developer_uid: rirv938
submission_id: rirv938-anthropic-20k-6_15373_v1
model_name: rirv938-anthropic-20k-6_15373_v1
model_group: rirv938/anthropic_20k_62
status: torndown
timestamp: 2025-01-02T16:07:41+00:00
num_battles: 19432
num_wins: 9979
celo_rating: 1278.35
family_friendly_score: 0.6006
family_friendly_standard_error: 0.0069264657654535475
submission_type: basic
model_repo: rirv938/anthropic_20k_624_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': 0.6515461274043404, 'latency_mean': 1.534750165939331, 'latency_p50': 1.539441704750061, 'latency_p90': 1.6856348991394043}, {'batch_size': 3, 'throughput': 1.2864424372206729, 'latency_mean': 2.326883875131607, 'latency_p50': 2.3112841844558716, 'latency_p90': 2.527068543434143}, {'batch_size': 5, 'throughput': 1.58895662296893, 'latency_mean': 3.1296986639499664, 'latency_p50': 3.1155511140823364, 'latency_p90': 3.535872387886047}, {'batch_size': 6, 'throughput': 1.6750163781985214, 'latency_mean': 3.569771554470062, 'latency_p50': 3.5788564682006836, 'latency_p90': 3.955218386650085}, {'batch_size': 8, 'throughput': 1.7669553544777286, 'latency_mean': 4.493878016471863, 'latency_p50': 4.472907900810242, 'latency_p90': 5.052438831329345}, {'batch_size': 10, 'throughput': 1.813844679256927, 'latency_mean': 5.456626417636872, 'latency_p50': 5.437151074409485, 'latency_p90': 6.106699061393738}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: rirv938-anthropic-20k-6_15373_v1
is_internal_developer: True
language_model: rirv938/anthropic_20k_624_bo8_80w_dpo5_v2
model_size: 13B
ranking_group: single
throughput_3p7s: 1.7
us_pacific_date: 2025-01-02
win_ratio: 0.5135343762865376
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-6-15373-v1-mkmlizer
Waiting for job on rirv938-anthropic-20k-6-15373-v1-mkmlizer to finish
Failed to get response for submission function_lijit_2024-11-26: ('http://chaiml-elo-alignment-run-3-v44-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:49306->127.0.0.1:8080: read: connection reset by peer\n')
rirv938-anthropic-20k-6-15373-v1-mkmlizer: Downloaded to shared memory in 93.796s
rirv938-anthropic-20k-6-15373-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp5qty31kw, device:0
rirv938-anthropic-20k-6-15373-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-anthropic-20k-6-15373-v1-mkmlizer: quantized model in 44.462s
rirv938-anthropic-20k-6-15373-v1-mkmlizer: Processed model rirv938/anthropic_20k_624_bo8_80w_dpo5_v2 in 138.258s
rirv938-anthropic-20k-6-15373-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-anthropic-20k-6-15373-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-anthropic-20k-6-15373-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-anthropic-20k-6-15373-v1
rirv938-anthropic-20k-6-15373-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-anthropic-20k-6-15373-v1/special_tokens_map.json
rirv938-anthropic-20k-6-15373-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-anthropic-20k-6-15373-v1/config.json
rirv938-anthropic-20k-6-15373-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-anthropic-20k-6-15373-v1/tokenizer_config.json
rirv938-anthropic-20k-6-15373-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-anthropic-20k-6-15373-v1/tokenizer.json
rirv938-anthropic-20k-6-15373-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-anthropic-20k-6-15373-v1/flywheel_model.0.safetensors
