developer_uid: NischayDnk
submission_id: chaiml-llama8b-retune7-_64875_v1
model_name: chaiml-llama8b-retune7-_64875_v1
model_group: ChaiML/llama8b-retune7-r
status: torndown
timestamp: 2025-06-23T15:04:55+00:00
num_battles: 15844
num_wins: 7865
celo_rating: 1285.69
family_friendly_score: 0.542
family_friendly_standard_error: 0.007046076922657033
submission_type: basic
model_repo: ChaiML/llama8b-retune7-rm-pointwise-datav1-900k-1e-64mckpt-newlinfull-seq512
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-_64875_v1
ineligible_reason: max_output_tokens!=64
is_internal_developer: False
language_model: ChaiML/llama8b-retune7-rm-pointwise-datav1-900k-1e-64mckpt-newlinfull-seq512
model_size: 8B
ranking_group: single
us_pacific_date: 2025-06-23
win_ratio: 0.4964024236303964
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-retune7-64875-v1-mkmlizer
Waiting for job on chaiml-llama8b-retune7-64875-v1-mkmlizer to finish
chaiml-llama8b-retune7-64875-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-llama8b-retune7-64875-v1-mkmlizer: ║ ║
chaiml-llama8b-retune7-64875-v1-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-llama8b-retune7-64875-v1-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-llama8b-retune7-64875-v1-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-llama8b-retune7-64875-v1-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-llama8b-retune7-64875-v1-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-llama8b-retune7-64875-v1-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-llama8b-retune7-64875-v1-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-llama8b-retune7-64875-v1-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-llama8b-retune7-64875-v1-mkmlizer: ║ ║
chaiml-llama8b-retune7-64875-v1-mkmlizer: ║ Version: 0.29.3 ║
chaiml-llama8b-retune7-64875-v1-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-llama8b-retune7-64875-v1-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-llama8b-retune7-64875-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-llama8b-retune7-64875-v1-mkmlizer: ║ ║
chaiml-llama8b-retune7-64875-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-llama8b-retune7-64875-v1-mkmlizer: ║ belonging to: ║
chaiml-llama8b-retune7-64875-v1-mkmlizer: ║ ║
chaiml-llama8b-retune7-64875-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-llama8b-retune7-64875-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-llama8b-retune7-64875-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-llama8b-retune7-64875-v1-mkmlizer: ║ ║
chaiml-llama8b-retune7-64875-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-llama8b-retune7-64875-v1-mkmlizer: Downloaded to shared memory in 29.154s
chaiml-llama8b-retune7-64875-v1-mkmlizer: Checking if ChaiML/llama8b-retune7-rm-pointwise-datav1-900k-1e-64mckpt-newlinfull-seq512 already exists in ChaiML
chaiml-llama8b-retune7-64875-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmp6rt3mobj, device:0
chaiml-llama8b-retune7-64875-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-llama8b-retune7-64875-v1-mkmlizer: quantized model in 18.953s
chaiml-llama8b-retune7-64875-v1-mkmlizer: Processed model ChaiML/llama8b-retune7-rm-pointwise-datav1-900k-1e-64mckpt-newlinfull-seq512 in 48.108s
chaiml-llama8b-retune7-64875-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-llama8b-retune7-64875-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-llama8b-retune7-64875-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-llama8b-retune7-64875-v1
chaiml-llama8b-retune7-64875-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-llama8b-retune7-64875-v1/config.json
chaiml-llama8b-retune7-64875-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-llama8b-retune7-64875-v1/special_tokens_map.json
chaiml-llama8b-retune7-64875-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-llama8b-retune7-64875-v1/tokenizer_config.json
chaiml-llama8b-retune7-64875-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-llama8b-retune7-64875-v1/tokenizer.json
