developer_uid: rirv938
submission_id: rirv938-anthropic-20k-9_79466_v1
model_name: rirv938-anthropic-20k-9_79466_v1
model_group: rirv938/anthropic_20k_93
status: torndown
timestamp: 2025-01-02T16:07:38+00:00
num_battles: 18801
num_wins: 9821
celo_rating: 1282.12
family_friendly_score: 0.6064
family_friendly_standard_error: 0.006909110507149239
submission_type: basic
model_repo: rirv938/anthropic_20k_936_bo8_80w_dpo5_v2
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 768
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6458538567111721, 'latency_mean': 1.5482810544967651, 'latency_p50': 1.5607517957687378, 'latency_p90': 1.7168642044067384}, {'batch_size': 3, 'throughput': 1.248178021685551, 'latency_mean': 2.3981024026870728, 'latency_p50': 2.4226311445236206, 'latency_p90': 2.630674886703491}, {'batch_size': 5, 'throughput': 1.5391486232995097, 'latency_mean': 3.2437828433513642, 'latency_p50': 3.2454434633255005, 'latency_p90': 3.651212787628174}, {'batch_size': 6, 'throughput': 1.6144113700117269, 'latency_mean': 3.6948525321483614, 'latency_p50': 3.6949310302734375, 'latency_p90': 4.131373357772827}, {'batch_size': 8, 'throughput': 1.71961067285639, 'latency_mean': 4.612054615020752, 'latency_p50': 4.5837507247924805, 'latency_p90': 5.269010829925537}, {'batch_size': 10, 'throughput': 1.7529634616695176, 'latency_mean': 5.673810940980911, 'latency_p50': 5.686405658721924, 'latency_p90': 6.4561219930648805}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: rirv938-anthropic-20k-9_79466_v1
is_internal_developer: True
language_model: rirv938/anthropic_20k_936_bo8_80w_dpo5_v2
model_size: 13B
ranking_group: single
throughput_3p7s: 1.62
us_pacific_date: 2025-01-02
win_ratio: 0.5223658316047018
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_of_text|>', 'You:'], 'max_input_tokens': 768, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '### Response:\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 rirv938-anthropic-20k-9-79466-v1-mkmlizer
Waiting for job on rirv938-anthropic-20k-9-79466-v1-mkmlizer to finish
rirv938-anthropic-20k-9-79466-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-anthropic-20k-9-79466-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-anthropic-20k-9-79466-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-anthropic-20k-9-79466-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-anthropic-20k-9-79466-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-anthropic-20k-9-79466-v1-mkmlizer: ║       /___/                                                         ║
rirv938-anthropic-20k-9-79466-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-20k-9-79466-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
rirv938-anthropic-20k-9-79466-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-anthropic-20k-9-79466-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-anthropic-20k-9-79466-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-20k-9-79466-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-anthropic-20k-9-79466-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-anthropic-20k-9-79466-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-20k-9-79466-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-anthropic-20k-9-79466-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-anthropic-20k-9-79466-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
rirv938-anthropic-20k-9-79466-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-20k-9-79466-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission function_lijit_2024-11-26: HTTPConnectionPool(host='chaiml-llama-8b-multihea-7878-v5-predictor.tenant-chaiml-guanaco.k2.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
rirv938-anthropic-20k-9-79466-v1-mkmlizer: Downloaded to shared memory in 94.216s
rirv938-anthropic-20k-9-79466-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmphvs0vah2, device:0
rirv938-anthropic-20k-9-79466-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-anthropic-20k-9-79466-v1-mkmlizer: quantized model in 45.162s
rirv938-anthropic-20k-9-79466-v1-mkmlizer: Processed model rirv938/anthropic_20k_936_bo8_80w_dpo5_v2 in 139.378s
