chaiml-exp89-dpo-megasf_72574

developer_uid: NischayDnk

submission_id: chaiml-exp89-dpo-megasf_72574_v1

model_name: chaiml-exp89-dpo-megasf_72574_v1

model_group: ChaiML/exp89-dpo-megasft

status: torndown

timestamp: 2025-03-16T20:40:04+00:00

num_battles: 7127

num_wins: 3789

celo_rating: 1301.2

family_friendly_score: 0.42200000000000004

family_friendly_standard_error: 0.006984497118619207

submission_type: basic

model_repo: ChaiML/exp89-dpo-megasfte2-24B-ssdelfilteredv10v11-simpo

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': 0.37184621552387875, 'latency_mean': 2.689219778776169, 'latency_p50': 2.6787742376327515, 'latency_p90': 2.994445466995239}, {'batch_size': 2, 'throughput': 0.5689549162273014, 'latency_mean': 3.5103405237197878, 'latency_p50': 3.518949508666992, 'latency_p90': 3.805882787704468}, {'batch_size': 3, 'throughput': 0.7317483553110863, 'latency_mean': 4.075588780641556, 'latency_p50': 4.067051649093628, 'latency_p90': 4.493559956550598}, {'batch_size': 4, 'throughput': 0.8477258061497791, 'latency_mean': 4.700405822992325, 'latency_p50': 4.679707050323486, 'latency_p90': 5.297829937934876}, {'batch_size': 5, 'throughput': 0.9398316404911118, 'latency_mean': 5.29621546626091, 'latency_p50': 5.240585923194885, 'latency_p90': 6.024877095222473}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-exp89-dpo-megasf_72574_v1

