developer_uid: NischayDnk
submission_id: chaiml-qwen25-14b-ft-sf_35028_v5
model_name: chaiml-qwen25-14b-ft-sf_35028_v5
model_group: ChaiML/qwen25-14B-ft-sft
status: inactive
timestamp: 2025-04-05T01:12:48+00:00
num_battles: 7314
num_wins: 3615
celo_rating: 1279.22
family_friendly_score: 0.5526
family_friendly_standard_error: 0.007031831055991035
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': 0.47152621042994386, 'latency_mean': 2.1207042717933655, 'latency_p50': 2.1267930269241333, 'latency_p90': 2.3392812252044677}, {'batch_size': 3, 'throughput': 0.8667406456989301, 'latency_mean': 3.449336061477661, 'latency_p50': 3.448927879333496, 'latency_p90': 3.7647812604904174}, {'batch_size': 5, 'throughput': 1.0621306403893354, 'latency_mean': 4.685087847709656, 'latency_p50': 4.682482719421387, 'latency_p90': 5.32045955657959}, {'batch_size': 6, 'throughput': 1.1070190767554164, 'latency_mean': 5.392375388145447, 'latency_p50': 5.382249116897583, 'latency_p90': 6.122823858261109}, {'batch_size': 10, 'throughput': 1.1975172926030215, 'latency_mean': 8.284718126058578, 'latency_p50': 8.288889169692993, 'latency_p90': 9.352657771110534}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: chaiml-qwen25-14b-ft-sf_35028_v5
is_internal_developer: True
language_model: ChaiML/qwen25-14B-ft-sft-exp2-del12k
model_size: 15B
ranking_group: single
throughput_3p7s: 0.92
us_pacific_date: 2025-04-04
win_ratio: 0.4942575881870386
generation_params: {'temperature': 0.775, 'top_p': 0.96, 'min_p': 0.02, 'top_k': 60, 'presence_penalty': 0.275, 'frequency_penalty': 0.275, 'stopping_words': ['\n', '<|im_end|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\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-qwen25-14b-ft-sf-35028-v5-mkmlizer
Waiting for job on chaiml-qwen25-14b-ft-sf-35028-v5-mkmlizer to finish
chaiml-qwen25-14b-ft-sf-35028-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-qwen25-14b-ft-sf-35028-v5-mkmlizer: ║ _____ __ __ ║
chaiml-qwen25-14b-ft-sf-35028-v5-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-qwen25-14b-ft-sf-35028-v5-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-qwen25-14b-ft-sf-35028-v5-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-qwen25-14b-ft-sf-35028-v5-mkmlizer: ║ /___/ ║
chaiml-qwen25-14b-ft-sf-35028-v5-mkmlizer: ║ ║
chaiml-qwen25-14b-ft-sf-35028-v5-mkmlizer: ║ Version: 0.12.8 ║
chaiml-qwen25-14b-ft-sf-35028-v5-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-qwen25-14b-ft-sf-35028-v5-mkmlizer: ║ https://mk1.ai ║
chaiml-qwen25-14b-ft-sf-35028-v5-mkmlizer: ║ ║
chaiml-qwen25-14b-ft-sf-35028-v5-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-qwen25-14b-ft-sf-35028-v5-mkmlizer: ║ belonging to: ║
chaiml-qwen25-14b-ft-sf-35028-v5-mkmlizer: ║ ║
chaiml-qwen25-14b-ft-sf-35028-v5-mkmlizer: ║ Chai Research Corp. ║
chaiml-qwen25-14b-ft-sf-35028-v5-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-qwen25-14b-ft-sf-35028-v5-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
chaiml-qwen25-14b-ft-sf-35028-v5-mkmlizer: ║ ║
chaiml-qwen25-14b-ft-sf-35028-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission jellywibble-aaron250405014117_v2: HTTPConnectionPool(host='jellywibble-aaron250405014117-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-qwen25-14b-ft-sf-35028-v5-mkmlizer: Downloaded to shared memory in 39.619s
chaiml-qwen25-14b-ft-sf-35028-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpj76z3mh4, device:0
chaiml-qwen25-14b-ft-sf-35028-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-qwen25-14b-ft-sf-35028-v5-mkmlizer: quantized model in 36.915s
chaiml-qwen25-14b-ft-sf-35028-v5-mkmlizer: Processed model ChaiML/qwen25-14B-ft-sft-exp2-del12k in 76.535s
chaiml-qwen25-14b-ft-sf-35028-v5-mkmlizer: creating bucket guanaco-mkml-models
chaiml-qwen25-14b-ft-sf-35028-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-qwen25-14b-ft-sf-35028-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-qwen25-14b-ft-sf-35028-v5
chaiml-qwen25-14b-ft-sf-35028-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-qwen25-14b-ft-sf-35028-v5/config.json
chaiml-qwen25-14b-ft-sf-35028-v5-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-qwen25-14b-ft-sf-35028-v5/added_tokens.json
chaiml-qwen25-14b-ft-sf-35028-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-qwen25-14b-ft-sf-35028-v5/special_tokens_map.json
chaiml-qwen25-14b-ft-sf-35028-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-qwen25-14b-ft-sf-35028-v5/tokenizer_config.json
chaiml-qwen25-14b-ft-sf-35028-v5-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-qwen25-14b-ft-sf-35028-v5/merges.txt