rirv938-anthropic-20k-9-79466-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-anthropic-20k-9-79466-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-anthropic-20k-9-79466-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-anthropic-20k-9-79466-v1
rirv938-anthropic-20k-9-79466-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-anthropic-20k-9-79466-v1/config.json
rirv938-anthropic-20k-9-79466-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-anthropic-20k-9-79466-v1/special_tokens_map.json
rirv938-anthropic-20k-9-79466-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-anthropic-20k-9-79466-v1/tokenizer_config.json
rirv938-anthropic-20k-9-79466-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-anthropic-20k-9-79466-v1/tokenizer.json
rirv938-anthropic-20k-9-79466-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-anthropic-20k-9-79466-v1/flywheel_model.0.safetensors
rirv938-anthropic-20k-9-79466-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:17, 20.25it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:13, 25.94it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:13, 26.72it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:13, 25.60it/s]
Loading 0:   6%|▌         | 20/363 [00:00<00:11, 29.66it/s]
Loading 0:   7%|▋         | 24/363 [00:01<00:16, 20.36it/s]
Loading 0:   7%|▋         | 27/363 [00:01<00:17, 19.56it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:14, 22.94it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:14, 22.73it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:13, 24.08it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:14, 21.66it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:11, 27.34it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:13, 23.98it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:10, 29.05it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:10, 29.27it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:15, 19.54it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:12, 24.10it/s]
Loading 0:  20%|██        | 73/363 [00:03<00:12, 23.17it/s]
Loading 0:  21%|██        | 77/363 [00:03<00:13, 21.63it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:10, 26.11it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:11, 23.28it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:09, 27.77it/s]
Loading 0:  26%|██▌       | 95/363 [00:03<00:11, 24.17it/s]
Loading 0:  28%|██▊       | 100/363 [00:04<00:09, 28.43it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:14, 18.31it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:11, 22.57it/s]
Loading 0:  31%|███       | 113/363 [00:04<00:12, 20.49it/s]
Loading 0:  33%|███▎      | 118/363 [00:04<00:10, 24.38it/s]
Loading 0:  34%|███▎      | 122/363 [00:05<00:11, 21.63it/s]
Loading 0:  35%|███▍      | 127/363 [00:05<00:09, 25.12it/s]
Loading 0:  36%|███▌      | 131/363 [00:05<00:10, 22.43it/s]
Loading 0:  37%|███▋      | 136/363 [00:05<00:08, 26.39it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:08, 27.06it/s]
Loading 0:  40%|███▉      | 145/363 [00:06<00:11, 19.56it/s]
Loading 0:  41%|████      | 149/363 [00:06<00:11, 18.91it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:09, 23.01it/s]
Loading 0:  44%|████▎     | 158/363 [00:06<00:09, 21.19it/s]
Loading 0:  45%|████▍     | 163/363 [00:06<00:08, 24.79it/s]
Loading 0:  46%|████▌     | 166/363 [00:07<00:07, 25.76it/s]
Loading 0:  47%|████▋     | 169/363 [00:07<00:07, 24.33it/s]
Loading 0:  47%|████▋     | 172/363 [00:07<00:07, 24.41it/s]
Loading 0:  48%|████▊     | 176/363 [00:07<00:08, 21.52it/s]
Loading 0:  50%|████▉     | 181/363 [00:07<00:06, 26.04it/s]
Loading 0:  51%|█████     | 184/363 [00:07<00:09, 19.13it/s]
Loading 0:  52%|█████▏    | 187/363 [00:08<00:08, 19.64it/s]
Loading 0:  52%|█████▏    | 190/363 [00:08<00:08, 21.14it/s]
Loading 0:  53%|█████▎    | 194/363 [00:08<00:08, 19.90it/s]
Loading 0:  55%|█████▍    | 199/363 [00:08<00:06, 24.90it/s]
Loading 0:  56%|█████▌    | 203/363 [00:08<00:07, 22.21it/s]
Loading 0:  57%|█████▋    | 208/363 [00:08<00:05, 26.93it/s]
Loading 0:  58%|█████▊    | 212/363 [00:09<00:06, 22.88it/s]
Loading 0:  60%|█████▉    | 217/363 [00:09<00:05, 27.19it/s]
Loading 0:  61%|██████    | 222/363 [00:09<00:05, 28.14it/s]
Loading 0:  62%|██████▏   | 226/363 [00:09<00:06, 20.11it/s]
Loading 0:  63%|██████▎   | 229/363 [00:09<00:06, 21.65it/s]
