chaiml-gy-exp78-sft-gy-_32548

developer_uid: rirv938

submission_id: chaiml-gy-exp78-sft-gy-_32548_v3

model_name: chaiml-gy-exp78-sft-gy-_32548_v3

model_group: ChaiML/gy-exp78-sft-gy-d

status: torndown

timestamp: 2025-07-08T15:10:26+00:00

num_battles: 11238

num_wins: 5564

celo_rating: 1293.48

family_friendly_score: 0.5278

family_friendly_standard_error: 0.007060129743850322

submission_type: basic

model_repo: ChaiML/gy-exp78-sft-gy-datamix-v1-AR-ep2

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.5191780989133326, 'latency_mean': 1.9259375751018524, 'latency_p50': 1.9109091758728027, 'latency_p90': 2.134325695037842}, {'batch_size': 3, 'throughput': 1.0462134838670376, 'latency_mean': 2.8489841651916503, 'latency_p50': 2.85689115524292, 'latency_p90': 3.141860747337341}, {'batch_size': 5, 'throughput': 1.3332219450023697, 'latency_mean': 3.7292935526371003, 'latency_p50': 3.7268329858779907, 'latency_p90': 4.127624416351319}, {'batch_size': 6, 'throughput': 1.432959445087898, 'latency_mean': 4.171449214220047, 'latency_p50': 4.155273675918579, 'latency_p90': 4.641553974151611}, {'batch_size': 8, 'throughput': 1.5731883766946333, 'latency_mean': 5.04600160241127, 'latency_p50': 5.0395543575286865, 'latency_p90': 5.601717734336853}, {'batch_size': 10, 'throughput': 1.647882155310645, 'latency_mean': 6.0066221702098845, 'latency_p50': 5.968283176422119, 'latency_p90': 6.760723948478699}]

gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}

display_name: chaiml-gy-exp78-sft-gy-_32548_v3

is_internal_developer: True

language_model: ChaiML/gy-exp78-sft-gy-datamix-v1-AR-ep2

model_size: 24B

ranking_group: single

throughput_3p7s: 1.33

us_pacific_date: 2025-07-08

win_ratio: 0.4951058907278875

generation_params: {'temperature': 1.0, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.45, 'frequency_penalty': 0.45, 'stopping_words': ['###', '\n', 'You:', '</s>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '<|im_start|>assistant\n{message}<|im_end|>\n', 'user_template': '<|im_start|>user\nYou:{message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n', '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-gy-exp78-sft-gy-32548-v3-mkmlizer
Waiting for job on chaiml-gy-exp78-sft-gy-32548-v3-mkmlizer to finish
chaiml-gy-exp78-sft-gy-32548-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp78-sft-gy-32548-v3-mkmlizer: ║                                                                     ║
chaiml-gy-exp78-sft-gy-32548-v3-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp78-sft-gy-32548-v3-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp78-sft-gy-32548-v3-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp78-sft-gy-32548-v3-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp78-sft-gy-32548-v3-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp78-sft-gy-32548-v3-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp78-sft-gy-32548-v3-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp78-sft-gy-32548-v3-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp78-sft-gy-32548-v3-mkmlizer: ║                                                                     ║
chaiml-gy-exp78-sft-gy-32548-v3-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp78-sft-gy-32548-v3-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp78-sft-gy-32548-v3-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp78-sft-gy-32548-v3-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp78-sft-gy-32548-v3-mkmlizer: ║                                                                     ║
chaiml-gy-exp78-sft-gy-32548-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp78-sft-gy-32548-v3-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp78-sft-gy-32548-v3-mkmlizer: ║                                                                     ║
chaiml-gy-exp78-sft-gy-32548-v3-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp78-sft-gy-32548-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp78-sft-gy-32548-v3-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp78-sft-gy-32548-v3-mkmlizer: ║                                                                     ║
chaiml-gy-exp78-sft-gy-32548-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp78-sft-gy-32548-v3-mkmlizer: Downloaded to shared memory in 175.530s
chaiml-gy-exp78-sft-gy-32548-v3-mkmlizer: Checking if ChaiML/gy-exp78-sft-gy-datamix-v1-AR-ep2 already exists in ChaiML
chaiml-gy-exp78-sft-gy-32548-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmptjmz6k3g, device:0
chaiml-gy-exp78-sft-gy-32548-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp78-sft-gy-32548-v3-mkmlizer: quantized model in 47.678s
chaiml-gy-exp78-sft-gy-32548-v3-mkmlizer: Processed model ChaiML/gy-exp78-sft-gy-datamix-v1-AR-ep2 in 223.209s
chaiml-gy-exp78-sft-gy-32548-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp78-sft-gy-32548-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp78-sft-gy-32548-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp78-sft-gy-32548-v3/nvidia
chaiml-gy-exp78-sft-gy-32548-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp78-sft-gy-32548-v3/nvidia/config.json
chaiml-gy-exp78-sft-gy-32548-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp78-sft-gy-32548-v3/nvidia/special_tokens_map.json
chaiml-gy-exp78-sft-gy-32548-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp78-sft-gy-32548-v3/nvidia/tokenizer_config.json
chaiml-gy-exp78-sft-gy-32548-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp78-sft-gy-32548-v3/nvidia/tokenizer.json
chaiml-gy-exp78-sft-gy-32548-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp78-sft-gy-32548-v3/nvidia/flywheel_model.1.safetensors
chaiml-gy-exp78-sft-gy-32548-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp78-sft-gy-32548-v3/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp78-sft-gy-32548-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:17, 20.88it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:09, 35.43it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:10, 32.13it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:10, 32.49it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:11, 28.50it/s]
Loading 0:   8%|▊         | 30/363 [00:00<00:09, 33.43it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:14, 22.58it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:15, 21.20it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:14, 22.47it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:14, 22.77it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:12, 25.09it/s]
Loading 0:  14%|█▍        | 51/363 [00:02<00:13, 23.01it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:11, 26.42it/s]
Loading 0:  16%|█▌        | 58/363 [00:02<00:11, 27.14it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 26.10it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:11, 26.78it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:12, 23.17it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:14, 19.91it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:11, 25.47it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:11, 24.52it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 25.88it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:10, 26.31it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:12, 21.16it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:09, 26.75it/s]
Loading 0:  28%|██▊       | 101/363 [00:04<00:11, 22.79it/s]
Loading 0:  29%|██▉       | 106/363 [00:04<00:09, 27.85it/s]
Loading 0:  30%|███       | 110/363 [00:04<00:10, 23.03it/s]
Loading 0:  31%|███       | 113/363 [00:04<00:12, 19.89it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:09, 26.40it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:09, 25.66it/s]
Loading 0:  36%|███▌      | 129/363 [00:05<00:08, 27.82it/s]
Loading 0:  36%|███▋      | 132/363 [00:05<00:09, 24.82it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 28.87it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:08, 27.34it/s]
Loading 0:  40%|████      | 147/363 [00:05<00:06, 31.63it/s]
Loading 0:  42%|████▏     | 151/363 [00:06<00:09, 21.63it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:10, 20.73it/s]
Loading 0:  43%|████▎     | 157/363 [00:06<00:09, 22.03it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:08, 22.88it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 25.99it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:08, 23.85it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 28.83it/s]
Loading 0:  49%|████▉     | 177/363 [00:07<00:07, 25.59it/s]
Loading 0:  50%|█████     | 182/363 [00:07<00:06, 28.04it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:07, 24.61it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 22.93it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 24.02it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 24.32it/s]
Loading 0:  55%|█████▌    | 200/363 [00:22<00:06, 24.32it/s]
Loading 0:  55%|█████▌    | 201/363 [00:22<03:00,  1.12s/it]
Loading 0:  56%|█████▌    | 203/363 [00:22<02:30,  1.06it/s]
Loading 0:  57%|█████▋    | 208/363 [00:22<01:30,  1.71it/s]
Loading 0:  58%|█████▊    | 211/363 [00:22<01:09,  2.20it/s]
Loading 0:  59%|█████▉    | 214/363 [00:22<00:51,  2.90it/s]
Loading 0:  60%|██████    | 218/363 [00:23<00:35,  4.14it/s]
Loading 0:  61%|██████    | 221/363 [00:23<00:27,  5.26it/s]
Loading 0:  62%|██████▏   | 224/363 [00:23<00:22,  6.29it/s]
Loading 0:  63%|██████▎   | 229/363 [00:23<00:14,  9.33it/s]
Loading 0:  64%|██████▍   | 232/363 [00:23<00:11, 11.15it/s]
Loading 0:  65%|██████▌   | 237/363 [00:23<00:08, 14.97it/s]
Loading 0:  66%|██████▌   | 240/363 [00:23<00:07, 15.90it/s]
Loading 0:  68%|██████▊   | 246/363 [00:24<00:05, 21.34it/s]
Loading 0:  69%|██████▉   | 250/363 [00:24<00:05, 22.21it/s]
Loading 0:  70%|███████   | 255/363 [00:24<00:04, 25.42it/s]
Loading 0:  71%|███████▏  | 259/363 [00:24<00:04, 25.42it/s]
Loading 0:  73%|███████▎  | 265/363 [00:24<00:03, 32.04it/s]
Loading 0:  74%|███████▍  | 269/363 [00:24<00:04, 23.19it/s]
Loading 0:  75%|███████▌  | 273/363 [00:25<00:03, 23.25it/s]
Loading 0:  76%|███████▌  | 276/363 [00:25<00:03, 22.22it/s]
Loading 0:  78%|███████▊  | 282/363 [00:25<00:03, 26.95it/s]
Loading 0:  79%|███████▊  | 285/363 [00:25<00:03, 24.91it/s]
Loading 0:  80%|████████  | 291/363 [00:25<00:02, 29.41it/s]
Loading 0:  81%|████████▏ | 295/363 [00:25<00:02, 28.06it/s]
Loading 0:  82%|████████▏ | 299/363 [00:26<00:02, 28.19it/s]
Loading 0:  84%|████████▎ | 304/363 [00:26<00:02, 25.12it/s]
Loading 0:  85%|████████▍ | 307/363 [00:26<00:02, 23.47it/s]
Loading 0:  85%|████████▌ | 310/363 [00:26<00:02, 24.57it/s]
Loading 0:  86%|████████▌ | 313/363 [00:26<00:02, 24.57it/s]
Loading 0:  88%|████████▊ | 318/363 [00:26<00:01, 27.55it/s]
Loading 0:  88%|████████▊ | 321/363 [00:26<00:01, 25.16it/s]
Loading 0:  90%|█████████ | 327/363 [00:27<00:01, 29.39it/s]
Loading 0:  91%|█████████ | 330/363 [00:27<00:01, 26.14it/s]
Loading 0:  92%|█████████▏| 335/363 [00:27<00:00, 28.46it/s]
Loading 0:  93%|█████████▎| 338/363 [00:27<00:00, 26.93it/s]
Loading 0:  94%|█████████▍| 341/363 [00:27<00:01, 16.17it/s]
Loading 0:  96%|█████████▌| 347/363 [00:28<00:00, 21.70it/s]
Loading 0:  96%|█████████▋| 350/363 [00:28<00:00, 22.42it/s]
Loading 0:  98%|█████████▊| 355/363 [00:28<00:00, 25.79it/s]
Loading 0:  99%|█████████▊| 358/363 [00:28<00:00, 23.26it/s]
                                                            
Job chaiml-gy-exp78-sft-gy-32548-v3-mkmlizer completed after 258.99s with status: succeeded
Stopping job with name chaiml-gy-exp78-sft-gy-32548-v3-mkmlizer
Pipeline stage MKMLizer completed in 259.53s
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-gy-exp78-sft-gy-32548-v3
Waiting for inference service chaiml-gy-exp78-sft-gy-32548-v3 to be ready
Failed to get response for submission chaiml-adrian-your-toxi_89049_v2: HTTPConnectionPool(host='chaiml-adrian-your-toxi-89049-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission chaiml-gy-exp122-dpo-ex_18452_v2: ('http://chaiml-gy-exp122-dpo-ex-18452-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:50838->127.0.0.1:8080: read: connection reset by peer\n')
Inference service chaiml-gy-exp78-sft-gy-32548-v3 ready after 401.8838939666748s
Pipeline stage MKMLDeployer completed in 402.48s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.452976942062378s
Received healthy response to inference request in 1.8693511486053467s
Received healthy response to inference request in 2.2341082096099854s
Received healthy response to inference request in 2.2516889572143555s
Received healthy response to inference request in 14.024280786514282s
5 requests
0 failed requests
5th percentile: 1.9423025608062745
10th percentile: 2.0152539730072023
20th percentile: 2.1611567974090575
30th percentile: 2.2376243591308596
40th percentile: 2.2446566581726075
50th percentile: 2.2516889572143555
60th percentile: 2.3322041511535643
70th percentile: 2.4127193450927735
80th percentile: 4.767237710952761
90th percentile: 9.395759248733523
95th percentile: 11.710020017623899
99th percentile: 13.561428632736206
mean time: 4.566481208801269
Pipeline stage StressChecker completed in 24.65s
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 0.94s
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 0.86s
Shutdown handler de-registered
chaiml-gy-exp78-sft-gy-_32548_v3 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 3390.98s
Shutdown handler de-registered
chaiml-gy-exp78-sft-gy-_32548_v3 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp78-sft-gy-_32548_v3 status is now torndown due to DeploymentManager action