chaiml-exp82-dpo-megasf_78696

developer_uid: NischayDnk

submission_id: chaiml-exp82-dpo-megasf_78696_v1

model_name: chaiml-exp82-dpo-megasf_78696_v1

model_group: ChaiML/exp82-dpo-megasft

status: torndown

timestamp: 2025-03-14T22:26:10+00:00

num_battles: 7037

num_wins: 3232

celo_rating: 1251.11

family_friendly_score: 0.5906

family_friendly_standard_error: 0.006954015243008891

submission_type: basic

model_repo: ChaiML/exp82-dpo-megasfte2-24B-sftbestof8-5k-v1

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.36619427647142283, 'latency_mean': 2.7306924998760223, 'latency_p50': 2.7209999561309814, 'latency_p90': 3.002500319480896}, {'batch_size': 2, 'throughput': 0.5734765205977344, 'latency_mean': 3.472445036172867, 'latency_p50': 3.4880120754241943, 'latency_p90': 3.811012530326843}, {'batch_size': 3, 'throughput': 0.7282531089873953, 'latency_mean': 4.113594539165497, 'latency_p50': 4.119095325469971, 'latency_p90': 4.497116327285767}, {'batch_size': 4, 'throughput': 0.8469094069364582, 'latency_mean': 4.709544752836227, 'latency_p50': 4.687007427215576, 'latency_p90': 5.2024287462234495}, {'batch_size': 5, 'throughput': 0.924959067325472, 'latency_mean': 5.370825136899948, 'latency_p50': 5.4209665060043335, 'latency_p90': 6.0522607326507565}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-exp82-dpo-megasf_78696_v1

