submission_id: rica40325-feedback-merged-7_v1
developer_uid: rica40325
alignment_samples: 11433
alignment_score: -2.1990782211956206
best_of: 16
celo_rating: 1184.92
display_name: rica40325-feedback-and_v1
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}
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}
gpu_counts: {'NVIDIA RTX A5000': 1}
is_internal_developer: False
language_model: rica40325/feedback-merged_7
latencies: [{'batch_size': 1, 'throughput': 0.9052279032739818, 'latency_mean': 1.1046064841747283, 'latency_p50': 1.10163152217865, 'latency_p90': 1.2373410940170289}, {'batch_size': 4, 'throughput': 1.7944708189622782, 'latency_mean': 2.2140306198596953, 'latency_p50': 2.2235352993011475, 'latency_p90': 2.4343116998672487}, {'batch_size': 5, 'throughput': 1.8763466838846203, 'latency_mean': 2.6526072680950166, 'latency_p50': 2.6485347747802734, 'latency_p90': 2.9471156358718873}, {'batch_size': 8, 'throughput': 2.0301649611645103, 'latency_mean': 3.917881076335907, 'latency_p50': 3.9231772422790527, 'latency_p90': 4.413156509399414}, {'batch_size': 10, 'throughput': 2.0200899324705044, 'latency_mean': 4.896845541000366, 'latency_p50': 4.886915326118469, 'latency_p90': 5.672121071815491}, {'batch_size': 12, 'throughput': 2.020351640704433, 'latency_mean': 5.860510776042938, 'latency_p50': 5.876417279243469, 'latency_p90': 6.710529804229736}, {'batch_size': 15, 'throughput': 2.061700842685683, 'latency_mean': 7.1179444789886475, 'latency_p50': 7.234634041786194, 'latency_p90': 7.950069069862366}]
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: rica40325/feedback-merge
model_name: rica40325-feedback-and_v1
model_num_parameters: 8030261248.0
model_repo: rica40325/feedback-merged_7
model_size: 8B
num_battles: 11433
num_wins: 4744
propriety_score: 0.7367864693446089
propriety_total_count: 946.0
ranking_group: single
status: inactive
submission_type: basic
throughput_3p7s: 2.02
timestamp: 2024-09-05T15:41:16+00:00
us_pacific_date: 2024-09-05
win_ratio: 0.4149392110557159
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 rica40325-feedback-merged-7-v1-mkmlizer
Waiting for job on rica40325-feedback-merged-7-v1-mkmlizer to finish
rica40325-feedback-merged-7-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rica40325-feedback-merged-7-v1-mkmlizer: ║     _____            __           __                                ║
rica40325-feedback-merged-7-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rica40325-feedback-merged-7-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rica40325-feedback-merged-7-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rica40325-feedback-merged-7-v1-mkmlizer: ║       /___/                                                         ║
rica40325-feedback-merged-7-v1-mkmlizer: ║                                                                     ║
rica40325-feedback-merged-7-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
rica40325-feedback-merged-7-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rica40325-feedback-merged-7-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rica40325-feedback-merged-7-v1-mkmlizer: ║                                                                     ║
rica40325-feedback-merged-7-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rica40325-feedback-merged-7-v1-mkmlizer: ║  belonging to:                                                      ║
rica40325-feedback-merged-7-v1-mkmlizer: ║                                                                     ║
rica40325-feedback-merged-7-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rica40325-feedback-merged-7-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rica40325-feedback-merged-7-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
rica40325-feedback-merged-7-v1-mkmlizer: ║                                                                     ║
rica40325-feedback-merged-7-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission blend_jidor_2024-08-22: ('http://zonemercy-virgo-edit-v2-1e5-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:41966->127.0.0.1:8080: read: connection reset by peer\n')
