zonemercy-graft-librav1e_3684

developer_uid: zonemercy

submission_id: zonemercy-graft-librav1e_3684_v1

model_name: zonemercy-graft-librav1e_3684_v1

model_group: zonemercy/Graft-Librav1E

status: torndown

timestamp: 2024-09-13T10:37:49+00:00

num_battles: 10376

num_wins: 4582

celo_rating: 1201.92

family_friendly_score: 0.0

submission_type: basic

model_repo: zonemercy/Graft-Librav1Elitev2

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6196787380197728, 'latency_mean': 1.6136791741847991, 'latency_p50': 1.6047130823135376, 'latency_p90': 1.7776138305664062}, {'batch_size': 3, 'throughput': 1.0890497455952959, 'latency_mean': 2.7536831998825075, 'latency_p50': 2.7541258335113525, 'latency_p90': 3.0296316385269164}, {'batch_size': 5, 'throughput': 1.2433919740427506, 'latency_mean': 4.006164447069168, 'latency_p50': 4.026402950286865, 'latency_p90': 4.572840332984924}, {'batch_size': 6, 'throughput': 1.2731973579603055, 'latency_mean': 4.686981093883515, 'latency_p50': 4.709554672241211, 'latency_p90': 5.32629292011261}, {'batch_size': 8, 'throughput': 1.2535379770359283, 'latency_mean': 6.3563276553154, 'latency_p50': 6.3573527336120605, 'latency_p90': 7.217028474807739}, {'batch_size': 10, 'throughput': 1.215330535000477, 'latency_mean': 8.181751766204833, 'latency_p50': 8.170941472053528, 'latency_p90': 9.348582887649536}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: zonemercy-graft-librav1e_3684_v1

is_internal_developer: True

language_model: zonemercy/Graft-Librav1Elitev2

model_size: 13B

ranking_group: single

throughput_3p7s: 1.22

us_pacific_date: 2024-09-13

win_ratio: 0.4415959907478797

generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['</s>', 'Bot:', 'User:', 'You:', '<|im_end|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}</s>', 'user_template': '{user_name}: {message}</s>', 'response_template': '{bot_name}:', 'truncate_by_message': True}

