developer_uid: NischayDnk
submission_id: chaiml-qwenrp-32b-sft-exp1_v1
model_name: chaiml-qwenrp-32b-sft-exp1_v1
model_group: ChaiML/qwenrp-32b-sft-ex
status: torndown
timestamp: 2025-04-24T11:46:57+00:00
num_battles: 6953
num_wins: 3518
celo_rating: 1289.45
family_friendly_score: 0.5571999999999999
family_friendly_standard_error: 0.007024644617345421
submission_type: basic
model_repo: ChaiML/qwenrp-32b-sft-exp1
model_architecture: Qwen2ForCausalLM
model_num_parameters: 32763417600.0
best_of: 5
max_input_tokens: 768
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.3866640673981663, 'latency_mean': 2.586165430545807, 'latency_p50': 2.5841383934020996, 'latency_p90': 2.877875733375549}, {'batch_size': 3, 'throughput': 0.8770079911581754, 'latency_mean': 3.4150804829597474, 'latency_p50': 3.4064838886260986, 'latency_p90': 3.8308835506439207}, {'batch_size': 5, 'throughput': 1.1931964528294365, 'latency_mean': 4.153479394912719, 'latency_p50': 4.1389665603637695, 'latency_p90': 4.599696302413941}, {'batch_size': 6, 'throughput': 1.2991160337336158, 'latency_mean': 4.584020668268204, 'latency_p50': 4.538585543632507, 'latency_p90': 5.1360328674316404}, {'batch_size': 8, 'throughput': 1.4742955672372182, 'latency_mean': 5.383867212533951, 'latency_p50': 5.365314245223999, 'latency_p90': 6.082773566246033}, {'batch_size': 10, 'throughput': 1.6101040719215984, 'latency_mean': 6.15590022444725, 'latency_p50': 6.1115639209747314, 'latency_p90': 6.98895571231842}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: chaiml-qwenrp-32b-sft-exp1_v1
is_internal_developer: False
language_model: ChaiML/qwenrp-32b-sft-exp1
model_size: 33B
ranking_group: single
throughput_3p7s: 1.02
us_pacific_date: 2025-04-24
win_ratio: 0.5059686466273551
generation_params: {'temperature': 0.45, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 60, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['\n', '<|im_start|>', '<|im_end|>'], 'max_input_tokens': 768, 'best_of': 5, 'max_output_tokens': 64}
formatter: {'memory_template': '<|system|>Family Friendly{memory}\n', 'prompt_template': '', 'bot_template': '<|im_start|>assistant\n{message}<|im_end|>\n', 'user_template': '<|im_start|>user\nYou:{message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n', '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 chaiml-qwenrp-32b-sft-exp1-v1-mkmlizer
Waiting for job on chaiml-qwenrp-32b-sft-exp1-v1-mkmlizer to finish
Retrying (%r) after connection broken by '%r': %s
chaiml-qwenrp-32b-sft-exp1-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-qwenrp-32b-sft-exp1-v1-mkmlizer: ║ _____ __ __ ║
chaiml-qwenrp-32b-sft-exp1-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-qwenrp-32b-sft-exp1-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-qwenrp-32b-sft-exp1-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-qwenrp-32b-sft-exp1-v1-mkmlizer: ║ /___/ ║
chaiml-qwenrp-32b-sft-exp1-v1-mkmlizer: ║ ║
chaiml-qwenrp-32b-sft-exp1-v1-mkmlizer: ║ Version: 0.12.8 ║
chaiml-qwenrp-32b-sft-exp1-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-qwenrp-32b-sft-exp1-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-qwenrp-32b-sft-exp1-v1-mkmlizer: ║ ║
chaiml-qwenrp-32b-sft-exp1-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-qwenrp-32b-sft-exp1-v1-mkmlizer: ║ belonging to: ║
chaiml-qwenrp-32b-sft-exp1-v1-mkmlizer: ║ ║
chaiml-qwenrp-32b-sft-exp1-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-qwenrp-32b-sft-exp1-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-qwenrp-32b-sft-exp1-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-qwenrp-32b-sft-exp1-v1-mkmlizer: ║ ║
chaiml-qwenrp-32b-sft-exp1-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-qwenrp-32b-sft-exp1-v1-mkmlizer: Downloaded to shared memory in 113.728s
chaiml-qwenrp-32b-sft-exp1-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpe4c59uhl, device:0
chaiml-qwenrp-32b-sft-exp1-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-qwenrp-32b-sft-exp1-v1-mkmlizer: quantized model in 64.023s
