developer_uid: NischayDnk
submission_id: chaiml-exp76-dpo-megasf_25631_v1
model_name: chaiml-exp76-dpo-megasf_25631_v1
model_group: ChaiML/exp76-dpo-megasft
status: torndown
timestamp: 2025-03-13T12:53:56+00:00
num_battles: 7370
num_wins: 1380
celo_rating: 1024.5
family_friendly_score: 0.0
family_friendly_standard_error: 0.0
submission_type: basic
model_repo: ChaiML/exp76-dpo-megasfte2-24B-ssdelfiltered1
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': 0.37296431602285546, 'latency_mean': 2.6811247193813323, 'latency_p50': 2.6790246963500977, 'latency_p90': 2.9946091413497924}, {'batch_size': 2, 'throughput': 0.5830534576653414, 'latency_mean': 3.4290759098529815, 'latency_p50': 3.4273020029067993, 'latency_p90': 3.754616355895996}, {'batch_size': 3, 'throughput': 0.743095126031616, 'latency_mean': 4.032360049486161, 'latency_p50': 4.023534059524536, 'latency_p90': 4.464345026016235}, {'batch_size': 4, 'throughput': 0.8604115557705548, 'latency_mean': 4.635282403230667, 'latency_p50': 4.604756236076355, 'latency_p90': 5.2092702150344845}, {'batch_size': 5, 'throughput': 0.9578783092646607, 'latency_mean': 5.207399109601974, 'latency_p50': 5.181097149848938, 'latency_p90': 5.88243601322174}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: chaiml-exp76-dpo-megasf_25631_v1
is_internal_developer: False
language_model: ChaiML/exp76-dpo-megasfte2-24B-ssdelfiltered1
model_size: 24B
ranking_group: single
throughput_3p7s: 0.66
us_pacific_date: 2025-03-13
win_ratio: 0.18724559023066487
generation_params: {'temperature': 0.4, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.45, 'frequency_penalty': 0.45, 'stopping_words': ['You:', '</s>', '###', '\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-exp76-dpo-megasf-25631-v1-mkmlizer
Waiting for job on chaiml-exp76-dpo-megasf-25631-v1-mkmlizer to finish
chaiml-exp76-dpo-megasf-25631-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-exp76-dpo-megasf-25631-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-exp76-dpo-megasf-25631-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-exp76-dpo-megasf-25631-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-exp76-dpo-megasf-25631-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-exp76-dpo-megasf-25631-v1-mkmlizer: ║       /___/                                                         ║
chaiml-exp76-dpo-megasf-25631-v1-mkmlizer: ║                                                                     ║
chaiml-exp76-dpo-megasf-25631-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-exp76-dpo-megasf-25631-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-exp76-dpo-megasf-25631-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-exp76-dpo-megasf-25631-v1-mkmlizer: ║                                                                     ║
chaiml-exp76-dpo-megasf-25631-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-exp76-dpo-megasf-25631-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-exp76-dpo-megasf-25631-v1-mkmlizer: ║                                                                     ║
chaiml-exp76-dpo-megasf-25631-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-exp76-dpo-megasf-25631-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-exp76-dpo-megasf-25631-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
chaiml-exp76-dpo-megasf-25631-v1-mkmlizer: ║                                                                     ║
chaiml-exp76-dpo-megasf-25631-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-exp76-dpo-megasf-25631-v1-mkmlizer: Downloaded to shared memory in 78.836s
chaiml-exp76-dpo-megasf-25631-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpe1w1nrxl, device:0
chaiml-exp76-dpo-megasf-25631-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-exp76-dpo-megasf-25631-v1-mkmlizer: quantized model in 56.824s
chaiml-exp76-dpo-megasf-25631-v1-mkmlizer: Processed model ChaiML/exp76-dpo-megasfte2-24B-ssdelfiltered1 in 135.661s
chaiml-exp76-dpo-megasf-25631-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-exp76-dpo-megasf-25631-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-exp76-dpo-megasf-25631-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-exp76-dpo-megasf-25631-v1
chaiml-exp76-dpo-megasf-25631-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-exp76-dpo-megasf-25631-v1/special_tokens_map.json
chaiml-exp76-dpo-megasf-25631-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-exp76-dpo-megasf-25631-v1/config.json
