chaiml-exp102-dpo-chosw_82634

developer_uid: NischayDnk

submission_id: chaiml-exp102-dpo-chosw_82634_v1

model_name: chaiml-exp102-dpo-chosw_82634_v1

model_group: ChaiML/exp102-dpo-choswo

status: torndown

timestamp: 2025-03-17T19:23:26+00:00

num_battles: 13738

num_wins: 7094

celo_rating: 1289.7

family_friendly_score: 0.5474

family_friendly_standard_error: 0.00703922211611482

submission_type: basic

model_repo: ChaiML/exp102-dpo-chosworst-24B-ssfilter5k

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': 0.37315195846983423, 'latency_mean': 2.6797787940502165, 'latency_p50': 2.672024726867676, 'latency_p90': 2.984157347679138}, {'batch_size': 2, 'throughput': 0.5772452148876699, 'latency_mean': 3.459990473985672, 'latency_p50': 3.4571454524993896, 'latency_p90': 3.788473105430603}, {'batch_size': 3, 'throughput': 0.7326694491758061, 'latency_mean': 4.075590790510177, 'latency_p50': 4.0617018938064575, 'latency_p90': 4.502012538909912}, {'batch_size': 4, 'throughput': 0.8527442576279226, 'latency_mean': 4.6838286530971525, 'latency_p50': 4.657257080078125, 'latency_p90': 5.215298366546631}, {'batch_size': 5, 'throughput': 0.9366094850704696, 'latency_mean': 5.302109962701797, 'latency_p50': 5.355320692062378, 'latency_p90': 5.920233988761901}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-exp102-dpo-chosw_82634_v1

is_internal_developer: False

language_model: ChaiML/exp102-dpo-chosworst-24B-ssfilter5k

model_size: 24B

ranking_group: single

throughput_3p7s: 0.65

us_pacific_date: 2025-03-17

win_ratio: 0.5163779298296696

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}:', '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-exp102-dpo-chosw-82634-v1-mkmlizer
Waiting for job on chaiml-exp102-dpo-chosw-82634-v1-mkmlizer to finish
chaiml-exp102-dpo-chosw-82634-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-exp102-dpo-chosw-82634-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-exp102-dpo-chosw-82634-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-exp102-dpo-chosw-82634-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-exp102-dpo-chosw-82634-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-exp102-dpo-chosw-82634-v1-mkmlizer: ║       /___/                                                         ║
chaiml-exp102-dpo-chosw-82634-v1-mkmlizer: ║                                                                     ║
chaiml-exp102-dpo-chosw-82634-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-exp102-dpo-chosw-82634-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-exp102-dpo-chosw-82634-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-exp102-dpo-chosw-82634-v1-mkmlizer: ║                                                                     ║
chaiml-exp102-dpo-chosw-82634-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-exp102-dpo-chosw-82634-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-exp102-dpo-chosw-82634-v1-mkmlizer: ║                                                                     ║
chaiml-exp102-dpo-chosw-82634-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-exp102-dpo-chosw-82634-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-exp102-dpo-chosw-82634-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
chaiml-exp102-dpo-chosw-82634-v1-mkmlizer: ║                                                                     ║
chaiml-exp102-dpo-chosw-82634-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-exp102-dpo-chosw-82634-v1-mkmlizer: Downloaded to shared memory in 85.093s
chaiml-exp102-dpo-chosw-82634-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpk7r857i1, device:0
chaiml-exp102-dpo-chosw-82634-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-exp102-dpo-chosw-82634-v1-mkmlizer: quantized model in 52.844s
chaiml-exp102-dpo-chosw-82634-v1-mkmlizer: Processed model ChaiML/exp102-dpo-chosworst-24B-ssfilter5k in 137.938s
chaiml-exp102-dpo-chosw-82634-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-exp102-dpo-chosw-82634-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-exp102-dpo-chosw-82634-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-exp102-dpo-chosw-82634-v1
chaiml-exp102-dpo-chosw-82634-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-exp102-dpo-chosw-82634-v1/config.json
chaiml-exp102-dpo-chosw-82634-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-exp102-dpo-chosw-82634-v1/special_tokens_map.json
chaiml-exp102-dpo-chosw-82634-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-exp102-dpo-chosw-82634-v1/tokenizer_config.json
chaiml-exp102-dpo-chosw-82634-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-exp102-dpo-chosw-82634-v1/tokenizer.json
chaiml-exp102-dpo-chosw-82634-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-exp102-dpo-chosw-82634-v1/flywheel_model.1.safetensors
chaiml-exp102-dpo-chosw-82634-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-exp102-dpo-chosw-82634-v1/flywheel_model.0.safetensors
chaiml-exp102-dpo-chosw-82634-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 38.21it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:11, 30.12it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:10, 32.99it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:11, 30.17it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:09, 35.09it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:10, 31.48it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:08, 38.85it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:15, 21.42it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:13, 23.81it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:12, 25.98it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 28.61it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:11, 27.54it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:10, 29.71it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 27.20it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 27.14it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:12, 24.00it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:14, 20.25it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:11, 25.37it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:11, 25.04it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 26.38it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:10, 26.52it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:12, 20.95it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:09, 27.78it/s]
Loading 0:  28%|██▊       | 102/363 [00:03<00:10, 25.25it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:11, 22.66it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:09, 25.81it/s]
Loading 0:  31%|███▏      | 114/363 [00:04<00:10, 23.55it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 29.01it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 28.47it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 31.35it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 28.94it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 31.65it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:07, 29.89it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:05, 35.85it/s]
Loading 0:  42%|████▏     | 153/363 [00:05<00:09, 23.01it/s]
Loading 0:  43%|████▎     | 157/363 [00:05<00:08, 25.55it/s]
Loading 0:  44%|████▍     | 161/363 [00:05<00:07, 26.55it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:06, 28.73it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:06, 28.12it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 30.85it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 29.25it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:06, 29.88it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:06, 27.62it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 24.35it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:06, 25.03it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 26.08it/s]
Loading 0:  55%|█████▌    | 200/363 [00:21<00:06, 26.08it/s]
Loading 0:  55%|█████▌    | 201/363 [00:21<02:57,  1.10s/it]
Loading 0:  56%|█████▌    | 203/363 [00:21<02:27,  1.08it/s]
Loading 0:  57%|█████▋    | 208/363 [00:21<01:28,  1.74it/s]
Loading 0:  58%|█████▊    | 211/363 [00:21<01:07,  2.24it/s]
Loading 0:  59%|█████▉    | 214/363 [00:22<00:50,  2.94it/s]
Loading 0:  60%|██████    | 218/363 [00:22<00:34,  4.22it/s]
Loading 0:  61%|██████    | 221/363 [00:22<00:26,  5.41it/s]
Loading 0:  62%|██████▏   | 224/363 [00:22<00:21,  6.52it/s]
Loading 0:  63%|██████▎   | 228/363 [00:22<00:14,  9.11it/s]
Loading 0:  64%|██████▎   | 231/363 [00:22<00:12, 10.51it/s]
Loading 0:  65%|██████▌   | 237/363 [00:22<00:08, 15.37it/s]
Loading 0:  66%|██████▌   | 240/363 [00:23<00:07, 15.77it/s]
Loading 0:  67%|██████▋   | 244/363 [00:23<00:06, 19.16it/s]
Loading 0:  68%|██████▊   | 247/363 [00:23<00:05, 20.73it/s]
Loading 0:  69%|██████▉   | 250/363 [00:23<00:05, 21.76it/s]
Loading 0:  70%|███████   | 255/363 [00:23<00:04, 25.79it/s]
Loading 0:  71%|███████▏  | 259/363 [00:23<00:04, 25.82it/s]
Loading 0:  73%|███████▎  | 266/363 [00:23<00:02, 32.39it/s]
Loading 0:  74%|███████▍  | 270/363 [00:24<00:04, 21.10it/s]
Loading 0:  75%|███████▌  | 274/363 [00:24<00:03, 24.04it/s]
Loading 0:  77%|███████▋  | 278/363 [00:24<00:03, 25.78it/s]
Loading 0:  78%|███████▊  | 282/363 [00:24<00:02, 27.72it/s]
Loading 0:  79%|███████▉  | 286/363 [00:24<00:02, 27.41it/s]
Loading 0:  80%|████████  | 291/363 [00:24<00:02, 30.61it/s]
Loading 0:  81%|████████▏ | 295/363 [00:25<00:02, 29.18it/s]
Loading 0:  82%|████████▏ | 299/363 [00:25<00:02, 29.63it/s]
Loading 0:  84%|████████▎ | 304/363 [00:25<00:02, 27.13it/s]
Loading 0:  85%|████████▍ | 307/363 [00:25<00:02, 23.55it/s]
Loading 0:  85%|████████▌ | 310/363 [00:25<00:02, 24.20it/s]
Loading 0:  86%|████████▌ | 313/363 [00:25<00:01, 25.37it/s]
Loading 0:  88%|████████▊ | 318/363 [00:25<00:01, 28.99it/s]
Loading 0:  88%|████████▊ | 321/363 [00:26<00:01, 26.41it/s]
Loading 0:  90%|█████████ | 327/363 [00:26<00:01, 31.96it/s]
Loading 0:  91%|█████████ | 331/363 [00:26<00:01, 30.75it/s]
Loading 0:  92%|█████████▏| 335/363 [00:26<00:00, 30.77it/s]
Loading 0:  93%|█████████▎| 339/363 [00:26<00:00, 31.07it/s]
Loading 0:  94%|█████████▍| 343/363 [00:33<00:10,  1.91it/s]
Loading 0:  96%|█████████▌| 347/363 [00:33<00:06,  2.65it/s]
Loading 0:  96%|█████████▋| 350/363 [00:33<00:03,  3.37it/s]
Loading 0:  98%|█████████▊| 355/363 [00:33<00:01,  5.06it/s]
Loading 0:  99%|█████████▉| 359/363 [00:33<00:00,  6.58it/s]
                                                            