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 zonemercy-graft-librav1e-3684-v1-mkmlizer
Waiting for job on zonemercy-graft-librav1e-3684-v1-mkmlizer to finish
Connection pool is full, discarding connection: %s. Connection pool size: %s
zonemercy-graft-librav1e-3684-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
zonemercy-graft-librav1e-3684-v1-mkmlizer: ║     _____            __           __                                ║
zonemercy-graft-librav1e-3684-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
zonemercy-graft-librav1e-3684-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
zonemercy-graft-librav1e-3684-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
zonemercy-graft-librav1e-3684-v1-mkmlizer: ║       /___/                                                         ║
zonemercy-graft-librav1e-3684-v1-mkmlizer: ║                                                                     ║
zonemercy-graft-librav1e-3684-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
zonemercy-graft-librav1e-3684-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
zonemercy-graft-librav1e-3684-v1-mkmlizer: ║  https://mk1.ai                                                     ║
zonemercy-graft-librav1e-3684-v1-mkmlizer: ║                                                                     ║
zonemercy-graft-librav1e-3684-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
zonemercy-graft-librav1e-3684-v1-mkmlizer: ║  belonging to:                                                      ║
zonemercy-graft-librav1e-3684-v1-mkmlizer: ║                                                                     ║
zonemercy-graft-librav1e-3684-v1-mkmlizer: ║  Chai Research Corp.                                                ║
zonemercy-graft-librav1e-3684-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
zonemercy-graft-librav1e-3684-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
zonemercy-graft-librav1e-3684-v1-mkmlizer: ║                                                                     ║
zonemercy-graft-librav1e-3684-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
zonemercy-graft-librav1e-3684-v1-mkmlizer: Downloaded to shared memory in 107.659s
zonemercy-graft-librav1e-3684-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp0ecra5_c, device:0
zonemercy-graft-librav1e-3684-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
zonemercy-graft-librav1e-3684-v1-mkmlizer: quantized model in 40.866s
zonemercy-graft-librav1e-3684-v1-mkmlizer: Processed model zonemercy/Graft-Librav1Elitev2 in 148.524s
zonemercy-graft-librav1e-3684-v1-mkmlizer: creating bucket guanaco-mkml-models
zonemercy-graft-librav1e-3684-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
zonemercy-graft-librav1e-3684-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/zonemercy-graft-librav1e-3684-v1
zonemercy-graft-librav1e-3684-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/zonemercy-graft-librav1e-3684-v1/config.json
zonemercy-graft-librav1e-3684-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/zonemercy-graft-librav1e-3684-v1/special_tokens_map.json
zonemercy-graft-librav1e-3684-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/zonemercy-graft-librav1e-3684-v1/tokenizer_config.json
zonemercy-graft-librav1e-3684-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/zonemercy-graft-librav1e-3684-v1/tokenizer.json
zonemercy-graft-librav1e-3684-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/zonemercy-graft-librav1e-3684-v1/flywheel_model.0.safetensors
zonemercy-graft-librav1e-3684-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 23.70it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:12, 28.82it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:14, 24.82it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:11, 31.26it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:14, 24.03it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:16, 21.04it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:12, 26.94it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:11, 28.13it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:11, 28.69it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:11, 27.99it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 29.85it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 28.90it/s]
Loading 0:  15%|█▌        | 56/363 [00:02<00:10, 29.02it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 25.28it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:13, 21.98it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:11, 26.68it/s]
Loading 0:  20%|█▉        | 72/363 [00:02<00:12, 23.97it/s]
Loading 0:  21%|██        | 77/363 [00:02<00:11, 24.41it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:09, 28.94it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 25.49it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:09, 30.10it/s]
Loading 0:  26%|██▌       | 95/363 [00:03<00:10, 26.32it/s]
Loading 0:  28%|██▊       | 100/363 [00:03<00:08, 30.38it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:12, 20.18it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:10, 24.75it/s]
Loading 0:  31%|███       | 113/363 [00:04<00:10, 22.85it/s]
Loading 0:  33%|███▎      | 118/363 [00:04<00:08, 27.23it/s]
Loading 0:  34%|███▎      | 122/363 [00:04<00:10, 24.01it/s]
Loading 0:  35%|███▍      | 127/363 [00:04<00:08, 28.16it/s]
Loading 0:  36%|███▌      | 131/363 [00:05<00:09, 25.03it/s]
Loading 0:  37%|███▋      | 136/363 [00:05<00:07, 29.59it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:07, 30.47it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:10, 21.31it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:10, 20.83it/s]
Loading 0:  42%|████▏     | 154/363 [00:05<00:08, 25.16it/s]
Loading 0:  44%|████▎     | 158/363 [00:06<00:08, 23.11it/s]
Loading 0:  45%|████▍     | 163/363 [00:06<00:07, 27.52it/s]
Loading 0:  46%|████▌     | 167/363 [00:06<00:07, 24.53it/s]
Loading 0:  47%|████▋     | 172/363 [00:06<00:06, 29.10it/s]
Loading 0:  48%|████▊     | 176/363 [00:06<00:07, 25.71it/s]
Loading 0:  50%|████▉     | 181/363 [00:06<00:06, 29.93it/s]
Loading 0:  51%|█████     | 185/363 [00:07<00:08, 21.07it/s]
Loading 0:  53%|█████▎    | 192/363 [00:07<00:06, 27.60it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 26.88it/s]
Loading 0:  55%|█████▌    | 201/363 [00:07<00:05, 29.91it/s]
Loading 0:  56%|█████▋    | 205/363 [00:07<00:05, 29.60it/s]
Loading 0:  58%|█████▊    | 210/363 [00:07<00:04, 32.02it/s]
Loading 0:  59%|█████▉    | 214/363 [00:08<00:04, 30.55it/s]
Loading 0:  60%|██████    | 218/363 [00:08<00:04, 30.44it/s]
Loading 0:  61%|██████▏   | 223/363 [00:08<00:05, 27.27it/s]
Loading 0:  62%|██████▏   | 226/363 [00:08<00:05, 25.42it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:05, 24.22it/s]
Loading 0:  65%|██████▌   | 237/363 [00:08<00:04, 31.02it/s]
Loading 0:  66%|██████▋   | 241/363 [00:09<00:04, 30.13it/s]
Loading 0:  68%|██████▊   | 246/363 [00:09<00:03, 31.88it/s]
Loading 0:  69%|██████▉   | 250/363 [00:09<00:03, 30.53it/s]
Loading 0:  70%|███████   | 255/363 [00:09<00:03, 32.91it/s]
Loading 0:  71%|███████▏  | 259/363 [00:09<00:03, 30.84it/s]
Loading 0:  72%|███████▏  | 263/363 [00:09<00:04, 24.16it/s]
Loading 0:  73%|███████▎  | 266/363 [00:10<00:04, 21.90it/s]
Loading 0:  75%|███████▌  | 273/363 [00:10<00:03, 28.61it/s]
Loading 0:  76%|███████▋  | 277/363 [00:10<00:03, 27.87it/s]
Loading 0:  78%|███████▊  | 282/363 [00:10<00:02, 29.90it/s]
Loading 0:  79%|███████▉  | 286/363 [00:10<00:02, 29.13it/s]
Loading 0:  80%|████████  | 291/363 [00:10<00:02, 31.56it/s]
Loading 0:  81%|████████▏ | 295/363 [00:10<00:02, 29.86it/s]
Loading 0:  82%|████████▏ | 299/363 [00:11<00:02, 29.82it/s]
Loading 0:  84%|████████▎ | 304/363 [00:11<00:02, 25.74it/s]
Loading 0:  85%|████████▍ | 307/363 [00:11<00:02, 24.53it/s]
Loading 0:  86%|████████▌ | 311/363 [00:11<00:02, 23.50it/s]
Loading 0:  88%|████████▊ | 318/363 [00:11<00:01, 30.59it/s]
Loading 0:  89%|████████▊ | 322/363 [00:11<00:01, 30.00it/s]
Loading 0:  90%|█████████ | 327/363 [00:12<00:01, 32.10it/s]
Loading 0:  91%|█████████ | 331/363 [00:12<00:01, 30.58it/s]
Loading 0:  93%|█████████▎| 336/363 [00:12<00:00, 32.45it/s]
Loading 0:  94%|█████████▎| 340/363 [00:12<00:00, 31.42it/s]
Loading 0:  95%|█████████▍| 344/363 [00:19<00:09,  2.01it/s]
Loading 0:  96%|█████████▌| 348/363 [00:19<00:05,  2.71it/s]
Loading 0:  97%|█████████▋| 353/363 [00:19<00:02,  3.94it/s]
Loading 0:  98%|█████████▊| 357/363 [00:19<00:01,  5.12it/s]
                                                            
