submission_id: jic062-instruct-v19-con_v1
developer_uid: chace9580
alignment_samples: 11681
alignment_score: 0.5083464292905143
best_of: 16
celo_rating: 1247.96
display_name: jic062-dpo-v1-1_v1
formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}:', 'truncate_by_message': False}
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', '|eot_id|', '|end_header_id|'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
gpu_counts: {'NVIDIA RTX A5000': 1}
is_internal_developer: False
language_model: jic062/instruct-v19-con
latencies: [{'batch_size': 1, 'throughput': 0.9046866550452982, 'latency_mean': 1.105264551639557, 'latency_p50': 1.1031291484832764, 'latency_p90': 1.2373622179031372}, {'batch_size': 3, 'throughput': 1.6243727733323317, 'latency_mean': 1.8407535898685454, 'latency_p50': 1.8270982503890991, 'latency_p90': 2.077649712562561}, {'batch_size': 5, 'throughput': 1.7512531324658247, 'latency_mean': 2.8366129100322723, 'latency_p50': 2.840794086456299, 'latency_p90': 3.2025198221206663}, {'batch_size': 6, 'throughput': 1.7892007973182702, 'latency_mean': 3.337230087518692, 'latency_p50': 3.3295676708221436, 'latency_p90': 3.7433563232421876}, {'batch_size': 8, 'throughput': 1.7498339765088966, 'latency_mean': 4.539290220737457, 'latency_p50': 4.50960111618042, 'latency_p90': 5.141216278076172}, {'batch_size': 10, 'throughput': 1.7704331168242264, 'latency_mean': 5.600895929336548, 'latency_p50': 5.545297980308533, 'latency_p90': 6.497097039222718}]
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: jic062/instruct-v19-con
model_name: jic062-dpo-v1-1_v1
model_num_parameters: 8030261248.0
model_repo: jic062/instruct-v19-con
model_size: 8B
num_battles: 11681
num_wins: 5950
propriety_score: 0.7417530631479736
propriety_total_count: 1061.0
ranking_group: single
status: inactive
submission_type: basic
throughput_3p7s: 1.78
timestamp: 2024-09-06T16:10:26+00:00
us_pacific_date: 2024-09-06
win_ratio: 0.5093741974146049
Download Preference Data
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 jic062-instruct-v19-con-v1-mkmlizer
Waiting for job on jic062-instruct-v19-con-v1-mkmlizer to finish
Failed to get response for submission zonemercy-lexical-nemo-_1518_v26: ('http://zonemercy-lexical-nemo-1518-v26-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\')]"}')
jic062-instruct-v19-con-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jic062-instruct-v19-con-v1-mkmlizer: ║     _____            __           __                                ║
jic062-instruct-v19-con-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
jic062-instruct-v19-con-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
jic062-instruct-v19-con-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
jic062-instruct-v19-con-v1-mkmlizer: ║       /___/                                                         ║
jic062-instruct-v19-con-v1-mkmlizer: ║                                                                     ║
jic062-instruct-v19-con-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
jic062-instruct-v19-con-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
jic062-instruct-v19-con-v1-mkmlizer: ║  https://mk1.ai                                                     ║
jic062-instruct-v19-con-v1-mkmlizer: ║                                                                     ║
jic062-instruct-v19-con-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
jic062-instruct-v19-con-v1-mkmlizer: ║  belonging to:                                                      ║
jic062-instruct-v19-con-v1-mkmlizer: ║                                                                     ║
jic062-instruct-v19-con-v1-mkmlizer: ║  Chai Research Corp.                                                ║
jic062-instruct-v19-con-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
jic062-instruct-v19-con-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
jic062-instruct-v19-con-v1-mkmlizer: ║                                                                     ║
jic062-instruct-v19-con-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission zonemercy-lexical-nemo-_1518_v26: ('http://zonemercy-lexical-nemo-1518-v26-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 zonemercy-lexical-nemo-_1518_v27: ('http://zonemercy-lexical-nemo-1518-v27-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\')]"}')