chaiml-exp76-dpo-megasf-25631-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-exp76-dpo-megasf-25631-v1/tokenizer_config.json
chaiml-exp76-dpo-megasf-25631-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-exp76-dpo-megasf-25631-v1/tokenizer.json
chaiml-exp76-dpo-megasf-25631-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-exp76-dpo-megasf-25631-v1/flywheel_model.1.safetensors
chaiml-exp76-dpo-megasf-25631-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-exp76-dpo-megasf-25631-v1/flywheel_model.0.safetensors
chaiml-exp76-dpo-megasf-25631-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 38.08it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:11, 29.70it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:11, 31.90it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:12, 27.59it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:11, 30.23it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:12, 26.10it/s]
Loading 0:   8%|▊         | 30/363 [00:00<00:10, 31.14it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:15, 21.11it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:16, 19.77it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:15, 21.03it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:15, 20.83it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:14, 22.40it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:13, 23.80it/s]
Loading 0:  14%|█▍        | 52/363 [00:02<00:13, 23.40it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:12, 24.56it/s]
Loading 0:  16%|█▌        | 58/363 [00:02<00:11, 25.65it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:12, 24.35it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:11, 25.52it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:10, 27.97it/s]
Loading 0:  20%|█▉        | 72/363 [00:03<00:14, 19.67it/s]
Loading 0:  21%|██        | 75/363 [00:03<00:14, 19.99it/s]
Loading 0:  21%|██▏       | 78/363 [00:03<00:13, 21.25it/s]
Loading 0:  22%|██▏       | 81/363 [00:03<00:14, 18.92it/s]
Loading 0:  23%|██▎       | 84/363 [00:03<00:13, 20.85it/s]
Loading 0:  24%|██▍       | 87/363 [00:03<00:14, 18.89it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:12, 22.22it/s]
Loading 0:  26%|██▌       | 94/363 [00:04<00:12, 21.72it/s]
Loading 0:  27%|██▋       | 97/363 [00:04<00:11, 22.81it/s]
Loading 0:  28%|██▊       | 100/363 [00:04<00:11, 23.48it/s]
Loading 0:  28%|██▊       | 103/363 [00:04<00:11, 22.30it/s]
Loading 0:  29%|██▉       | 106/363 [00:04<00:10, 23.43it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:14, 17.94it/s]
Loading 0:  31%|███       | 112/363 [00:04<00:12, 19.94it/s]
Loading 0:  32%|███▏      | 115/363 [00:05<00:12, 20.34it/s]
Loading 0:  33%|███▎      | 118/363 [00:05<00:11, 21.82it/s]
Loading 0:  33%|███▎      | 121/363 [00:05<00:10, 22.92it/s]
Loading 0:  34%|███▍      | 124/363 [00:05<00:10, 22.84it/s]
Loading 0:  36%|███▌      | 129/363 [00:05<00:08, 26.95it/s]
Loading 0:  36%|███▋      | 132/363 [00:05<00:09, 23.88it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 28.85it/s]
Loading 0:  39%|███▉      | 141/363 [00:06<00:08, 25.76it/s]
Loading 0:  40%|████      | 147/363 [00:06<00:06, 33.18it/s]
Loading 0:  42%|████▏     | 151/363 [00:06<00:08, 24.07it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:09, 21.81it/s]
Loading 0:  43%|████▎     | 157/363 [00:06<00:09, 22.79it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:08, 22.73it/s]
Loading 0:  45%|████▍     | 163/363 [00:06<00:08, 23.79it/s]
Loading 0:  46%|████▌     | 166/363 [00:07<00:08, 24.49it/s]
Loading 0:  47%|████▋     | 169/363 [00:07<00:08, 23.06it/s]
Loading 0:  47%|████▋     | 172/363 [00:07<00:07, 24.32it/s]
Loading 0:  48%|████▊     | 175/363 [00:07<00:07, 24.50it/s]
Loading 0:  49%|████▉     | 178/363 [00:07<00:07, 23.21it/s]
Loading 0:  50%|████▉     | 181/363 [00:07<00:07, 24.29it/s]
Loading 0:  51%|█████     | 186/363 [00:07<00:06, 25.78it/s]
Loading 0:  52%|█████▏    | 189/363 [00:08<00:10, 16.03it/s]
Loading 0:  53%|█████▎    | 193/363 [00:08<00:08, 19.26it/s]
Loading 0:  54%|█████▍    | 196/363 [00:08<00:08, 19.73it/s]
Loading 0:  55%|█████▍    | 199/363 [00:08<00:07, 21.13it/s]
Loading 0:  55%|█████▌    | 200/363 [00:23<00:07, 21.13it/s]
Loading 0:  55%|█████▌    | 201/363 [00:23<04:18,  1.59s/it]
Loading 0:  56%|█████▌    | 203/363 [00:23<03:21,  1.26s/it]
Loading 0:  57%|█████▋    | 208/363 [00:24<01:49,  1.42it/s]
Loading 0:  58%|█████▊    | 211/363 [00:24<01:20,  1.88it/s]
