developer_uid: NischayDnk
submission_id: chaiml-qwen14b-dpoexp2-s_6544_v2
model_name: chaiml-qwen14b-dpoexp2-s_6544_v2
model_group: ChaiML/qwen14b-dpoexp2-s
status: torndown
timestamp: 2025-04-08T23:18:00+00:00
num_battles: 8949
num_wins: 4428
celo_rating: 1278.41
family_friendly_score: 0.5356000000000001
family_friendly_standard_error: 0.007053121861984238
submission_type: basic
model_repo: ChaiML/qwen14b-dpoexp2-sftdel12kexp4-oldformat
model_architecture: Qwen2ForCausalLM
model_num_parameters: 14769689600.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.47245482308678327, 'latency_mean': 2.1165015745162963, 'latency_p50': 2.108703136444092, 'latency_p90': 2.331994724273682}, {'batch_size': 3, 'throughput': 0.8746187496965826, 'latency_mean': 3.4182045590877532, 'latency_p50': 3.427977442741394, 'latency_p90': 3.8254548788070677}, {'batch_size': 5, 'throughput': 1.0631437471289802, 'latency_mean': 4.68666030883789, 'latency_p50': 4.700215578079224, 'latency_p90': 5.248333144187927}, {'batch_size': 6, 'throughput': 1.118754309727602, 'latency_mean': 5.326271114349365, 'latency_p50': 5.365891218185425, 'latency_p90': 5.907220745086669}, {'batch_size': 10, 'throughput': 1.204284683646476, 'latency_mean': 8.237084978818894, 'latency_p50': 8.246200442314148, 'latency_p90': 9.135049104690552}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: chaiml-qwen14b-dpoexp2-s_6544_v2
is_internal_developer: False
language_model: ChaiML/qwen14b-dpoexp2-sftdel12kexp4-oldformat
model_size: 15B
ranking_group: single
throughput_3p7s: 0.93
us_pacific_date: 2025-04-08
win_ratio: 0.49480388870264835
generation_params: {'temperature': 0.7, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 80, 'presence_penalty': 0.3, 'frequency_penalty': 0.3, 'stopping_words': ['\n', '</s>', 'You:', '###'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '[INST]', 'prompt_template': '', 'bot_template': '\n{bot_name}: {message}', 'user_template': '\n{user_name}: {message}', 'response_template': '\n{bot_name}:', 'truncate_by_message': True}
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-qwen14b-dpoexp2-s-6544-v2-mkmlizer
Waiting for job on chaiml-qwen14b-dpoexp2-s-6544-v2-mkmlizer to finish
chaiml-qwen14b-dpoexp2-s-6544-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-qwen14b-dpoexp2-s-6544-v2-mkmlizer: ║ _____ __ __ ║
chaiml-qwen14b-dpoexp2-s-6544-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-qwen14b-dpoexp2-s-6544-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-qwen14b-dpoexp2-s-6544-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-qwen14b-dpoexp2-s-6544-v2-mkmlizer: ║ /___/ ║
chaiml-qwen14b-dpoexp2-s-6544-v2-mkmlizer: ║ ║
chaiml-qwen14b-dpoexp2-s-6544-v2-mkmlizer: ║ Version: 0.12.8 ║
chaiml-qwen14b-dpoexp2-s-6544-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-qwen14b-dpoexp2-s-6544-v2-mkmlizer: ║ https://mk1.ai ║
chaiml-qwen14b-dpoexp2-s-6544-v2-mkmlizer: ║ ║
chaiml-qwen14b-dpoexp2-s-6544-v2-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-qwen14b-dpoexp2-s-6544-v2-mkmlizer: ║ belonging to: ║
chaiml-qwen14b-dpoexp2-s-6544-v2-mkmlizer: ║ ║
chaiml-qwen14b-dpoexp2-s-6544-v2-mkmlizer: ║ Chai Research Corp. ║
chaiml-qwen14b-dpoexp2-s-6544-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-qwen14b-dpoexp2-s-6544-v2-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
chaiml-qwen14b-dpoexp2-s-6544-v2-mkmlizer: ║ ║
chaiml-qwen14b-dpoexp2-s-6544-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-qwen14b-dpoexp2-s-6544-v2-mkmlizer: Downloaded to shared memory in 42.894s
chaiml-qwen14b-dpoexp2-s-6544-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpl03famfs, device:0
chaiml-qwen14b-dpoexp2-s-6544-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-qwen14b-dpoexp2-s-6544-v2-mkmlizer: quantized model in 37.307s
chaiml-qwen14b-dpoexp2-s-6544-v2-mkmlizer: Processed model ChaiML/qwen14b-dpoexp2-sftdel12kexp4-oldformat in 80.201s
chaiml-qwen14b-dpoexp2-s-6544-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-qwen14b-dpoexp2-s-6544-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-qwen14b-dpoexp2-s-6544-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp2-s-6544-v2
chaiml-qwen14b-dpoexp2-s-6544-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp2-s-6544-v2/config.json
chaiml-qwen14b-dpoexp2-s-6544-v2-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp2-s-6544-v2/added_tokens.json
chaiml-qwen14b-dpoexp2-s-6544-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp2-s-6544-v2/special_tokens_map.json
chaiml-qwen14b-dpoexp2-s-6544-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp2-s-6544-v2/tokenizer_config.json
chaiml-qwen14b-dpoexp2-s-6544-v2-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp2-s-6544-v2/merges.txt