Loading 0:  64%|██████▍   | 232/363 [00:09<00:06, 21.52it/s]
Loading 0:  65%|██████▍   | 235/363 [00:10<00:05, 22.65it/s]
Loading 0:  66%|██████▌   | 239/363 [00:10<00:05, 20.75it/s]
Loading 0:  67%|██████▋   | 244/363 [00:10<00:04, 25.54it/s]
Loading 0:  68%|██████▊   | 248/363 [00:10<00:05, 22.65it/s]
Loading 0:  70%|██████▉   | 253/363 [00:10<00:04, 26.85it/s]
Loading 0:  71%|███████   | 257/363 [00:11<00:04, 23.45it/s]
Loading 0:  72%|███████▏  | 262/363 [00:11<00:03, 27.17it/s]
Loading 0:  73%|███████▎  | 266/363 [00:11<00:05, 17.57it/s]
Loading 0:  75%|███████▍  | 271/363 [00:11<00:04, 21.73it/s]
Loading 0:  75%|███████▌  | 274/363 [00:11<00:03, 23.06it/s]
Loading 0:  76%|███████▋  | 277/363 [00:11<00:03, 22.87it/s]
Loading 0:  77%|███████▋  | 280/363 [00:12<00:03, 24.14it/s]
Loading 0:  78%|███████▊  | 283/363 [00:12<00:03, 25.40it/s]
Loading 0:  79%|███████▉  | 286/363 [00:12<00:03, 24.26it/s]
Loading 0:  80%|███████▉  | 289/363 [00:12<00:02, 25.19it/s]
Loading 0:  80%|████████  | 292/363 [00:12<00:02, 26.39it/s]
Loading 0:  81%|████████▏ | 295/363 [00:12<00:02, 24.89it/s]
Loading 0:  82%|████████▏ | 298/363 [00:12<00:02, 25.84it/s]
Loading 0:  83%|████████▎ | 303/363 [00:12<00:02, 27.32it/s]
Loading 0:  84%|████████▍ | 306/363 [00:13<00:03, 17.02it/s]
Loading 0:  85%|████████▌ | 310/363 [00:13<00:02, 20.97it/s]
Loading 0:  86%|████████▌ | 313/363 [00:13<00:02, 21.02it/s]
Loading 0:  87%|████████▋ | 316/363 [00:13<00:02, 22.60it/s]
Loading 0:  88%|████████▊ | 320/363 [00:13<00:02, 20.89it/s]
Loading 0:  90%|████████▉ | 325/363 [00:13<00:01, 26.06it/s]
Loading 0:  91%|█████████ | 329/363 [00:14<00:01, 22.51it/s]
Loading 0:  92%|█████████▏| 334/363 [00:14<00:01, 26.62it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 23.28it/s]
Loading 0:  94%|█████████▍| 343/363 [00:14<00:00, 27.04it/s]
Loading 0:  96%|█████████▌| 347/363 [00:21<00:08,  1.90it/s]
Loading 0:  96%|█████████▋| 350/363 [00:21<00:05,  2.41it/s]
Loading 0:  97%|█████████▋| 353/363 [00:22<00:03,  3.07it/s]
Loading 0:  98%|█████████▊| 357/363 [00:22<00:01,  4.20it/s]
Loading 0: 100%|█████████▉| 362/363 [00:22<00:00,  6.26it/s]
                                                            

Job rirv938-anthropic-20k-9-79466-v1-mkmlizer completed after 166.32s with status: succeeded
Stopping job with name rirv938-anthropic-20k-9-79466-v1-mkmlizer
Pipeline stage MKMLizer completed in 166.82s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.22s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-anthropic-20k-9-79466-v1
Waiting for inference service rirv938-anthropic-20k-9-79466-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
Inference service rirv938-anthropic-20k-9-79466-v1 ready after 311.16044545173645s
Pipeline stage MKMLDeployer completed in 311.72s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.12845516204834s
Received healthy response to inference request in 1.5972743034362793s
Received healthy response to inference request in 1.6858620643615723s
Received healthy response to inference request in 1.8142788410186768s
Received healthy response to inference request in 1.517535924911499s
5 requests
0 failed requests
5th percentile: 1.5334836006164552
10th percentile: 1.549431276321411
20th percentile: 1.5813266277313232
30th percentile: 1.6149918556213378
40th percentile: 1.6504269599914552
50th percentile: 1.6858620643615723
60th percentile: 1.737228775024414
70th percentile: 1.788595485687256
80th percentile: 1.8771141052246094
90th percentile: 2.0027846336364745
95th percentile: 2.065619897842407
99th percentile: 2.115888109207153
mean time: 1.7486812591552734
Pipeline stage StressChecker completed in 9.95s
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 0.72s
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 0.66s
Shutdown handler de-registered
rirv938-anthropic-20k-9_79466_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 2667.65s
Shutdown handler de-registered
rirv938-anthropic-20k-9_79466_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-anthropic-20k-9_79466_v1 status is now torndown due to DeploymentManager action
rirv938-anthropic-20k-9_79466_v1 status is now torndown due to DeploymentManager action
rirv938-anthropic-20k-9_79466_v1 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1