chaiml-exp118-dpo-ftmeg_78741

developer_uid: NischayDnk

submission_id: chaiml-exp118-dpo-ftmeg_78741_v3

model_name: chaiml-exp118-dpo-ftmeg_78741_v3

model_group: ChaiML/exp118-DPO-ftmega

status: torndown

timestamp: 2025-03-25T19:03:46+00:00

num_battles: 7254

num_wins: 673

celo_rating: 874.81

family_friendly_score: 0.5898

family_friendly_standard_error: 0.006956090281185258

submission_type: basic

model_repo: ChaiML/exp118-DPO-ftmegasft-20ksspref-s01-e3

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': 0.36648814072358765, 'latency_mean': 2.7285136687755585, 'latency_p50': 2.7313120365142822, 'latency_p90': 3.02458336353302}, {'batch_size': 2, 'throughput': 0.5832392060343045, 'latency_mean': 3.427837852239609, 'latency_p50': 3.4096624851226807, 'latency_p90': 3.845712685585022}, {'batch_size': 3, 'throughput': 0.7258331633925547, 'latency_mean': 4.124074659347534, 'latency_p50': 4.1459269523620605, 'latency_p90': 4.492340612411499}, {'batch_size': 4, 'throughput': 0.8519071592532302, 'latency_mean': 4.666632996797562, 'latency_p50': 4.673682928085327, 'latency_p90': 5.181856799125671}, {'batch_size': 5, 'throughput': 0.9335020816884051, 'latency_mean': 5.3169117248058315, 'latency_p50': 5.361581802368164, 'latency_p90': 5.893210387229919}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-exp118-dpo-ftmeg_78741_v3

