developer_uid: azuruce
submission_id: chaiml-mistral-nemo-dpo-_5165_v2
model_name: chaiml-mistral-nemo-dpo-_5165_v2
model_group: ChaiML/mistral_nemo_dpo_
status: inactive
timestamp: 2024-12-19T09:08:27+00:00
num_battles: 11700
num_wins: 5922
celo_rating: 1267.22
family_friendly_score: 0.5746
family_friendly_standard_error: 0.006991921624274688
submission_type: basic
model_repo: ChaiML/mistral_nemo_dpo_241217_albert_v1-checkpoint-4680
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6301325791792989, 'latency_mean': 1.5869112241268157, 'latency_p50': 1.5865509510040283, 'latency_p90': 1.7342763423919678}, {'batch_size': 3, 'throughput': 1.2520714567839597, 'latency_mean': 2.3885922265052795, 'latency_p50': 2.3852983713150024, 'latency_p90': 2.6625273942947385}, {'batch_size': 5, 'throughput': 1.5684455105860025, 'latency_mean': 3.1741673696041106, 'latency_p50': 3.1502606868743896, 'latency_p90': 3.5635051012039183}, {'batch_size': 6, 'throughput': 1.682346518626197, 'latency_mean': 3.5335860478878023, 'latency_p50': 3.513423442840576, 'latency_p90': 4.076685571670533}, {'batch_size': 8, 'throughput': 1.8139377575939282, 'latency_mean': 4.3766265702247615, 'latency_p50': 4.362640023231506, 'latency_p90': 4.883654689788818}, {'batch_size': 10, 'throughput': 1.905677097438143, 'latency_mean': 5.217977433204651, 'latency_p50': 5.200000762939453, 'latency_p90': 5.903113913536072}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: chaiml-mistral-nemo-dpo-_5165_v2
is_internal_developer: True
language_model: ChaiML/mistral_nemo_dpo_241217_albert_v1-checkpoint-4680
model_size: 13B
ranking_group: single
throughput_3p7s: 1.73
us_pacific_date: 2024-12-19
win_ratio: 0.5061538461538462
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', '####', 'Bot:', 'User:', 'You:', '<|im_end|>', '<|eot_id|>'], 'max_input_tokens': 1024, 'best_of': 4, 'max_output_tokens': 64}
formatter: {'memory_template': '', 'prompt_template': '', '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 chaiml-mistral-nemo-dpo-5165-v2-mkmlizer
Waiting for job on chaiml-mistral-nemo-dpo-5165-v2-mkmlizer to finish
chaiml-mistral-nemo-dpo-5165-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral-nemo-dpo-5165-v2-mkmlizer: ║ _____ __ __ ║
chaiml-mistral-nemo-dpo-5165-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-mistral-nemo-dpo-5165-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-mistral-nemo-dpo-5165-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-mistral-nemo-dpo-5165-v2-mkmlizer: ║ /___/ ║
chaiml-mistral-nemo-dpo-5165-v2-mkmlizer: ║ ║
chaiml-mistral-nemo-dpo-5165-v2-mkmlizer: ║ Version: 0.11.12 ║
chaiml-mistral-nemo-dpo-5165-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-mistral-nemo-dpo-5165-v2-mkmlizer: ║ https://mk1.ai ║
chaiml-mistral-nemo-dpo-5165-v2-mkmlizer: ║ ║
chaiml-mistral-nemo-dpo-5165-v2-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-mistral-nemo-dpo-5165-v2-mkmlizer: ║ belonging to: ║
chaiml-mistral-nemo-dpo-5165-v2-mkmlizer: ║ ║
chaiml-mistral-nemo-dpo-5165-v2-mkmlizer: ║ Chai Research Corp. ║
chaiml-mistral-nemo-dpo-5165-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-mistral-nemo-dpo-5165-v2-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
chaiml-mistral-nemo-dpo-5165-v2-mkmlizer: ║ ║
