developer_uid: NischayDnk
submission_id: chaiml-qwen32b-sft-exp1_16150_v4
model_name: chaiml-qwen32b-sft-exp1_16150_v4
model_group: ChaiML/qwen32b-sft-exp1-
status: torndown
timestamp: 2025-04-14T03:39:26+00:00
num_battles: 6175
num_wins: 2994
celo_rating: 1262.54
family_friendly_score: 0.589
family_friendly_standard_error: 0.006958146304871722
submission_type: basic
model_repo: ChaiML/qwen32b-sft-exp1-noff-datav1-mix8k
model_architecture: Qwen2ForCausalLM
model_num_parameters: 32763417600.0
best_of: 1
max_input_tokens: 512
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.3018123613895509, 'latency_mean': 3.313247812986374, 'latency_p50': 3.3157390356063843, 'latency_p90': 3.7088778257369994}, {'batch_size': 3, 'throughput': 0.7105368916444157, 'latency_mean': 4.1998613166809085, 'latency_p50': 4.187668204307556, 'latency_p90': 4.675947999954223}, {'batch_size': 5, 'throughput': 1.0282982187711336, 'latency_mean': 4.818927235603333, 'latency_p50': 4.837390065193176, 'latency_p90': 5.424085903167724}, {'batch_size': 6, 'throughput': 1.1592977213110556, 'latency_mean': 5.127150934934616, 'latency_p50': 5.150994420051575, 'latency_p90': 5.789529180526733}, {'batch_size': 10, 'throughput': 1.5643678176760232, 'latency_mean': 6.31892582654953, 'latency_p50': 6.249939918518066, 'latency_p90': 7.166585826873779}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: chaiml-qwen32b-sft-exp1_16150_v4
is_internal_developer: False
language_model: ChaiML/qwen32b-sft-exp1-noff-datav1-mix8k
model_size: 33B
ranking_group: single
throughput_3p7s: 0.51
us_pacific_date: 2025-04-13
win_ratio: 0.4848582995951417
generation_params: {'temperature': 0.5, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 60, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['<|im_end|>', '\n'], 'max_input_tokens': 512, 'best_of': 1, 'max_output_tokens': 64}
formatter: {'memory_template': '<|system|>{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-qwen32b-sft-exp1-16150-v4-mkmlizer
Waiting for job on chaiml-qwen32b-sft-exp1-16150-v4-mkmlizer to finish
chaiml-qwen32b-sft-exp1-16150-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-qwen32b-sft-exp1-16150-v4-mkmlizer: ║ _____ __ __ ║
chaiml-qwen32b-sft-exp1-16150-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-qwen32b-sft-exp1-16150-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-qwen32b-sft-exp1-16150-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-qwen32b-sft-exp1-16150-v4-mkmlizer: ║ /___/ ║
chaiml-qwen32b-sft-exp1-16150-v4-mkmlizer: ║ ║
chaiml-qwen32b-sft-exp1-16150-v4-mkmlizer: ║ Version: 0.12.8 ║
chaiml-qwen32b-sft-exp1-16150-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-qwen32b-sft-exp1-16150-v4-mkmlizer: ║ https://mk1.ai ║
chaiml-qwen32b-sft-exp1-16150-v4-mkmlizer: ║ ║
chaiml-qwen32b-sft-exp1-16150-v4-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-qwen32b-sft-exp1-16150-v4-mkmlizer: ║ belonging to: ║
chaiml-qwen32b-sft-exp1-16150-v4-mkmlizer: ║ ║
chaiml-qwen32b-sft-exp1-16150-v4-mkmlizer: ║ Chai Research Corp. ║
