chaiml-llama-8b-nis-800_35125

developer_uid: NischayDnk
submission_id: chaiml-llama-8b-nis-800_35125_v1
model_name: chaiml-llama-8b-nis-800_35125_v1
model_group: ChaiML/llama_8b_nis_800k
status: torndown
timestamp: 2025-07-07T13:57:24+00:00
num_battles: 8986
num_wins: 4595
celo_rating: 1300.39
family_friendly_score: 0.0
family_friendly_standard_error: 0.0
submission_type: basic
model_repo: ChaiML/llama_8b_nis_800ksamp_512seq_retuneff_cos_time_lastep_565
model_architecture: LlamaForSequenceClassification
model_num_parameters: 8030261248.0
best_of: 1
max_input_tokens: 512
max_output_tokens: 1
reward_model: default
display_name: chaiml-llama-8b-nis-800_35125_v1
ineligible_reason: max_output_tokens!=64
is_internal_developer: False
language_model: ChaiML/llama_8b_nis_800ksamp_512seq_retuneff_cos_time_lastep_565
model_size: 8B
ranking_group: single
us_pacific_date: 2025-07-07
win_ratio: 0.5113509904295571
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 1, 'max_output_tokens': 1}
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '', '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-llama-8b-nis-800-35125-v1-mkmlizer
Waiting for job on chaiml-llama-8b-nis-800-35125-v1-mkmlizer to finish
chaiml-llama-8b-nis-800-35125-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-llama-8b-nis-800-35125-v1-mkmlizer: ║                                                                     ║
chaiml-llama-8b-nis-800-35125-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-llama-8b-nis-800-35125-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-llama-8b-nis-800-35125-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-llama-8b-nis-800-35125-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-llama-8b-nis-800-35125-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-llama-8b-nis-800-35125-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-llama-8b-nis-800-35125-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-llama-8b-nis-800-35125-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-llama-8b-nis-800-35125-v1-mkmlizer: ║                                                                     ║
chaiml-llama-8b-nis-800-35125-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-llama-8b-nis-800-35125-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-llama-8b-nis-800-35125-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-llama-8b-nis-800-35125-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-llama-8b-nis-800-35125-v1-mkmlizer: ║                                                                     ║
chaiml-llama-8b-nis-800-35125-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-llama-8b-nis-800-35125-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-llama-8b-nis-800-35125-v1-mkmlizer: ║                                                                     ║
chaiml-llama-8b-nis-800-35125-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-llama-8b-nis-800-35125-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-llama-8b-nis-800-35125-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-llama-8b-nis-800-35125-v1-mkmlizer: ║                                                                     ║
chaiml-llama-8b-nis-800-35125-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-llama-8b-nis-800-35125-v1-mkmlizer: Downloaded to shared memory in 29.199s
chaiml-llama-8b-nis-800-35125-v1-mkmlizer: Checking if ChaiML/llama_8b_nis_800ksamp_512seq_retuneff_cos_time_lastep_565 already exists in ChaiML
chaiml-llama-8b-nis-800-35125-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmpl2dmuxfv, device:0
chaiml-llama-8b-nis-800-35125-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-llama-8b-nis-800-35125-v1-mkmlizer: quantized model in 19.917s
chaiml-llama-8b-nis-800-35125-v1-mkmlizer: Processed model ChaiML/llama_8b_nis_800ksamp_512seq_retuneff_cos_time_lastep_565 in 49.116s
chaiml-llama-8b-nis-800-35125-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-llama-8b-nis-800-35125-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-llama-8b-nis-800-35125-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-llama-8b-nis-800-35125-v1/nvidia
chaiml-llama-8b-nis-800-35125-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-800-35125-v1/nvidia/config.json
chaiml-llama-8b-nis-800-35125-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-800-35125-v1/nvidia/special_tokens_map.json
chaiml-llama-8b-nis-800-35125-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-800-35125-v1/nvidia/tokenizer_config.json
chaiml-llama-8b-nis-800-35125-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-800-35125-v1/nvidia/tokenizer.json
chaiml-llama-8b-nis-800-35125-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-llama-8b-nis-800-35125-v1/nvidia/flywheel_model.0.safetensors
chaiml-llama-8b-nis-800-35125-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:07, 36.10it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:05, 54.34it/s]
Loading 0:   7%|▋         | 19/291 [00:00<00:05, 45.63it/s]
Loading 0:   8%|▊         | 24/291 [00:00<00:06, 43.96it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:05, 49.07it/s]