chaiml-mistral-nemo-dpo-5165-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral-nemo-dpo-5165-v2-mkmlizer: Downloaded to shared memory in 34.670s
chaiml-mistral-nemo-dpo-5165-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp44ntrd3a, device:0
chaiml-mistral-nemo-dpo-5165-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral-nemo-dpo-5165-v2-mkmlizer: quantized model in 36.042s
chaiml-mistral-nemo-dpo-5165-v2-mkmlizer: Processed model ChaiML/mistral_nemo_dpo_241217_albert_v1-checkpoint-4680 in 70.712s
chaiml-mistral-nemo-dpo-5165-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral-nemo-dpo-5165-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral-nemo-dpo-5165-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-5165-v2
chaiml-mistral-nemo-dpo-5165-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-5165-v2/config.json
chaiml-mistral-nemo-dpo-5165-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-5165-v2/special_tokens_map.json
chaiml-mistral-nemo-dpo-5165-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-5165-v2/tokenizer_config.json
chaiml-mistral-nemo-dpo-5165-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-5165-v2/tokenizer.json
chaiml-mistral-nemo-dpo-5165-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-5165-v2/flywheel_model.0.safetensors
chaiml-mistral-nemo-dpo-5165-v2-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:12, 29.62it/s] Loading 0: 4%|▍ | 14/363 [00:00<00:08, 41.95it/s] Loading 0: 6%|▌ | 22/363 [00:00<00:06, 52.60it/s] Loading 0: 8%|▊ | 28/363 [00:00<00:07, 47.49it/s] Loading 0: 9%|▉ | 33/363 [00:00<00:07, 45.44it/s] Loading 0: 11%|█ | 40/363 [00:00<00:06, 50.64it/s] Loading 0: 13%|█▎ | 46/363 [00:00<00:06, 47.87it/s] Loading 0: 14%|█▍ | 51/363 [00:01<00:06, 45.96it/s] Loading 0: 16%|█▌ | 57/363 [00:01<00:06, 49.43it/s] Loading 0: 17%|█▋ | 63/363 [00:01<00:08, 34.57it/s] Loading 0: 19%|█▊ | 68/363 [00:01<00:08, 36.84it/s] Loading 0: 20%|██ | 73/363 [00:01<00:08, 33.32it/s] Loading 0: 22%|██▏ | 81/363 [00:01<00:06, 41.91it/s] Loading 0: 24%|██▎ | 86/363 [00:02<00:06, 42.86it/s] Loading 0: 25%|██▌ | 91/363 [00:02<00:07, 36.30it/s] Loading 0: 27%|██▋ | 98/363 [00:02<00:06, 43.10it/s] Loading 0: 28%|██▊ | 103/363 [00:02<00:06, 42.74it/s] Loading 0: 30%|██▉ | 108/363 [00:02<00:05, 43.89it/s] Loading 0: 31%|███ | 113/363 [00:02<00:06, 38.29it/s] Loading 0: 33%|███▎ | 118/363 [00:02<00:06, 38.09it/s] Loading 0: 35%|███▍ | 126/363 [00:02<00:05, 46.06it/s] Loading 0: 36%|███▋ | 132/363 [00:03<00:05, 43.80it/s] Loading 0: 38%|███▊ | 137/363 [00:03<00:05, 42.65it/s] Loading 0: 39%|███▉ | 142/363 [00:03<00:06, 33.82it/s] Loading 0: 40%|████ | 146/363 [00:03<00:06, 33.73it/s] Loading 0: 41%|████▏ | 150/363 [00:03<00:06, 32.15it/s] Loading 0: 43%|████▎ | 157/363 [00:03<00:05, 38.96it/s] Loading 0: 45%|████▍ | 163/363 [00:04<00:05, 39.53it/s] Loading 0: 46%|████▋ | 168/363 [00:04<00:04, 39.56it/s] Loading 0: 48%|████▊ | 175/363 [00:04<00:04, 44.57it/s] Loading 0: 50%|████▉ | 180/363 [00:04<00:04, 44.39it/s] Loading 0: 51%|█████ | 185/363 [00:04<00:04, 37.29it/s] Loading 0: 53%|█████▎ | 193/363 [00:04<00:03, 45.26it/s] Loading 0: 55%|█████▍ | 199/363 [00:04<00:03, 44.31it/s] Loading 0: 56%|█████▌ | 204/363 [00:04<00:03, 43.08it/s] Loading 0: 58%|█████▊ | 211/363 [00:05<00:03, 