chaiml-ssnew-v6-dpo-lr5_89905

developer_uid: chai_backend_admin

submission_id: chaiml-ssnew-v6-dpo-lr5_89905_v1

model_name: chaiml-ssnew-v6-dpo-lr5_89905_v1

model_group: ChaiML/ssnew-v6-dpo-lr5e

status: inactive

timestamp: 2025-10-17T06:20:50+00:00

num_battles: 6058

num_wins: 3188

celo_rating: 1295.15

family_friendly_score: 0.5016

family_friendly_standard_error: 0.007071031607905596

submission_type: basic

model_repo: ChaiML/ssnew-v6-dpo-lr5e6b01r128-lora

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': 0.38266571001942207, 'latency_mean': 2.6131463122367857, 'latency_p50': 2.596449613571167, 'latency_p90': 2.878840517997742}, {'batch_size': 2, 'throughput': 0.5762039230488589, 'latency_mean': 3.465066599845886, 'latency_p50': 3.4820549488067627, 'latency_p90': 3.749071168899536}, {'batch_size': 3, 'throughput': 0.7221224183581088, 'latency_mean': 4.137253487110138, 'latency_p50': 4.138880372047424, 'latency_p90': 4.539859342575073}, {'batch_size': 4, 'throughput': 0.826882284719055, 'latency_mean': 4.8191999661922456, 'latency_p50': 4.783399701118469, 'latency_p90': 5.458799695968628}, {'batch_size': 5, 'throughput': 0.8863385386821354, 'latency_mean': 5.620222331285476, 'latency_p50': 5.565897583961487, 'latency_p90': 6.51968400478363}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: chaiml-ssnew-v6-dpo-lr5_89905_v1

