chaiml-workshopsft

developer_uid: cycy233

submission_id: chaiml-workshopsft_v5

model_name: c88

model_group: ChaiML/WorkshopSFT

status: torndown

timestamp: 2025-03-07T07:54:12+00:00

num_battles: 11449

num_wins: 5175

celo_rating: 1243.51

family_friendly_score: 0.5352

family_friendly_standard_error: 0.007053523374881521

submission_type: basic

model_repo: ChaiML/WorkshopSFT

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.6024895002428626, 'latency_mean': 1.6596831846237183, 'latency_p50': 1.6519896984100342, 'latency_p90': 1.8369157552719115}, {'batch_size': 3, 'throughput': 1.0988849272134902, 'latency_mean': 2.720335557460785, 'latency_p50': 2.71842360496521, 'latency_p90': 2.9716824293136597}, {'batch_size': 5, 'throughput': 1.3278871617570964, 'latency_mean': 3.7534118723869323, 'latency_p50': 3.7475496530532837, 'latency_p90': 4.20256917476654}, {'batch_size': 6, 'throughput': 1.3897050596275775, 'latency_mean': 4.297460272312164, 'latency_p50': 4.3266109228134155, 'latency_p90': 4.797146725654602}, {'batch_size': 8, 'throughput': 1.465898844614848, 'latency_mean': 5.417086143493652, 'latency_p50': 5.380346179008484, 'latency_p90': 6.127447533607483}, {'batch_size': 10, 'throughput': 1.4968970340515877, 'latency_mean': 6.621915847063065, 'latency_p50': 6.68737530708313, 'latency_p90': 7.510214781761169}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: c88

