developer_uid: cycy233
submission_id: cycy233-model3-4_v1
model_name: 486
model_group: cycy233/model3-4
status: torndown
timestamp: 2025-02-27T03:38:03+00:00
num_battles: 5381
num_wins: 2621
celo_rating: 1256.81
family_friendly_score: 0.5078
family_friendly_standard_error: 0.007070207351980563
submission_type: basic
model_repo: cycy233/model3-4
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.8457394143202169, 'latency_mean': 1.182326295375824, 'latency_p50': 1.188400387763977, 'latency_p90': 1.3063506126403808}, {'batch_size': 4, 'throughput': 1.795580451971823, 'latency_mean': 2.2158205735683443, 'latency_p50': 2.227465867996216, 'latency_p90': 2.453787088394165}, {'batch_size': 5, 'throughput': 1.9618449515089553, 'latency_mean': 2.541513396501541, 'latency_p50': 2.5342178344726562, 'latency_p90': 2.8357112884521483}, {'batch_size': 8, 'throughput': 2.1576548703430736, 'latency_mean': 3.6849625623226165, 'latency_p50': 3.709329605102539, 'latency_p90': 4.122655129432678}, {'batch_size': 10, 'throughput': 2.203339148548626, 'latency_mean': 4.508876832723618, 'latency_p50': 4.51630425453186, 'latency_p90': 5.010214924812317}, {'batch_size': 12, 'throughput': 2.2459675288013345, 'latency_mean': 5.29452499628067, 'latency_p50': 5.361230492591858, 'latency_p90': 5.949503970146179}, {'batch_size': 15, 'throughput': 2.2585290257507817, 'latency_mean': 6.551549233198166, 'latency_p50': 6.558933973312378, 'latency_p90': 7.27652382850647}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: 486
is_internal_developer: False
language_model: cycy233/model3-4
model_size: 8B
ranking_group: single
throughput_3p7s: 2.17
us_pacific_date: 2025-02-26
win_ratio: 0.4870841850957071
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.08, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
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}
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 cycy233-model3-4-v1-mkmlizer
Waiting for job on cycy233-model3-4-v1-mkmlizer to finish
cycy233-model3-4-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-model3-4-v1-mkmlizer: ║     _____            __           __                                ║
cycy233-model3-4-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-model3-4-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-model3-4-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-model3-4-v1-mkmlizer: ║       /___/                                                         ║
cycy233-model3-4-v1-mkmlizer: ║                                                                     ║
cycy233-model3-4-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
cycy233-model3-4-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-model3-4-v1-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-model3-4-v1-mkmlizer: ║                                                                     ║
cycy233-model3-4-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-model3-4-v1-mkmlizer: ║  belonging to:                                                      ║
cycy233-model3-4-v1-mkmlizer: ║                                                                     ║
cycy233-model3-4-v1-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-model3-4-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-model3-4-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
cycy233-model3-4-v1-mkmlizer: ║                                                                     ║
cycy233-model3-4-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-model3-4-v1-mkmlizer: Downloaded to shared memory in 33.993s
cycy233-model3-4-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpgjoyxcv9, device:0
cycy233-model3-4-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission nischaydnk-mistral24bas_99124_v4: HTTPConnectionPool(host='nischaydnk-mistral24bas-99124-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
cycy233-model3-4-v1-mkmlizer: quantized model in 27.863s
cycy233-model3-4-v1-mkmlizer: Processed model cycy233/model3-4 in 61.856s
cycy233-model3-4-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-model3-4-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-model3-4-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-model3-4-v1
cycy233-model3-4-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-model3-4-v1/config.json
cycy233-model3-4-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-model3-4-v1/special_tokens_map.json
cycy233-model3-4-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-model3-4-v1/tokenizer_config.json
cycy233-model3-4-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-model3-4-v1/tokenizer.json
cycy233-model3-4-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-model3-4-v1/flywheel_model.0.safetensors
cycy233-model3-4-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:08, 31.93it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:05, 49.79it/s]
Loading 0:   6%|▌         | 18/291 [00:00<00:05, 50.23it/s]
Loading 0:   8%|▊         | 24/291 [00:00<00:06, 39.75it/s]
Loading 0:  10%|█         | 30/291 [00:00<00:05, 44.55it/s]
