developer_uid: cloudyu
submission_id: cloudyu-chaiml-nemo-dpo-v7_v8
model_name: cloudyu-chaiml-nemo-dpo-v7_v7
model_group: cloudyu/ChaiML-Nemo-DPO-
status: inactive
timestamp: 2024-12-03T10:36:33+00:00
num_battles: 9867
num_wins: 4980
celo_rating: 1266.61
family_friendly_score: 0.5626
family_friendly_standard_error: 0.0070154292812343285
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': 0.6145263807408967, 'latency_mean': 1.6271911764144897, 'latency_p50': 1.6276137828826904, 'latency_p90': 1.7840323209762574}, {'batch_size': 3, 'throughput': 1.141230032680266, 'latency_mean': 2.6254676640033723, 'latency_p50': 2.6473947763442993, 'latency_p90': 2.969092535972595}, {'batch_size': 5, 'throughput': 1.3654705937977596, 'latency_mean': 3.6374756908416748, 'latency_p50': 3.6615593433380127, 'latency_p90': 4.1008951425552365}, {'batch_size': 6, 'throughput': 1.446348167124335, 'latency_mean': 4.127720420360565, 'latency_p50': 4.1258803606033325, 'latency_p90': 4.646100449562073}, {'batch_size': 8, 'throughput': 1.5087001020412008, 'latency_mean': 5.267949367761612, 'latency_p50': 5.2548452615737915, 'latency_p90': 5.944346785545349}, {'batch_size': 10, 'throughput': 1.535819023825674, 'latency_mean': 6.465240749120713, 'latency_p50': 6.441444396972656, 'latency_p90': 7.233002877235412}]
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: 1.39
us_pacific_date: 2024-12-03
win_ratio: 0.5047126786257221
generation_params: {'temperature': 1.0, '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-v8-mkmlizer
Waiting for job on cloudyu-chaiml-nemo-dpo-v7-v8-mkmlizer to finish
cloudyu-chaiml-nemo-dpo-v7-v8-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-chaiml-nemo-dpo-v7-v8-mkmlizer: ║ _____ __ __ ║
cloudyu-chaiml-nemo-dpo-v7-v8-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cloudyu-chaiml-nemo-dpo-v7-v8-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cloudyu-chaiml-nemo-dpo-v7-v8-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cloudyu-chaiml-nemo-dpo-v7-v8-mkmlizer: ║ /___/ ║
cloudyu-chaiml-nemo-dpo-v7-v8-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v7-v8-mkmlizer: ║ Version: 0.11.12 ║
cloudyu-chaiml-nemo-dpo-v7-v8-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cloudyu-chaiml-nemo-dpo-v7-v8-mkmlizer: ║ https://mk1.ai ║
cloudyu-chaiml-nemo-dpo-v7-v8-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v7-v8-mkmlizer: ║ The license key for the current software has been verified as ║
cloudyu-chaiml-nemo-dpo-v7-v8-mkmlizer: ║ belonging to: ║
cloudyu-chaiml-nemo-dpo-v7-v8-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v7-v8-mkmlizer: ║ Chai Research Corp. ║
cloudyu-chaiml-nemo-dpo-v7-v8-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cloudyu-chaiml-nemo-dpo-v7-v8-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
cloudyu-chaiml-nemo-dpo-v7-v8-mkmlizer: ║ ║
cloudyu-chaiml-nemo-dpo-v7-v8-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-chaiml-nemo-dpo-v7-v8-mkmlizer: Downloaded to shared memory in 32.276s
cloudyu-chaiml-nemo-dpo-v7-v8-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp0geyqbpp, device:0
cloudyu-chaiml-nemo-dpo-v7-v8-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
cloudyu-chaiml-nemo-dpo-v7-v8-mkmlizer: quantized model in 35.412s
cloudyu-chaiml-nemo-dpo-v7-v8-mkmlizer: Processed model cloudyu/ChaiML-Nemo-DPO-V7 in 67.688s
cloudyu-chaiml-nemo-dpo-v7-v8-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-chaiml-nemo-dpo-v7-v8-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-chaiml-nemo-dpo-v7-v8-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v7-v8
cloudyu-chaiml-nemo-dpo-v7-v8-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v7-v8/config.json
cloudyu-chaiml-nemo-dpo-v7-v8-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v7-v8/special_tokens_map.json
cloudyu-chaiml-nemo-dpo-v7-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v7-v8/tokenizer_config.json
cloudyu-chaiml-nemo-dpo-v7-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v7-v8/tokenizer.json
cloudyu-chaiml-nemo-dpo-v7-v8-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v7-v8/flywheel_model.0.safetensors
