developer_uid: azuruce
submission_id: chaiml-mistral-nemo-dpo-_5812_v1
model_name: chaiml-mistral-nemo-dpo-_5812_v1
model_group: ChaiML/mistral_nemo_dpo_
status: torndown
timestamp: 2024-12-21T18:54:15+00:00
num_battles: 19669
num_wins: 8774
celo_rating: 1227.05
family_friendly_score: 0.6018
family_friendly_standard_error: 0.006922958327189324
submission_type: basic
model_repo: ChaiML/mistral_nemo_dpo_round2_albert_20241220_v3-checkpoint-1035
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.630180724460016, 'latency_mean': 1.5867602670192718, 'latency_p50': 1.5892446041107178, 'latency_p90': 1.7469687223434447}, {'batch_size': 3, 'throughput': 1.2511631987658924, 'latency_mean': 2.38967680811882, 'latency_p50': 2.3989638090133667, 'latency_p90': 2.648665928840637}, {'batch_size': 5, 'throughput': 1.5880581653473014, 'latency_mean': 3.1274206507205964, 'latency_p50': 3.1088966131210327, 'latency_p90': 3.512423777580261}, {'batch_size': 6, 'throughput': 1.682448172313303, 'latency_mean': 3.54968666434288, 'latency_p50': 3.5461864471435547, 'latency_p90': 3.9882117033004763}, {'batch_size': 8, 'throughput': 1.8578384507203916, 'latency_mean': 4.27915632724762, 'latency_p50': 4.266658663749695, 'latency_p90': 4.880451107025146}, {'batch_size': 10, 'throughput': 1.9254899188616088, 'latency_mean': 5.149360439777374, 'latency_p50': 5.15272057056427, 'latency_p90': 5.784485030174255}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: chaiml-mistral-nemo-dpo-_5812_v1
is_internal_developer: True
language_model: ChaiML/mistral_nemo_dpo_round2_albert_20241220_v3-checkpoint-1035
model_size: 13B
ranking_group: single
throughput_3p7s: 1.73
us_pacific_date: 2024-12-21
win_ratio: 0.44608266815801517
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-5812-v1-mkmlizer
Waiting for job on chaiml-mistral-nemo-dpo-5812-v1-mkmlizer to finish
chaiml-mistral-nemo-dpo-5812-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral-nemo-dpo-5812-v1-mkmlizer: ║ _____ __ __ ║
chaiml-mistral-nemo-dpo-5812-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-mistral-nemo-dpo-5812-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-mistral-nemo-dpo-5812-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-mistral-nemo-dpo-5812-v1-mkmlizer: ║ /___/ ║
chaiml-mistral-nemo-dpo-5812-v1-mkmlizer: ║ ║
chaiml-mistral-nemo-dpo-5812-v1-mkmlizer: ║ Version: 0.11.12 ║
chaiml-mistral-nemo-dpo-5812-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-mistral-nemo-dpo-5812-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-mistral-nemo-dpo-5812-v1-mkmlizer: ║ ║
chaiml-mistral-nemo-dpo-5812-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-mistral-nemo-dpo-5812-v1-mkmlizer: ║ belonging to: ║
chaiml-mistral-nemo-dpo-5812-v1-mkmlizer: ║ ║
chaiml-mistral-nemo-dpo-5812-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-mistral-nemo-dpo-5812-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-mistral-nemo-dpo-5812-v1-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
chaiml-mistral-nemo-dpo-5812-v1-mkmlizer: ║ ║
chaiml-mistral-nemo-dpo-5812-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral-nemo-dpo-5812-v1-mkmlizer: Downloaded to shared memory in 53.577s
chaiml-mistral-nemo-dpo-5812-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmphmbjkxnv, device:0
chaiml-mistral-nemo-dpo-5812-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral-nemo-dpo-5812-v1-mkmlizer: quantized model in 35.899s
