chaiml-exp349-dpo-s3-sl_28707

developer_uid: NischayDnk

submission_id: chaiml-exp349-dpo-s3-sl_28707_v1

model_name: chaiml-exp349-dpo-s3-sl_28707_v1

model_group: ChaiML/exp349-dpo-s3-sle

status: torndown

timestamp: 2025-04-17T02:19:50+00:00

num_battles: 8204

num_wins: 4701

celo_rating: 1346.49

family_friendly_score: 0.46640000000000004

family_friendly_standard_error: 0.007055083840749166

submission_type: basic

model_repo: ChaiML/exp349-dpo-s3-slerpv2-data31full1350

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': 0.36726754003253304, 'latency_mean': 2.7227316021919252, 'latency_p50': 2.7278467416763306, 'latency_p90': 3.00310640335083}, {'batch_size': 2, 'throughput': 0.5767714928614857, 'latency_mean': 3.4652692174911497, 'latency_p50': 3.4866284132003784, 'latency_p90': 3.8079480648040773}, {'batch_size': 3, 'throughput': 0.7262168139778169, 'latency_mean': 4.120699056386948, 'latency_p50': 4.122886776924133, 'latency_p90': 4.54904580116272}, {'batch_size': 4, 'throughput': 0.845248243774657, 'latency_mean': 4.710202226638794, 'latency_p50': 4.724969506263733, 'latency_p90': 5.304553914070129}, {'batch_size': 5, 'throughput': 0.9362225977850541, 'latency_mean': 5.3045339930057525, 'latency_p50': 5.283698081970215, 'latency_p90': 5.895477962493897}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-exp349-dpo-s3-sl_28707_v1

