chaiml-gemma-exp3-dpo-s_66157

developer_uid: NischayDnk

submission_id: chaiml-gemma-exp3-dpo-s_66157_v2

model_name: chaiml-gemma-exp3-dpo-s_66157_v2

model_group: ChaiML/gemma-exp3-dpo-sf

status: torndown

timestamp: 2025-04-02T21:49:13+00:00

num_battles: 6951

num_wins: 3212

celo_rating: 1269.13

family_friendly_score: 0.5484

family_friendly_standard_error: 0.007037861038696345

submission_type: basic

model_repo: ChaiML/gemma-exp3-dpo-sftv2-v10filter

model_architecture: Gemma2ForCausalLM

model_num_parameters: 28731935232.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.27447511050024126, 'latency_mean': 3.643212435245514, 'latency_p50': 3.6189056634902954, 'latency_p90': 4.053857398033142}, {'batch_size': 2, 'throughput': 0.4181794994541929, 'latency_mean': 4.776012506484985, 'latency_p50': 4.767705798149109, 'latency_p90': 5.266316390037536}, {'batch_size': 3, 'throughput': 0.529710517450199, 'latency_mean': 5.652440673112869, 'latency_p50': 5.5993160009384155, 'latency_p90': 6.22041437625885}, {'batch_size': 5, 'throughput': 0.6640848847015325, 'latency_mean': 7.486042011976242, 'latency_p50': 7.467418193817139, 'latency_p90': 8.238049483299255}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-gemma-exp3-dpo-s_66157_v2