chaiml-qwen25-14b-ft-sf-35028-v5-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-qwen25-14b-ft-sf-35028-v5/vocab.json
chaiml-qwen25-14b-ft-sf-35028-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-qwen25-14b-ft-sf-35028-v5/tokenizer.json
chaiml-qwen25-14b-ft-sf-35028-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-qwen25-14b-ft-sf-35028-v5/flywheel_model.1.safetensors
chaiml-qwen25-14b-ft-sf-35028-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-qwen25-14b-ft-sf-35028-v5/flywheel_model.0.safetensors
chaiml-qwen25-14b-ft-sf-35028-v5-mkmlizer: Loading 0: 0%| | 0/579 [00:00<?, ?it/s] Loading 0: 3%|▎ | 15/579 [00:00<00:04, 133.15it/s] Loading 0: 5%|▌ | 29/579 [00:00<00:04, 116.43it/s] Loading 0: 8%|▊ | 47/579 [00:00<00:03, 139.20it/s] Loading 0: 11%|█ | 63/579 [00:00<00:03, 142.49it/s] Loading 0: 14%|█▍ | 81/579 [00:00<00:05, 92.32it/s] Loading 0: 16%|█▌ | 94/579 [00:00<00:04, 98.90it/s] Loading 0: 18%|█▊ | 107/579 [00:00<00:04, 104.90it/s] Loading 0: 21%|██ | 120/579 [00:01<00:04, 109.78it/s] Loading 0: 24%|██▍ | 138/579 [00:01<00:03, 127.24it/s] Loading 0: 27%|██▋ | 154/579 [00:01<00:03, 132.80it/s] Loading 0: 29%|██▉ | 169/579 [00:01<00:03, 127.19it/s] Loading 0: 32%|███▏ | 186/579 [00:01<00:02, 137.25it/s] Loading 0: 35%|███▍ | 201/579 [00:01<00:04, 85.98it/s] Loading 0: 38%|███▊ | 219/579 [00:01<00:03, 101.14it/s] Loading 0: 40%|████ | 232/579 [00:02<00:03, 105.94it/s] Loading 0: 42%|████▏ | 245/579 [00:02<00:03, 110.30it/s] Loading 0: 45%|████▌ | 263/579 [00:02<00:02, 125.93it/s] Loading 0: 48%|████▊ | 279/579 [00:02<00:02, 132.88it/s] Loading 0: 51%|█████▏ | 297/579 [00:02<00:02, 100.37it/s] Loading 0: 54%|█████▎ | 310/579 [00:02<00:02, 98.40it/s] Loading 0: 56%|█████▋ | 327/579 [00:02<00:02, 110.93it/s] Loading 0: 59%|█████▊ | 340/579 [00:03<00:02, 114.38it/s] Loading 0: 61%|██████ | 353/579 [00:03<00:01, 116.56it/s] Loading 0: 64%|██████▍ | 371/579 [00:03<00:01, 132.11it/s] Loading 0: 67%|██████▋ | 387/579 [00:03<00:01, 137.69it/s] Loading 0: 70%|██████▉ | 405/579 [00:03<00:01, 100.88it/s] Loading 0: 72%|███████▏ | 417/579 [00:03<00:01, 96.95it/s] Loading 0: 75%|███████▌ | 435/579 [00:03<00:01, 111.89it/s] Loading 0: 77%|███████▋ | 448/579 [00:03<00:01, 114.73it/s] Loading 0: 80%|███████▉ | 461/579 [00:04<00:01, 117.40it/s] Loading 0: 83%|████████▎ | 479/579 [00:04<00:00, 133.11it/s] Loading 0: 85%|████████▌ | 495/579 [00:04<00:00, 138.10it/s] Loading 0: 88%|████████▊ | 512/579 [00:22<00:00, 138.10it/s] Loading 0: 89%|████████▊ | 513/579 [00:26<00:26, 2.46it/s] Loading 0: 90%|████████▉ | 521/579 [00:26<00:19, 2.96it/s] Loading 0: 92%|█████████▏| 534/579 [00:26<00:10, 4.11it/s] Loading 0: 95%|█████████▌| 552/579 [00:26<00:04, 6.35it/s] Loading 0: 98%|█████████▊| 568/579 [00:26<00:01, 9.09it/s]
Job chaiml-qwen25-14b-ft-sf-35028-v5-mkmlizer completed after 104.22s with status: succeeded
Stopping job with name chaiml-qwen25-14b-ft-sf-35028-v5-mkmlizer
Pipeline stage MKMLizer completed in 104.71s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-qwen25-14b-ft-sf-35028-v5
Waiting for inference service chaiml-qwen25-14b-ft-sf-35028-v5 to be ready
Inference service chaiml-qwen25-14b-ft-sf-35028-v5 ready after 110.564199924469s
Pipeline stage MKMLDeployer completed in 111.09s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.479877233505249s
Received healthy response to inference request in 2.0418789386749268s
Received healthy response to inference request in 1.9074504375457764s
Received healthy response to inference request in 2.2571184635162354s
Received healthy response to inference request in 2.011007785797119s
5 requests
0 failed requests
5th percentile: 1.928161907196045
10th percentile: 1.9488733768463136
20th percentile: 1.9902963161468505
30th percentile: 2.0171820163726806
40th percentile: 2.029530477523804
50th percentile: 2.0418789386749268
60th percentile: 2.12797474861145
70th percentile: 2.2140705585479736
80th percentile: 2.301670217514038
90th percentile: 2.3907737255096437
95th percentile: 2.4353254795074464
99th percentile: 2.4709668827056883
mean time: 2.139466571807861
Pipeline stage StressChecker completed in 11.94s
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 0.63s
Shutdown handler de-registered
chaiml-qwen25-14b-ft-sf_35028_v5 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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4385.71s
Shutdown handler de-registered
chaiml-qwen25-14b-ft-sf_35028_v5 status is now inactive due to auto deactivation removed underperforming models
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1