developer_uid: NischayDnk
submission_id: chaiml-qwen25-14b-ft-sf_35028_v4
model_name: chaiml-qwen25-14b-ft-sf_35028_v4
model_group: ChaiML/qwen25-14B-ft-sft
status: inactive
timestamp: 2025-04-04T23:19:10+00:00
num_battles: 9232
num_wins: 4462
celo_rating: 1273.76
family_friendly_score: 0.5494
family_friendly_standard_error: 0.007036471274722863
submission_type: basic
model_repo: ChaiML/qwen25-14B-ft-sft-exp2-del12k
model_architecture: Qwen2ForCausalLM
model_num_parameters: 14769689600.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.4693134281402545, 'latency_mean': 2.130705490112305, 'latency_p50': 2.1314421892166138, 'latency_p90': 2.3523189783096314}, {'batch_size': 3, 'throughput': 0.8604592813507885, 'latency_mean': 3.473642864227295, 'latency_p50': 3.4676527976989746, 'latency_p90': 3.8403936862945556}, {'batch_size': 5, 'throughput': 1.0488836205215402, 'latency_mean': 4.736997301578522, 'latency_p50': 4.7486443519592285, 'latency_p90': 5.241353678703308}, {'batch_size': 6, 'throughput': 1.1151295285134863, 'latency_mean': 5.353714209794998, 'latency_p50': 5.356735348701477, 'latency_p90': 6.001351046562195}, {'batch_size': 10, 'throughput': 1.1922969091243691, 'latency_mean': 8.325261310338973, 'latency_p50': 8.332080602645874, 'latency_p90': 9.623687481880188}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: chaiml-qwen25-14b-ft-sf_35028_v4
is_internal_developer: True
language_model: ChaiML/qwen25-14B-ft-sft-exp2-del12k
model_size: 15B
ranking_group: single
throughput_3p7s: 0.91
us_pacific_date: 2025-04-04
win_ratio: 0.48331889081455803
generation_params: {'temperature': 0.9, 'top_p': 0.95, 'min_p': 0.02, 'top_k': 60, 'presence_penalty': 0.2, 'frequency_penalty': 0.2, 'stopping_words': ['\n', '<|im_end|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '', '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-qwen25-14b-ft-sf-35028-v4-mkmlizer
Waiting for job on chaiml-qwen25-14b-ft-sf-35028-v4-mkmlizer to finish
chaiml-qwen25-14b-ft-sf-35028-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-qwen25-14b-ft-sf-35028-v4-mkmlizer: ║ _____ __ __ ║
chaiml-qwen25-14b-ft-sf-35028-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-qwen25-14b-ft-sf-35028-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-qwen25-14b-ft-sf-35028-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-qwen25-14b-ft-sf-35028-v4-mkmlizer: ║ /___/ ║
chaiml-qwen25-14b-ft-sf-35028-v4-mkmlizer: ║ ║
chaiml-qwen25-14b-ft-sf-35028-v4-mkmlizer: ║ Version: 0.12.8 ║
chaiml-qwen25-14b-ft-sf-35028-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-qwen25-14b-ft-sf-35028-v4-mkmlizer: ║ https://mk1.ai ║
chaiml-qwen25-14b-ft-sf-35028-v4-mkmlizer: ║ ║
chaiml-qwen25-14b-ft-sf-35028-v4-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-qwen25-14b-ft-sf-35028-v4-mkmlizer: ║ belonging to: ║
chaiml-qwen25-14b-ft-sf-35028-v4-mkmlizer: ║ ║
chaiml-qwen25-14b-ft-sf-35028-v4-mkmlizer: ║ Chai Research Corp. ║
chaiml-qwen25-14b-ft-sf-35028-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-qwen25-14b-ft-sf-35028-v4-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
chaiml-qwen25-14b-ft-sf-35028-v4-mkmlizer: ║ ║