is_internal_developer: False

language_model: ChaiML/exp82-dpo-megasfte2-24B-sftbestof8-5k-v1

model_size: 24B

ranking_group: single

throughput_3p7s: 0.64

us_pacific_date: 2025-03-14

win_ratio: 0.459286627824357

generation_params: {'temperature': 0.4, 'top_p': 0.96, 'min_p': 0.025, 'top_k': 80, 'presence_penalty': 0.45, 'frequency_penalty': 0.45, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '[INST]<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{bot_name}:[/INST]', '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-exp82-dpo-megasf-78696-v1-mkmlizer
Waiting for job on chaiml-exp82-dpo-megasf-78696-v1-mkmlizer to finish
chaiml-exp82-dpo-megasf-78696-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-exp82-dpo-megasf-78696-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-exp82-dpo-megasf-78696-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-exp82-dpo-megasf-78696-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-exp82-dpo-megasf-78696-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-exp82-dpo-megasf-78696-v1-mkmlizer: ║       /___/                                                         ║
chaiml-exp82-dpo-megasf-78696-v1-mkmlizer: ║                                                                     ║
chaiml-exp82-dpo-megasf-78696-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-exp82-dpo-megasf-78696-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-exp82-dpo-megasf-78696-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-exp82-dpo-megasf-78696-v1-mkmlizer: ║                                                                     ║
chaiml-exp82-dpo-megasf-78696-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-exp82-dpo-megasf-78696-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-exp82-dpo-megasf-78696-v1-mkmlizer: ║                                                                     ║
chaiml-exp82-dpo-megasf-78696-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-exp82-dpo-megasf-78696-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-exp82-dpo-megasf-78696-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
chaiml-exp82-dpo-megasf-78696-v1-mkmlizer: ║                                                                     ║
chaiml-exp82-dpo-megasf-78696-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-exp82-dpo-megasf-78696-v1-mkmlizer: Downloaded to shared memory in 83.813s
chaiml-exp82-dpo-megasf-78696-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp3pi2g3y7, device:0
chaiml-exp82-dpo-megasf-78696-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-exp82-dpo-megasf-78696-v1-mkmlizer: quantized model in 52.778s
chaiml-exp82-dpo-megasf-78696-v1-mkmlizer: Processed model ChaiML/exp82-dpo-megasfte2-24B-sftbestof8-5k-v1 in 136.592s
chaiml-exp82-dpo-megasf-78696-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-exp82-dpo-megasf-78696-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-exp82-dpo-megasf-78696-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-exp82-dpo-megasf-78696-v1
chaiml-exp82-dpo-megasf-78696-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-exp82-dpo-megasf-78696-v1/config.json
chaiml-exp82-dpo-megasf-78696-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-exp82-dpo-megasf-78696-v1/special_tokens_map.json
chaiml-exp82-dpo-megasf-78696-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-exp82-dpo-megasf-78696-v1/tokenizer_config.json
chaiml-exp82-dpo-megasf-78696-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-exp82-dpo-megasf-78696-v1/tokenizer.json
chaiml-exp82-dpo-megasf-78696-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-exp82-dpo-megasf-78696-v1/flywheel_model.1.safetensors
chaiml-exp82-dpo-megasf-78696-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-exp82-dpo-megasf-78696-v1/flywheel_model.0.safetensors
chaiml-exp82-dpo-megasf-78696-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 37.70it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:11, 29.99it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:10, 32.89it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:11, 29.66it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:09, 34.50it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:10, 30.77it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:09, 36.66it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:15, 20.86it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:13, 23.42it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:12, 25.22it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 27.61it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:11, 26.69it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:10, 30.18it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:10, 28.46it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 29.41it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:11, 25.67it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:13, 21.86it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 27.37it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:09, 28.52it/s]
Loading 0:  24%|██▍       | 87/363 [00:03<00:11, 24.93it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:10, 27.16it/s]
Loading 0:  26%|██▌       | 94/363 [00:03<00:09, 26.95it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:08, 29.91it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:09, 28.39it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:11, 23.11it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:09, 26.37it/s]
Loading 0:  31%|███▏      | 114/363 [00:04<00:10, 23.92it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 28.51it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 26.90it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 29.91it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 28.80it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:07, 31.43it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:07, 29.69it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:06, 35.52it/s]
Loading 0:  42%|████▏     | 153/363 [00:05<00:09, 22.38it/s]
Loading 0:  43%|████▎     | 157/363 [00:05<00:08, 24.89it/s]
Loading 0:  44%|████▍     | 161/363 [00:05<00:07, 26.47it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 28.53it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:06, 27.91it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 30.76it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 29.31it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:06, 29.79it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:06, 26.88it/s]
Loading 0:  52%|█████▏    | 190/363 [00:06<00:07, 23.38it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 24.24it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 25.26it/s]
Loading 0:  55%|█████▌    | 200/363 [00:21<00:06, 25.26it/s]
Loading 0:  55%|█████▌    | 201/363 [00:21<02:58,  1.10s/it]
Loading 0:  56%|█████▌    | 203/363 [00:21<02:26,  1.09it/s]
Loading 0:  57%|█████▋    | 208/363 [00:21<01:28,  1.76it/s]
Loading 0:  58%|█████▊    | 211/363 [00:21<01:08,  2.23it/s]
Loading 0:  59%|█████▉    | 214/363 [00:21<00:50,  2.95it/s]
Loading 0:  60%|██████    | 218/363 [00:22<00:34,  4.23it/s]
Loading 0:  61%|██████    | 221/363 [00:22<00:26,  5.40it/s]
Loading 0:  62%|██████▏   | 224/363 [00:22<00:21,  6.51it/s]
Loading 0:  63%|██████▎   | 229/363 [00:22<00:14,  9.55it/s]
Loading 0:  64%|██████▍   | 232/363 [00:22<00:11, 11.31it/s]
Loading 0:  65%|██████▌   | 237/363 [00:22<00:08, 15.21it/s]
Loading 0:  66%|██████▌   | 240/363 [00:22<00:07, 16.07it/s]
Loading 0:  68%|██████▊   | 246/363 [00:23<00:05, 21.73it/s]
Loading 0:  69%|██████▉   | 250/363 [00:23<00:05, 22.08it/s]
Loading 0:  70%|███████   | 255/363 [00:23<00:04, 25.43it/s]
Loading 0:  71%|███████▏  | 259/363 [00:23<00:04, 25.44it/s]
Loading 0:  73%|███████▎  | 265/363 [00:23<00:03, 32.24it/s]
Loading 0:  74%|███████▍  | 269/363 [00:24<00:04, 22.94it/s]
Loading 0:  75%|███████▌  | 273/363 [00:24<00:03, 23.01it/s]
Loading 0:  76%|███████▌  | 276/363 [00:24<00:03, 21.96it/s]
Loading 0:  78%|███████▊  | 282/363 [00:24<00:03, 26.97it/s]
Loading 0:  79%|███████▉  | 286/363 [00:24<00:02, 26.27it/s]
Loading 0:  80%|████████  | 291/363 [00:24<00:02, 29.20it/s]
Loading 0:  81%|████████▏ | 295/363 [00:24<00:02, 27.08it/s]
Loading 0:  82%|████████▏ | 299/363 [00:25<00:02, 27.37it/s]
Loading 0:  84%|████████▎ | 304/363 [00:25<00:02, 25.28it/s]
Loading 0:  85%|████████▍ | 307/363 [00:25<00:02, 23.29it/s]
Loading 0:  85%|████████▌ | 310/363 [00:25<00:02, 24.17it/s]
Loading 0:  86%|████████▌ | 313/363 [00:25<00:02, 24.97it/s]
Loading 0:  88%|████████▊ | 318/363 [00:25<00:01, 28.29it/s]
Loading 0:  88%|████████▊ | 321/363 [00:25<00:01, 25.66it/s]
Loading 0:  90%|█████████ | 327/363 [00:26<00:01, 31.23it/s]
Loading 0:  91%|█████████ | 331/363 [00:26<00:01, 28.62it/s]
Loading 0:  92%|█████████▏| 335/363 [00:26<00:00, 29.18it/s]
Loading 0:  93%|█████████▎| 338/363 [00:26<00:00, 27.97it/s]
Loading 0:  94%|█████████▍| 341/363 [00:33<00:13,  1.68it/s]
Loading 0:  96%|█████████▌| 347/363 [00:33<00:05,  2.80it/s]
Loading 0:  96%|█████████▋| 350/363 [00:33<00:03,  3.53it/s]
Loading 0:  98%|█████████▊| 355/363 [00:33<00:01,  5.24it/s]
Loading 0:  99%|█████████▉| 359/363 [00:33<00:00,  6.82it/s]
                                                            