jic062-instruct-v19-con-v1-mkmlizer: Downloaded to shared memory in 35.017s
jic062-instruct-v19-con-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpsharzeb8, device:0
jic062-instruct-v19-con-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission zonemercy-lexical-nemo-_1518_v26: ('http://zonemercy-lexical-nemo-1518-v26-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\')]"}')
jic062-instruct-v19-con-v1-mkmlizer: quantized model in 26.702s
jic062-instruct-v19-con-v1-mkmlizer: Processed model jic062/instruct-v19-con in 61.720s
jic062-instruct-v19-con-v1-mkmlizer: creating bucket guanaco-mkml-models
jic062-instruct-v19-con-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jic062-instruct-v19-con-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jic062-instruct-v19-con-v1
jic062-instruct-v19-con-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jic062-instruct-v19-con-v1/config.json
jic062-instruct-v19-con-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jic062-instruct-v19-con-v1/special_tokens_map.json
jic062-instruct-v19-con-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jic062-instruct-v19-con-v1/tokenizer_config.json
jic062-instruct-v19-con-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jic062-instruct-v19-con-v1/tokenizer.json
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
jic062-instruct-v19-con-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jic062-instruct-v19-con-v1/flywheel_model.0.safetensors
jic062-instruct-v19-con-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:09, 31.46it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:05, 48.98it/s]
Loading 0:   6%|▌         | 18/291 [00:00<00:05, 50.89it/s]
Loading 0:   8%|▊         | 24/291 [00:00<00:06, 40.75it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:05, 48.25it/s]
Loading 0:  13%|█▎        | 37/291 [00:00<00:05, 47.61it/s]
Loading 0:  15%|█▍        | 43/291 [00:00<00:04, 49.90it/s]
Loading 0:  17%|█▋        | 50/291 [00:01<00:05, 44.96it/s]
Loading 0:  20%|█▉        | 58/291 [00:01<00:04, 52.77it/s]
Loading 0:  22%|██▏       | 64/291 [00:01<00:04, 46.95it/s]
Loading 0:  24%|██▍       | 70/291 [00:01<00:04, 47.58it/s]
Loading 0:  26%|██▌       | 76/291 [00:01<00:04, 47.94it/s]
Loading 0:  28%|██▊       | 81/291 [00:01<00:04, 48.11it/s]
Loading 0:  30%|██▉       | 86/291 [00:02<00:07, 29.10it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:05, 38.08it/s]
Loading 0:  34%|███▍      | 100/291 [00:02<00:04, 39.42it/s]
Loading 0:  36%|███▌      | 105/291 [00:02<00:04, 39.98it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:03, 45.70it/s]
Loading 0:  41%|████      | 118/291 [00:02<00:04, 42.78it/s]
Loading 0:  42%|████▏     | 123/291 [00:02<00:03, 43.53it/s]
Loading 0:  45%|████▍     | 130/291 [00:02<00:03, 48.88it/s]
Loading 0:  47%|████▋     | 136/291 [00:03<00:03, 45.17it/s]
Loading 0:  48%|████▊     | 141/291 [00:03<00:03, 44.07it/s]
Loading 0:  51%|█████     | 148/291 [00:03<00:02, 49.85it/s]
Loading 0:  53%|█████▎    | 154/291 [00:03<00:03, 45.04it/s]
Loading 0:  55%|█████▍    | 159/291 [00:03<00:02, 44.59it/s]
Loading 0:  57%|█████▋    | 165/291 [00:03<00:02, 46.95it/s]
Loading 0:  58%|█████▊    | 170/291 [00:03<00:02, 46.47it/s]
Loading 0:  60%|██████    | 175/291 [00:03<00:02, 45.74it/s]
Loading 0:  62%|██████▏   | 181/291 [00:04<00:02, 40.80it/s]
Loading 0:  64%|██████▍   | 187/291 [00:04<00:03, 33.82it/s]
Loading 0:  66%|██████▌   | 191/291 [00:04<00:02, 34.76it/s]
Loading 0:  67%|██████▋   | 195/291 [00:04<00:02, 34.26it/s]
Loading 0:  69%|██████▉   | 201/291 [00:04<00:02, 39.77it/s]
Loading 0:  71%|███████   | 206/291 [00:04<00:02, 40.71it/s]
Loading 0:  73%|███████▎  | 211/291 [00:04<00:01, 41.56it/s]
Loading 0:  75%|███████▍  | 217/291 [00:05<00:01, 41.58it/s]
Loading 0:  76%|███████▋  | 222/291 [00:05<00:01, 42.23it/s]
Loading 0:  79%|███████▊  | 229/291 [00:05<00:01, 48.55it/s]
Loading 0:  80%|████████  | 234/291 [00:05<00:01, 48.65it/s]
Loading 0:  82%|████████▏ | 239/291 [00:05<00:01, 38.92it/s]
Loading 0:  85%|████████▍ | 246/291 [00:05<00:01, 44.84it/s]
Loading 0:  86%|████████▋ | 251/291 [00:05<00:00, 44.25it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 43.16it/s]
Loading 0:  90%|█████████ | 262/291 [00:06<00:00, 41.51it/s]
Loading 0:  92%|█████████▏| 267/291 [00:06<00:00, 40.77it/s]