Loading 0:  13%|█▎        | 37/291 [00:00<00:05, 43.29it/s]
Loading 0:  14%|█▍        | 42/291 [00:00<00:05, 43.12it/s]
Loading 0:  17%|█▋        | 49/291 [00:01<00:05, 48.32it/s]
Loading 0:  19%|█▉        | 55/291 [00:01<00:05, 44.43it/s]
Loading 0:  21%|██        | 60/291 [00:01<00:05, 44.24it/s]
Loading 0:  23%|██▎       | 66/291 [00:01<00:04, 47.58it/s]
Loading 0:  24%|██▍       | 71/291 [00:01<00:04, 46.93it/s]
Loading 0:  26%|██▌       | 76/291 [00:01<00:04, 46.76it/s]
Loading 0:  28%|██▊       | 82/291 [00:01<00:04, 43.12it/s]
Loading 0:  30%|██▉       | 87/291 [00:02<00:06, 29.33it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:05, 36.24it/s]
Loading 0:  34%|███▍      | 100/291 [00:02<00:05, 36.86it/s]
Loading 0:  36%|███▌      | 105/291 [00:02<00:04, 38.06it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:04, 43.58it/s]
Loading 0:  41%|████      | 118/291 [00:02<00:04, 41.34it/s]
Loading 0:  42%|████▏     | 123/291 [00:02<00:04, 41.47it/s]
Loading 0:  45%|████▍     | 130/291 [00:03<00:03, 46.63it/s]
Loading 0:  46%|████▋     | 135/291 [00:03<00:03, 46.69it/s]
Loading 0:  48%|████▊     | 140/291 [00:03<00:03, 38.34it/s]
Loading 0:  51%|█████     | 148/291 [00:03<00:03, 46.55it/s]
Loading 0:  53%|█████▎    | 154/291 [00:03<00:03, 43.34it/s]
Loading 0:  55%|█████▍    | 159/291 [00:03<00:03, 41.81it/s]
Loading 0:  57%|█████▋    | 165/291 [00:03<00:02, 44.80it/s]
Loading 0:  58%|█████▊    | 170/291 [00:03<00:02, 43.57it/s]
Loading 0:  60%|██████    | 175/291 [00:04<00:02, 44.21it/s]
Loading 0:  62%|██████▏   | 180/291 [00:04<00:02, 43.08it/s]
Loading 0:  64%|██████▎   | 185/291 [00:04<00:02, 44.54it/s]
Loading 0:  65%|██████▌   | 190/291 [00:04<00:03, 27.12it/s]
Loading 0:  67%|██████▋   | 194/291 [00:04<00:03, 28.42it/s]
Loading 0:  69%|██████▉   | 201/291 [00:04<00:02, 36.60it/s]
Loading 0:  71%|███████   | 206/291 [00:05<00:02, 38.52it/s]
Loading 0:  73%|███████▎  | 211/291 [00:05<00:01, 40.85it/s]
Loading 0:  74%|███████▍  | 216/291 [00:05<00:01, 43.10it/s]
Loading 0:  76%|███████▌  | 221/291 [00:05<00:01, 35.83it/s]
Loading 0:  78%|███████▊  | 228/291 [00:05<00:01, 43.31it/s]
Loading 0:  80%|████████  | 233/291 [00:05<00:01, 44.09it/s]
Loading 0:  82%|████████▏ | 238/291 [00:05<00:01, 44.11it/s]
Loading 0:  84%|████████▎ | 243/291 [00:05<00:01, 44.18it/s]
Loading 0:  85%|████████▌ | 248/291 [00:06<00:01, 36.98it/s]
Loading 0:  88%|████████▊ | 256/291 [00:06<00:00, 45.17it/s]
Loading 0:  90%|█████████ | 262/291 [00:06<00:00, 42.08it/s]
Loading 0:  92%|█████████▏| 267/291 [00:06<00:00, 42.02it/s]
Loading 0:  94%|█████████▍| 273/291 [00:06<00:00, 46.22it/s]
Loading 0:  96%|█████████▌| 278/291 [00:06<00:00, 45.60it/s]
Loading 0:  97%|█████████▋| 283/291 [00:06<00:00, 38.87it/s]
Loading 0:  99%|█████████▉| 288/291 [00:07<00:00, 29.24it/s]
                                                            
Job chaiml-llama-8b-nis-800-35125-v1-mkmlizer completed after 74.35s with status: succeeded
Stopping job with name chaiml-llama-8b-nis-800-35125-v1-mkmlizer
Pipeline stage MKMLizer completed in 74.85s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.41s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-llama-8b-nis-800-35125-v1
Waiting for inference service chaiml-llama-8b-nis-800-35125-v1 to be ready
Failed to get response for submission chaiml-gy-exp109-dpo-ex_87031_v1: HTTPConnectionPool(host='chaiml-gy-exp109-dpo-ex-87031-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service chaiml-llama-8b-nis-800-35125-v1 ready after 190.72171235084534s
Pipeline stage MKMLDeployer completed in 191.25s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 4.010283946990967s
Received healthy response to inference request in 4.436952829360962s
Received healthy response to inference request in 4.5662620067596436s
Received healthy response to inference request in 2.5330491065979004s
Received healthy response to inference request in 3.094945192337036s
5 requests
0 failed requests
5th percentile: 2.6454283237457275
10th percentile: 2.7578075408935545
20th percentile: 2.982565975189209
30th percentile: 3.2780129432678224
40th percentile: 3.6441484451293946
50th percentile: 4.010283946990967
60th percentile: 4.180951499938965
70th percentile: 4.351619052886963
80th percentile: 4.462814664840698
90th percentile: 4.514538335800171
95th percentile: 4.540400171279908
99th percentile: 4.561089639663696
mean time: 3.728298616409302
Pipeline stage StressChecker completed in 20.00s
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 0.77s
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 1.11s
Shutdown handler de-registered
chaiml-llama-8b-nis-800_35125_v1 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 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-llama-8b-nis-800-35125-v1-profiler
Waiting for inference service chaiml-llama-8b-nis-800-35125-v1-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Received signal 15, running shutdown handler
Shutdown handler de-registered
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 3878.72s
Shutdown handler de-registered
chaiml-llama-8b-nis-800_35125_v1 status is now torndown due to DeploymentManager action