is_internal_developer: False

language_model: ChaiML/exp89-dpo-megasfte2-24B-ssdelfilteredv10v11-simpo

model_size: 24B

ranking_group: single

throughput_3p7s: 0.63

us_pacific_date: 2025-03-16

win_ratio: 0.5316402413357654

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}:[/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-exp89-dpo-megasf-72574-v1-mkmlizer
Waiting for job on chaiml-exp89-dpo-megasf-72574-v1-mkmlizer to finish
chaiml-exp89-dpo-megasf-72574-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-exp89-dpo-megasf-72574-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-exp89-dpo-megasf-72574-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-exp89-dpo-megasf-72574-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-exp89-dpo-megasf-72574-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-exp89-dpo-megasf-72574-v1-mkmlizer: ║       /___/                                                         ║
chaiml-exp89-dpo-megasf-72574-v1-mkmlizer: ║                                                                     ║
chaiml-exp89-dpo-megasf-72574-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-exp89-dpo-megasf-72574-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-exp89-dpo-megasf-72574-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-exp89-dpo-megasf-72574-v1-mkmlizer: ║                                                                     ║
chaiml-exp89-dpo-megasf-72574-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-exp89-dpo-megasf-72574-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-exp89-dpo-megasf-72574-v1-mkmlizer: ║                                                                     ║
chaiml-exp89-dpo-megasf-72574-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-exp89-dpo-megasf-72574-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-exp89-dpo-megasf-72574-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
chaiml-exp89-dpo-megasf-72574-v1-mkmlizer: ║                                                                     ║
chaiml-exp89-dpo-megasf-72574-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission jellywibble-enzo-mafia-enemy_v14: HTTPConnectionPool(host='jellywibble-enzo-mafia-enemy-v14-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-exp89-dpo-megasf-72574-v1-mkmlizer: quantized model in 53.499s
chaiml-exp89-dpo-megasf-72574-v1-mkmlizer: Processed model ChaiML/exp89-dpo-megasfte2-24B-ssdelfilteredv10v11-simpo in 136.394s
chaiml-exp89-dpo-megasf-72574-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-exp89-dpo-megasf-72574-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-exp89-dpo-megasf-72574-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-exp89-dpo-megasf-72574-v1
chaiml-exp89-dpo-megasf-72574-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-exp89-dpo-megasf-72574-v1/config.json
chaiml-exp89-dpo-megasf-72574-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-exp89-dpo-megasf-72574-v1/special_tokens_map.json
chaiml-exp89-dpo-megasf-72574-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-exp89-dpo-megasf-72574-v1/tokenizer_config.json
chaiml-exp89-dpo-megasf-72574-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-exp89-dpo-megasf-72574-v1/tokenizer.json
chaiml-exp89-dpo-megasf-72574-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-exp89-dpo-megasf-72574-v1/flywheel_model.1.safetensors
chaiml-exp89-dpo-megasf-72574-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-exp89-dpo-megasf-72574-v1/flywheel_model.0.safetensors
chaiml-exp89-dpo-megasf-72574-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 36.71it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:11, 29.68it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:10, 32.79it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:11, 29.70it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:09, 34.42it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:10, 30.94it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:08, 38.04it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:15, 21.32it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:13, 23.76it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:12, 24.95it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 27.35it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:11, 26.16it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:10, 28.72it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:10, 27.58it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 28.65it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:11, 25.02it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:13, 20.76it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:11, 25.66it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:11, 24.35it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 25.42it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:11, 24.82it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:13, 20.12it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:09, 27.37it/s]
Loading 0:  28%|██▊       | 102/363 [00:03<00:10, 24.64it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:11, 22.53it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:09, 25.61it/s]
Loading 0:  31%|███▏      | 114/363 [00:04<00:10, 23.07it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 28.17it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 27.01it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:08, 29.13it/s]
Loading 0:  37%|███▋      | 133/363 [00:05<00:08, 27.08it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 29.95it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:07, 28.77it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:06, 34.35it/s]
Loading 0:  42%|████▏     | 153/363 [00:05<00:09, 21.88it/s]
Loading 0:  43%|████▎     | 157/363 [00:05<00:08, 24.14it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:08, 24.89it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 27.72it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:07, 25.86it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 28.90it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 27.98it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:06, 28.43it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:06, 25.92it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 23.90it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:06, 24.53it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 24.67it/s]
Loading 0:  55%|█████▌    | 200/363 [00:21<00:06, 24.67it/s]
Loading 0:  55%|█████▌    | 201/363 [00:21<03:01,  1.12s/it]
Loading 0:  56%|█████▌    | 203/363 [00:22<02:30,  1.07it/s]
Loading 0:  57%|█████▋    | 208/363 [00:22<01:30,  1.72it/s]
Loading 0:  58%|█████▊    | 211/363 [00:22<01:09,  2.19it/s]
Loading 0:  59%|█████▉    | 214/363 [00:22<00:51,  2.88it/s]
Loading 0:  60%|██████    | 218/363 [00:22<00:35,  4.13it/s]
Loading 0:  61%|██████    | 221/363 [00:22<00:26,  5.27it/s]
Loading 0:  62%|██████▏   | 224/363 [00:23<00:21,  6.35it/s]
Loading 0:  63%|██████▎   | 228/363 [00:23<00:15,  8.88it/s]
Loading 0:  64%|██████▎   | 231/363 [00:23<00:12, 10.29it/s]
Loading 0:  65%|██████▌   | 237/363 [00:23<00:08, 15.38it/s]
Loading 0:  66%|██████▌   | 240/363 [00:23<00:07, 15.97it/s]
Loading 0:  68%|██████▊   | 246/363 [00:23<00:05, 21.55it/s]
Loading 0:  69%|██████▉   | 250/363 [00:23<00:05, 21.86it/s]
Loading 0:  70%|███████   | 255/363 [00:24<00:04, 24.22it/s]
Loading 0:  71%|███████   | 258/363 [00:24<00:04, 22.29it/s]
Loading 0:  73%|███████▎  | 264/363 [00:24<00:03, 28.83it/s]
Loading 0:  74%|███████▍  | 268/363 [00:24<00:04, 22.50it/s]
Loading 0:  75%|███████▍  | 271/363 [00:24<00:04, 21.41it/s]
Loading 0:  75%|███████▌  | 274/363 [00:24<00:03, 22.61it/s]
Loading 0:  76%|███████▋  | 277/363 [00:25<00:03, 23.03it/s]
Loading 0:  78%|███████▊  | 282/363 [00:25<00:03, 26.48it/s]
Loading 0:  79%|███████▊  | 285/363 [00:25<00:03, 24.11it/s]
Loading 0:  80%|████████  | 291/363 [00:25<00:02, 29.52it/s]
Loading 0:  81%|████████▏ | 295/363 [00:25<00:02, 28.11it/s]
Loading 0:  82%|████████▏ | 299/363 [00:25<00:02, 29.02it/s]
Loading 0:  84%|████████▎ | 304/363 [00:25<00:02, 27.35it/s]
Loading 0:  85%|████████▍ | 307/363 [00:26<00:02, 24.42it/s]
Loading 0:  85%|████████▌ | 310/363 [00:26<00:02, 25.03it/s]
Loading 0:  86%|████████▌ | 313/363 [00:26<00:01, 25.91it/s]
Loading 0:  88%|████████▊ | 318/363 [00:26<00:01, 28.89it/s]
Loading 0:  88%|████████▊ | 321/363 [00:26<00:01, 26.11it/s]
Loading 0:  90%|█████████ | 327/363 [00:26<00:01, 31.50it/s]
Loading 0:  91%|█████████ | 331/363 [00:26<00:01, 29.86it/s]
Loading 0:  92%|█████████▏| 335/363 [00:27<00:00, 29.39it/s]
Loading 0:  93%|█████████▎| 338/363 [00:27<00:00, 28.21it/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,  5.17it/s]
Loading 0:  99%|█████████▉| 359/363 [00:34<00:00,  6.67it/s]
                                                            
Job chaiml-exp89-dpo-megasf-72574-v1-mkmlizer completed after 166.46s with status: succeeded
Stopping job with name chaiml-exp89-dpo-megasf-72574-v1-mkmlizer
Pipeline stage MKMLizer completed in 166.92s
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-exp89-dpo-megasf-72574-v1
Waiting for inference service chaiml-exp89-dpo-megasf-72574-v1 to be ready
Inference service chaiml-exp89-dpo-megasf-72574-v1 ready after 90.61699104309082s
Pipeline stage MKMLDeployer completed in 91.11s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.6113617420196533s
Received healthy response to inference request in 2.578949451446533s
Received healthy response to inference request in 2.6303110122680664s
Received healthy response to inference request in 2.4684677124023438s
Received healthy response to inference request in 2.506969690322876s
5 requests
0 failed requests
5th percentile: 2.4761681079864504
10th percentile: 2.4838685035705566
20th percentile: 2.4992692947387694
30th percentile: 2.5213656425476074
40th percentile: 2.5501575469970703
50th percentile: 2.578949451446533
60th percentile: 2.5994940757751466
70th percentile: 2.62003870010376
80th percentile: 2.826521158218384
90th percentile: 3.2189414501190186
95th percentile: 3.415151596069336
99th percentile: 3.57211971282959
mean time: 2.7592119216918944
Pipeline stage StressChecker completed in 15.17s
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 0.93s
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 0.86s
Shutdown handler de-registered
chaiml-exp89-dpo-megasf_72574_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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-exp89-dpo-megasf-72574-v1-profiler
Waiting for inference service chaiml-exp89-dpo-megasf-72574-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 5540.85s
Shutdown handler de-registered
chaiml-exp89-dpo-megasf_72574_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-exp89-dpo-megasf_72574_v1 status is now torndown due to DeploymentManager action