chaiml-gy-exp77-dpo-exp5_8904

developer_uid: bogoconic1

submission_id: chaiml-gy-exp77-dpo-exp5_8904_v2

model_name: chaiml-gy-exp77-dpo-exp5_8904_v2

model_group: ChaiML/gy-exp77-dpo-exp5

status: torndown

timestamp: 2025-07-08T12:37:05+00:00

num_battles: 7651

num_wins: 4058

celo_rating: 1308.76

family_friendly_score: 0.5691999999999999

family_friendly_standard_error: 0.0070030187776415394

submission_type: basic

model_repo: ChaiML/gy-exp77-dpo-exp5sftdpos3-majib-0630-ep2

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.5902132135214739, 'latency_mean': 1.6941148948669433, 'latency_p50': 1.70671808719635, 'latency_p90': 1.855970025062561}, {'batch_size': 3, 'throughput': 1.0534791236066727, 'latency_mean': 2.839476739168167, 'latency_p50': 2.8314021825790405, 'latency_p90': 3.1667518854141234}, {'batch_size': 5, 'throughput': 1.2481447059198096, 'latency_mean': 3.9811540174484255, 'latency_p50': 4.020295023918152, 'latency_p90': 4.507904148101806}, {'batch_size': 6, 'throughput': 1.3091466757073016, 'latency_mean': 4.556155834197998, 'latency_p50': 4.567339539527893, 'latency_p90': 5.099965763092041}, {'batch_size': 8, 'throughput': 1.3767226298099544, 'latency_mean': 5.767006888389587, 'latency_p50': 5.757330656051636, 'latency_p90': 6.508669900894165}, {'batch_size': 10, 'throughput': 1.4139405880146618, 'latency_mean': 7.009047232866287, 'latency_p50': 7.060956954956055, 'latency_p90': 8.010575532913208}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-gy-exp77-dpo-exp5_8904_v2

