chaiml-4d70-fd43-linear-w01

developer_uid: rirv938

submission_id: chaiml-4d70-fd43-linear-w01_v16

model_name: chaiml-4d70-fd43-linear-w01_v16

model_group: ChaiML/4d70-fd43-linear-

status: torndown

timestamp: 2025-12-12T18:26:56+00:00

num_battles: 6386

num_wins: 3349

celo_rating: 1313.99

family_friendly_score: 0.5014000000000001

family_friendly_standard_error: 0.007071040093225324

submission_type: basic

model_repo: ChaiML/4d70-fd43-linear-w01

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1800

max_output_tokens: 74

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.630963457301749, 'latency_mean': 1.5847778344154357, 'latency_p50': 1.5802125930786133, 'latency_p90': 1.7378884315490724}, {'batch_size': 3, 'throughput': 1.2540841564864231, 'latency_mean': 2.3890829563140867, 'latency_p50': 2.3930169343948364, 'latency_p90': 2.6022070169448854}, {'batch_size': 5, 'throughput': 1.5732199901859043, 'latency_mean': 3.167009598016739, 'latency_p50': 3.1743401288986206, 'latency_p90': 3.515540361404419}, {'batch_size': 6, 'throughput': 1.6662815838232297, 'latency_mean': 3.569642950296402, 'latency_p50': 3.5571844577789307, 'latency_p90': 4.0033286809921265}, {'batch_size': 8, 'throughput': 1.8329783087503775, 'latency_mean': 4.336496284008026, 'latency_p50': 4.334948420524597, 'latency_p90': 4.816675138473511}, {'batch_size': 10, 'throughput': 1.9134224628416077, 'latency_mean': 5.185276075601577, 'latency_p50': 5.189582467079163, 'latency_p90': 5.960004901885986}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: chaiml-4d70-fd43-linear-w01_v16

ineligible_reason: max_output_tokens!=64

is_internal_developer: True

language_model: ChaiML/4d70-fd43-linear-w01

model_size: 13B

ranking_group: single

throughput_3p7s: 1.71

us_pacific_date: 2025-11-26

win_ratio: 0.524428437206389

generation_params: {'temperature': 0.85, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.08, 'frequency_penalty': 0.08, 'stopping_words': ['</s>', '<|im_start|>', '###', '\n', '<|im_end|>'], 'max_input_tokens': 1800, 'best_of': 8, 'max_output_tokens': 74}

formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{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-4d70-fd43-linear-w01-v16-mkmlizer
Waiting for job on chaiml-4d70-fd43-linear-w01-v16-mkmlizer to finish
Stopping job with name chaiml-4d70-fd43-linear-w01-v16-mkmlizer
%s, retrying in %s seconds...
Starting job with name chaiml-4d70-fd43-linear-w01-v16-mkmlizer
Waiting for job on chaiml-4d70-fd43-linear-w01-v16-mkmlizer to finish
Stopping job with name chaiml-4d70-fd43-linear-w01-v16-mkmlizer
%s, retrying in %s seconds...
Starting job with name chaiml-4d70-fd43-linear-w01-v16-mkmlizer
Waiting for job on chaiml-4d70-fd43-linear-w01-v16-mkmlizer to finish
chaiml-4d70-fd43-linear-w01-v16-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-4d70-fd43-linear-w01-v16-mkmlizer: ║                                                                     ║
chaiml-4d70-fd43-linear-w01-v16-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-4d70-fd43-linear-w01-v16-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-4d70-fd43-linear-w01-v16-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-4d70-fd43-linear-w01-v16-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-4d70-fd43-linear-w01-v16-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-4d70-fd43-linear-w01-v16-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-4d70-fd43-linear-w01-v16-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-4d70-fd43-linear-w01-v16-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-4d70-fd43-linear-w01-v16-mkmlizer: ║                                                                     ║
chaiml-4d70-fd43-linear-w01-v16-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-4d70-fd43-linear-w01-v16-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-4d70-fd43-linear-w01-v16-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-4d70-fd43-linear-w01-v16-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-4d70-fd43-linear-w01-v16-mkmlizer: ║                                                                     ║
chaiml-4d70-fd43-linear-w01-v16-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-4d70-fd43-linear-w01-v16-mkmlizer: ║  belonging to:                                                      ║
chaiml-4d70-fd43-linear-w01-v16-mkmlizer: ║                                                                     ║
chaiml-4d70-fd43-linear-w01-v16-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-4d70-fd43-linear-w01-v16-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-4d70-fd43-linear-w01-v16-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-4d70-fd43-linear-w01-v16-mkmlizer: ║                                                                     ║
chaiml-4d70-fd43-linear-w01-v16-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-4d70-fd43-linear-w01-v16-mkmlizer: Downloaded to shared memory in 21.209s
chaiml-4d70-fd43-linear-w01-v16-mkmlizer: Checking if ChaiML/4d70-fd43-linear-w01 already exists in ChaiML
chaiml-4d70-fd43-linear-w01-v16-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpdta_kr1a, device:0
chaiml-4d70-fd43-linear-w01-v16-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-4d70-fd43-linear-w01-v16-mkmlizer: quantized model in 26.128s
chaiml-4d70-fd43-linear-w01-v16-mkmlizer: Processed model ChaiML/4d70-fd43-linear-w01 in 47.337s
chaiml-4d70-fd43-linear-w01-v16-mkmlizer: creating bucket guanaco-mkml-models
chaiml-4d70-fd43-linear-w01-v16-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-4d70-fd43-linear-w01-v16-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-4d70-fd43-linear-w01-v16/nvidia
chaiml-4d70-fd43-linear-w01-v16-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-4d70-fd43-linear-w01-v16/nvidia/special_tokens_map.json
chaiml-4d70-fd43-linear-w01-v16-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-4d70-fd43-linear-w01-v16/nvidia/config.json
chaiml-4d70-fd43-linear-w01-v16-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-4d70-fd43-linear-w01-v16/nvidia/tokenizer.json
chaiml-4d70-fd43-linear-w01-v16-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-4d70-fd43-linear-w01-v16/nvidia/flywheel_model.0.safetensors
chaiml-4d70-fd43-linear-w01-v16-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:05<16:16,  2.70s/it]
Loading 0:   2%|▏         | 6/363 [00:05<04:20,  1.37it/s]
Loading 0:   4%|▍         | 14/363 [00:05<01:25,  4.09it/s]
Loading 0:   6%|▌         | 20/363 [00:05<00:51,  6.67it/s]
Loading 0:   7%|▋         | 25/363 [00:05<00:36,  9.36it/s]
Loading 0:   9%|▉         | 33/363 [00:06<00:22, 14.42it/s]
Loading 0:  11%|█         | 40/363 [00:06<00:18, 17.61it/s]
Loading 0:  12%|█▏        | 45/363 [00:06<00:14, 21.21it/s]
Loading 0:  14%|█▍        | 51/363 [00:06<00:12, 24.73it/s]
Loading 0:  16%|█▋        | 59/363 [00:06<00:09, 33.15it/s]
Loading 0:  18%|█▊        | 65/363 [00:06<00:08, 36.35it/s]
Loading 0:  20%|█▉        | 71/363 [00:06<00:07, 40.37it/s]
Loading 0:  21%|██▏       | 78/363 [00:07<00:07, 40.65it/s]
Loading 0:  24%|██▍       | 87/363 [00:07<00:06, 45.35it/s]
Loading 0:  26%|██▋       | 96/363 [00:07<00:05, 48.69it/s]
Loading 0:  29%|██▉       | 105/363 [00:07<00:05, 50.93it/s]
Loading 0:  31%|███▏      | 114/363 [00:07<00:04, 52.63it/s]
Loading 0:  33%|███▎      | 121/363 [00:08<00:06, 37.27it/s]
Loading 0:  35%|███▍      | 126/363 [00:08<00:06, 37.70it/s]
Loading 0:  36%|███▌      | 131/363 [00:08<00:06, 38.00it/s]
Loading 0:  37%|███▋      | 136/363 [00:08<00:05, 39.07it/s]
Loading 0:  39%|███▉      | 141/363 [00:08<00:06, 33.45it/s]
Loading 0:  41%|████      | 149/363 [00:08<00:05, 42.68it/s]
Loading 0:  43%|████▎     | 155/363 [00:08<00:04, 44.57it/s]
Loading 0:  44%|████▍     | 160/363 [00:08<00:04, 45.36it/s]
Loading 0:  46%|████▌     | 167/363 [00:09<00:03, 51.31it/s]
Loading 0:  48%|████▊     | 173/363 [00:09<00:03, 50.65it/s]
Loading 0:  49%|████▉     | 179/363 [00:09<00:03, 51.76it/s]
Loading 0:  51%|█████     | 186/363 [00:09<00:03, 48.54it/s]
Loading 0:  53%|█████▎    | 194/363 [00:09<00:03, 55.92it/s]
Loading 0:  55%|█████▌    | 200/363 [00:09<00:03, 53.61it/s]
Loading 0:  57%|█████▋    | 206/363 [00:09<00:04, 38.59it/s]
Loading 0:  59%|█████▊    | 213/363 [00:10<00:03, 40.09it/s]
Loading 0:  60%|██████    | 218/363 [00:10<00:03, 37.99it/s]
Loading 0:  61%|██████▏   | 223/363 [00:10<00:03, 39.79it/s]
Loading 0:  63%|██████▎   | 230/363 [00:10<00:02, 46.43it/s]
Loading 0:  65%|██████▌   | 236/363 [00:10<00:02, 46.21it/s]
Loading 0:  67%|██████▋   | 242/363 [00:10<00:02, 48.97it/s]
Loading 0:  69%|██████▊   | 249/363 [00:10<00:02, 46.33it/s]
Loading 0:  71%|███████   | 257/363 [00:10<00:01, 53.96it/s]
Loading 0:  72%|███████▏  | 263/363 [00:11<00:01, 52.39it/s]
Loading 0:  74%|███████▍  | 269/363 [00:11<00:01, 53.37it/s]
Loading 0:  76%|███████▌  | 276/363 [00:11<00:01, 47.68it/s]
Loading 0:  78%|███████▊  | 283/363 [00:11<00:01, 41.17it/s]
Loading 0:  80%|███████▉  | 289/363 [00:11<00:01, 44.79it/s]
Loading 0:  81%|████████  | 294/363 [00:11<00:01, 41.53it/s]
Loading 0:  83%|████████▎ | 303/363 [00:12<00:01, 46.05it/s]
Loading 0:  86%|████████▌ | 311/363 [00:12<00:00, 53.37it/s]
Loading 0:  87%|████████▋ | 317/363 [00:12<00:00, 52.12it/s]
Loading 0:  89%|████████▉ | 323/363 [00:12<00:00, 52.93it/s]
Loading 0:  91%|█████████ | 330/363 [00:12<00:00, 50.14it/s]
Loading 0:  93%|█████████▎| 338/363 [00:12<00:00, 57.12it/s]
Loading 0:  95%|█████████▍| 344/363 [00:12<00:00, 54.86it/s]
Loading 0:  96%|█████████▋| 350/363 [00:12<00:00, 54.97it/s]
Loading 0:  98%|█████████▊| 357/363 [00:12<00:00, 51.05it/s]
                                                            
