chaiml-nis-cogito14b-dpo_1613

developer_uid: NischayDnk

submission_id: chaiml-nis-cogito14b-dpo_1613_v2

model_name: chaiml-nis-cogito14b-dpo_1613_v2

model_group: ChaiML/nis-cogito14b-dpo

status: torndown

timestamp: 2025-04-17T07:24:35+00:00

num_battles: 9164

num_wins: 4664

celo_rating: 1288.87

family_friendly_score: 0.544

family_friendly_standard_error: 0.007043635424977645

submission_type: basic

model_repo: ChaiML/nis-cogito14b-dpostage1-exp2-ffsys-datav1

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': 0.4703455628066312, 'latency_mean': 2.1260264253616334, 'latency_p50': 2.1012943983078003, 'latency_p90': 2.3584840059280396}, {'batch_size': 3, 'throughput': 0.8621408337312206, 'latency_mean': 3.4624449026584627, 'latency_p50': 3.524460554122925, 'latency_p90': 3.82528293132782}, {'batch_size': 5, 'throughput': 1.0459592322672042, 'latency_mean': 4.766270411014557, 'latency_p50': 4.789935231208801, 'latency_p90': 5.393509793281555}, {'batch_size': 6, 'throughput': 1.1098600907888132, 'latency_mean': 5.380760939121246, 'latency_p50': 5.339355826377869, 'latency_p90': 6.054330134391784}, {'batch_size': 10, 'throughput': 1.198328861527398, 'latency_mean': 8.261115082502364, 'latency_p50': 8.18466055393219, 'latency_p90': 9.39877028465271}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-nis-cogito14b-dpo_1613_v2

