chaiml-exp71-dpo-ftexp1_51186

developer_uid: NischayDnk

submission_id: chaiml-exp71-dpo-ftexp1_51186_v2

model_name: chaiml-exp71-dpo-ftexp1_51186_v2

model_group: ChaiML/exp71-dpo-ftexp13

status: inactive

timestamp: 2025-03-13T06:49:14+00:00

num_battles: 7508

num_wins: 3846

celo_rating: 1282.15

family_friendly_score: 0.5986

family_friendly_standard_error: 0.006932215230357464

submission_type: basic

model_repo: ChaiML/exp71-dpo-ftexp13sft-24B-ssdelnofiltered15K-s035

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.36373530801609283, 'latency_mean': 2.7491606664657593, 'latency_p50': 2.7389650344848633, 'latency_p90': 3.039290761947632}, {'batch_size': 2, 'throughput': 0.5747133402083789, 'latency_mean': 3.4728326976299284, 'latency_p50': 3.4628430604934692, 'latency_p90': 3.8546802282333372}, {'batch_size': 3, 'throughput': 0.7151215735267555, 'latency_mean': 4.174671862125397, 'latency_p50': 4.1810081005096436, 'latency_p90': 4.614227628707885}, {'batch_size': 4, 'throughput': 0.842218052126039, 'latency_mean': 4.729193676710128, 'latency_p50': 4.765737295150757, 'latency_p90': 5.225233578681946}, {'batch_size': 5, 'throughput': 0.9155342570854827, 'latency_mean': 5.421548657417297, 'latency_p50': 5.426190257072449, 'latency_p90': 6.051189231872558}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-exp71-dpo-ftexp1_51186_v2

