dtnewman-trainer-poral-_21067

developer_uid: Jellywibble

submission_id: dtnewman-trainer-poral-_21067_v1

model_name: dtnewman-trainer-poral-_21067_v1

model_group: dtnewman/trainer_poral_2

status: torndown

timestamp: 2025-02-25T01:44:01+00:00

num_battles: 6026

num_wins: 2713

celo_rating: 1230.01

family_friendly_score: 0.6036

family_friendly_standard_error: 0.006917615774238983

submission_type: basic

model_repo: dtnewman/trainer_poral_2025-02-25-checkpoint-1

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.5981363526218343, 'latency_mean': 1.671795904636383, 'latency_p50': 1.6768490076065063, 'latency_p90': 1.845166277885437}, {'batch_size': 3, 'throughput': 1.1053608155045624, 'latency_mean': 2.70724311709404, 'latency_p50': 2.697009563446045, 'latency_p90': 3.0153116464614866}, {'batch_size': 5, 'throughput': 1.3267233705537196, 'latency_mean': 3.7548366034030916, 'latency_p50': 3.773733377456665, 'latency_p90': 4.176976990699768}, {'batch_size': 6, 'throughput': 1.3854730077980044, 'latency_mean': 4.307564511299133, 'latency_p50': 4.297237753868103, 'latency_p90': 4.864100074768066}, {'batch_size': 8, 'throughput': 1.4600408075499134, 'latency_mean': 5.4505944609642025, 'latency_p50': 5.406264662742615, 'latency_p90': 6.12304847240448}, {'batch_size': 10, 'throughput': 1.490099778237248, 'latency_mean': 6.649961000680923, 'latency_p50': 6.625372290611267, 'latency_p90': 7.55344135761261}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: dtnewman-trainer-poral-_21067_v1