is_internal_developer: True

language_model: ChaiML/ssnew-v6-dpo-lr5e6b01r128-lora

model_size: 24B

ranking_group: single

throughput_3p7s: 0.64

us_pacific_date: 2025-10-16

win_ratio: 0.5262462859029383

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', '</s>', 'You:'], '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
Starting job with name chaiml-ssnew-v6-dpo-lr5-89905-v1-mkmlizer
Waiting for job on chaiml-ssnew-v6-dpo-lr5-89905-v1-mkmlizer to finish
chaiml-ssnew-v6-dpo-lr5-89905-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ssnew-v6-dpo-lr5-89905-v1-mkmlizer: ║                                                                     ║
chaiml-ssnew-v6-dpo-lr5-89905-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ssnew-v6-dpo-lr5-89905-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ssnew-v6-dpo-lr5-89905-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ssnew-v6-dpo-lr5-89905-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ssnew-v6-dpo-lr5-89905-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ssnew-v6-dpo-lr5-89905-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ssnew-v6-dpo-lr5-89905-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ssnew-v6-dpo-lr5-89905-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ssnew-v6-dpo-lr5-89905-v1-mkmlizer: ║                                                                     ║
chaiml-ssnew-v6-dpo-lr5-89905-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ssnew-v6-dpo-lr5-89905-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ssnew-v6-dpo-lr5-89905-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ssnew-v6-dpo-lr5-89905-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ssnew-v6-dpo-lr5-89905-v1-mkmlizer: ║                                                                     ║
chaiml-ssnew-v6-dpo-lr5-89905-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ssnew-v6-dpo-lr5-89905-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ssnew-v6-dpo-lr5-89905-v1-mkmlizer: ║                                                                     ║
chaiml-ssnew-v6-dpo-lr5-89905-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ssnew-v6-dpo-lr5-89905-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ssnew-v6-dpo-lr5-89905-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ssnew-v6-dpo-lr5-89905-v1-mkmlizer: ║                                                                     ║
chaiml-ssnew-v6-dpo-lr5-89905-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ssnew-v6-dpo-lr5-89905-v1-mkmlizer: Downloaded to shared memory in 45.307s
chaiml-ssnew-v6-dpo-lr5-89905-v1-mkmlizer: Checking if ChaiML/ssnew-v6-dpo-lr5e6b01r128-lora already exists in ChaiML
chaiml-ssnew-v6-dpo-lr5-89905-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpknwj9nvn, device:0
chaiml-ssnew-v6-dpo-lr5-89905-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ssnew-v6-dpo-lr5-89905-v1-mkmlizer: quantized model in 41.943s
chaiml-ssnew-v6-dpo-lr5-89905-v1-mkmlizer: Processed model ChaiML/ssnew-v6-dpo-lr5e6b01r128-lora in 87.251s
chaiml-ssnew-v6-dpo-lr5-89905-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ssnew-v6-dpo-lr5-89905-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ssnew-v6-dpo-lr5-89905-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ssnew-v6-dpo-lr5-89905-v1/nvidia
chaiml-ssnew-v6-dpo-lr5-89905-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ssnew-v6-dpo-lr5-89905-v1/nvidia/config.json
chaiml-ssnew-v6-dpo-lr5-89905-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ssnew-v6-dpo-lr5-89905-v1/nvidia/special_tokens_map.json
chaiml-ssnew-v6-dpo-lr5-89905-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ssnew-v6-dpo-lr5-89905-v1/nvidia/tokenizer_config.json
chaiml-ssnew-v6-dpo-lr5-89905-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ssnew-v6-dpo-lr5-89905-v1/nvidia/tokenizer.json
chaiml-ssnew-v6-dpo-lr5-89905-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-ssnew-v6-dpo-lr5-89905-v1/nvidia/flywheel_model.1.safetensors
chaiml-ssnew-v6-dpo-lr5-89905-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ssnew-v6-dpo-lr5-89905-v1/nvidia/flywheel_model.0.safetensors
chaiml-ssnew-v6-dpo-lr5-89905-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 23.77it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:08, 39.81it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:08, 41.95it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 32.14it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 44.50it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:10, 31.14it/s]
Loading 0:  12%|█▏        | 42/363 [00:01<00:11, 28.03it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 33.31it/s]
Loading 0:  15%|█▍        | 53/363 [00:01<00:09, 33.20it/s]
Loading 0:  16%|█▌        | 58/363 [00:01<00:08, 34.02it/s]
Loading 0:  17%|█▋        | 62/363 [00:01<00:09, 30.88it/s]
Loading 0:  18%|█▊        | 66/363 [00:02<00:10, 27.73it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:11, 25.31it/s]
Loading 0:  20%|█▉        | 72/363 [00:02<00:18, 15.49it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:18, 15.24it/s]
Loading 0:  21%|██▏       | 78/363 [00:03<00:17, 16.23it/s]
Loading 0:  22%|██▏       | 80/363 [00:03<00:18, 15.33it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:12, 22.72it/s]
Loading 0:  25%|██▍       | 90/363 [00:03<00:11, 24.25it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:11, 23.59it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:08, 30.25it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:08, 29.66it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:09, 25.97it/s]
Loading 0:  31%|███       | 112/363 [00:04<00:08, 29.20it/s]
Loading 0:  32%|███▏      | 116/363 [00:04<00:08, 30.66it/s]
Loading 0:  33%|███▎      | 121/363 [00:04<00:07, 31.94it/s]
Loading 0:  34%|███▍      | 125/363 [00:04<00:07, 33.24it/s]
Loading 0:  36%|███▌      | 130/363 [00:04<00:06, 33.69it/s]
Loading 0:  37%|███▋      | 134/363 [00:04<00:06, 34.40it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 35.74it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:06, 32.76it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:05, 39.51it/s]
Loading 0:  42%|████▏     | 154/363 [00:05<00:07, 27.16it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:08, 25.42it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 32.69it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 31.35it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:05, 34.42it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:05, 31.87it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:05, 32.76it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:05, 29.42it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:06, 28.56it/s]
Loading 0:  54%|█████▎    | 195/363 [00:06<00:06, 25.83it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:12,  1.22it/s]
Loading 0:  56%|█████▌    | 203/363 [00:19<01:53,  1.41it/s]
Loading 0:  57%|█████▋    | 208/363 [00:19<01:12,  2.13it/s]
Loading 0:  58%|█████▊    | 211/363 [00:20<00:56,  2.69it/s]
Loading 0:  59%|█████▉    | 215/363 [00:20<00:39,  3.75it/s]
Loading 0:  60%|██████    | 218/363 [00:20<00:30,  4.78it/s]
Loading 0:  61%|██████    | 221/363 [00:20<00:23,  6.11it/s]
Loading 0:  62%|██████▏   | 224/363 [00:20<00:18,  7.34it/s]
Loading 0:  63%|██████▎   | 229/363 [00:20<00:12, 10.76it/s]
Loading 0:  64%|██████▍   | 232/363 [00:20<00:10, 12.74it/s]
Loading 0:  65%|██████▌   | 237/363 [00:20<00:07, 17.44it/s]
Loading 0:  66%|██████▋   | 241/363 [00:21<00:06, 19.80it/s]
Loading 0:  68%|██████▊   | 246/363 [00:21<00:04, 24.61it/s]
Loading 0:  69%|██████▉   | 250/363 [00:21<00:04, 25.61it/s]
Loading 0:  70%|███████   | 255/363 [00:21<00:03, 29.89it/s]
Loading 0:  71%|███████▏  | 259/363 [00:21<00:03, 29.60it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:02, 36.77it/s]
Loading 0:  75%|███████▍  | 271/363 [00:21<00:03, 26.57it/s]
Loading 0:  76%|███████▌  | 275/363 [00:22<00:03, 24.88it/s]
Loading 0:  78%|███████▊  | 282/363 [00:22<00:02, 32.13it/s]
Loading 0:  79%|███████▉  | 286/363 [00:22<00:02, 30.83it/s]
Loading 0:  80%|████████  | 291/363 [00:22<00:02, 33.64it/s]
Loading 0:  81%|████████▏ | 295/363 [00:22<00:02, 31.97it/s]
Loading 0:  82%|████████▏ | 299/363 [00:22<00:01, 32.88it/s]
Loading 0:  84%|████████▎ | 304/363 [00:23<00:01, 30.30it/s]
Loading 0:  85%|████████▍ | 308/363 [00:23<00:01, 29.94it/s]
Loading 0:  86%|████████▌ | 312/363 [00:23<00:01, 26.87it/s]
Loading 0:  88%|████████▊ | 318/363 [00:23<00:01, 32.72it/s]
Loading 0:  89%|████████▊ | 322/363 [00:23<00:01, 31.50it/s]
Loading 0:  90%|█████████ | 327/363 [00:23<00:01, 34.90it/s]
Loading 0:  91%|█████████ | 331/363 [00:23<00:00, 32.82it/s]
Loading 0:  92%|█████████▏| 335/363 [00:23<00:00, 33.71it/s]
Loading 0:  93%|█████████▎| 339/363 [00:24<00:00, 34.29it/s]
Loading 0:  94%|█████████▍| 343/363 [00:24<00:00, 20.61it/s]
Loading 0:  96%|█████████▌| 348/363 [00:24<00:00, 21.90it/s]
Loading 0:  98%|█████████▊| 355/363 [00:24<00:00, 29.38it/s]
Loading 0:  99%|█████████▉| 359/363 [00:24<00:00, 28.80it/s]
                                                            