Job zonemercy-graft-librav1e-3684-v1-mkmlizer completed after 179.18s with status: succeeded
Stopping job with name zonemercy-graft-librav1e-3684-v1-mkmlizer
Pipeline stage MKMLizer completed in 180.20s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.23s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service zonemercy-graft-librav1e-3684-v1
Waiting for inference service zonemercy-graft-librav1e-3684-v1 to be ready
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
Inference service zonemercy-graft-librav1e-3684-v1 ready after 181.16772413253784s
Pipeline stage MKMLDeployer completed in 181.53s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.999645471572876s
Received healthy response to inference request in 1.6927235126495361s
Received healthy response to inference request in 1.70051908493042s
Received healthy response to inference request in 1.634315013885498s
Received healthy response to inference request in 2.2504374980926514s
5 requests
0 failed requests
5th percentile: 1.6459967136383056
10th percentile: 1.6576784133911133
20th percentile: 1.6810418128967286
30th percentile: 1.694282627105713
40th percentile: 1.6974008560180665
50th percentile: 1.70051908493042
60th percentile: 1.9204864501953125
70th percentile: 2.140453815460205
80th percentile: 2.4002790927886966
90th percentile: 2.699962282180786
95th percentile: 2.849803876876831
99th percentile: 2.969677152633667
mean time: 2.0555281162261965
Pipeline stage StressChecker completed in 11.81s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 6.41s
Shutdown handler de-registered
zonemercy-graft-librav1e_3684_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 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service zonemercy-graft-librav1e-3684-v1-profiler
Waiting for inference service zonemercy-graft-librav1e-3684-v1-profiler to be ready
Inference service zonemercy-graft-librav1e-3684-v1-profiler ready after 180.40010571479797s
Pipeline stage MKMLProfilerDeployer completed in 180.78s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/zonemercy-graft-librdc84d65102120c3790e049f2439e3071-deplolw55r:/code/chaiverse_profiler_1726224472 --namespace tenant-chaiml-guanaco
kubectl exec -it zonemercy-graft-librdc84d65102120c3790e049f2439e3071-deplolw55r --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726224472 && python profiles.py profile --best_of_n 8 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 1024 --output_tokens 64 --summary /code/chaiverse_profiler_1726224472/summary.json'
kubectl exec -it zonemercy-graft-librdc84d65102120c3790e049f2439e3071-deplolw55r --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726224472/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1155.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service zonemercy-graft-librav1e-3684-v1-profiler is running
Tearing down inference service zonemercy-graft-librav1e-3684-v1-profiler
Service zonemercy-graft-librav1e-3684-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.77s
Shutdown handler de-registered
zonemercy-graft-librav1e_3684_v1 status is now inactive due to auto deactivation removed underperforming models
zonemercy-graft-librav1e_3684_v1 status is now torndown due to DeploymentManager action