chaiml-exp52-albert-sft_26828

developer_uid: NischayDnk

submission_id: chaiml-exp52-albert-sft_26828_v2

model_name: chaiml-exp52-albert-sft_26828_v2

model_group: ChaiML/exp52-albert-sft-

status: torndown

timestamp: 2025-03-07T13:59:55+00:00

num_battles: 10681

num_wins: 4964

celo_rating: 1251.1

family_friendly_score: 0.5746

family_friendly_standard_error: 0.006991921624274688

submission_type: basic

model_repo: ChaiML/exp52-albert-sft-allsamples-try1

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': 0.36945476441882286, 'latency_mean': 2.7066266667842864, 'latency_p50': 2.7010903358459473, 'latency_p90': 2.991960859298706}, {'batch_size': 2, 'throughput': 0.5761675983416379, 'latency_mean': 3.4635548007488253, 'latency_p50': 3.448222517967224, 'latency_p90': 3.825489044189453}, {'batch_size': 3, 'throughput': 0.7344427169617678, 'latency_mean': 4.082281795740127, 'latency_p50': 4.0677855014801025, 'latency_p90': 4.534836673736573}, {'batch_size': 4, 'throughput': 0.8490774844583117, 'latency_mean': 4.702590085268021, 'latency_p50': 4.689609169960022, 'latency_p90': 5.1620807409286495}, {'batch_size': 5, 'throughput': 0.944370948284535, 'latency_mean': 5.260379415750504, 'latency_p50': 5.234393000602722, 'latency_p90': 5.858799147605896}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-exp52-albert-sft_26828_v2