is_internal_developer: False

language_model: ChaiML/nis-cogito14b-dpostage1-exp2-ffsys-datav1

model_size: 15B

ranking_group: single

throughput_3p7s: 0.91

us_pacific_date: 2025-04-17

win_ratio: 0.5089480576167612

generation_params: {'temperature': 0.75, 'top_p': 0.96, 'min_p': 0.02, 'top_k': 60, 'presence_penalty': 0.2, 'frequency_penalty': 0.2, 'stopping_words': ['<|im_end|>', '\n'], 'max_input_tokens': 1024, 'best_of': 8, '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-nis-cogito14b-dpo-1613-v2-mkmlizer
Waiting for job on chaiml-nis-cogito14b-dpo-1613-v2-mkmlizer to finish
chaiml-nis-cogito14b-dpo-1613-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nis-cogito14b-dpo-1613-v2-mkmlizer: ║     _____            __           __                                ║
chaiml-nis-cogito14b-dpo-1613-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-nis-cogito14b-dpo-1613-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-nis-cogito14b-dpo-1613-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-nis-cogito14b-dpo-1613-v2-mkmlizer: ║       /___/                                                         ║
chaiml-nis-cogito14b-dpo-1613-v2-mkmlizer: ║                                                                     ║
chaiml-nis-cogito14b-dpo-1613-v2-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-nis-cogito14b-dpo-1613-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-nis-cogito14b-dpo-1613-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-nis-cogito14b-dpo-1613-v2-mkmlizer: ║                                                                     ║
chaiml-nis-cogito14b-dpo-1613-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-nis-cogito14b-dpo-1613-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-nis-cogito14b-dpo-1613-v2-mkmlizer: ║                                                                     ║
chaiml-nis-cogito14b-dpo-1613-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-nis-cogito14b-dpo-1613-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-nis-cogito14b-dpo-1613-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-nis-cogito14b-dpo-1613-v2-mkmlizer: ║                                                                     ║
chaiml-nis-cogito14b-dpo-1613-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nis-cogito14b-dpo-1613-v2-mkmlizer: Downloaded to shared memory in 38.590s
chaiml-nis-cogito14b-dpo-1613-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpik5bz4qa, device:0
chaiml-nis-cogito14b-dpo-1613-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nis-cogito14b-dpo-1613-v2-mkmlizer: quantized model in 36.402s
chaiml-nis-cogito14b-dpo-1613-v2-mkmlizer: Processed model ChaiML/nis-cogito14b-dpostage1-exp2-ffsys-datav1 in 74.993s
chaiml-nis-cogito14b-dpo-1613-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nis-cogito14b-dpo-1613-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nis-cogito14b-dpo-1613-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nis-cogito14b-dpo-1613-v2
chaiml-nis-cogito14b-dpo-1613-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nis-cogito14b-dpo-1613-v2/config.json
chaiml-nis-cogito14b-dpo-1613-v2-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-nis-cogito14b-dpo-1613-v2/added_tokens.json
chaiml-nis-cogito14b-dpo-1613-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nis-cogito14b-dpo-1613-v2/tokenizer_config.json
chaiml-nis-cogito14b-dpo-1613-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nis-cogito14b-dpo-1613-v2/special_tokens_map.json
chaiml-nis-cogito14b-dpo-1613-v2-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-nis-cogito14b-dpo-1613-v2/merges.txt
chaiml-nis-cogito14b-dpo-1613-v2-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-nis-cogito14b-dpo-1613-v2/vocab.json
chaiml-nis-cogito14b-dpo-1613-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nis-cogito14b-dpo-1613-v2/tokenizer.json
chaiml-nis-cogito14b-dpo-1613-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-nis-cogito14b-dpo-1613-v2/flywheel_model.1.safetensors
chaiml-nis-cogito14b-dpo-1613-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nis-cogito14b-dpo-1613-v2/flywheel_model.0.safetensors
chaiml-nis-cogito14b-dpo-1613-v2-mkmlizer: 
Loading 0:   0%|          | 0/579 [00:00<?, ?it/s]
Loading 0:   3%|▎         | 15/579 [00:00<00:04, 135.34it/s]
Loading 0:   5%|▌         | 29/579 [00:00<00:04, 121.36it/s]
Loading 0:   8%|▊         | 47/579 [00:00<00:03, 144.97it/s]
Loading 0:  11%|█         | 63/579 [00:00<00:03, 148.60it/s]
Loading 0:  14%|█▍        | 81/579 [00:00<00:05, 92.74it/s] 
Loading 0:  16%|█▌        | 94/579 [00:00<00:04, 100.11it/s]
Loading 0:  18%|█▊        | 107/579 [00:00<00:04, 106.17it/s]
Loading 0:  21%|██        | 120/579 [00:01<00:04, 111.25it/s]
Loading 0:  24%|██▍       | 138/579 [00:01<00:03, 128.66it/s]
Loading 0:  27%|██▋       | 154/579 [00:01<00:03, 134.49it/s]
Loading 0:  29%|██▉       | 169/579 [00:01<00:03, 128.75it/s]
Loading 0:  32%|███▏      | 184/579 [00:01<00:02, 133.99it/s]
Loading 0:  34%|███▍      | 198/579 [00:01<00:04, 78.65it/s] 
Loading 0:  37%|███▋      | 215/579 [00:01<00:03, 94.67it/s]
Loading 0:  39%|███▉      | 228/579 [00:02<00:03, 101.44it/s]
Loading 0:  42%|████▏     | 243/579 [00:02<00:03, 107.49it/s]
Loading 0:  44%|████▍     | 256/579 [00:02<00:03, 106.24it/s]
Loading 0:  46%|████▋     | 269/579 [00:02<00:02, 107.39it/s]
Loading 0:  50%|████▉     | 287/579 [00:02<00:02, 123.97it/s]
Loading 0:  52%|█████▏    | 301/579 [00:02<00:03, 84.12it/s] 
Loading 0:  54%|█████▍    | 315/579 [00:02<00:02, 94.80it/s]
Loading 0:  57%|█████▋    | 328/579 [00:03<00:02, 102.38it/s]
Loading 0:  59%|█████▉    | 341/579 [00:03<00:02, 107.93it/s]
Loading 0:  62%|██████▏   | 361/579 [00:03<00:01, 130.75it/s]
Loading 0:  65%|██████▍   | 376/579 [00:03<00:01, 128.94it/s]
Loading 0:  67%|██████▋   | 390/579 [00:03<00:01, 131.42it/s]
Loading 0:  70%|██████▉   | 405/579 [00:03<00:01, 101.18it/s]
Loading 0:  72%|███████▏  | 417/579 [00:03<00:01, 97.00it/s] 
Loading 0:  75%|███████▌  | 435/579 [00:03<00:01, 113.45it/s]
Loading 0:  77%|███████▋  | 448/579 [00:04<00:01, 116.93it/s]
Loading 0:  80%|███████▉  | 461/579 [00:04<00:00, 118.64it/s]
Loading 0:  83%|████████▎ | 480/579 [00:04<00:00, 137.42it/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<00:26,  2.50it/s] 
Loading 0:  90%|████████▉ | 521/579 [00:25<00:19,  3.01it/s]
Loading 0:  92%|█████████▏| 534/579 [00:25<00:10,  4.20it/s]
Loading 0:  95%|█████████▌| 552/579 [00:25<00:04,  6.50it/s]
Loading 0:  98%|█████████▊| 568/579 [00:26<00:01,  9.32it/s]
                                                            
Job chaiml-nis-cogito14b-dpo-1613-v2-mkmlizer completed after 105.1s with status: succeeded
Stopping job with name chaiml-nis-cogito14b-dpo-1613-v2-mkmlizer
Pipeline stage MKMLizer completed in 105.64s
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-nis-cogito14b-dpo-1613-v2
Waiting for inference service chaiml-nis-cogito14b-dpo-1613-v2 to be ready
Inference service chaiml-nis-cogito14b-dpo-1613-v2 ready after 130.46370601654053s
Pipeline stage MKMLDeployer completed in 131.01s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5416533946990967s
Received healthy response to inference request in 1.9662680625915527s
Received healthy response to inference request in 1.9080581665039062s
Received healthy response to inference request in 1.9581270217895508s
Received healthy response to inference request in 2.0696260929107666s
5 requests
0 failed requests
5th percentile: 1.9180719375610351
10th percentile: 1.928085708618164
20th percentile: 1.948113250732422
30th percentile: 1.9597552299499512
40th percentile: 1.9630116462707519
50th percentile: 1.9662680625915527
60th percentile: 2.0076112747192383
70th percentile: 2.048954486846924
80th percentile: 2.164031553268433
90th percentile: 2.3528424739837646
95th percentile: 2.4472479343414304
99th percentile: 2.5227723026275632
mean time: 2.0887465476989746
Pipeline stage StressChecker completed in 12.03s
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 0.73s
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 0.71s
Shutdown handler de-registered
chaiml-nis-cogito14b-dpo_1613_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 5189.55s
Shutdown handler de-registered
chaiml-nis-cogito14b-dpo_1613_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-nis-cogito14b-dpo_1613_v2 status is now torndown due to DeploymentManager action