cloudyu-chaiml-nemo-dpo-v7-v8-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:13, 26.56it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:07, 46.00it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:07, 44.03it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:07, 44.17it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 51.01it/s] Loading 0: 10%|█ | 37/363 [00:00<00:06, 49.28it/s] Loading 0: 12%|█▏ | 43/363 [00:00<00:06, 49.65it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:06, 51.68it/s] Loading 0: 15%|█▌ | 55/363 [00:01<00:06, 47.98it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:08, 34.43it/s] Loading 0: 18%|█▊ | 66/363 [00:01<00:08, 34.98it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:07, 39.65it/s] Loading 0: 21%|██▏ | 78/363 [00:01<00:06, 41.37it/s] Loading 0: 23%|██▎ | 83/363 [00:01<00:06, 42.48it/s] Loading 0: 25%|██▍ | 90/363 [00:02<00:05, 48.39it/s] Loading 0: 26%|██▋ | 96/363 [00:02<00:05, 47.27it/s] Loading 0: 28%|██▊ | 101/363 [00:02<00:05, 45.47it/s] Loading 0: 30%|███ | 109/363 [00:02<00:04, 53.89it/s] Loading 0: 32%|███▏ | 115/363 [00:02<00:05, 45.40it/s] Loading 0: 33%|███▎ | 120/363 [00:02<00:05, 41.91it/s] Loading 0: 35%|███▍ | 126/363 [00:02<00:05, 45.64it/s] Loading 0: 36%|███▋ | 132/363 [00:02<00:05, 45.40it/s] Loading 0: 38%|███▊ | 137/363 [00:03<00:04, 45.59it/s] Loading 0: 39%|███▉ | 142/363 [00:03<00:06, 35.90it/s] Loading 0: 40%|████ | 146/363 [00:03<00:05, 36.65it/s] Loading 0: 41%|████▏ | 150/363 [00:03<00:05, 36.09it/s] Loading 0: 43%|████▎ | 157/363 [00:03<00:04, 43.49it/s] Loading 0: 45%|████▍ | 163/363 [00:03<00:04, 44.19it/s] Loading 0: 46%|████▋ | 168/363 [00:03<00:04, 44.49it/s] Loading 0: 48%|████▊ | 175/363 [00:03<00:03, 50.24it/s] Loading 0: 50%|████▉ | 181/363 [00:04<00:03, 47.47it/s] Loading 0: 51%|█████ | 186/363 [00:04<00:03, 45.51it/s] Loading 0: 53%|█████▎ | 193/363 [00:04<00:03, 49.81it/s] Loading 0: 55%|█████▍ | 199/363 [00:04<00:03, 45.44it/s] Loading 0: 56%|█████▌ | 204/363 [00:04<00:03, 43.78it/s] Loading 0: 58%|█████▊ | 211/363 [00:04<00:03, 49.53it/s] Loading 0: 60%|█████▉ | 217/363 [00:04<00:03, 47.58it/s] Loading 0: 61%|██████▏ | 223/363 [00:05<00:03, 36.56it/s] Loading 0: 63%|██████▎ | 228/363 [00:05<00:03, 36.61it/s] Loading 0: 64%|██████▍ | 233/363 [00:05<00:03, 39.02it/s] Loading 0: 66%|██████▌ | 239/363 [00:05<00:03, 36.85it/s] Loading 0: 68%|██████▊ | 247/363 [00:05<00:02, 44.55it/s] Loading 0: 69%|██████▉ | 252/363 [00:05<00:02, 44.92it/s] Loading 0: 71%|███████ | 257/363 [00:05<00:02, 38.74it/s] Loading 0: 73%|███████▎ | 265/363 [00:06<00:02, 46.96it/s] Loading 0: 75%|███████▍ | 271/363 [00:06<00:01, 46.60it/s] Loading 0: 76%|███████▌ | 276/363 [00:06<00:01, 45.83it/s] Loading 0: 78%|███████▊ | 283/363 [00:06<00:01, 49.76it/s] Loading 0: 80%|███████▉ | 289/363 [00:06<00:01, 48.18it/s] Loading 0: 81%|████████ | 294/363 [00:06<00:01, 46.74it/s] Loading 0: 83%|████████▎ | 302/363 [00:06<00:01, 54.38it/s] Loading 0: 85%|████████▍ | 308/363 [00:13<00:18, 2.94it/s] Loading 0: 86%|████████▌ | 312/363 [00:13<00:13, 3.65it/s] Loading 0: 88%|████████▊ | 320/363 [00:13<00:07, 5.72it/s] Loading 0: 90%|████████▉ | 326/363 [00:14<00:04, 7.67it/s] Loading 0: 91%|█████████ | 331/363 [00:14<00:03, 9.77it/s] Loading 0: 93%|█████████▎| 338/363 [00:14<00:01, 13.74it/s] Loading 0: 95%|█████████▍| 344/363 [00:14<00:01, 17.21it/s] Loading 0: 96%|█████████▋| 350/363 [00:14<00:00, 21.44it/s] Loading 0: 98%|█████████▊| 356/363 [00:14<00:00, 26.37it/s] Loading 0: 100%|█████████▉| 362/363 [00:14<00:00, 30.04it/s]
Job cloudyu-chaiml-nemo-dpo-v7-v8-mkmlizer completed after 94.29s with status: succeeded
Stopping job with name cloudyu-chaiml-nemo-dpo-v7-v8-mkmlizer
Pipeline stage MKMLizer completed in 94.80s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cloudyu-chaiml-nemo-dpo-v7-v8
Waiting for inference service cloudyu-chaiml-nemo-dpo-v7-v8 to be ready
Inference service cloudyu-chaiml-nemo-dpo-v7-v8 ready after 150.61580204963684s
Pipeline stage MKMLDeployer completed in 151.19s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1650702953338623s
Received healthy response to inference request in 1.8218705654144287s
Received healthy response to inference request in 1.7837121486663818s
Received healthy response to inference request in 1.9831597805023193s
Received healthy response to inference request in 1.4382128715515137s
5 requests
0 failed requests
5th percentile: 1.5073127269744873
10th percentile: 1.5764125823974608
20th percentile: 1.7146122932434082
30th percentile: 1.7913438320159911
40th percentile: 1.80660719871521
50th percentile: 1.8218705654144287
60th percentile: 1.886386251449585
70th percentile: 1.9509019374847412
80th percentile: 2.019541883468628
90th percentile: 2.0923060894012453
95th percentile: 2.128688192367554
99th percentile: 2.1577938747406007
mean time: 1.8384051322937012
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 2.49s
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 2.40s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v7_v8 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 3173.70s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v7_v8 status is now inactive due to auto deactivation removed underperforming models