sanchuanhehe-adjusted-co_6428

developer_uid: sanchuanhehe

submission_id: sanchuanhehe-adjusted-co_6428_v1

model_name: sanchuanhehe-end-try-end_v3

model_group: sanchuanhehe/adjusted_co

status: torndown

timestamp: 2024-09-17T07:52:22+00:00

num_battles: 11205

num_wins: 5031

celo_rating: 1214.03

family_friendly_score: 0.0

submission_type: basic

model_repo: sanchuanhehe/adjusted_config_0_learning_rate_0.0001_lora_r_16_lora_alpha_16_load_in_8bit_0

model_architecture: MistralForCausalLM

model_num_parameters: 7241732096.0

best_of: 16

max_input_tokens: 512

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.9706857566643604, 'latency_mean': 1.030140551328659, 'latency_p50': 1.0203893184661865, 'latency_p90': 1.1495384454727173}, {'batch_size': 4, 'throughput': 1.9129154672456101, 'latency_mean': 2.0829413282871245, 'latency_p50': 2.0827319622039795, 'latency_p90': 2.3207812786102293}, {'batch_size': 5, 'throughput': 2.002613239958542, 'latency_mean': 2.4854584801197053, 'latency_p50': 2.4789782762527466, 'latency_p90': 2.7833229303359985}, {'batch_size': 8, 'throughput': 2.1271686361625375, 'latency_mean': 3.7373433578014374, 'latency_p50': 3.7478532791137695, 'latency_p90': 4.233035016059875}, {'batch_size': 10, 'throughput': 2.1382100374313593, 'latency_mean': 4.62754981637001, 'latency_p50': 4.558455228805542, 'latency_p90': 5.425515246391297}, {'batch_size': 12, 'throughput': 2.1453759976669167, 'latency_mean': 5.519744583368301, 'latency_p50': 5.545544385910034, 'latency_p90': 6.159547924995422}, {'batch_size': 15, 'throughput': 2.115477146252548, 'latency_mean': 6.943816138505936, 'latency_p50': 7.00201678276062, 'latency_p90': 7.812981033325196}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: sanchuanhehe-end-try-end_v3

is_internal_developer: False

language_model: sanchuanhehe/adjusted_config_0_learning_rate_0.0001_lora_r_16_lora_alpha_16_load_in_8bit_0

model_size: 7B

ranking_group: single

throughput_3p7s: 2.14

us_pacific_date: 2024-09-17

win_ratio: 0.44899598393574297

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': 512, 'best_of': 16, '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 sanchuanhehe-adjusted-co-6428-v1-mkmlizer
Waiting for job on sanchuanhehe-adjusted-co-6428-v1-mkmlizer to finish
Failed to get response for submission blend_hokok_2024-09-09: ('http://neversleep-noromaid-v0-8068-v150-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
sanchuanhehe-adjusted-co-6428-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sanchuanhehe-adjusted-co-6428-v1-mkmlizer: ║     _____            __           __                                ║
sanchuanhehe-adjusted-co-6428-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sanchuanhehe-adjusted-co-6428-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sanchuanhehe-adjusted-co-6428-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sanchuanhehe-adjusted-co-6428-v1-mkmlizer: ║       /___/                                                         ║
sanchuanhehe-adjusted-co-6428-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-6428-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
sanchuanhehe-adjusted-co-6428-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sanchuanhehe-adjusted-co-6428-v1-mkmlizer: ║  https://mk1.ai                                                     ║
sanchuanhehe-adjusted-co-6428-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-6428-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
sanchuanhehe-adjusted-co-6428-v1-mkmlizer: ║  belonging to:                                                      ║
sanchuanhehe-adjusted-co-6428-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-6428-v1-mkmlizer: ║  Chai Research Corp.                                                ║
sanchuanhehe-adjusted-co-6428-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sanchuanhehe-adjusted-co-6428-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
sanchuanhehe-adjusted-co-6428-v1-mkmlizer: ║                                                                     ║
sanchuanhehe-adjusted-co-6428-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission blend_hokok_2024-09-09: ('http://neversleep-noromaid-v0-8068-v150-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
sanchuanhehe-adjusted-co-6428-v1-mkmlizer: Downloaded to shared memory in 51.107s
sanchuanhehe-adjusted-co-6428-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp3xouhhxa, device:0
sanchuanhehe-adjusted-co-6428-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sanchuanhehe-adjusted-co-6428-v1-mkmlizer: quantized model in 20.863s
sanchuanhehe-adjusted-co-6428-v1-mkmlizer: Processed model sanchuanhehe/adjusted_config_0_learning_rate_0.0001_lora_r_16_lora_alpha_16_load_in_8bit_0 in 71.971s
sanchuanhehe-adjusted-co-6428-v1-mkmlizer: creating bucket guanaco-mkml-models
sanchuanhehe-adjusted-co-6428-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sanchuanhehe-adjusted-co-6428-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-6428-v1
sanchuanhehe-adjusted-co-6428-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-6428-v1/config.json
sanchuanhehe-adjusted-co-6428-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-6428-v1/tokenizer_config.json
sanchuanhehe-adjusted-co-6428-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-6428-v1/special_tokens_map.json
sanchuanhehe-adjusted-co-6428-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-6428-v1/tokenizer.model
sanchuanhehe-adjusted-co-6428-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-6428-v1/tokenizer.json
sanchuanhehe-adjusted-co-6428-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sanchuanhehe-adjusted-co-6428-v1/flywheel_model.0.safetensors
sanchuanhehe-adjusted-co-6428-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:05, 50.56it/s]
Loading 0:   8%|▊         | 22/291 [00:00<00:03, 85.47it/s]
Loading 0:  12%|█▏        | 34/291 [00:00<00:02, 87.06it/s]
Loading 0:  15%|█▍        | 43/291 [00:00<00:02, 86.76it/s]
Loading 0:  18%|█▊        | 52/291 [00:00<00:02, 81.97it/s]
Loading 0:  21%|██        | 61/291 [00:00<00:02, 84.33it/s]
Loading 0:  26%|██▌       | 76/291 [00:00<00:02, 94.53it/s]
Loading 0:  30%|███       | 88/291 [00:01<00:02, 90.59it/s]
Loading 0:  34%|███▎      | 98/291 [00:02<00:09, 21.30it/s]
Loading 0:  36%|███▋      | 106/291 [00:02<00:07, 25.83it/s]
Loading 0:  40%|███▉      | 116/291 [00:02<00:05, 33.29it/s]
Loading 0:  44%|████▎     | 127/291 [00:02<00:03, 42.94it/s]
Loading 0:  47%|████▋     | 136/291 [00:02<00:03, 47.13it/s]
Loading 0:  50%|████▉     | 145/291 [00:02<00:02, 54.39it/s]
Loading 0:  53%|█████▎    | 154/291 [00:03<00:02, 58.93it/s]
Loading 0:  56%|█████▌    | 163/291 [00:03<00:01, 64.89it/s]
Loading 0:  59%|█████▉    | 172/291 [00:03<00:01, 70.03it/s]
Loading 0:  63%|██████▎   | 184/291 [00:03<00:01, 75.63it/s]
Loading 0:  67%|██████▋   | 196/291 [00:03<00:01, 78.94it/s]
Loading 0:  70%|███████   | 205/291 [00:04<00:04, 20.19it/s]
Loading 0:  74%|███████▎  | 214/291 [00:05<00:03, 25.17it/s]
Loading 0:  77%|███████▋  | 223/291 [00:05<00:02, 30.93it/s]
Loading 0:  80%|███████▉  | 232/291 [00:05<00:01, 37.70it/s]
Loading 0:  85%|████████▍ | 247/291 [00:05<00:00, 50.95it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 53.35it/s]
Loading 0:  92%|█████████▏| 267/291 [00:05<00:00, 63.32it/s]
Loading 0:  95%|█████████▍| 276/291 [00:05<00:00, 68.51it/s]
Loading 0:  98%|█████████▊| 285/291 [00:05<00:00, 70.21it/s]
                                                            