is_internal_developer: True

language_model: dtnewman/trainer_poral_2025-02-25-checkpoint-1

model_size: 13B

ranking_group: single

throughput_3p7s: 1.32

us_pacific_date: 2025-02-24

win_ratio: 0.45021573182874214

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 dtnewman-trainer-poral-21067-v1-mkmlizer
Waiting for job on dtnewman-trainer-poral-21067-v1-mkmlizer to finish
dtnewman-trainer-poral-21067-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
dtnewman-trainer-poral-21067-v1-mkmlizer: ║     _____            __           __                                ║
dtnewman-trainer-poral-21067-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
dtnewman-trainer-poral-21067-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
dtnewman-trainer-poral-21067-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
dtnewman-trainer-poral-21067-v1-mkmlizer: ║       /___/                                                         ║
dtnewman-trainer-poral-21067-v1-mkmlizer: ║                                                                     ║
dtnewman-trainer-poral-21067-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
dtnewman-trainer-poral-21067-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
dtnewman-trainer-poral-21067-v1-mkmlizer: ║  https://mk1.ai                                                     ║
dtnewman-trainer-poral-21067-v1-mkmlizer: ║                                                                     ║
dtnewman-trainer-poral-21067-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
dtnewman-trainer-poral-21067-v1-mkmlizer: ║  belonging to:                                                      ║
dtnewman-trainer-poral-21067-v1-mkmlizer: ║                                                                     ║
dtnewman-trainer-poral-21067-v1-mkmlizer: ║  Chai Research Corp.                                                ║
dtnewman-trainer-poral-21067-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
dtnewman-trainer-poral-21067-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
dtnewman-trainer-poral-21067-v1-mkmlizer: ║                                                                     ║
dtnewman-trainer-poral-21067-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
dtnewman-trainer-poral-21067-v1-mkmlizer: Downloaded to shared memory in 56.263s
dtnewman-trainer-poral-21067-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_sixaf2c, device:0
dtnewman-trainer-poral-21067-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
dtnewman-trainer-poral-21067-v1-mkmlizer: quantized model in 35.870s
dtnewman-trainer-poral-21067-v1-mkmlizer: Processed model dtnewman/trainer_poral_2025-02-25-checkpoint-1 in 92.134s
dtnewman-trainer-poral-21067-v1-mkmlizer: creating bucket guanaco-mkml-models
dtnewman-trainer-poral-21067-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
dtnewman-trainer-poral-21067-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/dtnewman-trainer-poral-21067-v1
dtnewman-trainer-poral-21067-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/dtnewman-trainer-poral-21067-v1/tokenizer_config.json
dtnewman-trainer-poral-21067-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/dtnewman-trainer-poral-21067-v1/tokenizer.json
dtnewman-trainer-poral-21067-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/dtnewman-trainer-poral-21067-v1/flywheel_model.0.safetensors
dtnewman-trainer-poral-21067-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 28.26it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 49.88it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 48.29it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:06, 49.86it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 52.31it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:06, 49.89it/s]
Loading 0:  12%|█▏        | 43/363 [00:00<00:06, 50.81it/s]
Loading 0:  13%|█▎        | 49/363 [00:00<00:05, 52.96it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 49.93it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 36.22it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:08, 36.62it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 41.25it/s]
Loading 0:  21%|██        | 77/363 [00:01<00:06, 42.76it/s]
Loading 0:  23%|██▎       | 82/363 [00:01<00:07, 36.47it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:06, 45.34it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:05, 45.18it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:06, 43.31it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:05, 49.75it/s]
Loading 0:  31%|███▏      | 114/363 [00:02<00:05, 46.26it/s]
Loading 0:  33%|███▎      | 119/363 [00:02<00:05, 45.35it/s]
Loading 0:  35%|███▍      | 126/363 [00:02<00:04, 50.18it/s]
Loading 0:  36%|███▋      | 132/363 [00:02<00:04, 46.47it/s]
Loading 0:  38%|███▊      | 137/363 [00:03<00:05, 41.97it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:07, 31.29it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 32.22it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 32.35it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:05, 39.38it/s]
Loading 0:  45%|████▍     | 163/363 [00:03<00:04, 40.08it/s]
Loading 0:  46%|████▋     | 168/363 [00:03<00:04, 41.18it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:04, 46.88it/s]
Loading 0:  50%|████▉     | 181/363 [00:04<00:04, 45.40it/s]
Loading 0:  51%|█████     | 186/363 [00:04<00:04, 43.24it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 48.14it/s]
Loading 0:  55%|█████▍    | 199/363 [00:04<00:03, 46.53it/s]
Loading 0:  56%|█████▌    | 204/363 [00:04<00:03, 44.77it/s]
Loading 0:  58%|█████▊    | 211/363 [00:04<00:03, 49.38it/s]
Loading 0:  60%|█████▉    | 217/363 [00:04<00:03, 46.65it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:03, 35.24it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:03, 35.15it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:03, 33.84it/s]
Loading 0:  66%|██████▌   | 238/363 [00:05<00:03, 40.28it/s]
Loading 0:  67%|██████▋   | 244/363 [00:05<00:02, 40.87it/s]
Loading 0:  69%|██████▊   | 249/363 [00:05<00:02, 38.90it/s]
Loading 0:  70%|███████   | 255/363 [00:05<00:02, 43.41it/s]
Loading 0:  72%|███████▏  | 260/363 [00:06<00:02, 41.70it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:02, 42.51it/s]
Loading 0:  74%|███████▍  | 270/363 [00:06<00:02, 44.40it/s]
Loading 0:  76%|███████▌  | 275/363 [00:06<00:02, 38.98it/s]
Loading 0:  78%|███████▊  | 283/363 [00:06<00:01, 46.98it/s]
Loading 0:  80%|███████▉  | 289/363 [00:06<00:01, 45.90it/s]
Loading 0:  81%|████████  | 294/363 [00:06<00:01, 44.65it/s]
Loading 0:  83%|████████▎ | 302/363 [00:06<00:01, 52.80it/s]
Loading 0:  85%|████████▍ | 308/363 [00:13<00:18,  2.90it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:14,  3.61it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:07,  5.65it/s]
Loading 0:  90%|████████▉ | 325/363 [00:14<00:05,  7.28it/s]
Loading 0:  91%|█████████ | 330/363 [00:14<00:03,  8.96it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 13.33it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:01, 16.46it/s]
Loading 0:  96%|█████████▌| 349/363 [00:14<00:00, 19.32it/s]
Loading 0:  98%|█████████▊| 356/363 [00:14<00:00, 25.06it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 28.03it/s]
                                                            
Job dtnewman-trainer-poral-21067-v1-mkmlizer completed after 113.89s with status: succeeded
Stopping job with name dtnewman-trainer-poral-21067-v1-mkmlizer
Pipeline stage MKMLizer completed in 114.40s
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 dtnewman-trainer-poral-21067-v1
Waiting for inference service dtnewman-trainer-poral-21067-v1 to be ready
Inference service dtnewman-trainer-poral-21067-v1 ready after 251.0128767490387s
Pipeline stage MKMLDeployer completed in 251.54s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1636319160461426s
Received healthy response to inference request in 1.442674160003662s
Received healthy response to inference request in 1.4870214462280273s
Received healthy response to inference request in 1.4312725067138672s
Received healthy response to inference request in 1.5344364643096924s
5 requests
0 failed requests
5th percentile: 1.4335528373718263
10th percentile: 1.4358331680297851
20th percentile: 1.440393829345703
30th percentile: 1.4515436172485352
40th percentile: 1.4692825317382812
50th percentile: 1.4870214462280273
60th percentile: 1.5059874534606934
70th percentile: 1.5249534606933595
80th percentile: 1.6602755546569825
90th percentile: 1.9119537353515625
95th percentile: 2.0377928256988525
99th percentile: 2.1384640979766845
mean time: 1.6118072986602783
Pipeline stage StressChecker completed in 9.50s
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 0.63s
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 0.65s
Shutdown handler de-registered
dtnewman-trainer-poral-_21067_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 dtnewman-trainer-poral-21067-v1-profiler
Waiting for inference service dtnewman-trainer-poral-21067-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 2732.77s
Shutdown handler de-registered
dtnewman-trainer-poral-_21067_v1 status is now inactive due to auto deactivation removed underperforming models
dtnewman-trainer-poral-_21067_v1 status is now torndown due to DeploymentManager action