46.78it/s] Loading 0: 60%|█████▉ | 217/363 [00:05<00:03, 45.21it/s] Loading 0: 61%|██████▏ | 223/363 [00:05<00:04, 31.87it/s] Loading 0: 63%|██████▎ | 227/363 [00:05<00:04, 31.38it/s] Loading 0: 64%|██████▎ | 231/363 [00:05<00:04, 30.42it/s] Loading 0: 65%|██████▌ | 237/363 [00:05<00:03, 36.47it/s] Loading 0: 67%|██████▋ | 242/363 [00:06<00:03, 38.89it/s] Loading 0: 68%|██████▊ | 247/363 [00:06<00:02, 41.16it/s] Loading 0: 70%|██████▉ | 253/363 [00:06<00:02, 41.57it/s] Loading 0: 71%|███████ | 258/363 [00:06<00:02, 41.52it/s] Loading 0: 73%|███████▎ | 265/363 [00:06<00:02, 45.49it/s] Loading 0: 74%|███████▍ | 270/363 [00:06<00:02, 46.46it/s] Loading 0: 76%|███████▌ | 275/363 [00:06<00:02, 38.89it/s] Loading 0: 78%|███████▊ | 282/363 [00:06<00:01, 46.08it/s] Loading 0: 79%|███████▉ | 287/363 [00:07<00:01, 45.08it/s] Loading 0: 80%|████████ | 292/363 [00:07<00:01, 45.02it/s] Loading 0: 82%|████████▏ | 298/363 [00:07<00:01, 42.12it/s] Loading 0: 84%|████████▎ | 304/363 [00:14<00:22, 2.65it/s] Loading 0: 85%|████████▍ | 308/363 [00:14<00:16, 3.36it/s] Loading 0: 86%|████████▌ | 312/363 [00:14<00:11, 4.34it/s] Loading 0: 88%|████████▊ | 320/363 [00:14<00:06, 7.10it/s] Loading 0: 90%|████████▉ | 326/363 [00:14<00:03, 9.57it/s] Loading 0: 91%|█████████ | 331/363 [00:14<00:02, 12.18it/s] Loading 0: 93%|█████████▎| 339/363 [00:14<00:01, 17.01it/s] Loading 0: 96%|█████████▌| 347/363 [00:15<00:00, 23.30it/s] Loading 0: 97%|█████████▋| 353/363 [00:15<00:00, 26.92it/s] Loading 0: 99%|█████████▉| 359/363 [00:15<00:00, 30.23it/s]
Job chaiml-mistral-nemo-dpo-5165-v2-mkmlizer completed after 94.54s with status: succeeded
Stopping job with name chaiml-mistral-nemo-dpo-5165-v2-mkmlizer
Pipeline stage MKMLizer completed in 95.09s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-mistral-nemo-dpo-5165-v2
Waiting for inference service chaiml-mistral-nemo-dpo-5165-v2 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service chaiml-mistral-nemo-dpo-5165-v2 ready after 251.38015699386597s
Pipeline stage MKMLDeployer completed in 251.93s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.690187692642212s
Received healthy response to inference request in 0.8034141063690186s
Received healthy response to inference request in 1.2322468757629395s
Received healthy response to inference request in 1.032099962234497s
Received healthy response to inference request in 1.0392239093780518s
5 requests
0 failed requests
5th percentile: 0.8491512775421143
10th percentile: 0.89488844871521
20th percentile: 0.9863627910614013
30th percentile: 1.033524751663208
40th percentile: 1.0363743305206299
50th percentile: 1.0392239093780518
60th percentile: 1.1164330959320068
70th percentile: 1.1936422824859618
80th percentile: 1.323835039138794
90th percentile: 1.5070113658905029
95th percentile: 1.5985995292663573
99th percentile: 1.671870059967041
mean time: 1.1594345092773437
Pipeline stage StressChecker completed in 7.03s
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 2.54s
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
chaiml-mistral-nemo-dpo-_5165_v2 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 2983.66s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_5165_v2 status is now inactive due to auto deactivation removed underperforming models