloudyu-chaiml-nemo-dpo-v7-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v7-v1/flywheel_model.0.safetensors
cloudyu-chaiml-nemo-dpo-v7-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:12, 29.38it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:06, 52.07it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:06, 50.05it/s] Loading 0: 7%|▋ | 25/363 [00:00<00:06, 50.78it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 53.43it/s] Loading 0: 10%|█ | 37/363 [00:00<00:06, 49.36it/s] Loading 0: 12%|█▏ | 43/363 [00:00<00:06, 47.76it/s] Loading 0: 13%|█▎ | 49/363 [00:00<00:06, 50.59it/s] Loading 0: 15%|█▌ | 55/363 [00:01<00:06, 47.77it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:08, 35.39it/s] Loading 0: 18%|█▊ | 66/363 [00:01<00:08, 35.77it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:07, 40.39it/s] Loading 0: 21%|██▏ | 78/363 [00:01<00:06, 41.57it/s] Loading 0: 23%|██▎ | 83/363 [00:01<00:06, 41.77it/s] Loading 0: 25%|██▍ | 90/363 [00:02<00:05, 47.16it/s] Loading 0: 26%|██▋ | 96/363 [00:02<00:06, 44.22it/s] Loading 0: 28%|██▊ | 101/363 [00:02<00:06, 42.49it/s] Loading 0: 30%|██▉ | 108/363 [00:02<00:05, 48.87it/s] Loading 0: 31%|███▏ | 114/363 [00:02<00:05, 45.19it/s] Loading 0: 33%|███▎ | 119/363 [00:02<00:05, 43.79it/s] Loading 0: 35%|███▍ | 126/363 [00:02<00:04, 48.97it/s] Loading 0: 36%|███▋ | 132/363 [00:02<00:04, 46.87it/s] Loading 0: 38%|███▊ | 137/363 [00:03<00:04, 45.92it/s] Loading 0: 39%|███▉ | 142/363 [00:03<00:06, 35.25it/s] Loading 0: 40%|████ | 146/363 [00:03<00:06, 35.10it/s] Loading 0: 41%|████▏ | 150/363 [00:03<00:06, 34.48it/s] Loading 0: 43%|████▎ | 157/363 [00:03<00:04, 41.73it/s] Loading 0: 45%|████▍ | 163/363 [00:03<00:04, 41.73it/s] Loading 0: 46%|████▋ | 168/363 [00:03<00:04, 42.52it/s] Loading 0: 48%|████▊ | 175/363 [00:03<00:03, 48.74it/s] Loading 0: 50%|████▉ | 181/363 [00:04<00:03, 47.25it/s] Loading 0: 51%|█████ | 186/363 [00:04<00:03, 45.96it/s] Loading 0: 53%|█████▎ | 193/363 [00:04<00:03, 51.38it/s] Loading 0: 55%|█████▍ | 199/363 [00:04<00:03, 48.68it/s] Loading 0: 56%|█████▌ | 204/363 [00:04<00:03, 45.54it/s] Loading 0: 58%|█████▊ | 211/363 [00:04<00:03, 49.99it/s] Loading 0: 60%|█████▉ | 217/363 [00:04<00:03, 45.66it/s] Loading 0: 61%|██████ | 222/363 [00:04<00:03, 45.65it/s] Loading 0: 63%|██████▎ | 227/363 [00:05<00:04, 32.07it/s] Loading 0: 64%|██████▎ | 231/363 [00:05<00:04, 31.72it/s] Loading 0: 66%|██████▌ | 238/363 [00:05<00:03, 38.60it/s] Loading 0: 67%|██████▋ | 244/363 [00:05<00:03, 39.25it/s] Loading 0: 69%|██████▊ | 249/363 [00:05<00:02, 40.49it/s] Loading 0: 71%|███████ | 256/363 [00:05<00:02, 46.56it/s] Loading 0: 72%|███████▏ | 262/363 [00:06<00:02, 46.13it/s] Loading 0: 74%|███████▎ | 267/363 [00:06<00:02, 46.42it/s] Loading 0: 75%|███████▌ | 274/363 [00:06<00:01, 50.68it/s] Loading 0: 77%|███████▋ | 280/363 [00:06<00:01, 47.30it/s] Loading 0: 79%|███████▊ | 285/363 [00:06<00:01, 46.06it/s] Loading 0: 80%|████████ | 291/363 [00:06<00:01, 48.95it/s] Loading 0: 82%|████████▏ | 296/363 [00:06<00:01, 47.72it/s] Loading 0: 83%|████████▎ | 303/363 [00:06<00:01, 47.55it/s] Loading 0: 85%|████████▍ | 308/363 [00:13<00:20, 2.69it/s] Loading 0: 86%|████████▌ | 312/363 [00:13<00:14, 3.42it/s] Loading 0: 88%|████████▊ | 320/363 [00:13<00:07, 5.52it/s] Loading 0: 90%|████████▉ | 326/363 [00:13<00:04, 7.47it/s] Loading 0: 91%|█████████ | 331/363 [00:14<00:03, 9.57it/s] Loading 0: 93%|█████████▎| 338/363 [00:14<00:01, 13.58it/s] Loading 0: 95%|█████████▍| 344/363 [00:14<00:01, 17.03it/s] Loading 0: 96%|█████████▌| 349/363 [00:14<00:00, 20.31it/s] Loading 0: 98%|█████████▊| 356/363 [00:14<00:00, 26.52it/s] Loading 0: 100%|█████████▉| 362/363 [00:14<00:00, 29.83it/s]
Job cloudyu-chaiml-nemo-dpo-v7-v1-mkmlizer completed after 104.15s with status: succeeded
Stopping job with name cloudyu-chaiml-nemo-dpo-v7-v1-mkmlizer
Pipeline stage MKMLizer completed in 104.68s
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-v7-v1
Waiting for inference service cloudyu-chaiml-nemo-dpo-v7-v1 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
Inference service cloudyu-chaiml-nemo-dpo-v7-v1 ready after 120.43570971488953s
Pipeline stage MKMLDeployer completed in 120.95s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 2.0919086933135986s
Received healthy response to inference request in 2.0784263610839844s
Received healthy response to inference request in 1.8328688144683838s
Received healthy response to inference request in 1.9558210372924805s
5 requests
1 failed requests
5th percentile: 1.857459259033203
10th percentile: 1.8820497035980224
20th percentile: 1.9312305927276612
30th percentile: 1.9803421020507812
40th percentile: 2.029384231567383
50th percentile: 2.0784263610839844
60th percentile: 2.08381929397583
70th percentile: 2.0892122268676756
80th percentile: 5.700585126876835
90th percentile: 12.917937994003298
95th percentile: 16.526614427566525
99th percentile: 19.413555574417114
mean time: 5.618863153457641
%s, retrying in %s seconds...
Received healthy response to inference request in 1.684924602508545s
Received healthy response to inference request in 1.7649002075195312s
Received healthy response to inference request in 2.102240562438965s
Received healthy response to inference request in 1.6322345733642578s
Received healthy response to inference request in 2.0305027961730957s
5 requests
0 failed requests
5th percentile: 1.6427725791931151
10th percentile: 1.6533105850219727
20th percentile: 1.6743865966796876
30th percentile: 1.7009197235107423
40th percentile: 1.7329099655151368
50th percentile: 1.7649002075195312
60th percentile: 1.871141242980957
70th percentile: 1.9773822784423827
80th percentile: 2.0448503494262695
90th percentile: 2.073545455932617
95th percentile: 2.087893009185791
99th percentile: 2.09937105178833
mean time: 1.8429605484008789
Pipeline stage StressChecker completed in 39.93s
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 2.18s
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 2.47s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v7_v1 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 3013.40s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v7_v1 status is now inactive due to auto deactivation removed underperforming models