is_internal_developer: True

language_model: ChaiML/exp71-dpo-ftexp13sft-24B-ssdelnofiltered15K-s035

model_size: 24B

ranking_group: single

throughput_3p7s: 0.63

us_pacific_date: 2025-03-12

win_ratio: 0.5122535961640916

generation_params: {'temperature': 0.55, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 40, 'presence_penalty': 0.45, 'frequency_penalty': 0.45, 'stopping_words': ['\n', '</s>', 'You:', '###'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '[INST]\n\n<|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]\n\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-exp71-dpo-ftexp1-51186-v2-mkmlizer
Waiting for job on chaiml-exp71-dpo-ftexp1-51186-v2-mkmlizer to finish
chaiml-exp71-dpo-ftexp1-51186-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-exp71-dpo-ftexp1-51186-v2-mkmlizer: ║     _____            __           __                                ║
chaiml-exp71-dpo-ftexp1-51186-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-exp71-dpo-ftexp1-51186-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-exp71-dpo-ftexp1-51186-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-exp71-dpo-ftexp1-51186-v2-mkmlizer: ║       /___/                                                         ║
chaiml-exp71-dpo-ftexp1-51186-v2-mkmlizer: ║                                                                     ║
chaiml-exp71-dpo-ftexp1-51186-v2-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-exp71-dpo-ftexp1-51186-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-exp71-dpo-ftexp1-51186-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-exp71-dpo-ftexp1-51186-v2-mkmlizer: ║                                                                     ║
chaiml-exp71-dpo-ftexp1-51186-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-exp71-dpo-ftexp1-51186-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-exp71-dpo-ftexp1-51186-v2-mkmlizer: ║                                                                     ║
chaiml-exp71-dpo-ftexp1-51186-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-exp71-dpo-ftexp1-51186-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-exp71-dpo-ftexp1-51186-v2-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
chaiml-exp71-dpo-ftexp1-51186-v2-mkmlizer: ║                                                                     ║
chaiml-exp71-dpo-ftexp1-51186-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-exp71-dpo-ftexp1-51186-v2-mkmlizer: Downloaded to shared memory in 69.184s
chaiml-exp71-dpo-ftexp1-51186-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpcvf5mg2n, device:0
chaiml-exp71-dpo-ftexp1-51186-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-exp71-dpo-ftexp1-51186-v2-mkmlizer: quantized model in 53.224s
chaiml-exp71-dpo-ftexp1-51186-v2-mkmlizer: Processed model ChaiML/exp71-dpo-ftexp13sft-24B-ssdelnofiltered15K-s035 in 122.408s
chaiml-exp71-dpo-ftexp1-51186-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-exp71-dpo-ftexp1-51186-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-exp71-dpo-ftexp1-51186-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-exp71-dpo-ftexp1-51186-v2
chaiml-exp71-dpo-ftexp1-51186-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-exp71-dpo-ftexp1-51186-v2/config.json
chaiml-exp71-dpo-ftexp1-51186-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-exp71-dpo-ftexp1-51186-v2/special_tokens_map.json
chaiml-exp71-dpo-ftexp1-51186-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-exp71-dpo-ftexp1-51186-v2/tokenizer_config.json
chaiml-exp71-dpo-ftexp1-51186-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-exp71-dpo-ftexp1-51186-v2/flywheel_model.1.safetensors
chaiml-exp71-dpo-ftexp1-51186-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-exp71-dpo-ftexp1-51186-v2/flywheel_model.0.safetensors
chaiml-exp71-dpo-ftexp1-51186-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:17, 20.80it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:09, 37.35it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:10, 32.67it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:10, 32.66it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:11, 30.32it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:08, 37.26it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:14, 22.57it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:12, 24.89it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:12, 26.23it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 28.53it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:11, 27.92it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:09, 30.68it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:10, 28.30it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 29.35it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:10, 26.74it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:13, 22.11it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 27.79it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:09, 28.77it/s]
Loading 0:  24%|██▍       | 87/363 [00:03<00:11, 23.08it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:10, 25.64it/s]
Loading 0:  26%|██▌       | 94/363 [00:03<00:11, 23.89it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:09, 26.55it/s]
Loading 0:  28%|██▊       | 102/363 [00:03<00:10, 24.01it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:11, 22.76it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:09, 25.95it/s]
Loading 0:  31%|███▏      | 114/363 [00:04<00:10, 23.49it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 28.61it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 26.98it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 29.61it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:08, 28.31it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 30.42it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:07, 28.90it/s]
Loading 0:  41%|████      | 148/363 [00:05<00:06, 35.35it/s]
Loading 0:  42%|████▏     | 152/363 [00:05<00:08, 24.34it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:08, 23.71it/s]
Loading 0:  44%|████▍     | 159/363 [00:05<00:08, 22.70it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 27.45it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:07, 26.51it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 29.42it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 27.76it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:06, 28.27it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:06, 25.71it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 23.68it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 24.00it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 24.21it/s]
Loading 0:  55%|█████▌    | 200/363 [00:21<00:06, 24.21it/s]
Loading 0:  55%|█████▌    | 201/363 [00:21<03:00,  1.12s/it]
Loading 0:  56%|█████▌    | 203/363 [00:21<02:29,  1.07it/s]
Loading 0:  57%|█████▋    | 208/363 [00:22<01:29,  1.73it/s]
Loading 0:  58%|█████▊    | 211/363 [00:22<01:09,  2.19it/s]
Loading 0:  59%|█████▉    | 214/363 [00:22<00:51,  2.89it/s]
Loading 0:  60%|██████    | 218/363 [00:22<00:34,  4.15it/s]
Loading 0:  61%|██████    | 221/363 [00:22<00:26,  5.31it/s]
Loading 0:  62%|██████▏   | 224/363 [00:22<00:21,  6.34it/s]
Loading 0:  63%|██████▎   | 228/363 [00:22<00:15,  8.90it/s]
Loading 0:  64%|██████▎   | 231/363 [00:23<00:12, 10.31it/s]
Loading 0:  65%|██████▌   | 237/363 [00:23<00:08, 15.39it/s]
Loading 0:  66%|██████▋   | 241/363 [00:23<00:06, 17.52it/s]
Loading 0:  68%|██████▊   | 246/363 [00:23<00:05, 21.41it/s]
Loading 0:  69%|██████▉   | 250/363 [00:23<00:05, 22.33it/s]
Loading 0:  70%|███████   | 255/363 [00:23<00:04, 25.96it/s]
Loading 0:  71%|███████▏  | 259/363 [00:24<00:04, 23.97it/s]
Loading 0:  72%|███████▏  | 262/363 [00:24<00:04, 24.74it/s]
Loading 0:  74%|███████▎  | 267/363 [00:24<00:04, 21.75it/s]
Loading 0:  74%|███████▍  | 270/363 [00:24<00:04, 19.14it/s]
Loading 0:  75%|███████▌  | 274/363 [00:24<00:04, 22.04it/s]
Loading 0:  76%|███████▋  | 277/363 [00:24<00:03, 22.41it/s]
Loading 0:  78%|███████▊  | 282/363 [00:25<00:03, 26.20it/s]
Loading 0:  79%|███████▊  | 285/363 [00:25<00:03, 24.11it/s]
Loading 0:  80%|████████  | 291/363 [00:25<00:02, 28.51it/s]
Loading 0:  81%|████████  | 294/363 [00:25<00:02, 25.61it/s]
Loading 0:  82%|████████▏ | 299/363 [00:25<00:02, 28.36it/s]
Loading 0:  84%|████████▎ | 304/363 [00:25<00:02, 25.97it/s]
Loading 0:  85%|████████▍ | 307/363 [00:26<00:02, 23.70it/s]
Loading 0:  85%|████████▌ | 310/363 [00:26<00:02, 24.26it/s]
Loading 0:  86%|████████▌ | 313/363 [00:26<00:02, 24.85it/s]
Loading 0:  88%|████████▊ | 318/363 [00:26<00:01, 28.60it/s]
Loading 0:  88%|████████▊ | 321/363 [00:26<00:01, 26.32it/s]
Loading 0:  90%|█████████ | 327/363 [00:26<00:01, 31.22it/s]
Loading 0:  91%|█████████ | 331/363 [00:26<00:01, 29.67it/s]
Loading 0:  92%|█████████▏| 335/363 [00:26<00:00, 29.99it/s]
Loading 0:  93%|█████████▎| 339/363 [00:27<00:00, 30.59it/s]
Loading 0:  94%|█████████▍| 343/363 [00:33<00:10,  1.91it/s]
Loading 0:  96%|█████████▌| 348/363 [00:34<00:05,  2.79it/s]
Loading 0:  98%|█████████▊| 355/363 [00:34<00:01,  4.57it/s]
Loading 0:  99%|█████████▉| 359/363 [00:34<00:00,  5.73it/s]
                                                            
