chaiml-exp201-dpo-b01-2_30084

developer_uid: NischayDnk

submission_id: chaiml-exp201-dpo-b01-2_30084_v1

model_name: chaiml-exp201-dpo-b01-2_30084_v1

model_group: ChaiML/exp201-dpo-b01-2e

status: torndown

timestamp: 2025-04-12T15:51:32+00:00

num_battles: 6445

num_wins: 3620

celo_rating: 1336.85

family_friendly_score: 0.5198

family_friendly_standard_error: 0.007065521353728966

submission_type: basic

model_repo: ChaiML/exp201-dpo-b01-2e-ft-mistral31dpo3e-exp1-selfdist-9kconv-s75-1-1

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': 0.36666753546470293, 'latency_mean': 2.7271697533130648, 'latency_p50': 2.7231987714767456, 'latency_p90': 3.041442799568176}, {'batch_size': 2, 'throughput': 0.5697474449983215, 'latency_mean': 3.5005725872516633, 'latency_p50': 3.5233887434005737, 'latency_p90': 3.840834450721741}, {'batch_size': 3, 'throughput': 0.7156368141257355, 'latency_mean': 4.174895807504654, 'latency_p50': 4.200741291046143, 'latency_p90': 4.597543573379516}, {'batch_size': 4, 'throughput': 0.8392888322687241, 'latency_mean': 4.7371637678146366, 'latency_p50': 4.746290326118469, 'latency_p90': 5.210595178604126}, {'batch_size': 5, 'throughput': 0.9288243712422722, 'latency_mean': 5.343686838150024, 'latency_p50': 5.381641149520874, 'latency_p90': 5.987969064712524}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-exp201-dpo-b01-2_30084_v1

is_internal_developer: False

language_model: ChaiML/exp201-dpo-b01-2e-ft-mistral31dpo3e-exp1-selfdist-9kconv-s75-1-1