Job chaiml-exp102-dpo-chosw-82634-v1-mkmlizer completed after 165.83s with status: succeeded
Stopping job with name chaiml-exp102-dpo-chosw-82634-v1-mkmlizer
Pipeline stage MKMLizer completed in 166.34s
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-exp102-dpo-chosw-82634-v1
Waiting for inference service chaiml-exp102-dpo-chosw-82634-v1 to be ready
Inference service chaiml-exp102-dpo-chosw-82634-v1 ready after 90.4696192741394s
Pipeline stage MKMLDeployer completed in 91.03s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.42767333984375s
Received healthy response to inference request in 2.4938528537750244s
Received healthy response to inference request in 2.9236111640930176s
Received healthy response to inference request in 2.774716854095459s
Received healthy response to inference request in 3.013007879257202s
5 requests
0 failed requests
5th percentile: 2.5500256538391115
10th percentile: 2.606198453903198
20th percentile: 2.718544054031372
30th percentile: 2.8044957160949706
40th percentile: 2.8640534400939943
50th percentile: 2.9236111640930176
60th percentile: 2.9593698501586916
70th percentile: 2.995128536224365
80th percentile: 3.0959409713745116
90th percentile: 3.261807155609131
95th percentile: 3.3447402477264405
99th percentile: 3.411086721420288
mean time: 2.9265724182128907
Pipeline stage StressChecker completed in 16.04s
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 0.68s
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 0.80s
Shutdown handler de-registered
chaiml-exp102-dpo-chosw_82634_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 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.07s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-exp102-dpo-chosw-82634-v1-profiler
Waiting for inference service chaiml-exp102-dpo-chosw-82634-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 5434.58s
Shutdown handler de-registered
chaiml-exp102-dpo-chosw_82634_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-exp102-dpo-chosw_82634_v1 status is now torndown due to DeploymentManager action