is_internal_developer: False

language_model: ChaiML/exp349-dpo-s3-slerpv2-data31full1350

model_size: 24B

ranking_group: single

throughput_3p7s: 0.64

us_pacific_date: 2025-04-16

win_ratio: 0.5730131643100926

generation_params: {'temperature': 0.4, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 40, 'presence_penalty': 0.45, 'frequency_penalty': 0.45, 'stopping_words': ['<|im_end|>', '<|im_start|>', '\n'], '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-exp349-dpo-s3-sl-28707-v1-mkmlizer
Waiting for job on chaiml-exp349-dpo-s3-sl-28707-v1-mkmlizer to finish
chaiml-exp349-dpo-s3-sl-28707-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-exp349-dpo-s3-sl-28707-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-exp349-dpo-s3-sl-28707-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-exp349-dpo-s3-sl-28707-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-exp349-dpo-s3-sl-28707-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-exp349-dpo-s3-sl-28707-v1-mkmlizer: ║       /___/                                                         ║
chaiml-exp349-dpo-s3-sl-28707-v1-mkmlizer: ║                                                                     ║
chaiml-exp349-dpo-s3-sl-28707-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-exp349-dpo-s3-sl-28707-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-exp349-dpo-s3-sl-28707-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-exp349-dpo-s3-sl-28707-v1-mkmlizer: ║                                                                     ║
chaiml-exp349-dpo-s3-sl-28707-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-exp349-dpo-s3-sl-28707-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-exp349-dpo-s3-sl-28707-v1-mkmlizer: ║                                                                     ║
chaiml-exp349-dpo-s3-sl-28707-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-exp349-dpo-s3-sl-28707-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-exp349-dpo-s3-sl-28707-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-exp349-dpo-s3-sl-28707-v1-mkmlizer: ║                                                                     ║
chaiml-exp349-dpo-s3-sl-28707-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Unable to record family friendly update due to error: Invalid JSON input: JSON must contain 'User Safety' and 'Response Safety' fields
chaiml-exp349-dpo-s3-sl-28707-v1-mkmlizer: Downloaded to shared memory in 86.913s
chaiml-exp349-dpo-s3-sl-28707-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp3apjvk09, device:0
chaiml-exp349-dpo-s3-sl-28707-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-exp349-dpo-s3-sl-28707-v1-mkmlizer: quantized model in 52.921s
chaiml-exp349-dpo-s3-sl-28707-v1-mkmlizer: Processed model ChaiML/exp349-dpo-s3-slerpv2-data31full1350 in 139.848s
chaiml-exp349-dpo-s3-sl-28707-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-exp349-dpo-s3-sl-28707-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-exp349-dpo-s3-sl-28707-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-exp349-dpo-s3-sl-28707-v1
chaiml-exp349-dpo-s3-sl-28707-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-exp349-dpo-s3-sl-28707-v1/config.json
chaiml-exp349-dpo-s3-sl-28707-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-exp349-dpo-s3-sl-28707-v1/special_tokens_map.json
chaiml-exp349-dpo-s3-sl-28707-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-exp349-dpo-s3-sl-28707-v1/tokenizer_config.json
chaiml-exp349-dpo-s3-sl-28707-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-exp349-dpo-s3-sl-28707-v1/tokenizer.json
chaiml-exp349-dpo-s3-sl-28707-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-exp349-dpo-s3-sl-28707-v1/flywheel_model.1.safetensors
chaiml-exp349-dpo-s3-sl-28707-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-exp349-dpo-s3-sl-28707-v1/flywheel_model.0.safetensors
chaiml-exp349-dpo-s3-sl-28707-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.73it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:09, 37.81it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:09, 35.45it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:09, 36.11it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:10, 32.21it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:08, 37.73it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:14, 23.25it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:12, 25.61it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:11, 27.20it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 29.11it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:11, 27.06it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:10, 29.51it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:10, 28.00it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 29.00it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:11, 26.52it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:12, 22.39it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 27.93it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:09, 28.70it/s]
Loading 0:  24%|██▍       | 87/363 [00:03<00:11, 24.97it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:09, 27.76it/s]
Loading 0:  26%|██▌       | 95/363 [00:03<00:09, 28.74it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:09, 28.67it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:09, 27.91it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:10, 23.70it/s]
Loading 0:  31%|███       | 112/363 [00:04<00:09, 26.86it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:09, 26.72it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 29.65it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 28.38it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 30.35it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 28.89it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:07, 31.12it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:07, 29.37it/s]
Loading 0:  40%|████      | 147/363 [00:05<00:06, 33.91it/s]
Loading 0:  42%|████▏     | 151/363 [00:05<00:08, 25.30it/s]
Loading 0:  42%|████▏     | 154/363 [00:05<00:08, 23.68it/s]
Loading 0:  43%|████▎     | 157/363 [00:05<00:08, 24.49it/s]
Loading 0:  44%|████▍     | 160/363 [00:05<00:08, 24.71it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:07, 28.14it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:07, 25.68it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 29.90it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 28.19it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:06, 28.37it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:06, 25.22it/s]
Loading 0:  52%|█████▏    | 190/363 [00:06<00:07, 23.67it/s]
Loading 0:  53%|█████▎    | 193/363 [00:06<00:06, 24.67it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 25.09it/s]
Loading 0:  55%|█████▌    | 200/363 [00:21<00:06, 25.09it/s]
Loading 0:  55%|█████▌    | 201/363 [00:21<02:56,  1.09s/it]
Loading 0:  56%|█████▌    | 203/363 [00:21<02:25,  1.10it/s]
Loading 0:  57%|█████▋    | 208/363 [00:21<01:27,  1.77it/s]
Loading 0:  58%|█████▊    | 211/363 [00:21<01:07,  2.25it/s]
Loading 0:  59%|█████▉    | 214/363 [00:21<00:50,  2.97it/s]
Loading 0:  60%|██████    | 218/363 [00:21<00:34,  4.24it/s]
Loading 0:  61%|██████    | 221/363 [00:22<00:26,  5.43it/s]
Loading 0:  62%|██████▏   | 224/363 [00:22<00:21,  6.50it/s]
Loading 0:  63%|██████▎   | 228/363 [00:22<00:14,  9.10it/s]
Loading 0:  64%|██████▎   | 231/363 [00:22<00:12, 10.59it/s]
Loading 0:  65%|██████▌   | 237/363 [00:22<00:08, 15.67it/s]
Loading 0:  66%|██████▌   | 240/363 [00:22<00:07, 16.46it/s]
Loading 0:  68%|██████▊   | 246/363 [00:22<00:05, 21.87it/s]
Loading 0:  69%|██████▉   | 250/363 [00:23<00:04, 22.87it/s]
Loading 0:  70%|███████   | 255/363 [00:23<00:04, 26.04it/s]
Loading 0:  71%|███████▏  | 259/363 [00:23<00:03, 26.08it/s]
Loading 0:  73%|███████▎  | 265/363 [00:23<00:02, 32.67it/s]
Loading 0:  74%|███████▍  | 269/363 [00:23<00:04, 23.11it/s]
Loading 0:  75%|███████▌  | 273/363 [00:23<00:03, 23.37it/s]
Loading 0:  76%|███████▌  | 276/363 [00:24<00:03, 21.95it/s]
Loading 0:  78%|███████▊  | 282/363 [00:24<00:03, 26.69it/s]
Loading 0:  79%|███████▊  | 285/363 [00:24<00:03, 25.00it/s]
Loading 0:  80%|████████  | 291/363 [00:24<00:02, 29.74it/s]
Loading 0:  81%|████████▏ | 295/363 [00:24<00:02, 28.28it/s]
Loading 0:  82%|████████▏ | 299/363 [00:24<00:02, 28.33it/s]
Loading 0:  84%|████████▎ | 304/363 [00:25<00:02, 25.91it/s]
Loading 0:  85%|████████▍ | 307/363 [00:25<00:02, 23.48it/s]
Loading 0:  85%|████████▌ | 310/363 [00:25<00:02, 24.23it/s]
Loading 0:  86%|████████▌ | 313/363 [00:25<00:02, 24.68it/s]
Loading 0:  88%|████████▊ | 318/363 [00:25<00:01, 27.15it/s]
Loading 0:  88%|████████▊ | 321/363 [00:25<00:01, 24.54it/s]
Loading 0:  90%|█████████ | 327/363 [00:25<00:01, 28.37it/s]
Loading 0:  91%|█████████ | 330/363 [00:26<00:01, 25.96it/s]
Loading 0:  92%|█████████▏| 335/363 [00:26<00:00, 28.06it/s]
Loading 0:  93%|█████████▎| 338/363 [00:26<00:00, 27.19it/s]
Loading 0:  94%|█████████▍| 341/363 [00:33<00:13,  1.69it/s]
Loading 0:  96%|█████████▌| 347/363 [00:33<00:05,  2.81it/s]
Loading 0:  96%|█████████▋| 350/363 [00:33<00:03,  3.52it/s]
Loading 0:  98%|█████████▊| 355/363 [00:33<00:01,  5.21it/s]
Loading 0:  99%|█████████▉| 359/363 [00:33<00:00,  6.73it/s]
                                                            