chaiml-qwen25-14b-ft-sf-35028-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-qwen25-14b-ft-sf-35028-v4-mkmlizer: Downloaded to shared memory in 43.937s
chaiml-qwen25-14b-ft-sf-35028-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpxll2xsdb, device:0
chaiml-qwen25-14b-ft-sf-35028-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-qwen25-14b-ft-sf-35028-v4-mkmlizer: quantized model in 36.021s
chaiml-qwen25-14b-ft-sf-35028-v4-mkmlizer: Processed model ChaiML/qwen25-14B-ft-sft-exp2-del12k in 79.959s
chaiml-qwen25-14b-ft-sf-35028-v4-mkmlizer: creating bucket guanaco-mkml-models
chaiml-qwen25-14b-ft-sf-35028-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-qwen25-14b-ft-sf-35028-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-qwen25-14b-ft-sf-35028-v4
chaiml-qwen25-14b-ft-sf-35028-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-qwen25-14b-ft-sf-35028-v4/config.json
chaiml-qwen25-14b-ft-sf-35028-v4-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-qwen25-14b-ft-sf-35028-v4/added_tokens.json
chaiml-qwen25-14b-ft-sf-35028-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-qwen25-14b-ft-sf-35028-v4/tokenizer_config.json
chaiml-qwen25-14b-ft-sf-35028-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-qwen25-14b-ft-sf-35028-v4/special_tokens_map.json
chaiml-qwen25-14b-ft-sf-35028-v4-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-qwen25-14b-ft-sf-35028-v4/merges.txt
chaiml-qwen25-14b-ft-sf-35028-v4-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-qwen25-14b-ft-sf-35028-v4/vocab.json
chaiml-qwen25-14b-ft-sf-35028-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-qwen25-14b-ft-sf-35028-v4/tokenizer.json
chaiml-qwen25-14b-ft-sf-35028-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-qwen25-14b-ft-sf-35028-v4/flywheel_model.1.safetensors
chaiml-qwen25-14b-ft-sf-35028-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-qwen25-14b-ft-sf-35028-v4/flywheel_model.0.safetensors
chaiml-qwen25-14b-ft-sf-35028-v4-mkmlizer: Loading 0: 0%| | 0/579 [00:00<?, ?it/s] Loading 0: 3%|▎ | 15/579 [00:00<00:04, 140.66it/s] Loading 0: 5%|▌ | 30/579 [00:00<00:04, 127.49it/s] Loading 0: 8%|▊ | 47/579 [00:00<00:03, 144.76it/s] Loading 0: 11%|█ | 63/579 [00:00<00:03, 147.97it/s] Loading 0: 14%|█▍ | 81/579 [00:00<00:05, 94.79it/s] Loading 0: 16%|█▌ | 94/579 [00:00<00:04, 101.55it/s] Loading 0: 18%|█▊ | 107/579 [00:00<00:04, 107.35it/s] Loading 0: 21%|██ | 120/579 [00:01<00:04, 112.60it/s] Loading 0: 24%|██▍ | 140/579 [00:01<00:03, 135.65it/s] Loading 0: 27%|██▋ | 155/579 [00:01<00:03, 131.20it/s] Loading 0: 29%|██▉ | 169/579 [00:01<00:03, 132.01it/s] Loading 0: 32%|███▏ | 186/579 [00:01<00:02, 142.42it/s] Loading 0: 35%|███▍ | 201/579 [00:01<00:04, 87.28it/s] Loading 0: 38%|███▊ | 219/579 [00:01<00:03, 102.29it/s] Loading 0: 40%|████ | 232/579 [00:02<00:03, 107.26it/s] Loading 0: 42%|████▏ | 245/579 [00:02<00:02, 112.41it/s] Loading 0: 45%|████▌ | 263/579 [00:02<00:02, 128.91it/s] Loading 0: 48%|████▊ | 279/579 [00:02<00:02, 135.01it/s] Loading 0: 51%|█████▏ | 297/579 [00:02<00:02, 101.27it/s] Loading 0: 54%|█████▎ | 310/579 [00:02<00:02, 98.80it/s] Loading 