chaiml-mistral-nemo-dpo-5812-v1-mkmlizer: Processed model ChaiML/mistral_nemo_dpo_round2_albert_20241220_v3-checkpoint-1035 in 89.477s
chaiml-mistral-nemo-dpo-5812-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral-nemo-dpo-5812-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral-nemo-dpo-5812-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-5812-v1
chaiml-mistral-nemo-dpo-5812-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-5812-v1/config.json
chaiml-mistral-nemo-dpo-5812-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-5812-v1/special_tokens_map.json
chaiml-mistral-nemo-dpo-5812-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-5812-v1/tokenizer_config.json
chaiml-mistral-nemo-dpo-5812-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-5812-v1/tokenizer.json
chaiml-mistral-nemo-dpo-5812-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-5812-v1/flywheel_model.0.safetensors
chaiml-mistral-nemo-dpo-5812-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:12, 28.62it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:07, 48.77it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:07, 44.44it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:07, 43.50it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 49.16it/s] Loading 0: 10%|█ | 37/363 [00:00<00:07, 45.35it/s] Loading 0: 12%|█▏ | 42/363 [00:00<00:07, 43.94it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:06, 48.42it/s] Loading 0: 15%|█▌ | 55/363 [00:01<00:07, 43.87it/s] Loading 0: 17%|█▋ | 60/363 [00:01<00:06, 45.06it/s] Loading 0: 18%|█▊ | 65/363 [00:01<00:09, 30.51it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:07, 36.78it/s] Loading 0: 21%|██▏ | 78/363 [00:01<00:07, 37.54it/s] Loading 0: 23%|██▎ | 83/363 [00:02<00:07, 38.53it/s] Loading 0: 25%|██▍ | 90/363 [00:02<00:06, 43.94it/s] Loading 0: 26%|██▋ | 96/363 [00:02<00:06, 41.56it/s] Loading 0: 28%|██▊ | 101/363 [00:02<00:06, 39.99it/s] Loading 0: 29%|██▉ | 106/363 [00:02<00:06, 40.07it/s] Loading 0: 31%|███ | 112/363 [00:02<00:05, 43.87it/s] Loading 0: 32%|███▏ | 117/363 [00:02<00:05, 41.52it/s] Loading 0: 34%|███▎ | 122/363 [00:02<00:05, 42.50it/s] Loading 0: 35%|███▍ | 127/363 [00:03<00:06, 36.49it/s] Loading 0: 37%|███▋ | 134/363 [00:03<00:05, 43.61it/s] Loading 0: 38%|███▊ | 139/363 [00:03<00:05, 43.74it/s] Loading 0: 40%|███▉ | 144/363 [00:03<00:07, 27.70it/s] Loading 0: 41%|████ | 149/363 [00:03<00:07, 29.75it/s] Loading 0: 43%|████▎ | 156/363 [00:03<00:05, 37.28it/s] Loading 0: 44%|████▍ | 161/363 [00:04<00:05, 38.66it/s] Loading 0: 46%|████▌ | 166/363 [00:04<00:04, 40.22it/s] Loading 0: 47%|████▋ | 171/363 [00:04<00:04, 42.08it/s] Loading 0: 48%|████▊ | 176/363 [00:04<00:05, 36.12it/s] Loading 0: 50%|█████ | 183/363 [00:04<00:04, 43.27it/s] Loading 0: 52%|█████▏ | 188/363 [00:04<00:04, 43.37it/s] Loading 0: 53%|█████▎ | 193/363 [00:04<00:03, 44.70it/s] Loading 0: 55%|█████▍ | 198/363 [00:04<00:03, 45.79it/s] Loading 0: 56%|█████▌ | 203/363 [00:05<00:04, 37.19it/s] Loading 0: 58%|█████▊ | 210/363 [00:05<00:03, 44.66it/s] Loading 0: 59%|█████▉ | 215/363 [00:05<00:03, 44.24it/s] Loading 0: 61%|██████ | 220/363 [00:05<00:03, 45.55it/s] Loading 0: 62%|██████▏ | 225/363 [00:05<00:04, 28.52it/s] Loading 0: 63%|██████▎ | 230/363 [00:05<00:04, 30.50it/s] Loading 0: 65%|██████▌ | 237/363 [00:05<00:03, 37.83it/s] Loading 0: 67%|██████▋ | 242/363 [00:06<00:03, 37.49it/s] Loading 0: 68%|██████▊ | 