is_internal_developer: False

language_model: ChaiML/gy-exp77-dpo-exp5sftdpos3-majib-0630-ep2

model_size: 13B

ranking_group: single

throughput_3p7s: 1.22

us_pacific_date: 2025-07-08

win_ratio: 0.5303881845510391

generation_params: {'temperature': 0.6, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 60, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['\n', '<|im_end|>', '<|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': 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-gy-exp77-dpo-exp5-8904-v2-mkmlizer
Waiting for job on chaiml-gy-exp77-dpo-exp5-8904-v2-mkmlizer to finish
chaiml-gy-exp77-dpo-exp5-8904-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp77-dpo-exp5-8904-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp77-dpo-exp5-8904-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp77-dpo-exp5-8904-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp77-dpo-exp5-8904-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp77-dpo-exp5-8904-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp77-dpo-exp5-8904-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp77-dpo-exp5-8904-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp77-dpo-exp5-8904-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp77-dpo-exp5-8904-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp77-dpo-exp5-8904-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp77-dpo-exp5-8904-v2-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp77-dpo-exp5-8904-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp77-dpo-exp5-8904-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp77-dpo-exp5-8904-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp77-dpo-exp5-8904-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp77-dpo-exp5-8904-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp77-dpo-exp5-8904-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp77-dpo-exp5-8904-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp77-dpo-exp5-8904-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp77-dpo-exp5-8904-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp77-dpo-exp5-8904-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp77-dpo-exp5-8904-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp77-dpo-exp5-8904-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp77-dpo-exp5-8904-v2-mkmlizer: Downloaded to shared memory in 42.689s
chaiml-gy-exp77-dpo-exp5-8904-v2-mkmlizer: Checking if ChaiML/gy-exp77-dpo-exp5sftdpos3-majib-0630-ep2 already exists in ChaiML
chaiml-gy-exp77-dpo-exp5-8904-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpx70jec4d, device:0
chaiml-gy-exp77-dpo-exp5-8904-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp77-dpo-exp5-8904-v2-mkmlizer: quantized model in 31.212s
chaiml-gy-exp77-dpo-exp5-8904-v2-mkmlizer: Processed model ChaiML/gy-exp77-dpo-exp5sftdpos3-majib-0630-ep2 in 73.901s
chaiml-gy-exp77-dpo-exp5-8904-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp77-dpo-exp5-8904-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp77-dpo-exp5-8904-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp77-dpo-exp5-8904-v2/nvidia
chaiml-gy-exp77-dpo-exp5-8904-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp77-dpo-exp5-8904-v2/nvidia/config.json
chaiml-gy-exp77-dpo-exp5-8904-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp77-dpo-exp5-8904-v2/nvidia/special_tokens_map.json
chaiml-gy-exp77-dpo-exp5-8904-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp77-dpo-exp5-8904-v2/nvidia/tokenizer_config.json
chaiml-gy-exp77-dpo-exp5-8904-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp77-dpo-exp5-8904-v2/nvidia/tokenizer.json
chaiml-gy-exp77-dpo-exp5-8904-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp77-dpo-exp5-8904-v2/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp77-dpo-exp5-8904-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 29.40it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 48.25it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 44.69it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 42.86it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 48.42it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 45.35it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 43.66it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 48.21it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 45.90it/s]
Loading 0:  17%|█▋        | 60/363 [00:01<00:06, 46.83it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:11, 27.09it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:08, 32.66it/s]
Loading 0:  21%|██        | 76/363 [00:01<00:08, 34.26it/s]
Loading 0:  22%|██▏       | 81/363 [00:02<00:07, 36.91it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:06, 39.72it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:07, 34.86it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:06, 42.37it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:06, 40.38it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:06, 41.60it/s]
Loading 0:  31%|███       | 113/363 [00:02<00:07, 35.41it/s]
Loading 0:  33%|███▎      | 118/363 [00:03<00:06, 35.56it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:05, 42.69it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 42.18it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 42.43it/s]
Loading 0:  39%|███▊      | 140/363 [00:03<00:05, 43.13it/s]
Loading 0:  40%|███▉      | 145/363 [00:03<00:08, 26.55it/s]
Loading 0:  41%|████      | 149/363 [00:03<00:07, 27.14it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:05, 35.27it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 36.69it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 38.68it/s]
Loading 0:  47%|████▋     | 172/363 [00:04<00:04, 39.10it/s]
Loading 0:  49%|████▉     | 177/363 [00:04<00:04, 39.35it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 43.91it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:03, 44.02it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 44.46it/s]
Loading 0:  55%|█████▍    | 199/363 [00:05<00:03, 43.94it/s]
Loading 0:  56%|█████▌    | 204/363 [00:05<00:03, 42.47it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:03, 46.72it/s]
Loading 0:  59%|█████▉    | 215/363 [00:05<00:03, 45.67it/s]
Loading 0:  61%|██████    | 221/363 [00:05<00:02, 49.05it/s]
Loading 0:  62%|██████▏   | 226/363 [00:05<00:04, 28.33it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:04, 29.19it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 36.23it/s]
Loading 0:  67%|██████▋   | 242/363 [00:06<00:03, 38.29it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:02, 40.42it/s]
Loading 0:  70%|██████▉   | 253/363 [00:06<00:02, 40.19it/s]
Loading 0:  71%|███████   | 258/363 [00:06<00:02, 38.39it/s]
Loading 0:  73%|███████▎  | 264/363 [00:06<00:02, 43.21it/s]
Loading 0:  74%|███████▍  | 269/363 [00:06<00:02, 43.67it/s]
Loading 0:  75%|███████▌  | 274/363 [00:06<00:02, 42.35it/s]
Loading 0:  77%|███████▋  | 279/363 [00:07<00:01, 44.27it/s]
Loading 0:  78%|███████▊  | 284/363 [00:07<00:02, 37.56it/s]
Loading 0:  80%|████████  | 291/363 [00:07<00:01, 44.38it/s]
Loading 0:  82%|████████▏ | 296/363 [00:07<00:01, 43.68it/s]
Loading 0:  83%|████████▎ | 302/363 [00:07<00:01, 47.70it/s]
Loading 0:  85%|████████▍ | 307/363 [00:08<00:02, 21.99it/s]
Loading 0:  86%|████████▌ | 312/363 [00:08<00:02, 24.42it/s]
Loading 0:  88%|████████▊ | 320/363 [00:08<00:01, 33.08it/s]
Loading 0:  90%|████████▉ | 326/363 [00:08<00:01, 35.23it/s]
Loading 0:  91%|█████████ | 331/363 [00:08<00:00, 36.35it/s]
Loading 0:  93%|█████████▎| 337/363 [00:08<00:00, 41.22it/s]
Loading 0:  94%|█████████▍| 342/363 [00:08<00:00, 40.61it/s]
Loading 0:  96%|█████████▌| 347/363 [00:09<00:00, 41.88it/s]
Loading 0:  97%|█████████▋| 352/363 [00:09<00:00, 43.27it/s]
Loading 0:  98%|█████████▊| 357/363 [00:09<00:00, 36.31it/s]
                                                            
Job chaiml-gy-exp77-dpo-exp5-8904-v2-mkmlizer completed after 95.71s with status: succeeded
Stopping job with name chaiml-gy-exp77-dpo-exp5-8904-v2-mkmlizer
Pipeline stage MKMLizer completed in 96.49s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-gy-exp77-dpo-exp5-8904-v2
Waiting for inference service chaiml-gy-exp77-dpo-exp5-8904-v2 to be ready
Inference service chaiml-gy-exp77-dpo-exp5-8904-v2 ready after 191.23177099227905s
Pipeline stage MKMLDeployer completed in 192.32s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.108147144317627s
Received healthy response to inference request in 1.5581560134887695s
Received healthy response to inference request in 1.7447762489318848s
Received healthy response to inference request in 1.53694486618042s
Received healthy response to inference request in 1.6642963886260986s
5 requests
0 failed requests
5th percentile: 1.5411870956420899
10th percentile: 1.5454293251037599
20th percentile: 1.5539137840270996
30th percentile: 1.5793840885162354
40th percentile: 1.621840238571167
50th percentile: 1.6642963886260986
60th percentile: 1.696488332748413
70th percentile: 1.7286802768707275
80th percentile: 1.8174504280090333
90th percentile: 1.96279878616333
95th percentile: 2.0354729652404786
99th percentile: 2.0936123085021974
mean time: 1.72246413230896
Pipeline stage StressChecker completed in 10.20s
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 0.70s
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 0.63s
Shutdown handler de-registered
chaiml-gy-exp77-dpo-exp5_8904_v2 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 0.11s
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-gy-exp77-dpo-exp5-8904-v2-profiler
Waiting for inference service chaiml-gy-exp77-dpo-exp5-8904-v2-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 5127.68s
Shutdown handler de-registered
chaiml-gy-exp77-dpo-exp5_8904_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp77-dpo-exp5_8904_v2 status is now torndown due to DeploymentManager action