Job chaiml-exp82-dpo-megasf-78696-v1-mkmlizer completed after 165.64s with status: succeeded
Stopping job with name chaiml-exp82-dpo-megasf-78696-v1-mkmlizer
Pipeline stage MKMLizer completed in 166.12s
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-exp82-dpo-megasf-78696-v1
Waiting for inference service chaiml-exp82-dpo-megasf-78696-v1 to be ready
Inference service chaiml-exp82-dpo-megasf-78696-v1 ready after 100.35818672180176s
Pipeline stage MKMLDeployer completed in 100.88s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.472820520401001s
Received healthy response to inference request in 2.7852885723114014s
Received healthy response to inference request in 2.5434389114379883s
Received healthy response to inference request in 2.534287929534912s
Received healthy response to inference request in 2.5022504329681396s
5 requests
0 failed requests
5th percentile: 2.508657932281494
10th percentile: 2.5150654315948486
20th percentile: 2.5278804302215576
30th percentile: 2.5361181259155274
40th percentile: 2.5397785186767576
50th percentile: 2.5434389114379883
60th percentile: 2.6401787757873536
70th percentile: 2.736918640136719
80th percentile: 2.9227949619293216
90th percentile: 3.1978077411651613
95th percentile: 3.3353141307830807
99th percentile: 3.445319242477417
mean time: 2.7676172733306883
Pipeline stage StressChecker completed in 15.21s
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 0.69s
Shutdown handler de-registered
chaiml-exp82-dpo-megasf_78696_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 0.11s
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-exp82-dpo-megasf-78696-v1-profiler
Waiting for inference service chaiml-exp82-dpo-megasf-78696-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 5497.52s
Shutdown handler de-registered
chaiml-exp82-dpo-megasf_78696_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-exp82-dpo-megasf_78696_v1 status is now torndown due to DeploymentManager action