Loading 0:  59%|█████▉    | 214/363 [00:24<00:58,  2.53it/s]
Loading 0:  60%|█████▉    | 217/363 [00:24<00:42,  3.43it/s]
Loading 0:  61%|██████    | 220/363 [00:24<00:32,  4.40it/s]
Loading 0:  61%|██████▏   | 223/363 [00:24<00:24,  5.83it/s]
Loading 0:  62%|██████▏   | 226/363 [00:25<00:20,  6.81it/s]
Loading 0:  63%|██████▎   | 229/363 [00:25<00:15,  8.78it/s]
Loading 0:  64%|██████▍   | 232/363 [00:25<00:12, 10.69it/s]
Loading 0:  65%|██████▍   | 235/363 [00:25<00:09, 13.21it/s]
Loading 0:  66%|██████▌   | 238/363 [00:25<00:08, 15.49it/s]
Loading 0:  66%|██████▋   | 241/363 [00:25<00:07, 16.68it/s]
Loading 0:  67%|██████▋   | 244/363 [00:25<00:06, 18.56it/s]
Loading 0:  68%|██████▊   | 247/363 [00:26<00:05, 20.03it/s]
Loading 0:  69%|██████▉   | 250/363 [00:26<00:05, 19.88it/s]
Loading 0:  70%|██████▉   | 253/363 [00:26<00:04, 22.08it/s]
Loading 0:  71%|███████   | 256/363 [00:26<00:04, 22.89it/s]
Loading 0:  71%|███████▏  | 259/363 [00:26<00:04, 23.30it/s]
Loading 0:  73%|███████▎  | 266/363 [00:26<00:03, 31.29it/s]
Loading 0:  74%|███████▍  | 270/363 [00:27<00:04, 19.84it/s]
Loading 0:  75%|███████▌  | 274/363 [00:27<00:03, 22.75it/s]
Loading 0:  76%|███████▋  | 277/363 [00:27<00:03, 23.04it/s]
Loading 0:  78%|███████▊  | 282/363 [00:27<00:03, 26.62it/s]
Loading 0:  79%|███████▊  | 285/363 [00:27<00:03, 24.60it/s]
Loading 0:  80%|████████  | 291/363 [00:27<00:02, 29.42it/s]
Loading 0:  81%|████████▏ | 295/363 [00:27<00:02, 27.84it/s]
Loading 0:  82%|████████▏ | 299/363 [00:28<00:02, 28.42it/s]
Loading 0:  84%|████████▎ | 304/363 [00:28<00:02, 24.59it/s]
Loading 0:  85%|████████▍ | 307/363 [00:28<00:02, 21.76it/s]
Loading 0:  85%|████████▌ | 310/363 [00:28<00:02, 22.72it/s]
Loading 0:  86%|████████▌ | 313/363 [00:28<00:02, 22.27it/s]
Loading 0:  87%|████████▋ | 316/363 [00:28<00:02, 23.45it/s]
Loading 0:  88%|████████▊ | 319/363 [00:28<00:01, 24.12it/s]
Loading 0:  89%|████████▊ | 322/363 [00:29<00:01, 23.24it/s]
Loading 0:  90%|████████▉ | 325/363 [00:29<00:01, 24.27it/s]
Loading 0:  90%|█████████ | 328/363 [00:29<00:01, 24.57it/s]
Loading 0:  91%|█████████ | 331/363 [00:29<00:01, 23.79it/s]
Loading 0:  92%|█████████▏| 335/363 [00:29<00:01, 24.17it/s]
Loading 0:  93%|█████████▎| 338/363 [00:29<00:01, 22.48it/s]
Loading 0:  94%|█████████▍| 341/363 [00:36<00:15,  1.45it/s]
Loading 0:  95%|█████████▌| 346/363 [00:36<00:07,  2.39it/s]
Loading 0:  96%|█████████▌| 349/363 [00:37<00:04,  3.07it/s]
Loading 0:  98%|█████████▊| 355/363 [00:37<00:01,  5.10it/s]
Loading 0:  99%|█████████▉| 359/363 [00:37<00:00,  6.61it/s]
                                                            

Job chaiml-exp76-dpo-megasf-25631-v1-mkmlizer completed after 165.32s with status: succeeded
Stopping job with name chaiml-exp76-dpo-megasf-25631-v1-mkmlizer
Pipeline stage MKMLizer completed in 165.82s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-exp76-dpo-megasf-25631-v1
Waiting for inference service chaiml-exp76-dpo-megasf-25631-v1 to be ready
Inference service chaiml-exp76-dpo-megasf-25631-v1 ready after 100.39118933677673s
Pipeline stage MKMLDeployer completed in 100.91s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8551208972930908s
Received healthy response to inference request in 0.35762619972229004s
Received healthy response to inference request in 0.5561280250549316s
Received healthy response to inference request in 0.226485013961792s
Received healthy response to inference request in 0.2714204788208008s
5 requests
0 failed requests
5th percentile: 0.23547210693359374
10th percentile: 0.2444591999053955
20th percentile: 0.262433385848999
30th percentile: 0.28866162300109866
40th percentile: 0.32314391136169435
50th percentile: 0.35762619972229004
60th percentile: 0.43702692985534664
70th percentile: 0.5164276599884032
80th percentile: 0.8159265995025637
90th percentile: 1.3355237483978273
95th percentile: 1.5953223228454587
99th percentile: 1.8031611824035645
mean time: 0.6533561229705811
Pipeline stage StressChecker completed in 4.48s
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 0.72s
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 0.64s
Shutdown handler de-registered
chaiml-exp76-dpo-megasf_25631_v1 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
%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
%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
chaiml-exp76-dpo-megasf_25631_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-exp76-dpo-megasf_25631_v1 status is now torndown due to DeploymentManager action