chaiml-ssnew-v7-1-dpo-cosine

developer_uid: chai_backend_admin

submission_id: chaiml-ssnew-v7-1-dpo-cosine_v1

model_name: training123

model_group: ChaiML/ssnew-v7-1-dpo_co

status: torndown

timestamp: 2025-11-23T10:26:07+00:00

num_battles: 6947

num_wins: 3669

celo_rating: 1299.82

family_friendly_score: 0.0

family_friendly_standard_error: 0.0

submission_type: basic

model_repo: ChaiML/ssnew-v7-1-dpo_cosine

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': 0.4551387690881337, 'latency_mean': 2.1970066797733305, 'latency_p50': 2.195123791694641, 'latency_p90': 2.3989199876785277}, {'batch_size': 3, 'throughput': 0.844981662109336, 'latency_mean': 3.5463852846622466, 'latency_p50': 3.541214108467102, 'latency_p90': 3.8864133596420287}, {'batch_size': 5, 'throughput': 1.0085990580499833, 'latency_mean': 4.93537238240242, 'latency_p50': 4.956095814704895, 'latency_p90': 5.456445240974426}, {'batch_size': 6, 'throughput': 1.0692804465446308, 'latency_mean': 5.592098047733307, 'latency_p50': 5.6384031772613525, 'latency_p90': 6.282351517677307}, {'batch_size': 10, 'throughput': 1.1727257691930706, 'latency_mean': 8.466711554527283, 'latency_p50': 8.444164156913757, 'latency_p90': 9.510432457923889}]