Job chaiml-4d70-fd43-linear-w01-v16-mkmlizer completed after 134.67s with status: succeeded
Stopping job with name chaiml-4d70-fd43-linear-w01-v16-mkmlizer
Pipeline stage MKMLizer completed in 166.35s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-4d70-fd43-linear-w01-v16
Waiting for inference service chaiml-4d70-fd43-linear-w01-v16 to be ready
Inference service chaiml-4d70-fd43-linear-w01-v16 ready after 162.07113647460938s
Pipeline stage MKMLDeployer completed in 162.83s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.870410442352295s
Received healthy response to inference request in 1.5050368309020996s
Received healthy response to inference request in 1.4443295001983643s
Received healthy response to inference request in 1.6748042106628418s
Received healthy response to inference request in 1.8209021091461182s
5 requests
0 failed requests
5th percentile: 1.4564709663391113
10th percentile: 1.4686124324798584
20th percentile: 1.4928953647613525
30th percentile: 1.538990306854248
40th percentile: 1.6068972587585448
50th percentile: 1.6748042106628418
60th percentile: 1.7332433700561523
70th percentile: 1.791682529449463
80th percentile: 1.8308037757873534
90th percentile: 1.8506071090698242
95th percentile: 1.8605087757110597
99th percentile: 1.8684301090240478
mean time: 1.6630966186523437
Pipeline stage StressChecker completed in 9.57s
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 0.63s
Shutdown handler de-registered
chaiml-4d70-fd43-linear-w01_v16 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 2841.99s
Shutdown handler de-registered
chaiml-4d70-fd43-linear-w01_v16 status is now inactive due to auto deactivation removed underperforming models
chaiml-4d70-fd43-linear-w01_v16 status is now torndown due to DeploymentManager action