chaiml-gy-exp2-sft-dpo-_64511

developer_uid: bogoconic1

submission_id: chaiml-gy-exp2-sft-dpo-_64511_v1

model_name: chaiml-gy-exp2-sft-dpo-_64511_v1

model_group: ChaiML/gy-exp2-sft-dpo-n

status: torndown

timestamp: 2025-06-24T13:56:57+00:00

num_battles: 7601

num_wins: 3918

celo_rating: 1299.51

family_friendly_score: 0.4828

family_friendly_standard_error: 0.00706688276399149

submission_type: basic

model_repo: ChaiML/gy-exp2-sft-dpo-nis-mistral32-preferences-sftv1-1306-ep1

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.5922473001751689, 'latency_mean': 1.6883674132823945, 'latency_p50': 1.6830862760543823, 'latency_p90': 1.8791300773620605}, {'batch_size': 3, 'throughput': 1.0626787324136535, 'latency_mean': 2.816319383382797, 'latency_p50': 2.830042243003845, 'latency_p90': 3.0944483041763307}, {'batch_size': 5, 'throughput': 1.2853029947079218, 'latency_mean': 3.8786954510211946, 'latency_p50': 3.8797085285186768, 'latency_p90': 4.276527190208435}, {'batch_size': 6, 'throughput': 1.3573932104928224, 'latency_mean': 4.396839199066162, 'latency_p50': 4.41619336605072, 'latency_p90': 4.9515352010726925}, {'batch_size': 8, 'throughput': 1.4160232552639693, 'latency_mean': 5.620035066604614, 'latency_p50': 5.644387364387512, 'latency_p90': 6.3330714225769045}, {'batch_size': 10, 'throughput': 1.4612027761272504, 'latency_mean': 6.782658056020737, 'latency_p50': 6.782163619995117, 'latency_p90': 7.697853517532349}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-gy-exp2-sft-dpo-_64511_v1

is_internal_developer: True

language_model: ChaiML/gy-exp2-sft-dpo-nis-mistral32-preferences-sftv1-1306-ep1

model_size: 13B

ranking_group: single

throughput_3p7s: 1.26

us_pacific_date: 2025-06-24

win_ratio: 0.5154584923036443

generation_params: {'temperature': 0.45, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 60, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['<|im_end|>', '\n', '<|im_start|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '<|system|>Family Friendly{memory}\n', 'prompt_template': '', 'bot_template': '<|im_start|>assistant\n{message}<|im_end|>\n', 'user_template': '<|im_start|>user\nYou:{message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n', 'truncate_by_message': False}