is_internal_developer: False

language_model: ChaiML/exp118-DPO-ftmegasft-20ksspref-s01-e3

model_size: 24B

ranking_group: single

throughput_3p7s: 0.65

us_pacific_date: 2025-03-25

win_ratio: 0.09277639922801213

generation_params: {'temperature': 0.45, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.45, 'frequency_penalty': 0.45, 'stopping_words': ['\n', '</s>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '[INST]', 'prompt_template': "''", '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': '### Response:\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-exp118-dpo-ftmeg-78741-v3-mkmlizer
Waiting for job on chaiml-exp118-dpo-ftmeg-78741-v3-mkmlizer to finish
chaiml-exp118-dpo-ftmeg-78741-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-exp118-dpo-ftmeg-78741-v3-mkmlizer: ║     _____            __           __                                ║
chaiml-exp118-dpo-ftmeg-78741-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-exp118-dpo-ftmeg-78741-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-exp118-dpo-ftmeg-78741-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-exp118-dpo-ftmeg-78741-v3-mkmlizer: ║       /___/                                                         ║
chaiml-exp118-dpo-ftmeg-78741-v3-mkmlizer: ║                                                                     ║
chaiml-exp118-dpo-ftmeg-78741-v3-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-exp118-dpo-ftmeg-78741-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-exp118-dpo-ftmeg-78741-v3-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-exp118-dpo-ftmeg-78741-v3-mkmlizer: ║                                                                     ║
chaiml-exp118-dpo-ftmeg-78741-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-exp118-dpo-ftmeg-78741-v3-mkmlizer: ║  belonging to:                                                      ║
chaiml-exp118-dpo-ftmeg-78741-v3-mkmlizer: ║                                                                     ║
chaiml-exp118-dpo-ftmeg-78741-v3-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-exp118-dpo-ftmeg-78741-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-exp118-dpo-ftmeg-78741-v3-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
chaiml-exp118-dpo-ftmeg-78741-v3-mkmlizer: ║                                                                     ║
chaiml-exp118-dpo-ftmeg-78741-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-exp118-dpo-ftmeg-78741-v3-mkmlizer: Downloaded to shared memory in 66.122s
chaiml-exp118-dpo-ftmeg-78741-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp6oyk5gmr, device:0
chaiml-exp118-dpo-ftmeg-78741-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-exp118-dpo-ftmeg-78741-v3-mkmlizer: quantized model in 53.827s
chaiml-exp118-dpo-ftmeg-78741-v3-mkmlizer: Processed model ChaiML/exp118-DPO-ftmegasft-20ksspref-s01-e3 in 119.949s
chaiml-exp118-dpo-ftmeg-78741-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-exp118-dpo-ftmeg-78741-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-exp118-dpo-ftmeg-78741-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-exp118-dpo-ftmeg-78741-v3
chaiml-exp118-dpo-ftmeg-78741-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-exp118-dpo-ftmeg-78741-v3/config.json
chaiml-exp118-dpo-ftmeg-78741-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-exp118-dpo-ftmeg-78741-v3/special_tokens_map.json
chaiml-exp118-dpo-ftmeg-78741-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-exp118-dpo-ftmeg-78741-v3/tokenizer_config.json
chaiml-exp118-dpo-ftmeg-78741-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-exp118-dpo-ftmeg-78741-v3/tokenizer.json
chaiml-exp118-dpo-ftmeg-78741-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-exp118-dpo-ftmeg-78741-v3/flywheel_model.0.safetensors
chaiml-exp118-dpo-ftmeg-78741-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-exp118-dpo-ftmeg-78741-v3/flywheel_model.1.safetensors
chaiml-exp118-dpo-ftmeg-78741-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 39.59it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:11, 30.62it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:10, 32.96it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:12, 28.81it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:10, 32.56it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:11, 29.11it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:09, 34.95it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:14, 21.91it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:13, 24.58it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:12, 25.63it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 27.71it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:11, 26.07it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:10, 28.53it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 26.41it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:11, 26.77it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:12, 23.67it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:14, 20.22it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:11, 25.39it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:11, 24.88it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 26.54it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:10, 27.02it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:12, 21.53it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:09, 28.48it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:09, 27.07it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:11, 22.96it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:09, 25.78it/s]
Loading 0:  31%|███▏      | 114/363 [00:04<00:10, 23.21it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 27.56it/s]
Loading 0:  34%|███▍      | 123/363 [00:04<00:09, 24.36it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:08, 28.93it/s]
Loading 0:  37%|███▋      | 133/363 [00:05<00:08, 27.58it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 29.88it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:07, 28.47it/s]
Loading 0:  41%|████      | 148/363 [00:05<00:06, 34.99it/s]
Loading 0:  42%|████▏     | 152/363 [00:05<00:08, 24.17it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:09, 22.71it/s]
Loading 0:  44%|████▍     | 159/363 [00:06<00:09, 21.23it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 26.24it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:08, 24.11it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 28.67it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 27.38it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:06, 27.80it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:07, 23.94it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 22.06it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 23.08it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:07, 23.55it/s]
Loading 0:  55%|█████▌    | 200/363 [00:22<00:06, 23.55it/s]
Loading 0:  55%|█████▌    | 201/363 [00:22<03:03,  1.13s/it]
Loading 0:  56%|█████▌    | 203/363 [00:22<02:31,  1.06it/s]
Loading 0:  57%|█████▋    | 208/363 [00:22<01:31,  1.70it/s]
Loading 0:  58%|█████▊    | 211/363 [00:22<01:10,  2.16it/s]
Loading 0:  59%|█████▉    | 214/363 [00:22<00:52,  2.86it/s]
Loading 0:  60%|██████    | 218/363 [00:22<00:35,  4.10it/s]
Loading 0:  61%|██████    | 221/363 [00:23<00:26,  5.27it/s]
Loading 0:  62%|██████▏   | 224/363 [00:23<00:21,  6.33it/s]
Loading 0:  63%|██████▎   | 229/363 [00:23<00:14,  9.29it/s]
Loading 0:  64%|██████▍   | 232/363 [00:23<00:11, 11.05it/s]
Loading 0:  65%|██████▌   | 237/363 [00:23<00:08, 14.87it/s]
Loading 0:  66%|██████▌   | 240/363 [00:23<00:07, 15.53it/s]
Loading 0:  68%|██████▊   | 246/363 [00:24<00:05, 20.86it/s]
Loading 0:  69%|██████▊   | 249/363 [00:24<00:05, 20.28it/s]
Loading 0:  70%|███████   | 255/363 [00:24<00:04, 25.22it/s]
Loading 0:  71%|███████▏  | 259/363 [00:24<00:04, 25.22it/s]
Loading 0:  73%|███████▎  | 265/363 [00:24<00:03, 31.88it/s]
Loading 0:  74%|███████▍  | 269/363 [00:24<00:04, 22.83it/s]
Loading 0:  75%|███████▌  | 273/363 [00:25<00:03, 22.98it/s]
Loading 0:  76%|███████▌  | 276/363 [00:25<00:03, 22.00it/s]
Loading 0:  78%|███████▊  | 282/363 [00:25<00:03, 26.81it/s]
Loading 0:  79%|███████▉  | 286/363 [00:25<00:02, 26.03it/s]
Loading 0:  80%|████████  | 291/363 [00:25<00:02, 29.04it/s]
Loading 0:  81%|████████▏ | 295/363 [00:25<00:02, 27.22it/s]
Loading 0:  82%|████████▏ | 299/363 [00:25<00:02, 28.11it/s]
Loading 0:  84%|████████▎ | 304/363 [00:26<00:02, 25.11it/s]
Loading 0:  85%|████████▍ | 307/363 [00:26<00:02, 23.09it/s]
Loading 0:  85%|████████▌ | 310/363 [00:26<00:02, 24.06it/s]
Loading 0:  86%|████████▌ | 313/363 [00:26<00:02, 24.70it/s]
Loading 0:  88%|████████▊ | 318/363 [00:26<00:01, 27.64it/s]
Loading 0:  88%|████████▊ | 321/363 [00:26<00:01, 25.40it/s]
Loading 0:  90%|█████████ | 327/363 [00:27<00:01, 30.81it/s]
Loading 0:  91%|█████████ | 331/363 [00:27<00:01, 29.01it/s]
Loading 0:  92%|█████████▏| 335/363 [00:27<00:00, 29.32it/s]
Loading 0:  93%|█████████▎| 338/363 [00:27<00:00, 27.04it/s]
Loading 0:  94%|█████████▍| 341/363 [00:34<00:13,  1.67it/s]
Loading 0:  96%|█████████▌| 347/363 [00:34<00:05,  2.79it/s]
Loading 0:  96%|█████████▋| 350/363 [00:34<00:03,  3.50it/s]
Loading 0:  98%|█████████▊| 355/363 [00:34<00:01,  5.19it/s]
Loading 0:  99%|█████████▉| 359/363 [00:34<00:00,  6.75it/s]
                                                            