Job chaiml-ssnew-v6-dpo-lr5-89905-v1-mkmlizer completed after 154.49s with status: succeeded
Stopping job with name chaiml-ssnew-v6-dpo-lr5-89905-v1-mkmlizer
Pipeline stage MKMLizer completed in 154.99s
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-ssnew-v6-dpo-lr5-89905-v1
Waiting for inference service chaiml-ssnew-v6-dpo-lr5-89905-v1 to be ready
Inference service chaiml-ssnew-v6-dpo-lr5-89905-v1 ready after 60.4405083656311s
Pipeline stage MKMLDeployer completed in 60.96s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.687437057495117s
Received healthy response to inference request in 2.252509355545044s
Received healthy response to inference request in 2.2890474796295166s
Received healthy response to inference request in 2.414750099182129s
Received healthy response to inference request in 2.577147960662842s
5 requests
0 failed requests
5th percentile: 2.2598169803619386
10th percentile: 2.267124605178833
20th percentile: 2.281739854812622
30th percentile: 2.314188003540039
40th percentile: 2.364469051361084
50th percentile: 2.414750099182129
60th percentile: 2.479709243774414
70th percentile: 2.5446683883666994
80th percentile: 2.5992057800292967
90th percentile: 2.643321418762207
95th percentile: 2.6653792381286623
99th percentile: 2.6830254936218263
mean time: 2.4441783905029295
Pipeline stage StressChecker completed in 13.50s
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 0.69s
Shutdown handler de-registered
chaiml-ssnew-v6-dpo-lr5_89905_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 2997.96s
Shutdown handler de-registered
chaiml-ssnew-v6-dpo-lr5_89905_v1 status is now inactive due to auto deactivation removed underperforming models