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

display_name: training123

is_internal_developer: True

language_model: ChaiML/ssnew-v7-1-dpo_cosine

model_size: 24B

ranking_group: single

throughput_3p7s: 0.87

us_pacific_date: 2025-11-20

win_ratio: 0.528141643875054

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:', 'User:'], 'max_input_tokens': 2048, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {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-v7-1-dpo-cosine-v1-mkmlizer
Waiting for job on chaiml-ssnew-v7-1-dpo-cosine-v1-mkmlizer to finish
chaiml-ssnew-v7-1-dpo-cosine-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ssnew-v7-1-dpo-cosine-v1-mkmlizer: ║                                                                     ║
chaiml-ssnew-v7-1-dpo-cosine-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ssnew-v7-1-dpo-cosine-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ssnew-v7-1-dpo-cosine-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ssnew-v7-1-dpo-cosine-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ssnew-v7-1-dpo-cosine-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ssnew-v7-1-dpo-cosine-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ssnew-v7-1-dpo-cosine-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ssnew-v7-1-dpo-cosine-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ssnew-v7-1-dpo-cosine-v1-mkmlizer: ║                                                                     ║
chaiml-ssnew-v7-1-dpo-cosine-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ssnew-v7-1-dpo-cosine-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ssnew-v7-1-dpo-cosine-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ssnew-v7-1-dpo-cosine-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ssnew-v7-1-dpo-cosine-v1-mkmlizer: ║                                                                     ║
chaiml-ssnew-v7-1-dpo-cosine-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ssnew-v7-1-dpo-cosine-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ssnew-v7-1-dpo-cosine-v1-mkmlizer: ║                                                                     ║
chaiml-ssnew-v7-1-dpo-cosine-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ssnew-v7-1-dpo-cosine-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ssnew-v7-1-dpo-cosine-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ssnew-v7-1-dpo-cosine-v1-mkmlizer: ║                                                                     ║
chaiml-ssnew-v7-1-dpo-cosine-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ssnew-v7-1-dpo-cosine-v1-mkmlizer: Downloaded to shared memory in 69.618s
chaiml-ssnew-v7-1-dpo-cosine-v1-mkmlizer: Checking if ChaiML/ssnew-v7-1-dpo_cosine already exists in ChaiML
chaiml-ssnew-v7-1-dpo-cosine-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpm11qvfzw, device:0
chaiml-ssnew-v7-1-dpo-cosine-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ssnew-v7-1-dpo-cosine-v1-mkmlizer: quantized model in 47.137s
chaiml-ssnew-v7-1-dpo-cosine-v1-mkmlizer: Processed model ChaiML/ssnew-v7-1-dpo_cosine in 116.756s
chaiml-ssnew-v7-1-dpo-cosine-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ssnew-v7-1-dpo-cosine-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ssnew-v7-1-dpo-cosine-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ssnew-v7-1-dpo-cosine-v1/nvidia
chaiml-ssnew-v7-1-dpo-cosine-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ssnew-v7-1-dpo-cosine-v1/nvidia/config.json
chaiml-ssnew-v7-1-dpo-cosine-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ssnew-v7-1-dpo-cosine-v1/nvidia/tokenizer_config.json
chaiml-ssnew-v7-1-dpo-cosine-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ssnew-v7-1-dpo-cosine-v1/nvidia/special_tokens_map.json
chaiml-ssnew-v7-1-dpo-cosine-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ssnew-v7-1-dpo-cosine-v1/nvidia/tokenizer.json
Failed to get response for submission mistralai-mistral-nem_93303_v569: ('http://mistralai-mistral-nem-93303-v569-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
chaiml-ssnew-v7-1-dpo-cosine-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-ssnew-v7-1-dpo-cosine-v1/nvidia/flywheel_model.1.safetensors
chaiml-ssnew-v7-1-dpo-cosine-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ssnew-v7-1-dpo-cosine-v1/nvidia/flywheel_model.0.safetensors
chaiml-ssnew-v7-1-dpo-cosine-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 39.79it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:11, 31.19it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:10, 33.81it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:11, 29.85it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:09, 34.36it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:10, 30.92it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:08, 37.36it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:14, 22.55it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:12, 25.11it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:11, 26.63it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 28.83it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:11, 27.51it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:09, 30.76it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:10, 29.04it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 29.73it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:10, 26.64it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:13, 22.14it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 27.20it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:10, 26.24it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:09, 28.16it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:09, 28.49it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:12, 22.10it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:08, 29.52it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:09, 28.25it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:10, 24.15it/s]
Loading 0:  31%|███       | 112/363 [00:04<00:09, 26.67it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:09, 26.14it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 29.07it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 26.94it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 29.72it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:08, 27.94it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:07, 30.34it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:07, 28.18it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:06, 33.70it/s]
Loading 0:  42%|████▏     | 153/363 [00:05<00:09, 21.91it/s]
Loading 0:  43%|████▎     | 157/363 [00:05<00:08, 24.37it/s]
Loading 0:  44%|████▍     | 160/363 [00:05<00:08, 24.73it/s]
Loading 0:  45%|████▍     | 163/363 [00:06<00:08, 22.53it/s]
Loading 0:  46%|████▌     | 166/363 [00:06<00:08, 23.64it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:09, 20.63it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:07, 24.76it/s]
Loading 0:  49%|████▉     | 177/363 [00:06<00:08, 22.92it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:06, 26.47it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:07, 24.81it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 22.85it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 23.78it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 24.57it/s]
Loading 0:  55%|█████▌    | 200/363 [00:21<00:06, 24.57it/s]
Loading 0:  55%|█████▌    | 201/363 [00:21<03:02,  1.13s/it]
Loading 0:  56%|█████▌    | 203/363 [00:21<02:30,  1.06it/s]
Loading 0:  57%|█████▋    | 208/363 [00:22<01:30,  1.72it/s]
Loading 0:  58%|█████▊    | 211/363 [00:22<01:09,  2.18it/s]
Loading 0:  59%|█████▉    | 214/363 [00:22<00:51,  2.88it/s]
Loading 0:  60%|██████    | 218/363 [00:22<00:35,  4.13it/s]
Loading 0:  61%|██████    | 221/363 [00:22<00:26,  5.28it/s]
Loading 0:  62%|██████▏   | 224/363 [00:22<00:21,  6.37it/s]
Loading 0:  63%|██████▎   | 229/363 [00:23<00:14,  9.37it/s]
Loading 0:  64%|██████▍   | 232/363 [00:23<00:11, 11.10it/s]
Loading 0:  65%|██████▌   | 237/363 [00:23<00:08, 15.00it/s]
Loading 0:  66%|██████▌   | 240/363 [00:23<00:07, 15.68it/s]
Loading 0:  68%|██████▊   | 246/363 [00:23<00:05, 21.19it/s]
Loading 0:  69%|██████▉   | 250/363 [00:23<00:05, 21.96it/s]
Loading 0:  70%|██████▉   | 253/363 [00:23<00:04, 22.24it/s]
Loading 0:  71%|███████   | 256/363 [00:24<00:04, 23.36it/s]
Loading 0:  71%|███████▏  | 259/363 [00:24<00:04, 23.99it/s]
Loading 0:  73%|███████▎  | 265/363 [00:24<00:03, 31.96it/s]
Loading 0:  74%|███████▍  | 269/363 [00:24<00:04, 22.20it/s]
Loading 0:  75%|███████▍  | 272/363 [00:24<00:03, 22.91it/s]
Loading 0:  76%|███████▌  | 275/363 [00:24<00:04, 19.67it/s]
Loading 0:  78%|███████▊  | 282/363 [00:25<00:02, 27.05it/s]
Loading 0:  79%|███████▉  | 286/363 [00:25<00:02, 26.43it/s]
Loading 0:  80%|███████▉  | 289/363 [00:25<00:02, 26.22it/s]
Loading 0:  80%|████████  | 292/363 [00:25<00:02, 26.60it/s]
Loading 0:  81%|████████▏ | 295/363 [00:25<00:02, 26.80it/s]
Loading 0:  82%|████████▏ | 299/363 [00:25<00:02, 27.83it/s]
Loading 0:  84%|████████▎ | 304/363 [00:25<00:02, 26.08it/s]
Loading 0:  85%|████████▍ | 307/363 [00:26<00:02, 23.72it/s]
Loading 0:  85%|████████▌ | 310/363 [00:26<00:02, 24.50it/s]
Loading 0:  86%|████████▌ | 313/363 [00:26<00:01, 25.21it/s]
Loading 0:  88%|████████▊ | 318/363 [00:26<00:01, 28.54it/s]
Loading 0:  88%|████████▊ | 321/363 [00:26<00:01, 25.53it/s]
Loading 0:  90%|█████████ | 327/363 [00:26<00:01, 30.62it/s]
Loading 0:  91%|█████████ | 331/363 [00:26<00:01, 28.23it/s]
Loading 0:  92%|█████████▏| 335/363 [00:26<00:00, 28.56it/s]
Loading 0:  93%|█████████▎| 338/363 [00:27<00:00, 27.38it/s]
Loading 0:  94%|█████████▍| 341/363 [00:27<00:01, 16.20it/s]
Loading 0:  96%|█████████▌| 347/363 [00:27<00:00, 21.65it/s]
Loading 0:  96%|█████████▋| 350/363 [00:27<00:00, 21.96it/s]
Loading 0:  98%|█████████▊| 355/363 [00:27<00:00, 25.41it/s]
Loading 0:  99%|█████████▊| 358/363 [00:28<00:00, 23.83it/s]
                                                            
