developer_uid: NischayDnk
submission_id: chaiml-llama31-204m-exp_51325_v1
model_name: chaiml-llama31-204m-exp_51325_v1
model_group: ChaiML/llama31-204m-exp2
status: torndown
timestamp: 2025-06-23T13:38:15+00:00
num_battles: 20833
num_wins: 10366
celo_rating: 1286.74
family_friendly_score: 0.5314
family_friendly_standard_error: 0.0070571104568371325
submission_type: basic
model_repo: ChaiML/llama31-204m-exp2-data-dynamicv1-900k-full-1e-s1
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-llama31-204m-exp_51325_v1
ineligible_reason: max_output_tokens!=64
is_internal_developer: False
language_model: ChaiML/llama31-204m-exp2-data-dynamicv1-900k-full-1e-s1
model_size: 8B
ranking_group: single
us_pacific_date: 2025-06-23
win_ratio: 0.49757596121537945
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-llama31-204m-exp-51325-v1-mkmlizer
Waiting for job on chaiml-llama31-204m-exp-51325-v1-mkmlizer to finish
chaiml-llama31-204m-exp-51325-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-llama31-204m-exp-51325-v1-mkmlizer: ║ ║
chaiml-llama31-204m-exp-51325-v1-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-llama31-204m-exp-51325-v1-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-llama31-204m-exp-51325-v1-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-llama31-204m-exp-51325-v1-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-llama31-204m-exp-51325-v1-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-llama31-204m-exp-51325-v1-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-llama31-204m-exp-51325-v1-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-llama31-204m-exp-51325-v1-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-llama31-204m-exp-51325-v1-mkmlizer: ║ ║
chaiml-llama31-204m-exp-51325-v1-mkmlizer: ║ Version: 0.29.3 ║
chaiml-llama31-204m-exp-51325-v1-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-llama31-204m-exp-51325-v1-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-llama31-204m-exp-51325-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-llama31-204m-exp-51325-v1-mkmlizer: ║ ║
chaiml-llama31-204m-exp-51325-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-llama31-204m-exp-51325-v1-mkmlizer: ║ belonging to: ║
chaiml-llama31-204m-exp-51325-v1-mkmlizer: ║ ║
chaiml-llama31-204m-exp-51325-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-llama31-204m-exp-51325-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-llama31-204m-exp-51325-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-llama31-204m-exp-51325-v1-mkmlizer: ║ ║
chaiml-llama31-204m-exp-51325-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-llama31-204m-exp-51325-v1-mkmlizer: Downloaded to shared memory in 26.947s
chaiml-llama31-204m-exp-51325-v1-mkmlizer: Checking if ChaiML/llama31-204m-exp2-data-dynamicv1-900k-full-1e-s1 already exists in ChaiML
chaiml-llama31-204m-exp-51325-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmpuirp_s_d, device:0
chaiml-llama31-204m-exp-51325-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-llama31-204m-exp-51325-v1-mkmlizer: quantized model in 19.407s
chaiml-llama31-204m-exp-51325-v1-mkmlizer: Processed model ChaiML/llama31-204m-exp2-data-dynamicv1-900k-full-1e-s1 in 46.354s
chaiml-llama31-204m-exp-51325-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-llama31-204m-exp-51325-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-llama31-204m-exp-51325-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-llama31-204m-exp-51325-v1
chaiml-llama31-204m-exp-51325-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-llama31-204m-exp-51325-v1/special_tokens_map.json
chaiml-llama31-204m-exp-51325-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-llama31-204m-exp-51325-v1/config.json
chaiml-llama31-204m-exp-51325-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-llama31-204m-exp-51325-v1/tokenizer_config.json
chaiml-llama31-204m-exp-51325-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-llama31-204m-exp-51325-v1/tokenizer.json
chaiml-llama31-204m-exp-51325-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-llama31-204m-exp-51325-v1/flywheel_model.0.safetensors
chaiml-llama31-204m-exp-51325-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:08, 34.49it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:05, 52.55it/s] Loading 0: 7%|▋ | 19/291 [00:00<00:06, 45.20it/s] Loading 0: 8%|▊ | 24/291 [00:00<00:06, 44.18it/s] Loading 0: 11%|█ | 31/291 [00:00<00:05, 50.37it/s] Loading 0: 13%|█▎ | 37/291 [00:00<00:05, 43.92it/s] Loading 0: 14%|█▍ | 42/291 [00:00<00:05, 42.67it/s] Loading 0: 17%|█▋ | 49/291 [00:01<00:05, 47.63it/s] Loading 0: 19%|█▊ | 54/291 [00:01<00:04, 48.02it/s] Loading 0: 20%|██ | 59/291 [00:01<00:05, 39.58it/s] Loading 0: 23%|██▎ | 67/291 [00:01<00:04, 47.77it/s] Loading 0: 25%|██▌ | 73/291 [00:01<00:04, 44.78it/s] Loading 0: 27%|██▋ | 78/291 [00:01<00:04, 43.29it/s] Loading 0: 29%|██▊ | 83/291 [00:02<00:06, 31.56it/s] Loading 0: 30%|██▉ | 87/291 [00:02<00:06, 31.79it/s] Loading 0: 32%|███▏ | 94/291 [00:02<00:05, 38.96it/s] Loading 