Loading 0:  12%|█▏        | 35/291 [00:00<00:05, 43.93it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:05, 43.97it/s]
Loading 0:  16%|█▌        | 46/291 [00:01<00:06, 40.76it/s]
Loading 0:  18%|█▊        | 51/291 [00:01<00:05, 40.28it/s]
Loading 0:  20%|█▉        | 57/291 [00:01<00:05, 44.63it/s]
Loading 0:  21%|██▏       | 62/291 [00:01<00:05, 42.83it/s]
Loading 0:  23%|██▎       | 67/291 [00:01<00:05, 42.30it/s]
Loading 0:  25%|██▍       | 72/291 [00:01<00:05, 43.40it/s]
Loading 0:  26%|██▋       | 77/291 [00:01<00:06, 35.40it/s]
Loading 0:  29%|██▊       | 83/291 [00:02<00:07, 29.19it/s]
Loading 0:  30%|██▉       | 87/291 [00:02<00:06, 29.62it/s]
Loading 0:  32%|███▏      | 93/291 [00:02<00:05, 35.51it/s]
Loading 0:  34%|███▎      | 98/291 [00:02<00:05, 37.46it/s]
Loading 0:  35%|███▌      | 103/291 [00:02<00:04, 38.47it/s]
Loading 0:  37%|███▋      | 108/291 [00:02<00:04, 40.44it/s]
Loading 0:  39%|███▉      | 113/291 [00:02<00:05, 33.71it/s]
Loading 0:  41%|████      | 120/291 [00:03<00:04, 40.22it/s]
Loading 0:  43%|████▎     | 125/291 [00:03<00:04, 38.35it/s]
Loading 0:  45%|████▍     | 130/291 [00:03<00:04, 38.29it/s]
Loading 0:  46%|████▋     | 135/291 [00:03<00:03, 40.12it/s]
Loading 0:  48%|████▊     | 140/291 [00:03<00:04, 32.67it/s]
Loading 0:  51%|█████     | 147/291 [00:03<00:03, 39.60it/s]
Loading 0:  52%|█████▏    | 152/291 [00:03<00:03, 39.94it/s]
Loading 0:  54%|█████▍    | 157/291 [00:04<00:03, 39.48it/s]
Loading 0:  56%|█████▌    | 162/291 [00:04<00:03, 40.63it/s]
Loading 0:  57%|█████▋    | 167/291 [00:04<00:03, 33.83it/s]
Loading 0:  59%|█████▉    | 173/291 [00:04<00:03, 37.53it/s]
Loading 0:  62%|██████▏   | 179/291 [00:04<00:02, 40.93it/s]
Loading 0:  63%|██████▎   | 184/291 [00:04<00:02, 40.70it/s]
Loading 0:  65%|██████▍   | 189/291 [00:05<00:03, 25.67it/s]
Loading 0:  67%|██████▋   | 194/291 [00:05<00:03, 27.95it/s]
Loading 0:  69%|██████▉   | 201/291 [00:05<00:02, 34.85it/s]
Loading 0:  71%|███████   | 206/291 [00:05<00:02, 35.81it/s]
Loading 0:  73%|███████▎  | 211/291 [00:05<00:02, 36.40it/s]
Loading 0:  74%|███████▍  | 216/291 [00:05<00:01, 38.22it/s]
Loading 0:  76%|███████▌  | 221/291 [00:05<00:02, 31.55it/s]
Loading 0:  78%|███████▊  | 226/291 [00:06<00:01, 35.05it/s]
Loading 0:  79%|███████▉  | 230/291 [00:06<00:01, 33.48it/s]
Loading 0:  81%|████████▏ | 237/291 [00:06<00:01, 40.26it/s]
Loading 0:  83%|████████▎ | 242/291 [00:06<00:01, 38.24it/s]
Loading 0:  85%|████████▍ | 247/291 [00:06<00:01, 37.77it/s]
Loading 0:  86%|████████▋ | 251/291 [00:06<00:01, 37.74it/s]
Loading 0:  88%|████████▊ | 255/291 [00:06<00:00, 37.98it/s]
Loading 0:  89%|████████▉ | 259/291 [00:06<00:00, 36.71it/s]
Loading 0:  90%|█████████ | 263/291 [00:07<00:00, 37.28it/s]
Loading 0:  92%|█████████▏| 267/291 [00:07<00:00, 34.38it/s]
Loading 0:  94%|█████████▍| 273/291 [00:07<00:00, 39.79it/s]
Loading 0:  96%|█████████▌| 278/291 [00:07<00:00, 39.98it/s]
Loading 0:  97%|█████████▋| 283/291 [00:07<00:00, 33.05it/s]
Loading 0:  99%|█████████▊| 287/291 [00:13<00:01,  2.66it/s]
                                                            

Job cycy233-model3-4-v1-mkmlizer completed after 83.85s with status: succeeded
Stopping job with name cycy233-model3-4-v1-mkmlizer
Pipeline stage MKMLizer completed in 84.36s
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 cycy233-model3-4-v1
Waiting for inference service cycy233-model3-4-v1 to be ready
Failed to get response for submission nischaydnk-mistral24bas_99124_v4: HTTPConnectionPool(host='nischaydnk-mistral24bas-99124-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service cycy233-model3-4-v1 ready after 271.3401789665222s
Pipeline stage MKMLDeployer completed in 271.88s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8576159477233887s
Received healthy response to inference request in 1.2994475364685059s
Received healthy response to inference request in 1.2084147930145264s
Received healthy response to inference request in 1.1912133693695068s
Received healthy response to inference request in 1.5505821704864502s
5 requests
0 failed requests
5th percentile: 1.1946536540985107
10th percentile: 1.1980939388275147
20th percentile: 1.2049745082855225
30th percentile: 1.2266213417053222
40th percentile: 1.2630344390869142
50th percentile: 1.2994475364685059
60th percentile: 1.3999013900756836
70th percentile: 1.5003552436828613
80th percentile: 1.611988925933838
90th percentile: 1.7348024368286132
95th percentile: 1.7962091922760008
99th percentile: 1.8453345966339112
mean time: 1.4214547634124757
Pipeline stage StressChecker completed in 8.35s
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 0.86s
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 0.59s
Shutdown handler de-registered
cycy233-model3-4_v1 status is now deployed due to DeploymentManager action
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 2362.78s
Shutdown handler de-registered
cycy233-model3-4_v1 status is now inactive due to auto deactivation removed underperforming models
cycy233-model3-4_v1 status is now torndown due to DeploymentManager action