Job chaiml-ssnew-v7-1-dpo-cosine-v1-mkmlizer completed after 155.13s with status: succeeded
Stopping job with name chaiml-ssnew-v7-1-dpo-cosine-v1-mkmlizer
Pipeline stage MKMLizer completed in 156.00s
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-ssnew-v7-1-dpo-cosine-v1
Waiting for inference service chaiml-ssnew-v7-1-dpo-cosine-v1 to be ready
Inference service chaiml-ssnew-v7-1-dpo-cosine-v1 ready after 141.49721479415894s
Pipeline stage MKMLDeployer completed in 142.05s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9933815002441406s
Received healthy response to inference request in 1.8275673389434814s
Received healthy response to inference request in 1.963416337966919s
Received healthy response to inference request in 2.0102853775024414s
Received healthy response to inference request in 1.7728090286254883s
5 requests
0 failed requests
5th percentile: 1.7837606906890868
10th percentile: 1.7947123527526856
20th percentile: 1.816615676879883
30th percentile: 1.854737138748169
40th percentile: 1.909076738357544
50th percentile: 1.963416337966919
60th percentile: 1.9754024028778077
70th percentile: 1.9873884677886964
80th percentile: 1.9967622756958008
90th percentile: 2.003523826599121
95th percentile: 2.0069046020507812
99th percentile: 2.0096092224121094
mean time: 1.913491916656494
Pipeline stage StressChecker completed in 11.02s
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 0.87s
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 0.62s
Shutdown handler de-registered
chaiml-ssnew-v7-1-dpo-cosine_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-ssnew-v7-1-dpo-cosine-v1-profiler
Waiting for inference service chaiml-ssnew-v7-1-dpo-cosine-v1-profiler to be ready
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4627.53s
Shutdown handler de-registered
chaiml-ssnew-v7-1-dpo-cosine_v1 status is now torndown due to DeploymentManager action