Job chaiml-exp349-dpo-s3-sl-28707-v1-mkmlizer completed after 166.75s with status: succeeded
Stopping job with name chaiml-exp349-dpo-s3-sl-28707-v1-mkmlizer
Pipeline stage MKMLizer completed in 167.31s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.21s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-exp349-dpo-s3-sl-28707-v1
Waiting for inference service chaiml-exp349-dpo-s3-sl-28707-v1 to be ready
Inference service chaiml-exp349-dpo-s3-sl-28707-v1 ready after 140.49116015434265s
Pipeline stage MKMLDeployer completed in 141.01s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 3.5111331939697266s
Received healthy response to inference request in 2.526777505874634s
Received healthy response to inference request in 2.698474645614624s
Received healthy response to inference request in 3.1424672603607178s
5 requests
1 failed requests
5th percentile: 2.561116933822632
10th percentile: 2.59545636177063
20th percentile: 2.664135217666626
30th percentile: 2.7872731685638428
40th percentile: 2.9648702144622803
50th percentile: 3.1424672603607178
60th percentile: 3.2899336338043215
70th percentile: 3.4374000072479247
80th percentile: 6.843805789947513
90th percentile: 13.509150981903078
95th percentile: 16.841823577880856
99th percentile: 19.507961654663085
mean time: 6.410669755935669
%s, retrying in %s seconds...
Received healthy response to inference request in 2.775061845779419s
Received healthy response to inference request in 2.6046459674835205s
Received healthy response to inference request in 2.4491915702819824s
Received healthy response to inference request in 2.432058811187744s
Received healthy response to inference request in 2.5254573822021484s
5 requests
0 failed requests
5th percentile: 2.435485363006592
10th percentile: 2.4389119148254395
20th percentile: 2.4457650184631348
30th percentile: 2.4644447326660157
40th percentile: 2.494951057434082
50th percentile: 2.5254573822021484
60th percentile: 2.5571328163146974
70th percentile: 2.5888082504272463
80th percentile: 2.6387291431427
90th percentile: 2.7068954944610595
95th percentile: 2.7409786701202394
99th percentile: 2.768245210647583
mean time: 2.557283115386963
Pipeline stage StressChecker completed in 48.16s
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 0.86s
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 0.82s
Shutdown handler de-registered
chaiml-exp349-dpo-s3-sl_28707_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
Pipeline stage OfflineFamilyFriendlyScorer completed in 5700.37s
Shutdown handler de-registered
chaiml-exp349-dpo-s3-sl_28707_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-exp349-dpo-s3-sl_28707_v1 status is now torndown due to DeploymentManager action