Job chaiml-exp118-dpo-ftmeg-78741-v3-mkmlizer completed after 144.91s with status: succeeded
Stopping job with name chaiml-exp118-dpo-ftmeg-78741-v3-mkmlizer
Pipeline stage MKMLizer completed in 145.39s
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-exp118-dpo-ftmeg-78741-v3
Waiting for inference service chaiml-exp118-dpo-ftmeg-78741-v3 to be ready
Inference service chaiml-exp118-dpo-ftmeg-78741-v3 ready after 100.48852562904358s
Pipeline stage MKMLDeployer completed in 100.96s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.992617130279541s
Received healthy response to inference request in 2.491237163543701s
Received healthy response to inference request in 2.438626766204834s
Received healthy response to inference request in 2.446991443634033s
Received healthy response to inference request in 2.5986833572387695s
5 requests
0 failed requests
5th percentile: 2.440299701690674
10th percentile: 2.4419726371765136
20th percentile: 2.445318508148193
30th percentile: 2.455840587615967
40th percentile: 2.473538875579834
50th percentile: 2.491237163543701
60th percentile: 2.5342156410217287
70th percentile: 2.5771941184997558
80th percentile: 2.6774701118469237
90th percentile: 2.8350436210632326
95th percentile: 2.913830375671387
99th percentile: 2.9768597793579104
mean time: 2.5936311721801757
Pipeline stage StressChecker completed in 14.37s
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 0.69s
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 0.71s
Shutdown handler de-registered
chaiml-exp118-dpo-ftmeg_78741_v3 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 2068.67s
Shutdown handler de-registered
chaiml-exp118-dpo-ftmeg_78741_v3 status is now inactive due to auto deactivation removed underperforming models
chaiml-exp118-dpo-ftmeg_78741_v3 status is now torndown due to DeploymentManager action