Loading 0:  94%|█████████▍| 273/291 [00:06<00:00, 44.94it/s]
Loading 0:  96%|█████████▌| 278/291 [00:06<00:00, 43.54it/s]
Loading 0:  97%|█████████▋| 283/291 [00:06<00:00, 37.20it/s]
Loading 0:  99%|█████████▊| 287/291 [00:12<00:01,  2.84it/s]
                                                            

Job jic062-instruct-v19-con-v1-mkmlizer completed after 84.53s with status: succeeded
Stopping job with name jic062-instruct-v19-con-v1-mkmlizer
Pipeline stage MKMLizer completed in 85.90s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.20s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service jic062-instruct-v19-con-v1
Waiting for inference service jic062-instruct-v19-con-v1 to be ready
Failed to get response for submission mistralai-mixtral-8x7b_3473_v131: ('http://mistralai-mixtral-8x7b-3473-v131-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:43198->127.0.0.1:8080: read: connection reset by peer\n')
Failed to get response for submission zonemercy-lexical-nemo-_1518_v26: ('http://zonemercy-lexical-nemo-1518-v26-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 zonemercy-base-story-v1_v8: ('http://zonemercy-base-story-v1-v8-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 zonemercy-base-story-v1_v8: ('http://zonemercy-base-story-v1-v8-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 zonemercy-base-story-v1_v8: ('http://zonemercy-base-story-v1-v8-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:53168->127.0.0.1:8080: read: connection reset by peer\n')
Failed to get response for submission zonemercy-lexical-nemo-_1518_v27: ('http://zonemercy-lexical-nemo-1518-v27-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 zonemercy-base-story-v1_v8: ('http://zonemercy-base-story-v1-v8-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\')]"}')
Inference service jic062-instruct-v19-con-v1 ready after 150.52442502975464s
Pipeline stage MKMLDeployer completed in 151.01s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.374983787536621s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Received healthy response to inference request in 1.5469419956207275s
Received healthy response to inference request in 1.4963862895965576s
Received healthy response to inference request in 2.51005220413208s
Received healthy response to inference request in 1.819288730621338s
5 requests
0 failed requests
5th percentile: 1.5064974308013916
10th percentile: 1.5166085720062257
20th percentile: 1.5368308544158935
30th percentile: 1.6014113426208496
40th percentile: 1.7103500366210938
50th percentile: 1.819288730621338
60th percentile: 2.041566753387451
70th percentile: 2.2638447761535643
80th percentile: 2.401997470855713
90th percentile: 2.4560248374938967
95th percentile: 2.4830385208129884
99th percentile: 2.5046494674682616
mean time: 1.9495306015014648
Pipeline stage StressChecker completed in 10.53s
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 5.58s
Shutdown handler de-registered
jic062-instruct-v19-con_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 0.22s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service jic062-instruct-v19-con-v1-profiler
Waiting for inference service jic062-instruct-v19-con-v1-profiler to be ready
Inference service jic062-instruct-v19-con-v1-profiler ready after 150.39093136787415s
Pipeline stage MKMLProfilerDeployer completed in 150.95s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/jic062-instruct-v19-con-v1-profiler-predictor-00001-deployzfzcs:/code/chaiverse_profiler_1725639487 --namespace tenant-chaiml-guanaco
kubectl exec -it jic062-instruct-v19-con-v1-profiler-predictor-00001-deployzfzcs --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725639487 && 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_1725639487/summary.json'
kubectl exec -it jic062-instruct-v19-con-v1-profiler-predictor-00001-deployzfzcs --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725639487/summary.json'
Pipeline stage MKMLProfilerRunner completed in 804.47s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service jic062-instruct-v19-con-v1-profiler is running
Tearing down inference service jic062-instruct-v19-con-v1-profiler
Service jic062-instruct-v19-con-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.81s
Shutdown handler de-registered
jic062-instruct-v19-con_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics