developer_uid: NischayDnk
submission_id: chaiml-llama8b-retune7-r_4100_v1
model_name: chaiml-llama8b-retune7-r_4100_v1
model_group: ChaiML/llama8b-retune7-r
status: torndown
timestamp: 2025-06-22T07:33:55+00:00
num_battles: 7010
num_wins: 3483
celo_rating: 1284.61
family_friendly_score: 0.5402
family_friendly_standard_error: 0.0070481765017627075
submission_type: basic
model_repo: ChaiML/llama8b-retune7-rm-pointwise-datav1-500k-2e-64mckpt-newlinfull-seq512-1
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-llama8b-retune7-r_4100_v1
ineligible_reason: max_output_tokens!=64
is_internal_developer: False
language_model: ChaiML/llama8b-retune7-rm-pointwise-datav1-500k-2e-64mckpt-newlinfull-seq512-1
model_size: 8B
ranking_group: single
us_pacific_date: 2025-06-22
win_ratio: 0.49686162624821684
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': 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-llama8b-retune7-r-4100-v1-mkmlizer
Waiting for job on chaiml-llama8b-retune7-r-4100-v1-mkmlizer to finish
chaiml-llama8b-retune7-r-4100-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-llama8b-retune7-r-4100-v1-mkmlizer: ║ ║
chaiml-llama8b-retune7-r-4100-v1-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-llama8b-retune7-r-4100-v1-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-llama8b-retune7-r-4100-v1-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-llama8b-retune7-r-4100-v1-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-llama8b-retune7-r-4100-v1-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-llama8b-retune7-r-4100-v1-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-llama8b-retune7-r-4100-v1-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-llama8b-retune7-r-4100-v1-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-llama8b-retune7-r-4100-v1-mkmlizer: ║ ║
chaiml-llama8b-retune7-r-4100-v1-mkmlizer: ║ Version: 0.29.3 ║
chaiml-llama8b-retune7-r-4100-v1-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-llama8b-retune7-r-4100-v1-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-llama8b-retune7-r-4100-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-llama8b-retune7-r-4100-v1-mkmlizer: ║ ║
chaiml-llama8b-retune7-r-4100-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-llama8b-retune7-r-4100-v1-mkmlizer: ║ belonging to: ║
chaiml-llama8b-retune7-r-4100-v1-mkmlizer: ║ ║
chaiml-llama8b-retune7-r-4100-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-llama8b-retune7-r-4100-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-llama8b-retune7-r-4100-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-llama8b-retune7-r-4100-v1-mkmlizer: ║ ║
chaiml-llama8b-retune7-r-4100-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-llama8b-retune7-r-4100-v1-mkmlizer: Downloaded to shared memory in 28.231s
chaiml-llama8b-retune7-r-4100-v1-mkmlizer: Checking if ChaiML/llama8b-retune7-rm-pointwise-datav1-500k-2e-64mckpt-newlinfull-seq512-1 already exists in ChaiML
chaiml-llama8b-retune7-r-4100-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmpgrr38u__, device:0
chaiml-llama8b-retune7-r-4100-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-llama8b-retune7-r-4100-v1-mkmlizer: quantized model in 19.210s
chaiml-llama8b-retune7-r-4100-v1-mkmlizer: Processed model ChaiML/llama8b-retune7-rm-pointwise-datav1-500k-2e-64mckpt-newlinfull-seq512-1 in 47.442s
chaiml-llama8b-retune7-r-4100-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-llama8b-retune7-r-4100-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-llama8b-retune7-r-4100-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-llama8b-retune7-r-4100-v1
chaiml-llama8b-retune7-r-4100-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-llama8b-retune7-r-4100-v1/config.json
chaiml-llama8b-retune7-r-4100-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-llama8b-retune7-r-4100-v1/special_tokens_map.json
chaiml-llama8b-retune7-r-4100-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-llama8b-retune7-r-4100-v1/tokenizer_config.json
chaiml-llama8b-retune7-r-4100-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-llama8b-retune7-r-4100-v1/tokenizer.json