is_internal_developer: False

language_model: ChaiML/exp52-albert-sft-allsamples-try1

model_size: 24B

ranking_group: single

throughput_3p7s: 0.64

us_pacific_date: 2025-03-07

win_ratio: 0.4647504915270106

generation_params: {'temperature': 0.5, 'top_p': 0.9, 'min_p': 0.05, 'top_k': 40, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '<|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-exp52-albert-sft-26828-v2-mkmlizer
Waiting for job on chaiml-exp52-albert-sft-26828-v2-mkmlizer to finish
chaiml-exp52-albert-sft-26828-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-exp52-albert-sft-26828-v2-mkmlizer: ║     _____            __           __                                ║
chaiml-exp52-albert-sft-26828-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-exp52-albert-sft-26828-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-exp52-albert-sft-26828-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-exp52-albert-sft-26828-v2-mkmlizer: ║       /___/                                                         ║
chaiml-exp52-albert-sft-26828-v2-mkmlizer: ║                                                                     ║
chaiml-exp52-albert-sft-26828-v2-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-exp52-albert-sft-26828-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-exp52-albert-sft-26828-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-exp52-albert-sft-26828-v2-mkmlizer: ║                                                                     ║
chaiml-exp52-albert-sft-26828-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-exp52-albert-sft-26828-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-exp52-albert-sft-26828-v2-mkmlizer: ║                                                                     ║
chaiml-exp52-albert-sft-26828-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-exp52-albert-sft-26828-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-exp52-albert-sft-26828-v2-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
chaiml-exp52-albert-sft-26828-v2-mkmlizer: ║                                                                     ║
chaiml-exp52-albert-sft-26828-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-exp52-albert-sft-26828-v2-mkmlizer: Downloaded to shared memory in 63.481s
chaiml-exp52-albert-sft-26828-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp61ylf_tg, device:0
chaiml-exp52-albert-sft-26828-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-exp52-albert-sft-26828-v2-mkmlizer: quantized model in 53.631s
chaiml-exp52-albert-sft-26828-v2-mkmlizer: Processed model ChaiML/exp52-albert-sft-allsamples-try1 in 117.112s
chaiml-exp52-albert-sft-26828-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-exp52-albert-sft-26828-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-exp52-albert-sft-26828-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-exp52-albert-sft-26828-v2
chaiml-exp52-albert-sft-26828-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-exp52-albert-sft-26828-v2/config.json
chaiml-exp52-albert-sft-26828-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-exp52-albert-sft-26828-v2/special_tokens_map.json
chaiml-exp52-albert-sft-26828-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-exp52-albert-sft-26828-v2/tokenizer_config.json
chaiml-exp52-albert-sft-26828-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-exp52-albert-sft-26828-v2/tokenizer.json
chaiml-exp52-albert-sft-26828-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-exp52-albert-sft-26828-v2/flywheel_model.1.safetensors
chaiml-exp52-albert-sft-26828-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-exp52-albert-sft-26828-v2/flywheel_model.0.safetensors
chaiml-exp52-albert-sft-26828-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 37.81it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:11, 30.19it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:10, 33.38it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:12, 28.90it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:10, 33.81it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:11, 30.57it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:08, 37.72it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:14, 22.39it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:12, 25.02it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:12, 26.39it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 28.66it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:11, 27.32it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:10, 30.48it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:10, 28.83it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 29.70it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:10, 26.79it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:13, 21.95it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 27.74it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:09, 28.44it/s]
Loading 0:  24%|██▍       | 87/363 [00:03<00:11, 25.07it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:09, 27.75it/s]
Loading 0:  26%|██▌       | 95/363 [00:03<00:09, 28.82it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:08, 29.72it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:09, 28.36it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:10, 24.63it/s]
Loading 0:  31%|███       | 111/363 [00:03<00:09, 27.25it/s]
Loading 0:  31%|███▏      | 114/363 [00:04<00:10, 24.02it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 28.74it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 26.83it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:08, 29.20it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:08, 26.67it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:07, 28.54it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:08, 25.42it/s]
Loading 0:  40%|████      | 147/363 [00:05<00:06, 32.54it/s]
Loading 0:  42%|████▏     | 151/363 [00:05<00:08, 24.06it/s]
Loading 0:  42%|████▏     | 154/363 [00:05<00:09, 22.34it/s]
Loading 0:  43%|████▎     | 157/363 [00:05<00:08, 23.11it/s]
Loading 0:  44%|████▍     | 160/363 [00:05<00:08, 23.24it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 26.54it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:08, 23.72it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 28.88it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 27.20it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:06, 28.03it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:06, 25.33it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 22.86it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 23.58it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 24.41it/s]
Loading 0:  55%|█████▌    | 200/363 [00:21<00:06, 24.41it/s]
Loading 0:  55%|█████▌    | 201/363 [00:21<03:02,  1.13s/it]
Loading 0:  56%|█████▌    | 203/363 [00:22<02:31,  1.06it/s]
Loading 0:  57%|█████▋    | 208/363 [00:22<01:30,  1.71it/s]
Loading 0:  58%|█████▊    | 211/363 [00:22<01:09,  2.18it/s]
Loading 0:  59%|█████▉    | 214/363 [00:22<00:51,  2.87it/s]
Loading 0:  60%|██████    | 218/363 [00:22<00:35,  4.11it/s]
Loading 0:  61%|██████    | 221/363 [00:22<00:26,  5.27it/s]
Loading 0:  62%|██████▏   | 224/363 [00:22<00:21,  6.32it/s]
Loading 0:  63%|██████▎   | 228/363 [00:23<00:15,  8.84it/s]
Loading 0:  64%|██████▎   | 231/363 [00:23<00:12, 10.23it/s]
Loading 0:  65%|██████▌   | 237/363 [00:23<00:08, 15.22it/s]
Loading 0:  66%|██████▌   | 240/363 [00:23<00:07, 15.92it/s]
Loading 0:  68%|██████▊   | 246/363 [00:23<00:05, 21.47it/s]
Loading 0:  69%|██████▉   | 250/363 [00:23<00:05, 22.54it/s]
Loading 0:  70%|███████   | 255/363 [00:23<00:04, 25.91it/s]
Loading 0:  71%|███████▏  | 259/363 [00:24<00:04, 25.12it/s]
Loading 0:  73%|███████▎  | 266/363 [00:24<00:03, 31.11it/s]
Loading 0:  74%|███████▍  | 270/363 [00:24<00:04, 20.87it/s]
Loading 0:  75%|███████▌  | 274/363 [00:24<00:03, 23.41it/s]
Loading 0:  76%|███████▋  | 277/363 [00:24<00:03, 23.38it/s]
Loading 0:  78%|███████▊  | 282/363 [00:25<00:03, 26.37it/s]
Loading 0:  79%|███████▉  | 286/363 [00:25<00:02, 26.20it/s]
Loading 0:  80%|████████  | 291/363 [00:25<00:02, 28.81it/s]
Loading 0:  81%|████████▏ | 295/363 [00:25<00:02, 27.16it/s]
Loading 0:  82%|████████▏ | 299/363 [00:25<00:02, 27.64it/s]
Loading 0:  84%|████████▎ | 304/363 [00:25<00:02, 24.87it/s]
Loading 0:  85%|████████▍ | 307/363 [00:26<00:02, 22.65it/s]
Loading 0:  85%|████████▌ | 310/363 [00:26<00:02, 23.52it/s]
Loading 0:  86%|████████▌ | 313/363 [00:26<00:02, 23.65it/s]
Loading 0:  88%|████████▊ | 318/363 [00:26<00:01, 26.40it/s]
Loading 0:  88%|████████▊ | 321/363 [00:26<00:01, 23.94it/s]
Loading 0:  90%|█████████ | 327/363 [00:26<00:01, 29.15it/s]
Loading 0:  91%|█████████ | 330/363 [00:26<00:01, 26.39it/s]
Loading 0:  92%|█████████▏| 335/363 [00:27<00:00, 29.16it/s]
Loading 0:  93%|█████████▎| 338/363 [00:27<00:00, 28.10it/s]
Loading 0:  94%|█████████▍| 341/363 [00:33<00:13,  1.69it/s]
Loading 0:  96%|█████████▌| 347/363 [00:34<00:05,  2.81it/s]
Loading 0:  96%|█████████▋| 350/363 [00:34<00:03,  3.51it/s]
Loading 0:  98%|█████████▊| 355/363 [00:34<00:01,  5.21it/s]
Loading 0:  99%|█████████▉| 359/363 [00:34<00:00,  6.76it/s]
                                                            