0: 34%|███▍ | 100/291 [00:02<00:04, 38.70it/s] Loading 0: 36%|███▌ | 105/291 [00:02<00:04, 38.92it/s] Loading 0: 38%|███▊ | 112/291 [00:02<00:03, 44.86it/s] Loading 0: 41%|████ | 118/291 [00:02<00:04, 42.85it/s] Loading 0: 42%|████▏ | 123/291 [00:02<00:03, 42.99it/s] Loading 0: 45%|████▍ | 130/291 [00:03<00:03, 48.11it/s] Loading 0: 47%|████▋ | 136/291 [00:03<00:03, 43.90it/s] Loading 0: 48%|████▊ | 141/291 [00:03<00:03, 43.06it/s] Loading 0: 51%|█████ | 148/291 [00:03<00:02, 47.79it/s] Loading 0: 53%|█████▎ | 154/291 [00:03<00:03, 44.18it/s] Loading 0: 55%|█████▍ | 159/291 [00:03<00:03, 43.50it/s] Loading 0: 57%|█████▋ | 166/291 [00:03<00:02, 49.16it/s] Loading 0: 59%|█████▉ | 172/291 [00:03<00:02, 45.41it/s] Loading 0: 62%|██████▏ | 179/291 [00:04<00:02, 49.59it/s] Loading 0: 64%|██████▎ | 185/291 [00:04<00:02, 50.74it/s] Loading 0: 66%|██████▌ | 191/291 [00:04<00:03, 31.51it/s] Loading 0: 67%|██████▋ | 196/291 [00:04<00:02, 33.47it/s] Loading 0: 69%|██████▉ | 201/291 [00:04<00:02, 36.71it/s] Loading 0: 71%|███████ | 206/291 [00:04<00:02, 38.57it/s] Loading 0: 73%|███████▎ | 211/291 [00:05<00:01, 40.85it/s] Loading 0: 75%|███████▍ | 217/291 [00:05<00:01, 39.85it/s] Loading 0: 76%|███████▋ | 222/291 [00:05<00:01, 40.49it/s] Loading 0: 79%|███████▊ | 229/291 [00:05<00:01, 46.25it/s] Loading 0: 81%|████████ | 235/291 [00:05<00:01, 42.38it/s] Loading 0: 82%|████████▏ | 240/291 [00:05<00:01, 40.59it/s] Loading 0: 85%|████████▍ | 246/291 [00:05<00:00, 45.12it/s] Loading 0: 86%|████████▋ | 251/291 [00:05<00:00, 45.52it/s] Loading 0: 88%|████████▊ | 256/291 [00:06<00:00, 46.60it/s] Loading 0: 90%|█████████ | 262/291 [00:06<00:00, 43.87it/s] Loading 0: 92%|█████████▏| 267/291 [00:06<00:00, 43.63it/s] Loading 0: 94%|█████████▍| 274/291 [00:06<00:00, 48.85it/s] Loading 0: 96%|█████████▌| 280/291 [00:06<00:00, 44.78it/s] Loading 0: 98%|█████████▊| 285/291 [00:06<00:00, 43.94it/s] Loading 0: 100%|█████████▉| 290/291 [00:06<00:00, 32.54it/s]
Job chaiml-llama31-204m-exp-51325-v1-mkmlizer completed after 73.85s with status: succeeded
Stopping job with name chaiml-llama31-204m-exp-51325-v1-mkmlizer
Pipeline stage MKMLizer completed in 74.43s
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-llama31-204m-exp-51325-v1
Waiting for inference service chaiml-llama31-204m-exp-51325-v1 to be ready
Inference service chaiml-llama31-204m-exp-51325-v1 ready after 120.45984411239624s
Pipeline stage MKMLDeployer completed in 121.47s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 4.590876340866089s
Received healthy response to inference request in 6.010126113891602s
Received healthy response to inference request in 3.3737053871154785s
{"detail":"HTTPConnectionPool(host='chaiml-llama31-204m-exp-51325-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Max retries exceeded with url: /v1/models/GPT-J-6B-lit-v2:predict (Caused by ConnectTimeoutError(<urllib3.connection.HTTPConnection object at 0x74ae68785950>, 'Connection to chaiml-llama31-204m-exp-51325-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com timed out. (connect timeout=12.0)'))"}
Received unhealthy response to inference request!
Received healthy response to inference request in 3.5627951622009277s
5 requests
1 failed requests
5th percentile: 3.4115233421325684
10th percentile: 3.449341297149658
20th percentile: 3.524977207183838
30th percentile: 3.76841139793396
40th percentile: 4.179643869400024
50th percentile: 4.590876340866089
60th percentile: 5.158576250076294
70th percentile: 5.726276159286499
80th percentile: 8.148142004013064
90th percentile: 12.424173784255983
95th percentile: 14.56218967437744
99th percentile: 16.27260238647461
mean time: 6.8475417137146
%s, retrying in %s seconds...
Received healthy response to inference request in 4.942746639251709s
Received healthy response to inference request in 3.676462173461914s
Received healthy response to inference request in 6.0053393840789795s
Received healthy response to inference request in 2.659374713897705s
Received healthy response to inference request in 3.8985226154327393s
5 requests
0 failed requests
5th percentile: 2.862792205810547
10th percentile: 3.0662096977233886
20th percentile: 3.473044681549072
30th percentile: 3.7208742618560793
40th percentile: 3.8096984386444093
50th percentile: 3.8985226154327393
60th percentile: 4.316212224960327
70th percentile: 4.733901834487915
80th percentile: 5.155265188217164
90th percentile: 5.580302286148071
95th percentile: 5.792820835113525
99th percentile: 5.962835674285889
mean time: 4.236489105224609
Pipeline stage StressChecker completed in 58.32s
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 0.68s
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 0.74s
Shutdown handler de-registered
chaiml-llama31-204m-exp_51325_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 7854.89s
Shutdown handler de-registered
chaiml-llama31-204m-exp_51325_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-llama31-204m-exp_51325_v1 status is now torndown due to DeploymentManager action