Job chaiml-exp71-dpo-ftexp1-51186-v2-mkmlizer completed after 155.42s with status: succeeded
Stopping job with name chaiml-exp71-dpo-ftexp1-51186-v2-mkmlizer
Pipeline stage MKMLizer completed in 155.91s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-exp71-dpo-ftexp1-51186-v2
Waiting for inference service chaiml-exp71-dpo-ftexp1-51186-v2 to be ready
Inference service chaiml-exp71-dpo-ftexp1-51186-v2 ready after 100.35992741584778s
Pipeline stage MKMLDeployer completed in 100.91s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.9937386512756348s
Received healthy response to inference request in 1.8108601570129395s
Received healthy response to inference request in 2.0800893306732178s
Received healthy response to inference request in 2.313887596130371s
Received healthy response to inference request in 2.4373013973236084s
5 requests
0 failed requests
5th percentile: 1.864705991744995
10th percentile: 1.9185518264770507
20th percentile: 2.026243495941162
30th percentile: 2.1268489837646483
40th percentile: 2.2203682899475097
50th percentile: 2.313887596130371
60th percentile: 2.363253116607666
70th percentile: 2.412618637084961
80th percentile: 2.5485888481140138
90th percentile: 2.771163749694824
95th percentile: 2.8824512004852294
99th percentile: 2.971481161117554
mean time: 2.327175426483154
Pipeline stage StressChecker completed in 13.37s
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 0.67s
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 0.76s
Shutdown handler de-registered
chaiml-exp71-dpo-ftexp1_51186_v2 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 0.11s
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-exp71-dpo-ftexp1-51186-v2-profiler
Waiting for inference service chaiml-exp71-dpo-ftexp1-51186-v2-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
Pipeline stage OfflineFamilyFriendlyScorer completed in 2914.54s
Shutdown handler de-registered
chaiml-exp71-dpo-ftexp1_51186_v2 status is now inactive due to auto deactivation removed underperforming models