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-gy-exp2-sft-dpo-64511-v1-mkmlizer
Waiting for job on chaiml-gy-exp2-sft-dpo-64511-v1-mkmlizer to finish
chaiml-gy-exp2-sft-dpo-64511-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp2-sft-dpo-64511-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp2-sft-dpo-64511-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp2-sft-dpo-64511-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp2-sft-dpo-64511-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp2-sft-dpo-64511-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp2-sft-dpo-64511-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp2-sft-dpo-64511-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp2-sft-dpo-64511-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp2-sft-dpo-64511-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp2-sft-dpo-64511-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp2-sft-dpo-64511-v1-mkmlizer: ║  Version: 0.29.3                                                    ║
chaiml-gy-exp2-sft-dpo-64511-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp2-sft-dpo-64511-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp2-sft-dpo-64511-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp2-sft-dpo-64511-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp2-sft-dpo-64511-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp2-sft-dpo-64511-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp2-sft-dpo-64511-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp2-sft-dpo-64511-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp2-sft-dpo-64511-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp2-sft-dpo-64511-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp2-sft-dpo-64511-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp2-sft-dpo-64511-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp2-sft-dpo-64511-v1-mkmlizer: Downloaded to shared memory in 39.503s
chaiml-gy-exp2-sft-dpo-64511-v1-mkmlizer: Checking if ChaiML/gy-exp2-sft-dpo-nis-mistral32-preferences-sftv1-1306-ep1 already exists in ChaiML
chaiml-gy-exp2-sft-dpo-64511-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmph41pcp8x, device:0
chaiml-gy-exp2-sft-dpo-64511-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp2-sft-dpo-64511-v1-mkmlizer: quantized model in 31.039s
chaiml-gy-exp2-sft-dpo-64511-v1-mkmlizer: Processed model ChaiML/gy-exp2-sft-dpo-nis-mistral32-preferences-sftv1-1306-ep1 in 70.810s
chaiml-gy-exp2-sft-dpo-64511-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp2-sft-dpo-64511-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp2-sft-dpo-64511-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp2-sft-dpo-64511-v1
chaiml-gy-exp2-sft-dpo-64511-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp2-sft-dpo-64511-v1/config.json
chaiml-gy-exp2-sft-dpo-64511-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp2-sft-dpo-64511-v1/special_tokens_map.json
chaiml-gy-exp2-sft-dpo-64511-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp2-sft-dpo-64511-v1/tokenizer_config.json
chaiml-gy-exp2-sft-dpo-64511-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp2-sft-dpo-64511-v1/flywheel_model.0.safetensors
chaiml-gy-exp2-sft-dpo-64511-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:10, 33.35it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:06, 51.91it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 45.13it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 43.22it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 48.83it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 43.89it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 42.49it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 47.16it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:07, 43.62it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 33.59it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:09, 32.87it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:07, 37.96it/s]
Loading 0:  21%|██        | 76/363 [00:01<00:07, 39.15it/s]
Loading 0:  22%|██▏       | 81/363 [00:01<00:06, 40.96it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:06, 42.80it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:07, 35.45it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:06, 42.46it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:06, 42.25it/s]
Loading 0:  30%|███       | 109/363 [00:02<00:05, 46.02it/s]
Loading 0:  31%|███▏      | 114/363 [00:02<00:06, 39.65it/s]
Loading 0:  33%|███▎      | 119/363 [00:02<00:06, 39.39it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:05, 43.66it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 44.03it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 42.06it/s]
Loading 0:  39%|███▊      | 140/363 [00:03<00:05, 43.82it/s]
Loading 0:  40%|███▉      | 145/363 [00:03<00:07, 27.25it/s]
Loading 0:  41%|████      | 149/363 [00:03<00:07, 28.02it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:05, 35.87it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 37.78it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:04, 39.65it/s]
Loading 0:  47%|████▋     | 172/363 [00:04<00:04, 38.62it/s]
Loading 0:  49%|████▉     | 177/363 [00:04<00:04, 38.52it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 43.51it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:03, 44.10it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 43.44it/s]
Loading 0:  55%|█████▍    | 198/363 [00:04<00:03, 43.48it/s]
Loading 0:  56%|█████▌    | 203/363 [00:05<00:04, 36.34it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:03, 42.63it/s]
Loading 0:  59%|█████▉    | 215/363 [00:05<00:03, 42.52it/s]
Loading 0:  61%|██████    | 221/363 [00:05<00:03, 46.24it/s]
Loading 0:  62%|██████▏   | 226/363 [00:05<00:04, 29.77it/s]
Loading 0:  63%|██████▎   | 230/363 [00:05<00:04, 29.43it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 36.81it/s]
Loading 0:  67%|██████▋   | 242/363 [00:06<00:03, 38.80it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:02, 40.29it/s]
Loading 0:  69%|██████▉   | 252/363 [00:06<00:02, 42.56it/s]
Loading 0:  71%|███████   | 257/363 [00:06<00:02, 36.50it/s]
Loading 0:  73%|███████▎  | 264/363 [00:06<00:02, 44.05it/s]
Loading 0:  74%|███████▍  | 269/363 [00:06<00:02, 43.71it/s]
Loading 0:  75%|███████▌  | 274/363 [00:06<00:02, 43.27it/s]
Loading 0:  77%|███████▋  | 279/363 [00:06<00:01, 44.29it/s]
Loading 0:  78%|███████▊  | 284/363 [00:07<00:02, 36.88it/s]
Loading 0:  80%|████████  | 291/363 [00:07<00:01, 42.76it/s]
Loading 0:  82%|████████▏ | 296/363 [00:07<00:01, 42.86it/s]
Loading 0:  83%|████████▎ | 301/363 [00:07<00:01, 43.68it/s]
Loading 0:  84%|████████▍ | 306/363 [00:07<00:02, 24.08it/s]
Loading 0:  85%|████████▌ | 310/363 [00:08<00:02, 25.20it/s]
Loading 0:  87%|████████▋ | 314/363 [00:08<00:01, 27.36it/s]
Loading 0:  88%|████████▊ | 319/363 [00:08<00:01, 31.70it/s]
Loading 0:  89%|████████▉ | 323/363 [00:08<00:01, 32.90it/s]
Loading 0:  91%|█████████ | 329/363 [00:08<00:00, 38.49it/s]
Loading 0:  92%|█████████▏| 334/363 [00:08<00:00, 39.99it/s]
Loading 0:  93%|█████████▎| 339/363 [00:08<00:00, 34.84it/s]
Loading 0:  95%|█████████▌| 346/363 [00:08<00:00, 42.33it/s]
Loading 0:  97%|█████████▋| 351/363 [00:09<00:00, 42.58it/s]
Loading 0:  98%|█████████▊| 356/363 [00:09<00:00, 43.63it/s]
Loading 0: 100%|█████████▉| 362/363 [00:09<00:00, 41.87it/s]
                                                            
Job chaiml-gy-exp2-sft-dpo-64511-v1-mkmlizer completed after 93.93s with status: succeeded
Stopping job with name chaiml-gy-exp2-sft-dpo-64511-v1-mkmlizer
Pipeline stage MKMLizer completed in 94.66s
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-gy-exp2-sft-dpo-64511-v1
Waiting for inference service chaiml-gy-exp2-sft-dpo-64511-v1 to be ready
Inference service chaiml-gy-exp2-sft-dpo-64511-v1 ready after 130.4830687046051s
Pipeline stage MKMLDeployer completed in 131.03s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.477691888809204s
Received healthy response to inference request in 1.5522267818450928s
Received healthy response to inference request in 1.7026550769805908s
Received healthy response to inference request in 1.6781978607177734s
Received healthy response to inference request in 1.5650904178619385s
5 requests
0 failed requests
5th percentile: 1.5547995090484619
10th percentile: 1.557372236251831
20th percentile: 1.5625176906585694
30th percentile: 1.5877119064331056
40th percentile: 1.6329548835754395
50th percentile: 1.6781978607177734
60th percentile: 1.6879807472229005
70th percentile: 1.6977636337280273
80th percentile: 1.8576624393463137
90th percentile: 2.167677164077759
95th percentile: 2.3226845264434814
99th percentile: 2.4466904163360597
mean time: 1.7951724052429199
Pipeline stage StressChecker completed in 10.18s
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 0.71s
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-gy-exp2-sft-dpo-_64511_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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4896.81s
Shutdown handler de-registered
chaiml-gy-exp2-sft-dpo-_64511_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp2-sft-dpo-_64511_v1 status is now torndown due to DeploymentManager action