model_size: 24B

ranking_group: single

throughput_3p7s: 0.62

us_pacific_date: 2025-04-12

win_ratio: 0.5616757176105508

generation_params: {'temperature': 0.5, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 70, 'presence_penalty': 0.45, 'frequency_penalty': 0.45, 'stopping_words': ['<|im_start|>', '\n', '<|im_end|>'], '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-exp201-dpo-b01-2-30084-v1-mkmlizer
Waiting for job on chaiml-exp201-dpo-b01-2-30084-v1-mkmlizer to finish
chaiml-exp201-dpo-b01-2-30084-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-exp201-dpo-b01-2-30084-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-exp201-dpo-b01-2-30084-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-exp201-dpo-b01-2-30084-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-exp201-dpo-b01-2-30084-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-exp201-dpo-b01-2-30084-v1-mkmlizer: ║       /___/                                                         ║
chaiml-exp201-dpo-b01-2-30084-v1-mkmlizer: ║                                                                     ║
chaiml-exp201-dpo-b01-2-30084-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-exp201-dpo-b01-2-30084-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-exp201-dpo-b01-2-30084-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-exp201-dpo-b01-2-30084-v1-mkmlizer: ║                                                                     ║
chaiml-exp201-dpo-b01-2-30084-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-exp201-dpo-b01-2-30084-v1-mkmlizer: ║  belonging to:                                                      ║
Failed to get response for submission jellywibble-felix-black_21853_v1: HTTPConnectionPool(host='jellywibble-felix-black-21853-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-exp201-dpo-b01-2-30084-v1-mkmlizer: ║                                                                     ║
chaiml-exp201-dpo-b01-2-30084-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-exp201-dpo-b01-2-30084-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-exp201-dpo-b01-2-30084-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
chaiml-exp201-dpo-b01-2-30084-v1-mkmlizer: ║                                                                     ║
chaiml-exp201-dpo-b01-2-30084-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-exp201-dpo-b01-2-30084-v1-mkmlizer: Downloaded to shared memory in 81.887s
chaiml-exp201-dpo-b01-2-30084-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpo0yb3y28, device:0
chaiml-exp201-dpo-b01-2-30084-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-exp201-dpo-b01-2-30084-v1-mkmlizer: quantized model in 53.086s
chaiml-exp201-dpo-b01-2-30084-v1-mkmlizer: Processed model ChaiML/exp201-dpo-b01-2e-ft-mistral31dpo3e-exp1-selfdist-9kconv-s75-1-1 in 134.974s
chaiml-exp201-dpo-b01-2-30084-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-exp201-dpo-b01-2-30084-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-exp201-dpo-b01-2-30084-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-exp201-dpo-b01-2-30084-v1
chaiml-exp201-dpo-b01-2-30084-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-exp201-dpo-b01-2-30084-v1/config.json
chaiml-exp201-dpo-b01-2-30084-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-exp201-dpo-b01-2-30084-v1/special_tokens_map.json
chaiml-exp201-dpo-b01-2-30084-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-exp201-dpo-b01-2-30084-v1/tokenizer_config.json
chaiml-exp201-dpo-b01-2-30084-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-exp201-dpo-b01-2-30084-v1/tokenizer.json
Failed to get response for submission jellywibble-felix-black_21853_v1: HTTPConnectionPool(host='jellywibble-felix-black-21853-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-exp201-dpo-b01-2-30084-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-exp201-dpo-b01-2-30084-v1/flywheel_model.1.safetensors
chaiml-exp201-dpo-b01-2-30084-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-exp201-dpo-b01-2-30084-v1/flywheel_model.0.safetensors
chaiml-exp201-dpo-b01-2-30084-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.95it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:09, 36.09it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:10, 34.00it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:09, 34.85it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:10, 31.63it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:08, 37.23it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:14, 23.12it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:12, 25.65it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:12, 26.51it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 27.78it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:11, 26.63it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:10, 29.12it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 27.23it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 28.03it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:11, 24.90it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:13, 21.56it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 26.71it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:10, 26.07it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:09, 27.83it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:10, 27.19it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:12, 21.61it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:09, 29.07it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:09, 28.02it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:11, 23.21it/s]
Loading 0:  31%|███       | 112/363 [00:04<00:09, 26.18it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:09, 26.29it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 28.73it/s]
Loading 0:  34%|███▍      | 123/363 [00:04<00:09, 26.00it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 30.47it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:08, 28.56it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:07, 30.35it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:07, 28.94it/s]
Loading 0:  40%|████      | 147/363 [00:05<00:06, 33.48it/s]
Loading 0:  42%|████▏     | 151/363 [00:05<00:08, 25.24it/s]
Loading 0:  42%|████▏     | 154/363 [00:05<00:08, 23.61it/s]
Loading 0:  43%|████▎     | 157/363 [00:05<00:08, 24.71it/s]
Loading 0:  44%|████▍     | 160/363 [00:05<00:08, 25.11it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:06, 28.33it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:07, 25.35it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 30.50it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 28.89it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:06, 28.94it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:06, 26.54it/s]
Loading 0:  52%|█████▏    | 190/363 [00:06<00:07, 24.21it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:06, 25.12it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 25.65it/s]
Loading 0:  55%|█████▌    | 200/363 [00:21<00:06, 25.65it/s]
Loading 0:  55%|█████▌    | 201/363 [00:21<02:59,  1.11s/it]
Loading 0:  56%|█████▌    | 203/363 [00:21<02:28,  1.08it/s]
Loading 0:  57%|█████▋    | 208/363 [00:21<01:28,  1.74it/s]
Loading 0:  58%|█████▊    | 211/363 [00:21<01:08,  2.22it/s]
Loading 0:  59%|█████▉    | 214/363 [00:22<00:50,  2.93it/s]
Loading 0:  60%|██████    | 218/363 [00:22<00:34,  4.18it/s]
Loading 0:  61%|██████    | 221/363 [00:22<00:26,  5.33it/s]
Loading 0:  62%|██████▏   | 224/363 [00:22<00:21,  6.35it/s]
Loading 0:  63%|██████▎   | 229/363 [00:22<00:14,  9.34it/s]
Loading 0:  64%|██████▍   | 232/363 [00:22<00:11, 11.01it/s]
Loading 0:  65%|██████▌   | 237/363 [00:23<00:08, 14.85it/s]
Loading 0:  66%|██████▌   | 240/363 [00:23<00:07, 15.67it/s]
Loading 0:  68%|██████▊   | 246/363 [00:23<00:05, 20.80it/s]
Loading 0:  69%|██████▊   | 249/363 [00:23<00:05, 20.37it/s]
Loading 0:  70%|███████   | 255/363 [00:23<00:04, 25.65it/s]
Loading 0:  71%|███████▏  | 259/363 [00:23<00:04, 25.64it/s]
Loading 0:  73%|███████▎  | 265/363 [00:23<00:03, 32.19it/s]
Loading 0:  74%|███████▍  | 269/363 [00:24<00:04, 23.31it/s]
Loading 0:  75%|███████▌  | 273/363 [00:24<00:03, 23.43it/s]
Loading 0:  76%|███████▌  | 276/363 [00:24<00:03, 22.59it/s]
Loading 0:  78%|███████▊  | 282/363 [00:24<00:02, 27.39it/s]
Loading 0:  79%|███████▉  | 286/363 [00:24<00:02, 26.80it/s]
Loading 0:  80%|████████  | 291/363 [00:24<00:02, 28.93it/s]
Loading 0:  81%|████████▏ | 295/363 [00:25<00:02, 27.74it/s]
Loading 0:  82%|████████▏ | 299/363 [00:25<00:02, 28.26it/s]
Loading 0:  84%|████████▎ | 304/363 [00:25<00:02, 25.85it/s]
Loading 0:  85%|████████▍ | 307/363 [00:25<00:02, 24.11it/s]
Loading 0:  85%|████████▌ | 310/363 [00:25<00:02, 25.10it/s]
Loading 0:  86%|████████▌ | 313/363 [00:25<00:01, 25.59it/s]
Loading 0:  88%|████████▊ | 318/363 [00:25<00:01, 28.83it/s]
Loading 0:  88%|████████▊ | 321/363 [00:26<00:01, 25.67it/s]
Loading 0:  90%|█████████ | 327/363 [00:26<00:01, 29.98it/s]
Loading 0:  91%|█████████ | 331/363 [00:26<00:01, 28.33it/s]
Loading 0:  92%|█████████▏| 335/363 [00:26<00:00, 28.60it/s]
Loading 0:  93%|█████████▎| 338/363 [00:26<00:00, 27.64it/s]
Loading 0:  94%|█████████▍| 341/363 [00:33<00:13,  1.68it/s]
Loading 0:  96%|█████████▌| 347/363 [00:33<00:05,  2.81it/s]
Loading 0:  96%|█████████▋| 350/363 [00:33<00:03,  3.54it/s]
Loading 0:  98%|█████████▊| 355/363 [00:33<00:01,  5.23it/s]
Loading 0:  99%|█████████▉| 359/363 [00:34<00:00,  6.79it/s]
                                                            