Job chaiml-exp52-albert-sft-26828-v2-mkmlizer completed after 145.03s with status: succeeded
Stopping job with name chaiml-exp52-albert-sft-26828-v2-mkmlizer
Pipeline stage MKMLizer completed in 145.60s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.41s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-exp52-albert-sft-26828-v2
Waiting for inference service chaiml-exp52-albert-sft-26828-v2 to be ready
Inference service chaiml-exp52-albert-sft-26828-v2 ready after 100.36458277702332s
Pipeline stage MKMLDeployer completed in 100.94s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.2671618461608887s
Received healthy response to inference request in 2.5188491344451904s
Received healthy response to inference request in 2.956899881362915s
Received healthy response to inference request in 2.4415993690490723s
Received healthy response to inference request in 2.458728551864624s
5 requests
0 failed requests
5th percentile: 2.4450252056121826
10th percentile: 2.448451042175293
20th percentile: 2.4553027153015137
30th percentile: 2.4707526683807375
40th percentile: 2.494800901412964
50th percentile: 2.5188491344451904
60th percentile: 2.69406943321228
70th percentile: 2.86928973197937
80th percentile: 3.0189522743225097
90th percentile: 3.1430570602416994
95th percentile: 3.205109453201294
99th percentile: 3.2547513675689697
mean time: 2.728647756576538
Pipeline stage StressChecker completed in 15.01s
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 0.80s
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-exp52-albert-sft_26828_v2 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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5448.25s
Shutdown handler de-registered
chaiml-exp52-albert-sft_26828_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-exp52-albert-sft_26828_v2 status is now torndown due to DeploymentManager action