chaiml-llama8b-retune7-r-4100-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:08, 33.08it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:05, 54.25it/s] Loading 0: 7%|▋ | 19/291 [00:00<00:05, 47.59it/s] Loading 0: 9%|▊ | 25/291 [00:00<00:05, 50.63it/s] Loading 0: 11%|█ | 32/291 [00:00<00:05, 46.82it/s] Loading 0: 14%|█▎ | 40/291 [00:00<00:04, 55.03it/s] Loading 0: 16%|█▌ | 46/291 [00:00<00:04, 50.07it/s] Loading 0: 18%|█▊ | 52/291 [00:01<00:04, 48.63it/s] Loading 0: 20%|█▉ | 58/291 [00:01<00:04, 50.68it/s] Loading 0: 22%|██▏ | 64/291 [00:01<00:04, 45.42it/s] Loading 0: 24%|██▎ | 69/291 [00:01<00:04, 45.64it/s] Loading 0: 26%|██▌ | 76/291 [00:01<00:04, 50.86it/s] Loading 0: 28%|██▊ | 82/291 [00:01<00:04, 46.29it/s] Loading 0: 30%|██▉ | 87/291 [00:02<00:06, 31.14it/s] Loading 0: 32%|███▏ | 94/291 [00:02<00:05, 37.89it/s] Loading 0: 34%|███▍ | 100/291 [00:02<00:04, 38.96it/s] Loading 0: 36%|███▌ | 105/291 [00:02<00:04, 39.93it/s] Loading 0: 38%|███▊ | 112/291 [00:02<00:03, 46.12it/s] Loading 0: 41%|████ | 118/291 [00:02<00:03, 45.32it/s] Loading 0: 42%|████▏ | 123/291 [00:02<00:03, 46.00it/s] Loading 0: 45%|████▍ | 130/291 [00:02<00:03, 51.89it/s] Loading 0: 47%|████▋ | 136/291 [00:02<00:03, 47.50it/s] Loading 0: 49%|████▉ | 142/291 [00:03<00:03, 48.66it/s] Loading 0: 51%|█████ | 149/291 [00:03<00:03, 45.01it/s] Loading 0: 54%|█████▍ | 157/291 [00:03<00:02, 51.79it/s] Loading 0: 56%|█████▌ | 163/291 [00:03<00:02, 47.87it/s] Loading 0: 58%|█████▊ | 169/291 [00:03<00:02, 48.23it/s] Loading 0: 61%|██████ | 177/291 [00:03<00:02, 49.28it/s] Loading 0: 63%|██████▎ | 183/291 [00:03<00:02, 49.02it/s] Loading 0: 65%|██████▍ | 188/291 [00:04<00:02, 36.02it/s] Loading 0: 66%|██████▋ | 193/291 [00:04<00:02, 36.74it/s] Loading 0: 68%|██████▊ | 199/291 [00:04<00:02, 37.88it/s] Loading 0: 70%|███████ | 204/291 [00:04<00:02, 38.50it/s] Loading 0: 72%|███████▏ | 210/291 [00:04<00:01, 43.38it/s] Loading 0: 74%|███████▍ | 215/291 [00:04<00:01, 43.12it/s] Loading 0: 76%|███████▌ | 220/291 [00:04<00:01, 44.68it/s] Loading 0: 78%|███████▊ | 226/291 [00:05<00:01, 41.70it/s] Loading 0: 79%|███████▉ | 231/291 [00:05<00:01, 42.06it/s] Loading 0: 82%|████████▏ | 238/291 [00:05<00:01, 48.27it/s] Loading 0: 84%|████████▍ | 244/291 [00:05<00:01, 45.24it/s] Loading 0: 86%|████████▌ | 249/291 [00:05<00:00, 44.71it/s] Loading 0: 88%|████████▊ | 256/291 [00:05<00:00, 50.72it/s] Loading 0: 90%|█████████ | 262/291 [00:05<00:00, 46.80it/s] Loading 0: 92%|█████████▏| 267/291 [00:05<00:00, 44.96it/s] Loading 0: 94%|█████████▍| 273/291 [00:06<00:00, 47.74it/s] Loading 0: 96%|█████████▌| 278/291 [00:06<00:00, 47.24it/s] Loading 0: 97%|█████████▋| 283/291 [00:06<00:00, 40.82it/s] Loading 0: 99%|█████████▉| 288/291 [00:06<00:00, 30.81it/s]
Job chaiml-llama8b-retune7-r-4100-v1-mkmlizer completed after 74.01s with status: succeeded
Stopping job with name chaiml-llama8b-retune7-r-4100-v1-mkmlizer
Pipeline stage MKMLizer completed in 74.60s
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-llama8b-retune7-r-4100-v1
Waiting for inference service chaiml-llama8b-retune7-r-4100-v1 to be ready
Inference service chaiml-llama8b-retune7-r-4100-v1 ready after 120.4778254032135s
Pipeline stage MKMLDeployer completed in 121.01s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 5.098431825637817s
Received healthy response to inference request in 4.820166349411011s
Received healthy response to inference request in 3.6012775897979736s
Received healthy response to inference request in 3.283794403076172s
Received healthy response to inference request in 3.34959077835083s
5 requests
0 failed requests
5th percentile: 3.2969536781311035
10th percentile: 3.310112953186035
20th percentile: 3.3364315032958984
30th percentile: 3.3999281406402586
40th percentile: 3.500602865219116
50th percentile: 3.6012775897979736
60th percentile: 4.0888330936431885
70th percentile: 4.576388597488403
80th percentile: 4.875819444656372
90th percentile: 4.987125635147095
95th percentile: 5.042778730392456
99th percentile: 5.087301206588745
mean time: 4.030652189254761
Pipeline stage StressChecker completed in 21.61s
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 0.76s
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 0.88s
Shutdown handler de-registered
chaiml-llama8b-retune7-r_4100_v1 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
Pipeline stage OfflineFamilyFriendlyScorer completed in 4351.18s
Shutdown handler de-registered
chaiml-llama8b-retune7-r_4100_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-llama8b-retune7-r_4100_v1 status is now torndown due to DeploymentManager action