Job chaiml-exp201-dpo-b01-2-30084-v1-mkmlizer completed after 177.82s with status: succeeded
Stopping job with name chaiml-exp201-dpo-b01-2-30084-v1-mkmlizer
Pipeline stage MKMLizer completed in 178.30s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.36s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-exp201-dpo-b01-2-30084-v1
Waiting for inference service chaiml-exp201-dpo-b01-2-30084-v1 to be ready
Inference service chaiml-exp201-dpo-b01-2-30084-v1 ready after 120.43762946128845s
Pipeline stage MKMLDeployer completed in 120.98s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.1500418186187744s
Received healthy response to inference request in 2.6070716381073s
Received healthy response to inference request in 2.4972639083862305s
Received healthy response to inference request in 3.133157253265381s
Received healthy response to inference request in 2.528357744216919s
5 requests
0 failed requests
5th percentile: 2.5034826755523683
10th percentile: 2.509701442718506
20th percentile: 2.522138977050781
30th percentile: 2.544100522994995
40th percentile: 2.5755860805511475
50th percentile: 2.6070716381073
60th percentile: 2.817505884170532
70th percentile: 3.0279401302337647
80th percentile: 3.1365341663360597
90th percentile: 3.143287992477417
95th percentile: 3.1466649055480955
99th percentile: 3.1493664360046387
mean time: 2.783178472518921
Pipeline stage StressChecker completed in 15.20s
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 0.87s
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 0.72s
Shutdown handler de-registered
chaiml-exp201-dpo-b01-2_30084_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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-exp201-dpo-b01-2-30084-v1-profiler
Waiting for inference service chaiml-exp201-dpo-b01-2-30084-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
clean up pipeline due to error=DeploymentChecksError('None: None')
Shutdown handler de-registered
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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
clean up pipeline due to error=DeploymentChecksError('None: None')
Shutdown handler de-registered
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 4041.53s
Shutdown handler de-registered
chaiml-exp201-dpo-b01-2_30084_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-exp201-dpo-b01-2_30084_v1 status is now torndown due to DeploymentManager action