chaiml-qwen14b-dpoexp2-s-6544-v2-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp2-s-6544-v2/vocab.json
chaiml-qwen14b-dpoexp2-s-6544-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp2-s-6544-v2/tokenizer.json
chaiml-qwen14b-dpoexp2-s-6544-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp2-s-6544-v2/flywheel_model.1.safetensors
chaiml-qwen14b-dpoexp2-s-6544-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp2-s-6544-v2/flywheel_model.0.safetensors
chaiml-qwen14b-dpoexp2-s-6544-v2-mkmlizer: Loading 0: 0%| | 0/579 [00:00<?, ?it/s] Loading 0: 3%|▎ | 15/579 [00:00<00:04, 133.61it/s] Loading 0: 5%|▌ | 29/579 [00:00<00:04, 117.47it/s] Loading 0: 8%|▊ | 47/579 [00:00<00:03, 138.67it/s] Loading 0: 11%|█ | 63/579 [00:00<00:03, 140.21it/s] Loading 0: 14%|█▍ | 81/579 [00:00<00:05, 87.55it/s] Loading 0: 16%|█▌ | 94/579 [00:00<00:05, 94.85it/s] Loading 0: 18%|█▊ | 107/579 [00:01<00:04, 99.66it/s] Loading 0: 21%|██ | 120/579 [00:01<00:04, 104.92it/s] Loading 0: 24%|██▍ | 138/579 [00:01<00:03, 122.50it/s] Loading 0: 27%|██▋ | 154/579 [00:01<00:03, 128.62it/s] Loading 0: 29%|██▉ | 168/579 [00:01<00:03, 121.72it/s] Loading 0: 32%|███▏ | 186/579 [00:01<00:02, 135.26it/s] Loading 0: 35%|███▍ | 201/579 [00:01<00:04, 83.75it/s] Loading 0: 38%|███▊ | 219/579 [00:02<00:03, 99.13it/s] Loading 0: 40%|████ | 232/579 [00:02<00:03, 102.90it/s] Loading 0: 42%|████▏ | 245/579 [00:02<00:03, 107.42it/s] Loading 0: 45%|████▌ | 263/579 [00:02<00:02, 123.75it/s] Loading 0: 48%|████▊ | 279/579 [00:02<00:02, 130.31it/s] Loading 0: 51%|█████▏ | 297/579 [00:02<00:02, 96.46it/s] Loading 0: 53%|█████▎ | 309/579 [00:02<00:02, 92.75it/s] Loading 0: 56%|█████▋ | 327/579 [00:03<00:02, 106.47it/s] Loading 0: 59%|█████▊ | 340/579 [00:03<00:02, 110.15it/s] Loading 0: 61%|██████ | 353/579 [00:03<00:01, 113.77it/s] Loading 0: 64%|██████▍ | 371/579 [00:03<00:01, 129.72it/s] Loading 0: 67%|██████▋ | 387/579 [00:03<00:01, 135.36it/s] Loading 0: 70%|██████▉ | 405/579 [00:03<00:01, 95.86it/s] Loading 0: 72%|███████▏ | 417/579 [00:03<00:01, 91.28it/s] Loading 0: 75%|███████▌ | 435/579 [00:04<00:01, 105.21it/s] Loading 0: 77%|███████▋ | 448/579 [00:04<00:01, 108.21it/s] Loading 0: 80%|███████▉ | 461/579 [00:04<00:01, 110.92it/s] Loading 0: 83%|████████▎ | 479/579 [00:04<00:00, 126.51it/s] Loading 0: 85%|████████▌ | 495/579 [00:04<00:00, 129.20it/s] Loading 0: 88%|████████▊ | 512/579 [00:22<00:00, 129.20it/s] Loading 0: 89%|████████▊ | 513/579 [00:26<00:27, 2.43it/s] Loading 0: 90%|████████▉ | 521/579 [00:26<00:19, 2.92it/s] Loading 0: 92%|█████████▏| 534/579 [00:26<00:11, 4.06it/s] Loading 0: 95%|█████████▌| 552/579 [00:26<00:04, 6.28it/s] Loading 0: 98%|█████████▊| 568/579 [00:26<00:01, 8.99it/s]
Job chaiml-qwen14b-dpoexp2-s-6544-v2-mkmlizer completed after 105.09s with status: succeeded
Stopping job with name chaiml-qwen14b-dpoexp2-s-6544-v2-mkmlizer
Pipeline stage MKMLizer completed in 105.55s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-qwen14b-dpoexp2-s-6544-v2
Waiting for inference service chaiml-qwen14b-dpoexp2-s-6544-v2 to be ready
Unable to record family friendly update due to error: Invalid JSON input: JSON must contain 'User Safety' and 'Response Safety' fields
Inference service chaiml-qwen14b-dpoexp2-s-6544-v2 ready after 110.55908393859863s
Pipeline stage MKMLDeployer completed in 111.06s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4592082500457764s
Received healthy response to inference request in 1.955871820449829s
Received healthy response to inference request in 2.1408843994140625s
Received healthy response to inference request in 2.176786422729492s
Received healthy response to inference request in 2.0521111488342285s
5 requests
0 failed requests
5th percentile: 1.975119686126709
10th percentile: 1.9943675518035888
20th percentile: 2.0328632831573485
30th percentile: 2.0698657989501954
40th percentile: 2.1053750991821287
50th percentile: 2.1408843994140625
60th percentile: 2.1552452087402343
70th percentile: 2.169606018066406
80th percentile: 2.233270788192749
90th percentile: 2.346239519119263
95th percentile: 2.4027238845825196
99th percentile: 2.447911376953125
mean time: 2.1569724082946777
Pipeline stage StressChecker completed in 12.01s
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 0.63s
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 0.70s
Shutdown handler de-registered
chaiml-qwen14b-dpoexp2-s_6544_v2 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 4913.30s
Shutdown handler de-registered
chaiml-qwen14b-dpoexp2-s_6544_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-qwen14b-dpoexp2-s_6544_v2 status is now torndown due to DeploymentManager action