Job sanchuanhehe-adjusted-co-6428-v1-mkmlizer completed after 95.88s with status: succeeded
Stopping job with name sanchuanhehe-adjusted-co-6428-v1-mkmlizer
Pipeline stage MKMLizer completed in 98.00s
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 sanchuanhehe-adjusted-co-6428-v1
Waiting for inference service sanchuanhehe-adjusted-co-6428-v1 to be ready
Failed to get response for submission blend_sinam_2024-09-09: ('http://zonemercy-lexical-nemo-1518-v18-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '{"error":"ValueError : [TypeError(\\"\'numpy.int64\' object is not iterable\\"), TypeError(\'vars() argument must have __dict__ attribute\')]"}')
Failed to get response for submission blend_hokok_2024-09-09: ('http://neversleep-noromaid-v0-8068-v150-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Inference service sanchuanhehe-adjusted-co-6428-v1 ready after 171.81281733512878s
Pipeline stage MKMLDeployer completed in 172.25s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4501049518585205s
Received healthy response to inference request in 2.276632308959961s
Received healthy response to inference request in 1.713843584060669s
Received healthy response to inference request in 2.5737366676330566s
Received healthy response to inference request in 2.623124361038208s
5 requests
0 failed requests
5th percentile: 1.8264013290405274
10th percentile: 1.9389590740203857
20th percentile: 2.1640745639801025
30th percentile: 2.311326837539673
40th percentile: 2.3807158946990965
50th percentile: 2.4501049518585205
60th percentile: 2.499557638168335
70th percentile: 2.5490103244781492
80th percentile: 2.583614206314087
90th percentile: 2.6033692836761473
95th percentile: 2.6132468223571776
99th percentile: 2.6211488533020018
mean time: 2.327488374710083
Pipeline stage StressChecker completed in 12.56s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Pipeline stage TriggerMKMLProfilingPipeline completed in 5.25s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_6428_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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service sanchuanhehe-adjusted-co-6428-v1-profiler
Waiting for inference service sanchuanhehe-adjusted-co-6428-v1-profiler to be ready
Inference service sanchuanhehe-adjusted-co-6428-v1-profiler ready after 180.4403576850891s
Pipeline stage MKMLProfilerDeployer completed in 180.83s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/sanchuanhehe-adjustede38f63f03f41bc99de6822ddff58f63-deplocmxhh:/code/chaiverse_profiler_1726560067 --namespace tenant-chaiml-guanaco
kubectl exec -it sanchuanhehe-adjustede38f63f03f41bc99de6822ddff58f63-deplocmxhh --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726560067 && python profiles.py profile --best_of_n 16 --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 512 --output_tokens 64 --summary /code/chaiverse_profiler_1726560067/summary.json'
kubectl exec -it sanchuanhehe-adjustede38f63f03f41bc99de6822ddff58f63-deplocmxhh --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726560067/summary.json'
Pipeline stage MKMLProfilerRunner completed in 791.79s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service sanchuanhehe-adjusted-co-6428-v1-profiler is running
Tearing down inference service sanchuanhehe-adjusted-co-6428-v1-profiler
Service sanchuanhehe-adjusted-co-6428-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.88s
Shutdown handler de-registered
sanchuanhehe-adjusted-co_6428_v1 status is now inactive due to auto deactivation removed underperforming models
sanchuanhehe-adjusted-co_6428_v1 status is now torndown due to DeploymentManager action