rirv938-anthropic-20k-6-15373-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:18, 19.35it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:14, 24.07it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:16, 21.24it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:12, 27.05it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:16, 20.36it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:18, 18.10it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:14, 23.58it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:14, 23.17it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:13, 24.05it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:12, 25.34it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:13, 24.15it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:12, 25.01it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:14, 21.80it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:11, 26.49it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:10, 27.56it/s]
Loading 0:  17%|█▋        | 63/363 [00:02<00:14, 20.29it/s]
Loading 0:  18%|█▊        | 66/363 [00:02<00:14, 20.62it/s]
Loading 0:  19%|█▉        | 69/363 [00:03<00:13, 22.11it/s]
Loading 0:  20%|█▉        | 72/363 [00:03<00:14, 20.35it/s]
Loading 0:  21%|██        | 77/363 [00:03<00:13, 21.22it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:10, 25.74it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:12, 22.55it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:10, 26.46it/s]
Loading 0:  26%|██▌       | 94/363 [00:04<00:09, 26.92it/s]
Loading 0:  27%|██▋       | 97/363 [00:04<00:10, 25.00it/s]
Loading 0:  28%|██▊       | 100/363 [00:04<00:10, 26.02it/s]
Loading 0:  28%|██▊       | 103/363 [00:04<00:13, 19.10it/s]
Loading 0:  29%|██▉       | 106/363 [00:04<00:12, 19.80it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:11, 21.77it/s]
Loading 0:  31%|███       | 113/363 [00:04<00:12, 20.28it/s]
Loading 0:  33%|███▎      | 118/363 [00:05<00:09, 25.32it/s]
Loading 0:  34%|███▎      | 122/363 [00:05<00:11, 21.70it/s]
Loading 0:  35%|███▍      | 127/363 [00:05<00:09, 26.20it/s]
Loading 0:  36%|███▌      | 131/363 [00:05<00:10, 22.88it/s]
Loading 0:  37%|███▋      | 136/363 [00:05<00:08, 27.65it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:07, 28.36it/s]
Loading 0:  40%|███▉      | 145/363 [00:06<00:11, 19.68it/s]
Loading 0:  41%|████      | 148/363 [00:06<00:10, 21.21it/s]
Loading 0:  42%|████▏     | 151/363 [00:06<00:09, 21.49it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:09, 22.46it/s]
Loading 0:  44%|████▎     | 158/363 [00:06<00:09, 20.77it/s]
Loading 0:  45%|████▍     | 163/363 [00:07<00:07, 25.68it/s]
Loading 0:  46%|████▌     | 167/363 [00:07<00:08, 22.84it/s]
Loading 0:  47%|████▋     | 172/363 [00:07<00:07, 27.01it/s]
Loading 0:  48%|████▊     | 176/363 [00:07<00:07, 23.81it/s]
Loading 0:  50%|████▉     | 181/363 [00:07<00:06, 28.13it/s]
Loading 0:  51%|█████     | 185/363 [00:08<00:09, 18.69it/s]
Loading 0:  52%|█████▏    | 190/363 [00:08<00:07, 22.87it/s]
Loading 0:  53%|█████▎    | 194/363 [00:08<00:07, 21.35it/s]
Loading 0:  55%|█████▍    | 199/363 [00:08<00:06, 25.81it/s]
Loading 0:  56%|█████▌    | 203/363 [00:08<00:06, 23.41it/s]
Loading 0:  57%|█████▋    | 208/363 [00:08<00:05, 27.80it/s]
Loading 0:  58%|█████▊    | 212/363 [00:09<00:06, 23.85it/s]
Loading 0:  60%|█████▉    | 217/363 [00:09<00:05, 27.86it/s]
Loading 0:  61%|██████    | 222/363 [00:09<00:04, 28.39it/s]
Loading 0:  62%|██████▏   | 226/363 [00:09<00:06, 20.37it/s]
Loading 0:  63%|██████▎   | 230/363 [00:09<00:06, 19.27it/s]
Loading 0:  65%|██████▍   | 235/363 [00:10<00:05, 23.66it/s]
Loading 0:  66%|██████▌   | 238/363 [00:10<00:05, 24.63it/s]
Loading 0:  66%|██████▋   | 241/363 [00:10<00:05, 23.75it/s]
Loading 0:  67%|██████▋   | 244/363 [00:10<00:04, 25.03it/s]
Loading 0:  68%|██████▊   | 248/363 [00:10<00:05, 22.76it/s]