rica40325-feedback-merged-7-v1-mkmlizer: Downloaded to shared memory in 60.311s
rica40325-feedback-merged-7-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmppwhdcjxn, device:0
rica40325-feedback-merged-7-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rica40325-feedback-merged-7-v1-mkmlizer: quantized model in 29.111s
rica40325-feedback-merged-7-v1-mkmlizer: Processed model rica40325/feedback-merged_7 in 89.422s
rica40325-feedback-merged-7-v1-mkmlizer: creating bucket guanaco-mkml-models
rica40325-feedback-merged-7-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rica40325-feedback-merged-7-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rica40325-feedback-merged-7-v1
rica40325-feedback-merged-7-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rica40325-feedback-merged-7-v1/config.json
rica40325-feedback-merged-7-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rica40325-feedback-merged-7-v1/special_tokens_map.json
rica40325-feedback-merged-7-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rica40325-feedback-merged-7-v1/tokenizer_config.json
rica40325-feedback-merged-7-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rica40325-feedback-merged-7-v1/tokenizer.json
rica40325-feedback-merged-7-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rica40325-feedback-merged-7-v1/flywheel_model.0.safetensors
rica40325-feedback-merged-7-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:10, 26.42it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:06, 43.99it/s]
Loading 0:   6%|▌         | 17/291 [00:00<00:06, 40.36it/s]
Loading 0:   8%|▊         | 22/291 [00:00<00:06, 40.04it/s]
Loading 0:   9%|▉         | 27/291 [00:00<00:06, 41.55it/s]
Loading 0:  11%|█         | 32/291 [00:00<00:06, 41.47it/s]
Loading 0:  13%|█▎        | 37/291 [00:01<00:09, 26.93it/s]
Loading 0:  14%|█▍        | 41/291 [00:01<00:09, 26.33it/s]
Loading 0:  16%|█▋        | 48/291 [00:01<00:07, 33.57it/s]
Loading 0:  18%|█▊        | 52/291 [00:01<00:07, 33.36it/s]
Loading 0:  20%|█▉        | 57/291 [00:01<00:06, 36.33it/s]
Loading 0:  21%|██        | 61/291 [00:01<00:06, 34.87it/s]
Loading 0:  23%|██▎       | 66/291 [00:01<00:05, 38.25it/s]
Loading 0:  24%|██▍       | 71/291 [00:02<00:05, 37.20it/s]
Loading 0:  26%|██▌       | 75/291 [00:02<00:06, 31.89it/s]
Loading 0:  27%|██▋       | 80/291 [00:02<00:07, 28.41it/s]
Loading 0:  29%|██▉       | 84/291 [00:02<00:07, 27.15it/s]
Loading 0:  31%|███       | 90/291 [00:02<00:06, 32.43it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:06, 31.33it/s]
Loading 0:  34%|███▍      | 99/291 [00:02<00:05, 34.64it/s]
Loading 0:  35%|███▌      | 103/291 [00:03<00:05, 32.12it/s]
Loading 0:  37%|███▋      | 108/291 [00:03<00:05, 35.12it/s]
Loading 0:  38%|███▊      | 112/291 [00:03<00:05, 33.92it/s]
Loading 0:  40%|███▉      | 116/291 [00:03<00:04, 35.16it/s]
Loading 0:  42%|████▏     | 122/291 [00:03<00:04, 40.25it/s]
Loading 0:  44%|████▎     | 127/291 [00:03<00:04, 37.06it/s]
Loading 0:  46%|████▌     | 133/291 [00:03<00:04, 32.22it/s]
Loading 0:  47%|████▋     | 137/291 [00:04<00:04, 31.80it/s]
Loading 0:  48%|████▊     | 141/291 [00:04<00:05, 28.93it/s]
Loading 0:  51%|█████     | 147/291 [00:04<00:04, 34.17it/s]
Loading 0:  52%|█████▏    | 151/291 [00:04<00:04, 31.83it/s]
Loading 0:  54%|█████▎    | 156/291 [00:04<00:04, 32.91it/s]
Loading 0:  55%|█████▍    | 160/291 [00:04<00:04, 31.47it/s]
Loading 0:  57%|█████▋    | 165/291 [00:04<00:03, 33.29it/s]
Loading 0:  58%|█████▊    | 169/291 [00:05<00:03, 32.37it/s]
Loading 0:  60%|█████▉    | 174/291 [00:05<00:03, 34.76it/s]
Loading 0:  61%|██████    | 178/291 [00:05<00:03, 32.91it/s]
Loading 0:  63%|██████▎   | 184/291 [00:05<00:02, 39.36it/s]
Loading 0:  65%|██████▍   | 189/291 [00:05<00:04, 24.78it/s]
Loading 0:  67%|██████▋   | 194/291 [00:05<00:03, 26.03it/s]
Loading 0:  69%|██████▉   | 201/291 [00:06<00:02, 33.09it/s]
Loading 0:  71%|███████   | 206/291 [00:06<00:02, 33.40it/s]
Loading 0:  72%|███████▏  | 210/291 [00:06<00:02, 34.58it/s]