chaiml-qwen32b-sft-exp1-16150-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-qwen32b-sft-exp1-16150-v4-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
chaiml-qwen32b-sft-exp1-16150-v4-mkmlizer: ║ ║
chaiml-qwen32b-sft-exp1-16150-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-qwen32b-sft-exp1-16150-v4-mkmlizer: Downloaded to shared memory in 93.328s
chaiml-qwen32b-sft-exp1-16150-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpnwx4wkxa, device:0
chaiml-qwen32b-sft-exp1-16150-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-qwen32b-sft-exp1-16150-v4-mkmlizer: quantized model in 63.081s
chaiml-qwen32b-sft-exp1-16150-v4-mkmlizer: Processed model ChaiML/qwen32b-sft-exp1-noff-datav1-mix8k in 156.409s
chaiml-qwen32b-sft-exp1-16150-v4-mkmlizer: creating bucket guanaco-mkml-models
chaiml-qwen32b-sft-exp1-16150-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-qwen32b-sft-exp1-16150-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-qwen32b-sft-exp1-16150-v4
chaiml-qwen32b-sft-exp1-16150-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-qwen32b-sft-exp1-16150-v4/config.json
chaiml-qwen32b-sft-exp1-16150-v4-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-qwen32b-sft-exp1-16150-v4/added_tokens.json
chaiml-qwen32b-sft-exp1-16150-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-qwen32b-sft-exp1-16150-v4/special_tokens_map.json
chaiml-qwen32b-sft-exp1-16150-v4-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-qwen32b-sft-exp1-16150-v4/merges.txt
chaiml-qwen32b-sft-exp1-16150-v4-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-qwen32b-sft-exp1-16150-v4/vocab.json
chaiml-qwen32b-sft-exp1-16150-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-qwen32b-sft-exp1-16150-v4/tokenizer_config.json
chaiml-qwen32b-sft-exp1-16150-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-qwen32b-sft-exp1-16150-v4/tokenizer.json
chaiml-qwen32b-sft-exp1-16150-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-qwen32b-sft-exp1-16150-v4/flywheel_model.2.safetensors
chaiml-qwen32b-sft-exp1-16150-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-qwen32b-sft-exp1-16150-v4/flywheel_model.0.safetensors
chaiml-qwen32b-sft-exp1-16150-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-qwen32b-sft-exp1-16150-v4/flywheel_model.1.safetensors
chaiml-qwen32b-sft-exp1-16150-v4-mkmlizer: Loading 0: 0%| | 0/771 [00:00<?, ?it/s] Loading 0: 1%| | 5/771 [00:00<00:20, 37.48it/s] Loading 0: 2%|▏ | 16/771 [00:00<00:10, 73.03it/s] Loading 0: 4%|▎ | 27/771 [00:00<00:08, 86.36it/s] Loading 0: 5%|▍ | 36/771 [00:00<00:08, 85.82it/s] Loading 0: 6%|▌ | 46/771 [00:00<00:13, 54.21it/s] Loading 0: 7%|▋ | 53/771 [00:00<00:15, 45.71it/s] Loading 0: 8%|▊ | 64/771 [00:01<00:12, 58.19it/s] Loading 0: 10%|▉ | 75/771 [00:01<00:10, 69.04it/s] Loading 0: 11%|█ | 84/771 [00:01<00:09, 73.40it/s] Loading 0: 12%|█▏ | 93/771 [00:01<00:09, 70.81it/s] Loading 0: 14%|█▎ | 106/771 [00:01<00:10, 60.66it/s] Loading 0: 15%|█▍ | 113/771 [00:01<00:11, 57.55it/s] Loading 0: 16%|█▌ | 121/771 [00:01<00:11, 58.15it/s] Loading 0: 17%|█▋ | 132/771 [00:02<00:09, 69.03it/s] Loading 0: 18%|█▊ | 142/771 [00:02<00:08, 75.92it/s] Loading 0: 20%|█▉ | 152/771 [00:02<00:07, 81.12it/s] Loading 0: 21%|██ | 161/771 [00:02<00:07, 76.28it/s] Loading 0: 22%|██▏ | 170/771 [00:02<00:11, 54.32it/s] Loading 0: 23%|██▎ | 177/771 [00:02<00:11, 53.57it/s] Loading 0: 24%|██▍ | 185/771 [00:02<00:10, 54.57it/s] Loading 0: 25%|██▌ | 196/771 [00:03<00:08, 66.28it/s] Loading 0: 27%|██▋ | 207/771 [00:03<00:07, 75.99it/s] Loading 0: 28%|██▊ | 216/771 [00:03<00:07, 78.77it/s] Loading 0: 29%|██▉ | 226/771 [00:03<00:09, 59.32it/s] Loading 0: 30%|███ | 234/771 [00:03<00:10, 51.49it/s] Loading 0: 32%|███▏ | 244/771 [00:03<00:08, 60.65it/s] Loading 0: 33%|███▎ | 255/771 [00:03<00:07, 71.02it/s] Loading 0: 34%|███▍ | 264/771 [00:04<00:06, 75.12it/s] Loading 0: 35%|███▌ | 273/771 [00:04<00:06, 72.45it/s] Loading 0: 37%|███▋ | 286/771 [00:04<00:07, 62.29it/s] Loading 0: 38%|███▊ | 294/771 [00:04<00:08, 53.64it/s] Loading 0: 39%|███▉ | 303/771 [00:19<03:38, 2.14it/s] Loading 0: 41%|████ | 313/771 [00:19<02:29, 3.07it/s] Loading 0: 42%|████▏ | 321/771 [00:19<01:50, 4.08it/s] Loading 0: 43%|████▎ | 329/771 [00:19<01:20, 5.47it/s] Loading 0: 45%|████▍ | 346/771 [00:19<00:46, 9.12it/s] Loading 0: 46%|████▌ | 353/771 [00:20<00:39, 10.54it/s] Loading 0: 47%|████▋ | 365/771 [00:20<00:26, 15.07it/s] Loading 0: 49%|████▉ | 377/771 [00:20<00:19, 20.68it/s] Loading 0: 50%|█████ | 388/771 [00:20<00:14, 27.26it/s] Loading 0: 52%|█████▏ | 398/771 [00:20<00:10, 33.93it/s] Loading 0: 53%|█████▎ | 407/771 [00:20<00:10, 35.07it/s] Loading 0: 54%|█████▍ | 415/771 [00:20<00:09, 37.57it/s] Loading 0: 55%|█████▌ | 425/771 [00:21<00:07, 44.01it/s] Loading 0: 57%|█████▋ | 436/771 [00:21<00:06, 54.35it/s] Loading 0: 58%|█████▊ | 447/771 [00:21<00:05, 64.54it/s] Loading 0: 59%|█████▉ | 456/771 [00:21<00:04, 69.45it/s] Loading 0: 60%|██████ | 466/771 [00:21<00:05, 56.89it/s] Loading 0: 61%|██████▏ | 474/771 [00:21<00:05, 49.93it/s] Loading 0: 63%|██████▎ | 484/771 [00:21<00:04, 59.14it/s] Loading 0: 64%|██████▍ | 495/771 [00:22<00:03, 69.60it/s] Loading 0: 65%|██████▌ | 504/771 [00:22<00:03, 73.97it/s] Loading 0: 67%|██████▋ | 513/771 [00:22<00:03, 71.63it/s] Loading 0: 68%|██████▊ | 526/771 [00:22<00:04, 60.27it/s] Loading 0: 69%|██████▉ | 533/771 [00:22<00:04, 50.87it/s] Loading 0: 71%|███████ | 544/771 [00:22<00:03, 61.50it/s] Loading 0: 72%|███████▏ | 555/771 [00:23<00:03, 71.38it/s] Loading 0: 73%|███████▎ | 564/771 [00:23<00:02, 75.31it/s] Loading 0: 74%|███████▍ | 573/771 [00:23<00:02, 72.54it/s] Loading 0: 76%|███████▌ | 586/771 [00:23<00:02, 63.27it/s] Loading 0: 77%|███████▋ | 594/771 [00:23<00:03, 54.79it/s] Loading 0: 78%|███████▊ | 604/771 [00:23<00:02, 63.49it/s] Loading 0: 80%|███████▉ | 616/771 [00:23<00:02, 69.47it/s] Loading 0: 81%|████████▏ | 627/771 [00:38<00:59, 2.41it/s] Loading 0: 83%|████████▎ | 637/771 [00:38<00:39, 3.35it/s] Loading 0: 84%|████████▍ | 646/771 [00:38<00:28, 4.43it/s] Loading 0: 85%|████████▍ | 653/771 [00:39<00:21, 5.40it/s] Loading 0: 86%|████████▋ | 665/771 [00:39<00:12, 8.16it/s] Loading 0: 88%|████████▊ | 676/771 [00:39<00:08, 11.61it/s] Loading 