is_internal_developer: False

language_model: ChaiML/WorkshopSFT

model_size: 13B

ranking_group: single

throughput_3p7s: 1.32

us_pacific_date: 2025-03-06

win_ratio: 0.452004541881387

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': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '<|im_start|>system\n{memory}\n', 'prompt_template': '\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{bot_name}:', '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-workshopsft-v5-mkmlizer
Waiting for job on chaiml-workshopsft-v5-mkmlizer to finish
chaiml-workshopsft-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-workshopsft-v5-mkmlizer: ║     _____            __           __                                ║
chaiml-workshopsft-v5-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-workshopsft-v5-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-workshopsft-v5-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-workshopsft-v5-mkmlizer: ║       /___/                                                         ║
chaiml-workshopsft-v5-mkmlizer: ║                                                                     ║
chaiml-workshopsft-v5-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-workshopsft-v5-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-workshopsft-v5-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-workshopsft-v5-mkmlizer: ║                                                                     ║
chaiml-workshopsft-v5-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-workshopsft-v5-mkmlizer: ║  belonging to:                                                      ║
chaiml-workshopsft-v5-mkmlizer: ║                                                                     ║
chaiml-workshopsft-v5-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-workshopsft-v5-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-workshopsft-v5-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
chaiml-workshopsft-v5-mkmlizer: ║                                                                     ║
chaiml-workshopsft-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-workshopsft-v5-mkmlizer: Downloaded to shared memory in 42.890s
chaiml-workshopsft-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpgqfo59y9, device:0
chaiml-workshopsft-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-workshopsft-v5-mkmlizer: quantized model in 35.637s
chaiml-workshopsft-v5-mkmlizer: Processed model ChaiML/WorkshopSFT in 78.528s
chaiml-workshopsft-v5-mkmlizer: creating bucket guanaco-mkml-models
chaiml-workshopsft-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-workshopsft-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-workshopsft-v5
chaiml-workshopsft-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-workshopsft-v5/config.json
chaiml-workshopsft-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-workshopsft-v5/special_tokens_map.json
chaiml-workshopsft-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-workshopsft-v5/tokenizer_config.json
chaiml-workshopsft-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-workshopsft-v5/tokenizer.json
chaiml-workshopsft-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-workshopsft-v5/flywheel_model.0.safetensors
chaiml-workshopsft-v5-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 28.94it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:06, 51.04it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 49.10it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:06, 50.32it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 53.16it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:06, 48.99it/s]
Loading 0:  12%|█▏        | 43/363 [00:00<00:06, 49.83it/s]
Loading 0:  13%|█▎        | 49/363 [00:00<00:06, 51.87it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 48.22it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 33.70it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:08, 34.35it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 38.99it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:06, 41.12it/s]
Loading 0:  23%|██▎       | 83/363 [00:01<00:06, 42.11it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:05, 46.63it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:05, 46.07it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:05, 45.16it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:04, 51.21it/s]
Loading 0:  31%|███▏      | 114/363 [00:02<00:05, 46.99it/s]
Loading 0:  33%|███▎      | 119/363 [00:02<00:05, 45.86it/s]
Loading 0:  35%|███▍      | 126/363 [00:02<00:04, 50.83it/s]
Loading 0:  36%|███▋      | 132/363 [00:02<00:04, 48.69it/s]
Loading 0:  38%|███▊      | 137/363 [00:03<00:04, 47.39it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:06, 35.65it/s]
Loading 0:  40%|████      | 147/363 [00:03<00:06, 35.66it/s]
Loading 0:  42%|████▏     | 151/363 [00:03<00:05, 35.51it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:05, 39.93it/s]
Loading 0:  45%|████▍     | 163/363 [00:03<00:04, 40.53it/s]
Loading 0:  46%|████▋     | 168/363 [00:03<00:04, 41.27it/s]
Loading 0:  48%|████▊     | 175/363 [00:03<00:03, 47.08it/s]
Loading 0:  50%|████▉     | 180/363 [00:04<00:03, 47.52it/s]
Loading 0:  51%|█████     | 185/363 [00:04<00:04, 39.80it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 47.85it/s]
Loading 0:  55%|█████▍    | 199/363 [00:04<00:03, 46.64it/s]
Loading 0:  56%|█████▌    | 204/363 [00:04<00:03, 45.58it/s]
Loading 0:  58%|█████▊    | 211/363 [00:04<00:03, 50.37it/s]
Loading 0:  60%|█████▉    | 217/363 [00:04<00:03, 46.95it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:03, 36.37it/s]
Loading 0:  63%|██████▎   | 228/363 [00:05<00:03, 35.59it/s]
Loading 0:  64%|██████▍   | 232/363 [00:05<00:03, 35.60it/s]
Loading 0:  66%|██████▌   | 238/363 [00:05<00:03, 39.67it/s]
Loading 0:  67%|██████▋   | 243/363 [00:05<00:02, 42.08it/s]
Loading 0:  68%|██████▊   | 248/363 [00:05<00:03, 36.23it/s]
Loading 0:  70%|███████   | 255/363 [00:05<00:02, 43.79it/s]
Loading 0:  72%|███████▏  | 260/363 [00:06<00:02, 43.84it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:02, 44.48it/s]
Loading 0:  75%|███████▍  | 271/363 [00:06<00:02, 42.55it/s]
Loading 0:  76%|███████▌  | 276/363 [00:06<00:02, 41.52it/s]
Loading 0:  78%|███████▊  | 283/363 [00:06<00:01, 46.36it/s]
Loading 0:  80%|███████▉  | 289/363 [00:06<00:01, 43.21it/s]
Loading 0:  81%|████████  | 294/363 [00:06<00:01, 41.19it/s]
Loading 0:  83%|████████▎ | 301/363 [00:06<00:01, 47.48it/s]
Loading 0:  84%|████████▍ | 306/363 [00:13<00:21,  2.70it/s]
Loading 0:  85%|████████▌ | 310/363 [00:13<00:15,  3.43it/s]
Loading 0:  87%|████████▋ | 316/363 [00:13<00:09,  4.98it/s]
Loading 0:  88%|████████▊ | 321/363 [00:14<00:06,  6.54it/s]
Loading 0:  91%|█████████ | 329/363 [00:14<00:03, 10.16it/s]
Loading 0:  92%|█████████▏| 335/363 [00:14<00:02, 13.18it/s]
Loading 0:  94%|█████████▎| 340/363 [00:14<00:01, 16.13it/s]
Loading 0:  96%|█████████▌| 347/363 [00:14<00:00, 21.49it/s]
Loading 0:  97%|█████████▋| 353/363 [00:14<00:00, 25.40it/s]
Loading 0:  99%|█████████▊| 358/363 [00:14<00:00, 28.73it/s]
                                                            
Job chaiml-workshopsft-v5-mkmlizer completed after 103.75s with status: succeeded
Stopping job with name chaiml-workshopsft-v5-mkmlizer
Pipeline stage MKMLizer completed in 104.24s
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-workshopsft-v5
Waiting for inference service chaiml-workshopsft-v5 to be ready
Inference service chaiml-workshopsft-v5 ready after 90.51090359687805s
Pipeline stage MKMLDeployer completed in 91.06s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3291263580322266s
Received healthy response to inference request in 1.6003820896148682s
Received healthy response to inference request in 1.8475995063781738s
Received healthy response to inference request in 1.7376701831817627s
Received healthy response to inference request in 1.8734641075134277s
5 requests
0 failed requests
5th percentile: 1.627839708328247
10th percentile: 1.655297327041626
20th percentile: 1.7102125644683839
30th percentile: 1.759656047821045
40th percentile: 1.8036277770996094
50th percentile: 1.8475995063781738
60th percentile: 1.8579453468322753
70th percentile: 1.868291187286377
80th percentile: 1.9645965576171875
90th percentile: 2.146861457824707
95th percentile: 2.2379939079284665
99th percentile: 2.3108998680114747
mean time: 1.8776484489440919
Pipeline stage StressChecker completed in 10.75s
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 0.64s
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 0.65s
Shutdown handler de-registered
chaiml-workshopsft_v5 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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-workshopsft-v5-profiler
Waiting for inference service chaiml-workshopsft-v5-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
Pipeline stage OfflineFamilyFriendlyScorer completed in 4483.46s
Shutdown handler de-registered
chaiml-workshopsft_v5 status is now inactive due to auto deactivation removed underperforming models
chaiml-workshopsft_v5 status is now torndown due to DeploymentManager action