247/363 [00:06<00:03, 38.65it/s] Loading 0: 69%|██████▉ | 252/363 [00:06<00:02, 41.33it/s] Loading 0: 71%|███████ | 257/363 [00:06<00:03, 35.33it/s] Loading 0: 73%|███████▎ | 264/363 [00:06<00:02, 43.08it/s] Loading 0: 74%|███████▍ | 269/363 [00:06<00:02, 43.50it/s] Loading 0: 75%|███████▌ | 274/363 [00:06<00:02, 44.03it/s] Loading 0: 77%|███████▋ | 280/363 [00:07<00:01, 41.85it/s] Loading 0: 79%|███████▊ | 285/363 [00:07<00:01, 41.07it/s] Loading 0: 80%|████████ | 291/363 [00:07<00:01, 44.91it/s] Loading 0: 82%|████████▏ | 296/363 [00:07<00:01, 44.12it/s] Loading 0: 83%|████████▎ | 301/363 [00:07<00:01, 45.25it/s] Loading 0: 84%|████████▍ | 306/363 [00:14<00:22, 2.49it/s] Loading 0: 85%|████████▌ | 310/363 [00:14<00:16, 3.22it/s] Loading 0: 87%|████████▋ | 314/363 [00:14<00:11, 4.23it/s] Loading 0: 88%|████████▊ | 319/363 [00:14<00:07, 5.94it/s] Loading 0: 89%|████████▉ | 323/363 [00:14<00:05, 7.68it/s] Loading 0: 91%|█████████ | 329/363 [00:14<00:03, 11.17it/s] Loading 0: 92%|█████████▏| 335/363 [00:14<00:01, 14.88it/s] Loading 0: 94%|█████████▎| 340/363 [00:14<00:01, 18.37it/s] Loading 0: 96%|█████████▌| 347/363 [00:15<00:00, 24.76it/s] Loading 0: 97%|█████████▋| 353/363 [00:15<00:00, 27.93it/s] Loading 0: 99%|█████████▊| 358/363 [00:15<00:00, 30.57it/s]
Job chaiml-mistral-nemo-dpo-5812-v1-mkmlizer completed after 114.56s with status: succeeded
Stopping job with name chaiml-mistral-nemo-dpo-5812-v1-mkmlizer
Pipeline stage MKMLizer completed in 115.09s
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 chaiml-mistral-nemo-dpo-5812-v1
Waiting for inference service chaiml-mistral-nemo-dpo-5812-v1 to be ready
Inference service chaiml-mistral-nemo-dpo-5812-v1 ready after 501.8508152961731s
Pipeline stage MKMLDeployer completed in 502.45s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.89388108253479s
Received healthy response to inference request in 0.8047857284545898s
Received healthy response to inference request in 0.9096629619598389s
Received healthy response to inference request in 0.866553544998169s
Received healthy response to inference request in 1.3440985679626465s
5 requests
0 failed requests
5th percentile: 0.8171392917633057
10th percentile: 0.8294928550720215
20th percentile: 0.8541999816894531
30th percentile: 0.8751754283905029
40th percentile: 0.8924191951751709
50th percentile: 0.9096629619598389
60th percentile: 1.083437204360962
70th percentile: 1.257211446762085
80th percentile: 1.4540550708770752
90th percentile: 1.6739680767059326
95th percentile: 1.7839245796203613
99th percentile: 1.8718897819519043
mean time: 1.1637963771820068
Pipeline stage StressChecker completed in 7.18s
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 0.80s
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 0.77s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_5812_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-mistral-nemo-dpo-5812-v1-profiler
Waiting for inference service chaiml-mistral-nemo-dpo-5812-v1-profiler to be ready
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 2487.83s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_5812_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-mistral-nemo-dpo-_5812_v1 status is now torndown due to DeploymentManager action
chaiml-mistral-nemo-dpo-_5812_v1 status is now torndown due to DeploymentManager action
chaiml-mistral-nemo-dpo-_5812_v1 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1