chaiml-qwenrp-32b-sft-exp1-v1-mkmlizer: Processed model ChaiML/qwenrp-32b-sft-exp1 in 177.751s
chaiml-qwenrp-32b-sft-exp1-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-qwenrp-32b-sft-exp1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-qwenrp-32b-sft-exp1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-qwenrp-32b-sft-exp1-v1
chaiml-qwenrp-32b-sft-exp1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-qwenrp-32b-sft-exp1-v1/config.json
chaiml-qwenrp-32b-sft-exp1-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-qwenrp-32b-sft-exp1-v1/added_tokens.json
chaiml-qwenrp-32b-sft-exp1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-qwenrp-32b-sft-exp1-v1/special_tokens_map.json
chaiml-qwenrp-32b-sft-exp1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-qwenrp-32b-sft-exp1-v1/tokenizer_config.json
chaiml-qwenrp-32b-sft-exp1-v1-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-qwenrp-32b-sft-exp1-v1/merges.txt
chaiml-qwenrp-32b-sft-exp1-v1-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-qwenrp-32b-sft-exp1-v1/vocab.json
chaiml-qwenrp-32b-sft-exp1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-qwenrp-32b-sft-exp1-v1/tokenizer.json
chaiml-qwenrp-32b-sft-exp1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-qwenrp-32b-sft-exp1-v1/flywheel_model.2.safetensors
chaiml-qwenrp-32b-sft-exp1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-qwenrp-32b-sft-exp1-v1/flywheel_model.0.safetensors
chaiml-qwenrp-32b-sft-exp1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-qwenrp-32b-sft-exp1-v1/flywheel_model.1.safetensors
chaiml-qwenrp-32b-sft-exp1-v1-mkmlizer: Loading 0: 0%| | 0/771 [00:00<?, ?it/s] Loading 0: 1%| | 5/771 [00:00<00:20, 36.80it/s] Loading 0: 2%|▏ | 16/771 [00:00<00:11, 68.43it/s] Loading 0: 4%|▎ | 27/771 [00:00<00:09, 80.00it/s] Loading 0: 5%|▍ | 36/771 [00:00<00:08, 82.28it/s] Loading 0: 6%|▌ | 46/771 [00:00<00:13, 54.25it/s] Loading 0: 7%|▋ | 53/771 [00:00<00:15, 46.83it/s] Loading 0: 8%|▊ | 64/771 [00:01<00:12, 58.84it/s] Loading 0: 10%|▉ | 75/771 [00:01<00:10, 68.33it/s] Loading 0: 11%|█ | 83/771 [00:01<00:09, 69.37it/s] Loading 0: 12%|█▏ | 91/771 [00:01<00:10, 65.68it/s] Loading 0: 14%|█▎ | 106/771 [00:01<00:11, 60.02it/s] Loading 0: 15%|█▍ | 113/771 [00:01<00:11, 56.41it/s] Loading 0: 16%|█▌ | 121/771 [00:02<00:11, 56.56it/s] Loading 0: 17%|█▋ | 132/771 [00:02<00:09, 66.53it/s] Loading 0: 18%|█▊ | 142/771 [00:02<00:08, 72.54it/s] Loading 0: 20%|█▉ | 152/771 [00:02<00:07, 77.54it/s] Loading 0: 21%|██ | 161/771 [00:02<00:08, 72.15it/s] Loading 0: 22%|██▏ | 169/771 [00:02<00:12, 49.07it/s] Loading 0: 23%|██▎ | 176/771 [00:02<00:12, 49.47it/s] Loading 0: 24%|██▍ | 184/771 [00:03<00:10, 55.28it/s] Loading 0: 25%|██▌ | 195/771 [00:03<00:08, 67.25it/s] Loading 0: 26%|██▋ | 204/771 [00:03<00:07, 72.65it/s] Loading 0: 28%|██▊ | 213/771 [00:03<00:07, 70.87it/s] Loading 0: 29%|██▉ | 226/771 [00:03<00:08, 62.20it/s] Loading 0: 30%|███ | 233/771 [00:03<00:10, 52.24it/s] Loading 0: 32%|███▏ | 244/771 [00:03<00:08, 63.14it/s] Loading 0: 33%|███▎ | 255/771 [00:04<00:07, 73.02it/s] Loading 0: 34%|███▍ | 264/771 [00:04<00:06, 76.89it/s] Loading 0: 35%|███▌ | 273/771 [00:04<00:06, 72.55it/s] Loading 0: 37%|███▋ | 286/771 [00:04<00:07, 62.67it/s] Loading 0: 38%|███▊ | 294/771 [00:04<00:08, 54.00it/s] Loading 0: 39%|███▉ | 303/771 [00:19<03:42, 2.11it/s] Loading 0: 40%|████ | 311/771 [00:19<02:42, 2.83it/s] Loading 0: 41%|████ | 318/771 [00:19<02:02, 3.71it/s] Loading 0: 43%|████▎ | 329/771 [00:19<01:18, 5.63it/s] Loading 0: 45%|████▍ | 346/771 [00:20<00:45, 9.36it/s] Loading 0: 46%|████▌ | 353/771 [00:20<00:39, 10.55it/s] Loading 0: 47%|████▋ | 364/771 [00:20<00:27, 14.74it/s] Loading 0: 49%|████▊ | 375/771 [00:20<00:19, 20.11it/s] Loading 0: 50%|████▉ | 385/771 [00:20<00:14, 26.10it/s] Loading 0: 51%|█████ | 394/771 [00:20<00:12, 31.30it/s] Loading 0: 53%|█████▎ | 406/771 [00:21<00:10, 35.31it/s] Loading 0: 54%|█████▎ | 413/771 [00:21<00:10, 34.88it/s] Loading 0: 55%|█████▌ | 425/771 [00:21<00:07, 44.03it/s] Loading 0: 57%|█████▋ | 436/771 [00:21<00:06, 53.99it/s] Loading 0: 58%|█████▊ | 448/771 [00:21<00:05, 61.52it/s] Loading 0: 59%|█████▉ | 458/771 [00:21<00:04, 68.73it/s] Loading 0: 61%|██████ | 467/771 [00:22<00:05, 54.24it/s] Loading 0: 62%|██████▏ | 475/771 [00:22<00:05, 52.52it/s] Loading 0: 63%|██████▎ | 485/771 [00:22<00:04, 57.35it/s] Loading 0: 64%|██████▍ | 496/771 [00:22<00:04, 67.98it/s] Loading 0: 66%|██████▌ | 507/771 [00:22<00:03, 77.31it/s] Loading 0: 67%|██████▋ | 517/771 [00:22<00:03, 82.69it/s] Loading 0: 68%|██████▊ | 527/771 [00:22<00:04, 59.67it/s] Loading 0: 69%|██████▉ | 535/771 [00:23<00:04, 56.10it/s] Loading 0: 71%|███████ | 545/771 [00:23<00:03, 60.38it/s] Loading 0: 72%|███████▏ | 556/771 [00:23<00:03, 70.44it/s] Loading 0: 74%|███████▎ | 568/771 [00:23<00:02, 74.44it/s] Loading 0: 75%|███████▍ | 578/771 [00:23<00:02, 79.67it/s] Loading 0: 76%|███████▌ | 587/771 [00:23<00:03, 60.43it/s] Loading 0: 77%|███████▋ | 595/771 [00:24<00:03, 56.52it/s] Loading 0: 78%|███████▊ | 604/771 [00:24<00:02, 63.36it/s] Loading 0: 80%|███████▉ | 615/771 [00:24<00:02, 73.85it/s] Loading 0: 81%|████████ | 624/771 [00:24<00:01, 77.51it/s] Loading 0: 82%|████████▏ | 633/771 [00:38<01:05, 2.11it/s] Loading 0: 84%|████████▍ | 646/771 [00:39<00:38, 3.28it/s] Loading 0: 85%|████████▍ | 654/771 [00:39<00:28, 4.16it/s] Loading 0: 86%|████████▋ | 665/771 [00:39<00:17, 6.02it/s] Loading 0: 88%|████████▊ | 677/771 [00:39<00:10, 8.77it/s] Loading 0: 89%|████████▉ | 689/771 [00:39<00:06, 12.38it/s] Loading 0: 92%|█████████▏| 706/771 [00:40<00:03, 18.13it/s] Loading 0: 93%|█████████▎| 714/771 [00:40<00:02, 20.44it/s] Loading 0: 94%|█████████▍| 725/771 [00:40<00:01, 26.12it/s] Loading 0: 95%|█████████▌| 736/771 [00:40<00:01, 33.58it/s] Loading 0: 97%|█████████▋| 747/771 [00:40<00:00, 42.15it/s] Loading 0: 98%|█████████▊| 756/771 [00:40<00:00, 48.74it/s] Loading 0: 99%|█████████▉| 766/771 [00:48<00:01, 4.15it/s]
Job chaiml-qwenrp-32b-sft-exp1-v1-mkmlizer completed after 207.05s with status: succeeded
Stopping job with name chaiml-qwenrp-32b-sft-exp1-v1-mkmlizer
Pipeline stage MKMLizer completed in 207.58s
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 chaiml-qwenrp-32b-sft-exp1-v1
Waiting for inference service chaiml-qwenrp-32b-sft-exp1-v1 to be ready
Failed to get response for submission chaiml-ghost-girl-letha_81645_v2: HTTPConnectionPool(host='chaiml-ghost-girl-letha-81645-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service chaiml-qwenrp-32b-sft-exp1-v1 ready after 130.4355595111847s
Pipeline stage MKMLDeployer completed in 130.95s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.2631680965423584s
Received healthy response to inference request in 2.7210426330566406s
Received healthy response to inference request in 2.9220452308654785s
Received healthy response to inference request in 2.522982358932495s
Received healthy response to inference request in 2.6441433429718018s
5 requests
0 failed requests
5th percentile: 2.5472145557403563
10th percentile: 2.571446752548218
20th percentile: 2.6199111461639406
30th percentile: 2.6595232009887697
40th percentile: 2.690282917022705
50th percentile: 2.7210426330566406
60th percentile: 2.801443672180176
70th percentile: 2.881844711303711
80th percentile: 2.9902698040008544
90th percentile: 3.1267189502716066
95th percentile: 3.1949435234069825
99th percentile: 3.249523181915283
mean time: 2.8146763324737547
Pipeline stage StressChecker completed in 15.65s
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 0.74s
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 0.80s
Shutdown handler de-registered
chaiml-qwenrp-32b-sft-exp1_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5245.31s
Shutdown handler de-registered
chaiml-qwenrp-32b-sft-exp1_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-qwenrp-32b-sft-exp1_v1 status is now torndown due to DeploymentManager action