chaiml-llama8b-retune7-64875-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:07, 39.55it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:04, 59.98it/s] Loading 0: 7%|▋ | 20/291 [00:00<00:05, 53.00it/s] Loading 0: 9%|▉ | 26/291 [00:00<00:04, 53.13it/s] Loading 0: 11%|█ | 32/291 [00:00<00:05, 43.47it/s] Loading 0: 14%|█▎ | 40/291 [00:00<00:04, 52.49it/s] Loading 0: 16%|█▌ | 46/291 [00:00<00:05, 48.03it/s] Loading 0: 18%|█▊ | 52/291 [00:01<00:04, 49.06it/s] Loading 0: 20%|█▉ | 58/291 [00:01<00:04, 51.28it/s] Loading 0: 22%|██▏ | 64/291 [00:01<00:04, 47.07it/s] Loading 0: 24%|██▎ | 69/291 [00:01<00:04, 46.46it/s] Loading 0: 26%|██▌ | 76/291 [00:01<00:04, 51.93it/s] Loading 0: 28%|██▊ | 82/291 [00:01<00:04, 45.83it/s] Loading 0: 30%|██▉ | 87/291 [00:02<00:06, 30.74it/s] Loading 0: 32%|███▏ | 94/291 [00:02<00:05, 37.35it/s] Loading 0: 34%|███▍ | 100/291 [00:02<00:05, 37.29it/s] Loading 0: 36%|███▌ | 105/291 [00:02<00:04, 38.29it/s] Loading 0: 38%|███▊ | 112/291 [00:02<00:04, 44.17it/s] Loading 0: 41%|████ | 118/291 [00:02<00:04, 42.57it/s] Loading 0: 42%|████▏ | 123/291 [00:02<00:03, 42.56it/s] Loading 0: 45%|████▍ | 130/291 [00:02<00:03, 48.02it/s] Loading 0: 47%|████▋ | 136/291 [00:03<00:03, 44.57it/s] Loading 0: 48%|████▊ | 141/291 [00:03<00:03, 44.28it/s] Loading 0: 51%|█████ | 148/291 [00:03<00:02, 49.27it/s] Loading 0: 53%|█████▎ | 154/291 [00:03<00:03, 44.53it/s] Loading 0: 55%|█████▍ | 159/291 [00:03<00:02, 44.17it/s] Loading 0: 57%|█████▋ | 166/291 [00:03<00:02, 49.30it/s] Loading 0: 59%|█████▉ | 172/291 [00:03<00:02, 45.50it/s] Loading 0: 62%|██████▏ | 179/291 [00:03<00:02, 49.84it/s] Loading 0: 64%|██████▎ | 185/291 [00:04<00:02, 51.04it/s] Loading 0: 66%|██████▌ | 191/291 [00:04<00:03, 32.15it/s] Loading 0: 67%|██████▋ | 196/291 [00:04<00:02, 34.15it/s] Loading 0: 69%|██████▉ | 202/291 [00:04<00:02, 38.52it/s] Loading 0: 71%|███████▏ | 208/291 [00:04<00:02, 38.55it/s] Loading 0: 73%|███████▎ | 213/291 [00:04<00:01, 39.69it/s] Loading 0: 76%|███████▌ | 220/291 [00:05<00:01, 45.10it/s] Loading 0: 78%|███████▊ | 226/291 [00:05<00:01, 42.25it/s] Loading 0: 79%|███████▉ | 231/291 [00:05<00:01, 42.56it/s] Loading 0: 82%|████████▏ | 238/291 [00:05<00:01, 48.01it/s] Loading 0: 84%|████████▍ | 244/291 [00:05<00:01, 44.77it/s] Loading 0: 86%|████████▌ | 249/291 [00:05<00:00, 44.52it/s] Loading 0: 88%|████████▊ | 256/291 [00:05<00:00, 49.98it/s] Loading 0: 90%|█████████ | 262/291 [00:05<00:00, 44.70it/s] Loading 0: 92%|█████████▏| 267/291 [00:06<00:00, 44.21it/s] Loading 0: 94%|█████████▍| 274/291 [00:06<00:00, 49.04it/s] Loading 0: 96%|█████████▌| 280/291 [00:06<00:00, 45.41it/s] Loading 0: 98%|█████████▊| 285/291 [00:06<00:00, 44.75it/s] Loading 0: 100%|█████████▉| 290/291 [00:06<00:00, 32.68it/s]
Job chaiml-llama8b-retune7-64875-v1-mkmlizer completed after 74.81s with status: succeeded
Stopping job with name chaiml-llama8b-retune7-64875-v1-mkmlizer
Pipeline stage MKMLizer completed in 75.61s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-llama8b-retune7-64875-v1
Waiting for inference service chaiml-llama8b-retune7-64875-v1 to be ready
Inference service chaiml-llama8b-retune7-64875-v1 ready after 120.48124408721924s
Pipeline stage MKMLDeployer completed in 121.08s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 5.32566237449646s
Received healthy response to inference request in 3.5244836807250977s
Received healthy response to inference request in 4.11487889289856s
Received healthy response to inference request in 2.7260749340057373s
Received healthy response to inference request in 3.9455342292785645s
5 requests
0 failed requests
5th percentile: 2.8857566833496096
10th percentile: 3.0454384326934814
20th percentile: 3.3648019313812254
30th percentile: 3.608693790435791
40th percentile: 3.777114009857178
50th percentile: 3.9455342292785645
60th percentile: 4.013272094726562
70th percentile: 4.08100996017456
80th percentile: 4.35703558921814
90th percentile: 4.8413489818572994
95th percentile: 5.08350567817688
99th percentile: 5.2772310352325436
mean time: 3.9273268222808837
Pipeline stage StressChecker completed in 21.32s
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 0.81s
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-llama8b-retune7-_64875_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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 8580.17s
Shutdown handler de-registered
chaiml-llama8b-retune7-_64875_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-llama8b-retune7-_64875_v1 status is now torndown due to DeploymentManager action