0: 56%|█████▋ | 327/579 [00:02<00:02, 111.78it/s] Loading 0: 59%|█████▊ | 340/579 [00:02<00:02, 115.65it/s] Loading 0: 61%|██████ | 354/579 [00:03<00:01, 121.52it/s] Loading 0: 64%|██████▍ | 371/579 [00:03<00:01, 133.42it/s] Loading 0: 67%|██████▋ | 387/579 [00:03<00:01, 135.73it/s] Loading 0: 70%|██████▉ | 405/579 [00:03<00:01, 100.85it/s] Loading 0: 72%|███████▏ | 417/579 [00:03<00:01, 96.56it/s] Loading 0: 75%|███████▌ | 435/579 [00:03<00:01, 111.90it/s] Loading 0: 77%|███████▋ | 448/579 [00:03<00:01, 115.97it/s] Loading 0: 80%|███████▉ | 461/579 [00:03<00:00, 119.04it/s] Loading 0: 83%|████████▎ | 479/579 [00:04<00:00, 134.94it/s] Loading 0: 85%|████████▌ | 495/579 [00:04<00:00, 140.34it/s] Loading 0: 88%|████████▊ | 512/579 [00:25<00:00, 140.34it/s] Loading 0: 89%|████████▊ | 513/579 [00:25<00:25, 2.57it/s] Loading 0: 90%|████████▉ | 521/579 [00:25<00:18, 3.08it/s] Loading 0: 92%|█████████▏| 534/579 [00:25<00:10, 4.28it/s] Loading 0: 95%|█████████▌| 552/579 [00:25<00:04, 6.62it/s] Loading 0: 98%|█████████▊| 568/579 [00:25<00:01, 9.47it/s]
Job chaiml-qwen25-14b-ft-sf-35028-v4-mkmlizer completed after 104.78s with status: succeeded
Stopping job with name chaiml-qwen25-14b-ft-sf-35028-v4-mkmlizer
Pipeline stage MKMLizer completed in 105.31s
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 chaiml-qwen25-14b-ft-sf-35028-v4
Waiting for inference service chaiml-qwen25-14b-ft-sf-35028-v4 to be ready
Inference service chaiml-qwen25-14b-ft-sf-35028-v4 ready after 120.4606556892395s
Pipeline stage MKMLDeployer completed in 120.98s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5576727390289307s
Received healthy response to inference request in 2.2375826835632324s
Received healthy response to inference request in 2.3982815742492676s
Received healthy response to inference request in 1.9525485038757324s
Received healthy response to inference request in 2.124600887298584s
5 requests
0 failed requests
5th percentile: 1.9869589805603027
10th percentile: 2.021369457244873
20th percentile: 2.0901904106140137
30th percentile: 2.1471972465515137
40th percentile: 2.192389965057373
50th percentile: 2.2375826835632324
60th percentile: 2.3018622398376465
70th percentile: 2.3661417961120605
80th percentile: 2.4301598072052
90th percentile: 2.4939162731170654
95th percentile: 2.525794506072998
99th percentile: 2.551297092437744
mean time: 2.2541372776031494
Pipeline stage StressChecker completed in 12.77s
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 0.71s
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 0.67s
Shutdown handler de-registered
chaiml-qwen25-14b-ft-sf_35028_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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-qwen25-14b-ft-sf-35028-v4-profiler
Waiting for inference service chaiml-qwen25-14b-ft-sf-35028-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
Pipeline stage OfflineFamilyFriendlyScorer completed in 2621.09s
Shutdown handler de-registered
chaiml-qwen25-14b-ft-sf_35028_v4 status is now inactive due to auto deactivation removed underperforming models
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1