chaiml-mistral-nemo-dpo-_4679

developer_uid: azuruce

submission_id: chaiml-mistral-nemo-dpo-_4679_v1

model_name: chaiml-mistral-nemo-dpo-_4679_v1

model_group: ChaiML/mistral_nemo_dpo_

status: torndown

timestamp: 2024-12-21T19:18:43+00:00

num_battles: 15886

num_wins: 7395

celo_rating: 1234.42

family_friendly_score: 0.5946

family_friendly_standard_error: 0.006943354232645775

submission_type: basic

model_repo: ChaiML/mistral_nemo_dpo_round2_albert_20241220_v3-checkpoint-207

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.6381560915196057, 'latency_mean': 1.5669467043876648, 'latency_p50': 1.5606999397277832, 'latency_p90': 1.7291444540023804}, {'batch_size': 3, 'throughput': 1.2717848474052484, 'latency_mean': 2.34993816614151, 'latency_p50': 2.3392343521118164, 'latency_p90': 2.6091217279434202}, {'batch_size': 5, 'throughput': 1.6302061033411666, 'latency_mean': 3.056234449148178, 'latency_p50': 3.076686978340149, 'latency_p90': 3.453668928146362}, {'batch_size': 6, 'throughput': 1.7225404276173066, 'latency_mean': 3.465937217473984, 'latency_p50': 3.466017246246338, 'latency_p90': 3.9038771390914917}, {'batch_size': 8, 'throughput': 1.8904926708085408, 'latency_mean': 4.200242546796798, 'latency_p50': 4.215128660202026, 'latency_p90': 4.7506164550781245}, {'batch_size': 10, 'throughput': 1.965454693660235, 'latency_mean': 5.051724792718887, 'latency_p50': 5.039082765579224, 'latency_p90': 5.71035099029541}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-mistral-nemo-dpo-_4679_v1

