chaiml-1031-quang-ir-lt_17085

developer_uid: chai_backend_admin

submission_id: chaiml-1031-quang-ir-lt_17085_v1

model_name: training123

model_group: ChaiML/1031-quang-ir-ltr

status: inactive

timestamp: 2025-11-01T06:27:08+00:00

num_battles: 6653

num_wins: 3413

celo_rating: 1302.97

family_friendly_score: 0.513

family_friendly_standard_error: 0.007068677386894949

submission_type: basic

model_repo: ChaiML/1031-quang-ir-ltry-mix3-maxb3-cld3b-iq8-adh8_5e63e

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 8

max_input_tokens: 2048

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.38082104530489636, 'latency_mean': 2.6257836961746217, 'latency_p50': 2.6282986402511597, 'latency_p90': 2.894368529319763}, {'batch_size': 2, 'throughput': 0.5639763643073324, 'latency_mean': 3.5314906239509583, 'latency_p50': 3.533724546432495, 'latency_p90': 3.838819432258606}, {'batch_size': 3, 'throughput': 0.6964786511031875, 'latency_mean': 4.286526571512223, 'latency_p50': 4.285780072212219, 'latency_p90': 4.726680469512939}, {'batch_size': 4, 'throughput': 0.7883390712937226, 'latency_mean': 5.055565081834793, 'latency_p50': 5.074495434761047, 'latency_p90': 5.810005021095276}, {'batch_size': 5, 'throughput': 0.8524959666032143, 'latency_mean': 5.837055510282516, 'latency_p50': 5.818010091781616, 'latency_p90': 6.4542893171310425}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/1031-quang-ir-ltry-mix3-maxb3-cld3b-iq8-adh8_5e63e

model_size: 24B

ranking_group: single

throughput_3p7s: 0.6

us_pacific_date: 2025-10-31

win_ratio: 0.5130016533894484

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['</s>', '\n', 'You:', '####\n', '####'], 'max_input_tokens': 2048, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': "{bot_name}'s persona: {memory}", 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': 'You: {message}\n', 'response_template': '####\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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Starting job with name chaiml-1031-quang-ir-lt-17085-v1-mkmlizer
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Waiting for job on chaiml-1031-quang-ir-lt-17085-v1-mkmlizer to finish
chaiml-1031-quang-ir-lt-17085-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-1031-quang-ir-lt-17085-v1-mkmlizer: ║                                                                     ║
chaiml-1031-quang-ir-lt-17085-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-1031-quang-ir-lt-17085-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-1031-quang-ir-lt-17085-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-1031-quang-ir-lt-17085-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-1031-quang-ir-lt-17085-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-1031-quang-ir-lt-17085-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-1031-quang-ir-lt-17085-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-1031-quang-ir-lt-17085-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-1031-quang-ir-lt-17085-v1-mkmlizer: ║                                                                     ║
chaiml-1031-quang-ir-lt-17085-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-1031-quang-ir-lt-17085-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-1031-quang-ir-lt-17085-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-1031-quang-ir-lt-17085-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-1031-quang-ir-lt-17085-v1-mkmlizer: ║                                                                     ║
chaiml-1031-quang-ir-lt-17085-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-1031-quang-ir-lt-17085-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-1031-quang-ir-lt-17085-v1-mkmlizer: ║                                                                     ║
chaiml-1031-quang-ir-lt-17085-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-1031-quang-ir-lt-17085-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-1031-quang-ir-lt-17085-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-1031-quang-ir-lt-17085-v1-mkmlizer: ║                                                                     ║
chaiml-1031-quang-ir-lt-17085-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-1031-quang-ir-lt-17085-v1-mkmlizer: Downloaded to shared memory in 61.056s
chaiml-1031-quang-ir-lt-17085-v1-mkmlizer: Checking if ChaiML/1031-quang-ir-ltry-mix3-maxb3-cld3b-iq8-adh8_5e63e already exists in ChaiML
chaiml-1031-quang-ir-lt-17085-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp76w0as7x, device:0
chaiml-1031-quang-ir-lt-17085-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-1031-quang-ir-lt-17085-v1-mkmlizer: quantized model in 42.619s
chaiml-1031-quang-ir-lt-17085-v1-mkmlizer: Processed model ChaiML/1031-quang-ir-ltry-mix3-maxb3-cld3b-iq8-adh8_5e63e in 103.675s
chaiml-1031-quang-ir-lt-17085-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-1031-quang-ir-lt-17085-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-1031-quang-ir-lt-17085-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-1031-quang-ir-lt-17085-v1/nvidia
chaiml-1031-quang-ir-lt-17085-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-1031-quang-ir-lt-17085-v1/nvidia/config.json
chaiml-1031-quang-ir-lt-17085-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-1031-quang-ir-lt-17085-v1/nvidia/special_tokens_map.json
chaiml-1031-quang-ir-lt-17085-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-1031-quang-ir-lt-17085-v1/nvidia/tokenizer_config.json
chaiml-1031-quang-ir-lt-17085-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-1031-quang-ir-lt-17085-v1/nvidia/flywheel_model.1.safetensors
chaiml-1031-quang-ir-lt-17085-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-1031-quang-ir-lt-17085-v1/nvidia/flywheel_model.0.safetensors
chaiml-1031-quang-ir-lt-17085-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.93it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:08, 39.72it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:09, 37.09it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:09, 36.46it/s]
Loading 0:   7%|▋         | 26/363 [00:00<00:09, 36.87it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 42.22it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:12, 25.95it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:13, 24.17it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 31.38it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 29.85it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:09, 33.41it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 31.41it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:09, 32.02it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:10, 28.67it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:11, 25.95it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 29.98it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:08, 31.41it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:09, 27.79it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:09, 27.15it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:07, 34.52it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:08, 32.37it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:09, 27.69it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:08, 30.04it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:08, 29.81it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:07, 31.88it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:07, 30.41it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:06, 33.99it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 31.64it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 34.86it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:06, 32.30it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 38.86it/s]
Loading 0:  42%|████▏     | 153/363 [00:05<00:08, 24.83it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:08, 25.02it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 31.78it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 30.54it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 33.64it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 31.81it/s]
Loading 0:  50%|█████     | 182/363 [00:05<00:05, 32.52it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:06, 28.50it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:06, 28.02it/s]
Loading 0:  53%|█████▎    | 194/363 [00:06<00:07, 23.64it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:14,  1.21it/s]
Loading 0:  56%|█████▌    | 203/363 [00:19<01:55,  1.39it/s]
Loading 0:  57%|█████▋    | 208/363 [00:19<01:14,  2.08it/s]
Loading 0:  58%|█████▊    | 211/363 [00:20<00:57,  2.63it/s]
Loading 0:  59%|█████▉    | 214/363 [00:20<00:44,  3.36it/s]
Loading 0:  60%|██████    | 218/363 [00:20<00:31,  4.66it/s]
Loading 0:  61%|██████    | 221/363 [00:20<00:24,  5.79it/s]
Loading 0:  62%|██████▏   | 224/363 [00:20<00:20,  6.64it/s]
Loading 0:  63%|██████▎   | 229/363 [00:20<00:13,  9.78it/s]
Loading 0:  64%|██████▍   | 232/363 [00:21<00:11, 11.65it/s]
Loading 0:  65%|██████▌   | 237/363 [00:21<00:07, 16.10it/s]
Loading 0:  66%|██████▋   | 241/363 [00:21<00:06, 18.26it/s]
Loading 0:  68%|██████▊   | 246/363 [00:21<00:05, 23.02it/s]
Loading 0:  69%|██████▉   | 250/363 [00:21<00:04, 24.12it/s]
Loading 0:  70%|███████   | 255/363 [00:21<00:03, 28.61it/s]
Loading 0:  71%|███████▏  | 259/363 [00:21<00:03, 28.23it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:02, 35.31it/s]
Loading 0:  75%|███████▍  | 271/363 [00:22<00:03, 25.35it/s]
Loading 0:  76%|███████▌  | 275/363 [00:22<00:03, 23.67it/s]
Loading 0:  78%|███████▊  | 282/363 [00:22<00:02, 30.75it/s]
Loading 0:  79%|███████▉  | 286/363 [00:22<00:02, 30.12it/s]
Loading 0:  80%|████████  | 291/363 [00:22<00:02, 33.45it/s]
Loading 0:  81%|████████▏ | 295/363 [00:22<00:02, 31.99it/s]
Loading 0:  82%|████████▏ | 299/363 [00:23<00:01, 33.00it/s]
Loading 0:  84%|████████▎ | 304/363 [00:23<00:01, 30.02it/s]
Loading 0:  85%|████████▍ | 308/363 [00:23<00:02, 25.07it/s]
Loading 0:  86%|████████▌ | 311/363 [00:23<00:02, 21.84it/s]
Loading 0:  88%|████████▊ | 318/363 [00:23<00:01, 29.82it/s]
Loading 0:  89%|████████▊ | 322/363 [00:23<00:01, 29.40it/s]
Loading 0:  90%|█████████ | 327/363 [00:24<00:01, 32.99it/s]
Loading 0:  91%|█████████ | 331/363 [00:24<00:01, 31.24it/s]
Loading 0:  92%|█████████▏| 335/363 [00:24<00:00, 32.20it/s]
Loading 0:  93%|█████████▎| 339/363 [00:24<00:00, 32.38it/s]
Loading 0:  94%|█████████▍| 343/363 [00:24<00:00, 20.04it/s]
Loading 0:  96%|█████████▌| 348/363 [00:25<00:00, 21.66it/s]
Loading 0:  98%|█████████▊| 355/363 [00:25<00:00, 29.09it/s]
Loading 0:  99%|█████████▉| 359/363 [00:25<00:00, 28.51it/s]
                                                            
Job chaiml-1031-quang-ir-lt-17085-v1-mkmlizer completed after 175.39s with status: succeeded
Stopping job with name chaiml-1031-quang-ir-lt-17085-v1-mkmlizer
Pipeline stage MKMLizer completed in 176.46s
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-1031-quang-ir-lt-17085-v1
Waiting for inference service chaiml-1031-quang-ir-lt-17085-v1 to be ready
Inference service chaiml-1031-quang-ir-lt-17085-v1 ready after 130.55085062980652s
Pipeline stage MKMLDeployer completed in 131.15s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3446571826934814s
Received healthy response to inference request in 2.512305974960327s
Received healthy response to inference request in 2.4265670776367188s
Received healthy response to inference request in 2.1374030113220215s
Received healthy response to inference request in 2.2053050994873047s
5 requests
0 failed requests
5th percentile: 2.150983428955078
10th percentile: 2.164563846588135
20th percentile: 2.191724681854248
30th percentile: 2.23317551612854
40th percentile: 2.2889163494110107
50th percentile: 2.3446571826934814
60th percentile: 2.3774211406707764
70th percentile: 2.4101850986480713
80th percentile: 2.4437148571014404
90th percentile: 2.478010416030884
95th percentile: 2.4951581954956055
99th percentile: 2.508876419067383
mean time: 2.3252476692199706
Pipeline stage StressChecker completed in 13.58s
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 0.69s
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-1031-quang-ir-lt_17085_v1 status is now deployed due to DeploymentManager action
Unable to record family friendly update due to error: Invalid JSON input: Expecting value: line 1 column 1 (char 0)
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 2976.93s
Shutdown handler de-registered
chaiml-1031-quang-ir-lt_17085_v1 status is now inactive due to auto deactivation removed underperforming models