0: 89%|████████▉ | 688/771 [00:39<00:05, 16.31it/s] Loading 0: 91%|█████████ | 698/771 [00:39<00:03, 21.35it/s] Loading 0: 92%|█████████▏| 707/771 [00:39<00:02, 24.21it/s] Loading 0: 93%|█████████▎| 715/771 [00:39<00:02, 27.69it/s] Loading 0: 94%|█████████▍| 724/771 [00:40<00:01, 34.54it/s] Loading 0: 95%|█████████▌| 736/771 [00:40<00:00, 43.70it/s] Loading 0: 97%|█████████▋| 747/771 [00:40<00:00, 53.82it/s] Loading 0: 98%|█████████▊| 756/771 [00:40<00:00, 60.12it/s] Loading 0: 99%|█████████▉| 766/771 [00:48<00:01, 4.07it/s]
Job chaiml-qwen32b-sft-exp1-16150-v4-mkmlizer completed after 198.1s with status: succeeded
Stopping job with name chaiml-qwen32b-sft-exp1-16150-v4-mkmlizer
Pipeline stage MKMLizer completed in 198.59s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-qwen32b-sft-exp1-16150-v4
Waiting for inference service chaiml-qwen32b-sft-exp1-16150-v4 to be ready
Failed to get response for submission jellywibble-felix-black_21853_v1: HTTPConnectionPool(host='jellywibble-felix-black-21853-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission jellywibble-felix-black_21853_v1: HTTPConnectionPool(host='jellywibble-felix-black-21853-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission jellywibble-felix-black_21853_v1: HTTPConnectionPool(host='jellywibble-felix-black-21853-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service chaiml-qwen32b-sft-exp1-16150-v4 ready after 120.69035458564758s
Pipeline stage MKMLDeployer completed in 121.24s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.6634888648986816s
Received healthy response to inference request in 3.044750213623047s
Received healthy response to inference request in 3.061960220336914s
Received healthy response to inference request in 3.0486209392547607s
Received healthy response to inference request in 3.0333099365234375s
5 requests
0 failed requests
5th percentile: 3.0355979919433596
10th percentile: 3.037886047363281
20th percentile: 3.042462158203125
30th percentile: 3.0455243587493896
40th percentile: 3.047072649002075
50th percentile: 3.0486209392547607
60th percentile: 3.053956651687622
70th percentile: 3.059292364120483
80th percentile: 3.1822659492492678
90th percentile: 3.4228774070739747
95th percentile: 3.543183135986328
99th percentile: 3.639427719116211
mean time: 3.170426034927368
Pipeline stage StressChecker completed in 17.17s
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 0.66s
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 0.95s
Shutdown handler de-registered
chaiml-qwen32b-sft-exp1_16150_v4 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 0.11s
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 chaiml-qwen32b-sft-exp1-16150-v4-profiler
Waiting for inference service chaiml-qwen32b-sft-exp1-16150-v4-profiler to be ready
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 5261.55s
Shutdown handler de-registered
chaiml-qwen32b-sft-exp1_16150_v4 status is now inactive due to auto deactivation removed underperforming models
chaiml-qwen32b-sft-exp1_16150_v4 status is now torndown due to DeploymentManager action