Loading 0:  70%|██████▉   | 253/363 [00:10<00:04, 27.37it/s]
Loading 0:  71%|███████   | 257/363 [00:11<00:04, 23.73it/s]
Loading 0:  72%|███████▏  | 262/363 [00:11<00:03, 28.08it/s]
Loading 0:  73%|███████▎  | 266/363 [00:11<00:05, 17.79it/s]
Loading 0:  75%|███████▍  | 271/363 [00:11<00:04, 21.72it/s]
Loading 0:  75%|███████▌  | 274/363 [00:11<00:03, 22.91it/s]
Loading 0:  76%|███████▋  | 277/363 [00:11<00:03, 23.09it/s]
Loading 0:  77%|███████▋  | 280/363 [00:12<00:03, 23.85it/s]
Loading 0:  78%|███████▊  | 284/363 [00:12<00:03, 22.02it/s]
Loading 0:  80%|████████  | 291/363 [00:12<00:02, 28.87it/s]
Loading 0:  81%|████████▏ | 295/363 [00:12<00:02, 27.72it/s]
Loading 0:  82%|████████▏ | 299/363 [00:12<00:02, 28.21it/s]
Loading 0:  84%|████████▎ | 304/363 [00:12<00:02, 24.05it/s]
Loading 0:  85%|████████▍ | 307/363 [00:13<00:02, 22.58it/s]
Loading 0:  86%|████████▌ | 311/363 [00:13<00:02, 21.32it/s]
Loading 0:  87%|████████▋ | 316/363 [00:13<00:01, 26.53it/s]
Loading 0:  88%|████████▊ | 320/363 [00:13<00:01, 23.98it/s]
Loading 0:  90%|█████████ | 327/363 [00:13<00:01, 30.24it/s]
Loading 0:  91%|█████████ | 331/363 [00:13<00:01, 29.47it/s]
Loading 0:  93%|█████████▎| 336/363 [00:14<00:00, 31.99it/s]
Loading 0:  94%|█████████▎| 340/363 [00:14<00:00, 30.39it/s]
Loading 0:  95%|█████████▍| 344/363 [00:21<00:09,  1.99it/s]
Loading 0:  96%|█████████▌| 348/363 [00:21<00:05,  2.66it/s]
Loading 0:  97%|█████████▋| 353/363 [00:21<00:02,  3.82it/s]
Loading 0:  98%|█████████▊| 357/363 [00:21<00:01,  4.91it/s]
Loading 0: 100%|█████████▉| 362/363 [00:21<00:00,  6.94it/s]
                                                            

Job rirv938-anthropic-20k-6-15373-v1-mkmlizer completed after 165.42s with status: succeeded
Stopping job with name rirv938-anthropic-20k-6-15373-v1-mkmlizer
Pipeline stage MKMLizer completed in 166.41s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-anthropic-20k-6-15373-v1
Waiting for inference service rirv938-anthropic-20k-6-15373-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service rirv938-anthropic-20k-6-15373-v1 ready after 321.5823073387146s
Pipeline stage MKMLDeployer completed in 322.20s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.210662603378296s
Received healthy response to inference request in 1.7536993026733398s
Received healthy response to inference request in 1.7836811542510986s
Received healthy response to inference request in 1.4784793853759766s
Received healthy response to inference request in 1.3990588188171387s
5 requests
0 failed requests
5th percentile: 1.4149429321289062
10th percentile: 1.4308270454406737
20th percentile: 1.462595272064209
30th percentile: 1.5335233688354493
40th percentile: 1.6436113357543944
50th percentile: 1.7536993026733398
60th percentile: 1.7656920433044434
70th percentile: 1.777684783935547
80th percentile: 1.869077444076538
90th percentile: 2.039870023727417
95th percentile: 2.1252663135528564
99th percentile: 2.193583345413208
mean time: 1.72511625289917
Pipeline stage StressChecker completed in 10.26s
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 0.68s
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 0.74s
Shutdown handler de-registered
rirv938-anthropic-20k-6_15373_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 2620.78s
Shutdown handler de-registered
rirv938-anthropic-20k-6_15373_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-anthropic-20k-6_15373_v1 status is now torndown due to DeploymentManager action
rirv938-anthropic-20k-6_15373_v1 status is now torndown due to DeploymentManager action
rirv938-anthropic-20k-6_15373_v1 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1