is_internal_developer: False

language_model: ChaiML/mistral_nemo_dpo_round2_albert_20241220_v3-checkpoint-207

model_size: 13B

ranking_group: single

throughput_3p7s: 1.79

us_pacific_date: 2024-12-21

win_ratio: 0.46550421755004406

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': ['User:', '<|im_end|>', 'You:', '<|eot_id|>', '####', '</s>', '\n', 'Bot:'], '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-4679-v1-mkmlizer
Waiting for job on chaiml-mistral-nemo-dpo-4679-v1-mkmlizer to finish
chaiml-mistral-nemo-dpo-4679-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral-nemo-dpo-4679-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-mistral-nemo-dpo-4679-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-mistral-nemo-dpo-4679-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-mistral-nemo-dpo-4679-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-mistral-nemo-dpo-4679-v1-mkmlizer: ║       /___/                                                         ║
chaiml-mistral-nemo-dpo-4679-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-4679-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-mistral-nemo-dpo-4679-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-mistral-nemo-dpo-4679-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral-nemo-dpo-4679-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-4679-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral-nemo-dpo-4679-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral-nemo-dpo-4679-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-4679-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral-nemo-dpo-4679-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral-nemo-dpo-4679-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-mistral-nemo-dpo-4679-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-4679-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-mistral-nemo-dpo-4679-v1-mkmlizer: Downloaded to shared memory in 55.140s
chaiml-mistral-nemo-dpo-4679-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpwwqjk4n3, device:0
chaiml-mistral-nemo-dpo-4679-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-mistral-nemo-dpo-4679-v1-mkmlizer: quantized model in 37.673s
chaiml-mistral-nemo-dpo-4679-v1-mkmlizer: Processed model ChaiML/mistral_nemo_dpo_round2_albert_20241220_v3-checkpoint-207 in 92.814s
chaiml-mistral-nemo-dpo-4679-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral-nemo-dpo-4679-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral-nemo-dpo-4679-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-4679-v1
chaiml-mistral-nemo-dpo-4679-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-4679-v1/flywheel_model.0.safetensors
chaiml-mistral-nemo-dpo-4679-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:13, 27.38it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 48.37it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 45.07it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 43.71it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 50.21it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:06, 46.83it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 41.95it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:06, 45.09it/s]
Loading 0:  15%|█▍        | 53/363 [00:01<00:07, 43.77it/s]
Loading 0:  17%|█▋        | 60/363 [00:01<00:06, 45.77it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:09, 29.83it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:08, 36.28it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:07, 38.07it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:07, 38.83it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:06, 43.75it/s]
Loading 0:  26%|██▌       | 95/363 [00:02<00:06, 44.61it/s]
Loading 0:  28%|██▊       | 100/363 [00:02<00:07, 36.04it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:06, 39.47it/s]
Loading 0:  31%|███       | 112/363 [00:02<00:05, 42.15it/s]
Loading 0:  32%|███▏      | 117/363 [00:02<00:06, 39.03it/s]
Loading 0:  34%|███▎      | 122/363 [00:02<00:06, 39.78it/s]
Loading 0:  35%|███▍      | 127/363 [00:03<00:07, 31.29it/s]
Loading 0:  37%|███▋      | 134/363 [00:03<00:05, 38.93it/s]
Loading 0:  38%|███▊      | 139/363 [00:03<00:05, 39.61it/s]
Loading 0:  40%|███▉      | 144/363 [00:03<00:08, 25.43it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:07, 26.81it/s]
Loading 0:  43%|████▎     | 157/363 [00:04<00:05, 35.10it/s]
Loading 0:  45%|████▍     | 163/363 [00:04<00:05, 36.30it/s]
Loading 0:  46%|████▋     | 168/363 [00:04<00:05, 36.89it/s]
Loading 0:  48%|████▊     | 174/363 [00:04<00:04, 41.67it/s]
Loading 0:  49%|████▉     | 179/363 [00:04<00:04, 41.81it/s]
Loading 0:  51%|█████     | 184/363 [00:04<00:04, 42.52it/s]
Loading 0:  52%|█████▏    | 189/363 [00:04<00:04, 42.86it/s]
Loading 0:  53%|█████▎    | 194/363 [00:05<00:04, 34.78it/s]
Loading 0:  55%|█████▌    | 201/363 [00:05<00:03, 41.28it/s]
Loading 0:  57%|█████▋    | 206/363 [00:05<00:03, 40.78it/s]
Loading 0:  58%|█████▊    | 211/363 [00:05<00:03, 41.73it/s]
Loading 0:  60%|█████▉    | 216/363 [00:05<00:03, 43.38it/s]
Loading 0:  61%|██████    | 221/363 [00:05<00:03, 42.27it/s]
Loading 0:  62%|██████▏   | 226/363 [00:06<00:05, 24.90it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:05, 25.22it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 32.62it/s]
Loading 0:  67%|██████▋   | 242/363 [00:06<00:03, 34.55it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:03, 36.35it/s]
Loading 0:  69%|██████▉   | 252/363 [00:06<00:02, 37.62it/s]
Loading 0:  71%|███████   | 257/363 [00:06<00:03, 31.94it/s]
Loading 0:  73%|███████▎  | 264/363 [00:07<00:02, 38.08it/s]
Loading 0:  74%|███████▍  | 269/363 [00:07<00:02, 38.62it/s]
Loading 0:  75%|███████▌  | 274/363 [00:07<00:02, 39.49it/s]
Loading 0:  77%|███████▋  | 279/363 [00:07<00:02, 40.74it/s]
Loading 0:  78%|███████▊  | 284/363 [00:07<00:02, 34.34it/s]
Loading 0:  80%|████████  | 291/363 [00:07<00:01, 42.15it/s]
Loading 0:  82%|████████▏ | 296/363 [00:07<00:01, 42.58it/s]
Loading 0:  83%|████████▎ | 302/363 [00:07<00:01, 46.49it/s]
Loading 0:  85%|████████▍ | 307/363 [00:14<00:22,  2.48it/s]
Loading 0:  86%|████████▌ | 312/363 [00:15<00:15,  3.37it/s]
Loading 0:  88%|████████▊ | 320/363 [00:15<00:08,  5.37it/s]
Loading 0:  90%|████████▉ | 325/363 [00:15<00:05,  6.96it/s]
Loading 0:  91%|█████████ | 330/363 [00:15<00:03,  8.68it/s]
Loading 0:  93%|█████████▎| 338/363 [00:15<00:01, 13.01it/s]
Loading 0:  94%|█████████▍| 343/363 [00:15<00:01, 15.72it/s]
Loading 0:  96%|█████████▌| 348/363 [00:15<00:00, 17.18it/s]
Loading 0:  98%|█████████▊| 355/363 [00:16<00:00, 23.25it/s]
Loading 0:  99%|█████████▉| 360/363 [00:16<00:00, 26.57it/s]
                                                            
Job chaiml-mistral-nemo-dpo-4679-v1-mkmlizer completed after 125.17s with status: succeeded
Stopping job with name chaiml-mistral-nemo-dpo-4679-v1-mkmlizer
Pipeline stage MKMLizer completed in 125.65s
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-4679-v1
Waiting for inference service chaiml-mistral-nemo-dpo-4679-v1 to be ready
Inference service chaiml-mistral-nemo-dpo-4679-v1 ready after 260.9938714504242s
Pipeline stage MKMLDeployer completed in 261.50s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 0.9646480083465576s
Received healthy response to inference request in 1.3685190677642822s
Received healthy response to inference request in 1.4323859214782715s
Received healthy response to inference request in 1.4084842205047607s
Received healthy response to inference request in 1.0359928607940674s
5 requests
0 failed requests
5th percentile: 0.9789169788360595
10th percentile: 0.9931859493255615
20th percentile: 1.0217238903045653
30th percentile: 1.1024981021881104
40th percentile: 1.2355085849761962
50th percentile: 1.3685190677642822
60th percentile: 1.3845051288604737
70th percentile: 1.400491189956665
80th percentile: 1.413264560699463
90th percentile: 1.422825241088867
95th percentile: 1.4276055812835693
99th percentile: 1.431429853439331
mean time: 1.2420060157775878
Pipeline stage StressChecker completed in 7.50s
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 0.67s
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 0.62s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_4679_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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-mistral-nemo-dpo-4679-v1-profiler
Waiting for inference service chaiml-mistral-nemo-dpo-4679-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 2399.45s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_4679_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-mistral-nemo-dpo-_4679_v1 status is now torndown due to DeploymentManager action
chaiml-mistral-nemo-dpo-_4679_v1 status is now torndown due to DeploymentManager action
chaiml-mistral-nemo-dpo-_4679_v1 status is now torndown due to DeploymentManager action