Loading 0:  74%|███████▎  | 214/291 [00:06<00:02, 31.22it/s]
Loading 0:  75%|███████▌  | 219/291 [00:06<00:02, 34.14it/s]
Loading 0:  77%|███████▋  | 223/291 [00:06<00:02, 32.12it/s]
Loading 0:  78%|███████▊  | 227/291 [00:06<00:02, 31.48it/s]
Loading 0:  79%|███████▉  | 231/291 [00:07<00:01, 30.90it/s]
Loading 0:  81%|████████  | 235/291 [00:07<00:02, 23.31it/s]
Loading 0:  82%|████████▏ | 239/291 [00:07<00:02, 23.20it/s]
Loading 0:  85%|████████▍ | 246/291 [00:07<00:01, 30.52it/s]
Loading 0:  86%|████████▌ | 250/291 [00:07<00:01, 30.06it/s]
Loading 0:  87%|████████▋ | 254/291 [00:07<00:01, 30.01it/s]
Loading 0:  89%|████████▊ | 258/291 [00:08<00:01, 28.06it/s]
Loading 0:  91%|█████████ | 264/291 [00:08<00:00, 33.68it/s]
Loading 0:  92%|█████████▏| 268/291 [00:08<00:00, 33.20it/s]
Loading 0:  94%|█████████▍| 273/291 [00:08<00:00, 36.69it/s]
Loading 0:  95%|█████████▌| 277/291 [00:08<00:00, 35.20it/s]
Loading 0:  97%|█████████▋| 281/291 [00:08<00:00, 33.70it/s]
Loading 0:  98%|█████████▊| 286/291 [00:14<00:01,  2.62it/s]
Loading 0:  99%|█████████▉| 289/291 [00:14<00:00,  3.24it/s]
                                                            

Job rica40325-feedback-merged-7-v1-mkmlizer completed after 115.25s with status: succeeded
Stopping job with name rica40325-feedback-merged-7-v1-mkmlizer
Pipeline stage MKMLizer completed in 117.15s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rica40325-feedback-merged-7-v1
Waiting for inference service rica40325-feedback-merged-7-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service rica40325-feedback-merged-7-v1 ready after 141.54334235191345s
Pipeline stage MKMLDeployer completed in 142.03s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9659805297851562s
Received healthy response to inference request in 2.1925852298736572s
Received healthy response to inference request in 1.4517228603363037s
Received healthy response to inference request in 1.736736536026001s
Received healthy response to inference request in 1.511871337890625s
5 requests
0 failed requests
5th percentile: 1.463752555847168
10th percentile: 1.4757822513580323
20th percentile: 1.4998416423797607
30th percentile: 1.5568443775177
40th percentile: 1.6467904567718505
50th percentile: 1.736736536026001
60th percentile: 1.828434133529663
70th percentile: 1.9201317310333252
80th percentile: 2.0113014698028566
90th percentile: 2.101943349838257
95th percentile: 2.147264289855957
99th percentile: 2.183521041870117
mean time: 1.7717792987823486
Pipeline stage StressChecker completed in 9.80s
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 5.69s
Shutdown handler de-registered
rica40325-feedback-merged-7_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 0.15s
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 rica40325-feedback-merged-7-v1-profiler
Waiting for inference service rica40325-feedback-merged-7-v1-profiler to be ready
Inference service rica40325-feedback-merged-7-v1-profiler ready after 140.3456757068634s
Pipeline stage MKMLProfilerDeployer completed in 140.73s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rica40325-feedback-m8babdd26bb2a0435efd7a4993ef2faa6-deplo977s8:/code/chaiverse_profiler_1725551384 --namespace tenant-chaiml-guanaco
kubectl exec -it rica40325-feedback-m8babdd26bb2a0435efd7a4993ef2faa6-deplo977s8 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725551384 && 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_1725551384/summary.json'
kubectl exec -it rica40325-feedback-m8babdd26bb2a0435efd7a4993ef2faa6-deplo977s8 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725551384/summary.json'
Pipeline stage MKMLProfilerRunner completed in 839.28s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rica40325-feedback-merged-7-v1-profiler is running
Tearing down inference service rica40325-feedback-merged-7-v1-profiler
Service rica40325-feedback-merged-7-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.60s
Shutdown handler de-registered
rica40325-feedback-merged-7_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics