developer_uid: chai_backend_admin
submission_id: chaiml-1031-quang-ir-ltr_9208_v1
model_name: training123
model_group: ChaiML/1031-quang-ir-ltr
status: inactive
timestamp: 2025-10-31T22:26:00+00:00
num_battles: 5777
num_wins: 2969
celo_rating: 1290.23
family_friendly_score: 0.505
family_friendly_standard_error: 0.007070714249635605
submission_type: basic
model_repo: ChaiML/1031-quang-ir-ltry-mix3-maxb3-cld3b-iq8-adh8_5e62ep
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': 0.38179380401414453, 'latency_mean': 2.6190881538391113, 'latency_p50': 2.598507285118103, 'latency_p90': 2.8724462747573853}, {'batch_size': 2, 'throughput': 0.5766666581492823, 'latency_mean': 3.459190192222595, 'latency_p50': 3.4370458126068115, 'latency_p90': 3.7593507528305055}, {'batch_size': 3, 'throughput': 0.7130443885901379, 'latency_mean': 4.189056022167206, 'latency_p50': 4.181254744529724, 'latency_p90': 4.636690092086792}, {'batch_size': 4, 'throughput': 0.8117491849143014, 'latency_mean': 4.9108252108097075, 'latency_p50': 4.922704458236694, 'latency_p90': 5.710464811325073}, {'batch_size': 5, 'throughput': 0.8728192131608368, 'latency_mean': 5.70941257238388, 'latency_p50': 5.752074360847473, 'latency_p90': 6.516151213645935}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: training123
is_internal_developer: True
language_model: ChaiML/1031-quang-ir-ltry-mix3-maxb3-cld3b-iq8-adh8_5e62ep
model_size: 24B
ranking_group: single
throughput_3p7s: 0.63
us_pacific_date: 2025-10-31
win_ratio: 0.5139345681149385
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': ['####\n', '####', 'You:', '</s>', '\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
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
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
Starting job with name chaiml-1031-quang-ir-ltr-9208-v1-mkmlizer
Waiting for job on chaiml-1031-quang-ir-ltr-9208-v1-mkmlizer to finish
chaiml-1031-quang-ir-ltr-9208-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-1031-quang-ir-ltr-9208-v1-mkmlizer: ║                                                                     ║
chaiml-1031-quang-ir-ltr-9208-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-1031-quang-ir-ltr-9208-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-1031-quang-ir-ltr-9208-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-1031-quang-ir-ltr-9208-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-1031-quang-ir-ltr-9208-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-1031-quang-ir-ltr-9208-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-1031-quang-ir-ltr-9208-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-1031-quang-ir-ltr-9208-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-1031-quang-ir-ltr-9208-v1-mkmlizer: ║                                                                     ║
chaiml-1031-quang-ir-ltr-9208-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-1031-quang-ir-ltr-9208-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-1031-quang-ir-ltr-9208-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-1031-quang-ir-ltr-9208-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-1031-quang-ir-ltr-9208-v1-mkmlizer: ║                                                                     ║
chaiml-1031-quang-ir-ltr-9208-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-1031-quang-ir-ltr-9208-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-1031-quang-ir-ltr-9208-v1-mkmlizer: ║                                                                     ║
chaiml-1031-quang-ir-ltr-9208-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-1031-quang-ir-ltr-9208-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-1031-quang-ir-ltr-9208-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-1031-quang-ir-ltr-9208-v1-mkmlizer: ║                                                                     ║
chaiml-1031-quang-ir-ltr-9208-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
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
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-1031-quang-ir-ltr-9208-v1-mkmlizer: Downloaded to shared memory in 78.658s
chaiml-1031-quang-ir-ltr-9208-v1-mkmlizer: Checking if ChaiML/1031-quang-ir-ltry-mix3-maxb3-cld3b-iq8-adh8_5e62ep already exists in ChaiML
chaiml-1031-quang-ir-ltr-9208-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpj4a0kwoi, device:0
chaiml-1031-quang-ir-ltr-9208-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-1031-quang-ir-ltr-9208-v1-mkmlizer: quantized model in 41.864s
chaiml-1031-quang-ir-ltr-9208-v1-mkmlizer: Processed model ChaiML/1031-quang-ir-ltry-mix3-maxb3-cld3b-iq8-adh8_5e62ep in 120.523s
chaiml-1031-quang-ir-ltr-9208-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-1031-quang-ir-ltr-9208-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-1031-quang-ir-ltr-9208-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-1031-quang-ir-ltr-9208-v1/nvidia
chaiml-1031-quang-ir-ltr-9208-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-1031-quang-ir-ltr-9208-v1/nvidia/config.json
chaiml-1031-quang-ir-ltr-9208-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-1031-quang-ir-ltr-9208-v1/nvidia/special_tokens_map.json
chaiml-1031-quang-ir-ltr-9208-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-1031-quang-ir-ltr-9208-v1/nvidia/tokenizer_config.json
chaiml-1031-quang-ir-ltr-9208-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-1031-quang-ir-ltr-9208-v1/nvidia/tokenizer.json
chaiml-1031-quang-ir-ltr-9208-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-1031-quang-ir-ltr-9208-v1/nvidia/flywheel_model.1.safetensors
chaiml-1031-quang-ir-ltr-9208-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-1031-quang-ir-ltr-9208-v1/nvidia/flywheel_model.0.safetensors
chaiml-1031-quang-ir-ltr-9208-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 22.49it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:09, 38.33it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:08, 41.11it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 31.78it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 44.39it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:10, 30.14it/s]
Loading 0:  12%|█▏        | 42/363 [00:01<00:11, 27.48it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 32.72it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:09, 31.72it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:08, 35.09it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 33.25it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:08, 34.50it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:09, 31.01it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:10, 27.42it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 31.39it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:08, 32.18it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:10, 27.54it/s]
Loading 0:  25%|██▌       | 92/363 [00:02<00:10, 26.93it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:07, 34.30it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:08, 32.27it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:09, 27.51it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:08, 30.11it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:08, 30.81it/s]
Loading 0:  33%|███▎      | 121/363 [00:03<00:07, 32.21it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:07, 33.57it/s]
Loading 0:  36%|███▌      | 130/363 [00:04<00:06, 34.18it/s]
Loading 0:  37%|███▋      | 134/363 [00:04<00:06, 33.85it/s]
Loading 0:  38%|███▊      | 139/363 [00:04<00:06, 34.29it/s]
Loading 0:  39%|███▉      | 143/363 [00:04<00:06, 34.85it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 39.83it/s]
Loading 0:  42%|████▏     | 154/363 [00:04<00:07, 27.43it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:08, 25.55it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 32.94it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 31.84it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 35.21it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 31.89it/s]
Loading 0:  50%|█████     | 182/363 [00:05<00:05, 32.82it/s]
Loading 0:  52%|█████▏    | 187/363 [00:05<00:05, 30.34it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:05, 29.54it/s]
Loading 0:  54%|█████▎    | 195/363 [00:06<00:06, 26.29it/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<01:13,  2.10it/s]
Loading 0:  58%|█████▊    | 212/363 [00:19<00:54,  2.79it/s]
Loading 0:  60%|█████▉    | 217/363 [00:19<00:35,  4.07it/s]
Loading 0:  61%|██████    | 220/363 [00:20<00:29,  4.88it/s]
Loading 0:  61%|██████▏   | 223/363 [00:20<00:22,  6.09it/s]
Loading 0:  62%|██████▏   | 226/363 [00:20<00:19,  7.18it/s]
Loading 0:  63%|██████▎   | 230/363 [00:20<00:14,  9.16it/s]
Loading 0:  65%|██████▌   | 237/363 [00:20<00:08, 14.80it/s]
Loading 0:  66%|██████▋   | 241/363 [00:20<00:07, 16.62it/s]
Loading 0:  68%|██████▊   | 246/363 [00:20<00:05, 20.92it/s]
Loading 0:  69%|██████▉   | 250/363 [00:21<00:05, 22.41it/s]
Loading 0:  70%|███████   | 255/363 [00:21<00:04, 26.84it/s]
Loading 0:  71%|███████▏  | 259/363 [00:21<00:03, 27.13it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:02, 34.30it/s]
Loading 0:  75%|███████▍  | 271/363 [00:21<00:03, 25.28it/s]
Loading 0:  76%|███████▌  | 275/363 [00:21<00:03, 23.90it/s]
Loading 0:  78%|███████▊  | 282/363 [00:22<00:02, 31.08it/s]
Loading 0:  79%|███████▉  | 286/363 [00:22<00:02, 30.36it/s]
Loading 0:  80%|████████  | 291/363 [00:22<00:02, 33.59it/s]
Loading 0:  81%|████████▏ | 295/363 [00:22<00:02, 32.28it/s]
Loading 0:  82%|████████▏ | 299/363 [00:22<00:01, 33.29it/s]
Loading 0:  84%|████████▎ | 304/363 [00:22<00:01, 31.11it/s]
Loading 0:  85%|████████▍ | 308/363 [00:22<00:01, 30.00it/s]
Loading 0:  86%|████████▌ | 312/363 [00:23<00:01, 26.63it/s]
Loading 0:  88%|████████▊ | 318/363 [00:23<00:01, 32.43it/s]
Loading 0:  89%|████████▊ | 322/363 [00:23<00:01, 31.51it/s]
Loading 0:  90%|█████████ | 327/363 [00:23<00:01, 34.82it/s]
Loading 0:  91%|█████████ | 331/363 [00:23<00:00, 33.10it/s]
Loading 0:  92%|█████████▏| 335/363 [00:23<00:00, 33.83it/s]
Loading 0:  93%|█████████▎| 339/363 [00:23<00:00, 34.27it/s]
Loading 0:  94%|█████████▍| 343/363 [00:24<00:00, 20.71it/s]
Loading 0:  96%|█████████▌| 348/363 [00:24<00:00, 22.28it/s]
Loading 0:  98%|█████████▊| 355/363 [00:24<00:00, 29.69it/s]
Loading 0:  99%|█████████▉| 359/363 [00:24<00:00, 28.47it/s]
                                                            

Job chaiml-1031-quang-ir-ltr-9208-v1-mkmlizer completed after 195.38s with status: succeeded
Stopping job with name chaiml-1031-quang-ir-ltr-9208-v1-mkmlizer
Pipeline stage MKMLizer completed in 197.06s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
%s, retrying in %s seconds...
Creating inference service chaiml-1031-quang-ir-ltr-9208-v1
Waiting for inference service chaiml-1031-quang-ir-ltr-9208-v1 to be ready
Inference service chaiml-1031-quang-ir-ltr-9208-v1 ready after 130.57510638237s
Pipeline stage MKMLDeployer completed in 131.32s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6455068588256836s
Received healthy response to inference request in 2.258229970932007s
Received healthy response to inference request in 2.3420920372009277s
Received healthy response to inference request in 2.1572799682617188s
Received healthy response to inference request in 2.413236618041992s
5 requests
0 failed requests
5th percentile: 2.1774699687957764
10th percentile: 2.197659969329834
20th percentile: 2.238039970397949
30th percentile: 2.275002384185791
40th percentile: 2.3085472106933596
50th percentile: 2.3420920372009277
60th percentile: 2.3705498695373537
70th percentile: 2.399007701873779
80th percentile: 2.4596906661987306
90th percentile: 2.552598762512207
95th percentile: 2.5990528106689452
99th percentile: 2.636216049194336
mean time: 2.363269090652466
Pipeline stage StressChecker completed in 13.30s
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 0.73s
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 0.79s
Shutdown handler de-registered
chaiml-1031-quang-ir-ltr_9208_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
Pipeline stage OfflineFamilyFriendlyScorer completed in 3081.21s
Shutdown handler de-registered