is_internal_developer: False

language_model: ChaiML/gemma-exp3-dpo-sftv2-v10filter

model_size: 29B

ranking_group: single

throughput_3p7s: 0.28

us_pacific_date: 2025-04-02

win_ratio: 0.46209178535462525

generation_params: {'temperature': 0.45, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 40, 'presence_penalty': 0.2, 'frequency_penalty': 0.2, 'stopping_words': ['<|im_end|>', '<|im_start|>', '\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}:', '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-gemma-exp3-dpo-s-66157-v2-mkmlizer
Waiting for job on chaiml-gemma-exp3-dpo-s-66157-v2-mkmlizer to finish
chaiml-gemma-exp3-dpo-s-66157-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gemma-exp3-dpo-s-66157-v2-mkmlizer: ║     _____            __           __                                ║
chaiml-gemma-exp3-dpo-s-66157-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-gemma-exp3-dpo-s-66157-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-gemma-exp3-dpo-s-66157-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-gemma-exp3-dpo-s-66157-v2-mkmlizer: ║       /___/                                                         ║
chaiml-gemma-exp3-dpo-s-66157-v2-mkmlizer: ║                                                                     ║
chaiml-gemma-exp3-dpo-s-66157-v2-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-gemma-exp3-dpo-s-66157-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-gemma-exp3-dpo-s-66157-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gemma-exp3-dpo-s-66157-v2-mkmlizer: ║                                                                     ║
chaiml-gemma-exp3-dpo-s-66157-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gemma-exp3-dpo-s-66157-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-gemma-exp3-dpo-s-66157-v2-mkmlizer: ║                                                                     ║
chaiml-gemma-exp3-dpo-s-66157-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gemma-exp3-dpo-s-66157-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gemma-exp3-dpo-s-66157-v2-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
chaiml-gemma-exp3-dpo-s-66157-v2-mkmlizer: ║                                                                     ║
chaiml-gemma-exp3-dpo-s-66157-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission chaiml-sft-gemma2-28b-v_83370_v1: HTTPConnectionPool(host='chaiml-sft-gemma2-28b-v-83370-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-gemma-exp3-dpo-s-66157-v2-mkmlizer: Downloaded to shared memory in 84.467s
chaiml-gemma-exp3-dpo-s-66157-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpkp29nd36, device:0
chaiml-gemma-exp3-dpo-s-66157-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission chaiml-sft-gemma2-28b-v_83370_v1: HTTPConnectionPool(host='chaiml-sft-gemma2-28b-v-83370-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-gemma-exp3-dpo-s-66157-v2-mkmlizer: quantized model in 69.317s
chaiml-gemma-exp3-dpo-s-66157-v2-mkmlizer: Processed model ChaiML/gemma-exp3-dpo-sftv2-v10filter in 153.784s
chaiml-gemma-exp3-dpo-s-66157-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gemma-exp3-dpo-s-66157-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gemma-exp3-dpo-s-66157-v2
chaiml-gemma-exp3-dpo-s-66157-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gemma-exp3-dpo-s-66157-v2/config.json
chaiml-gemma-exp3-dpo-s-66157-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gemma-exp3-dpo-s-66157-v2/special_tokens_map.json
chaiml-gemma-exp3-dpo-s-66157-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gemma-exp3-dpo-s-66157-v2/tokenizer_config.json
chaiml-gemma-exp3-dpo-s-66157-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/chaiml-gemma-exp3-dpo-s-66157-v2/tokenizer.model
chaiml-gemma-exp3-dpo-s-66157-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gemma-exp3-dpo-s-66157-v2/tokenizer.json
chaiml-gemma-exp3-dpo-s-66157-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-gemma-exp3-dpo-s-66157-v2/flywheel_model.2.safetensors
chaiml-gemma-exp3-dpo-s-66157-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gemma-exp3-dpo-s-66157-v2/flywheel_model.0.safetensors
chaiml-gemma-exp3-dpo-s-66157-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gemma-exp3-dpo-s-66157-v2/flywheel_model.1.safetensors
chaiml-gemma-exp3-dpo-s-66157-v2-mkmlizer: 
Loading 0:   0%|          | 0/508 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/508 [00:00<00:13, 37.61it/s]
Loading 0:   2%|▏         | 12/508 [00:00<00:11, 44.70it/s]
Loading 0:   3%|▎         | 17/508 [00:00<00:14, 33.45it/s]
Loading 0:   5%|▍         | 23/508 [00:00<00:12, 40.10it/s]
Loading 0:   6%|▌         | 28/508 [00:00<00:17, 27.97it/s]
Loading 0:   6%|▋         | 32/508 [00:01<00:17, 26.98it/s]
Loading 0:   7%|▋         | 38/508 [00:01<00:15, 30.73it/s]
Loading 0:   9%|▉         | 47/508 [00:01<00:11, 39.17it/s]
Loading 0:  10%|█         | 52/508 [00:01<00:11, 41.22it/s]
Loading 0:  11%|█▏        | 58/508 [00:01<00:10, 41.54it/s]
Loading 0:  12%|█▏        | 63/508 [00:01<00:10, 42.70it/s]
Loading 0:  13%|█▎        | 68/508 [00:01<00:11, 37.49it/s]
Loading 0:  14%|█▍        | 73/508 [00:02<00:15, 27.39it/s]
Loading 0:  15%|█▌        | 78/508 [00:02<00:14, 29.43it/s]
Loading 0:  16%|█▌        | 82/508 [00:02<00:14, 29.86it/s]
Loading 0:  17%|█▋        | 88/508 [00:02<00:12, 33.01it/s]
Loading 0:  19%|█▉        | 97/508 [00:02<00:09, 41.25it/s]
Loading 0:  20%|██        | 102/508 [00:02<00:09, 42.68it/s]
Loading 0:  21%|██▏       | 108/508 [00:02<00:09, 41.73it/s]
Loading 0:  22%|██▏       | 113/508 [00:03<00:09, 42.93it/s]
Loading 0:  23%|██▎       | 118/508 [00:03<00:11, 33.17it/s]
Loading 0:  24%|██▍       | 124/508 [00:03<00:09, 38.46it/s]
Loading 0:  25%|██▌       | 129/508 [00:03<00:09, 40.27it/s]
Loading 0:  27%|██▋       | 135/508 [00:03<00:09, 39.87it/s]
Loading 0:  28%|██▊       | 140/508 [00:03<00:08, 41.78it/s]
Loading 0:  29%|██▊       | 146/508 [00:03<00:08, 41.97it/s]
Loading 0:  30%|██▉       | 151/508 [00:04<00:08, 43.39it/s]
Loading 0:  31%|███       | 157/508 [00:04<00:08, 43.30it/s]
Loading 0:  32%|███▏      | 162/508 [00:04<00:07, 44.32it/s]
Loading 0:  33%|███▎      | 168/508 [00:04<00:07, 48.02it/s]
Loading 0:  34%|███▍      | 173/508 [00:04<00:11, 29.61it/s]
Loading 0:  35%|███▌      | 179/508 [00:04<00:09, 35.13it/s]
Loading 0:  36%|███▌      | 184/508 [00:04<00:08, 37.79it/s]
Loading 0:  37%|███▋      | 190/508 [00:05<00:08, 37.98it/s]
Loading 0:  38%|███▊      | 195/508 [00:19<04:18,  1.21it/s]
Loading 0:  39%|███▉      | 199/508 [00:19<03:15,  1.58it/s]
Loading 0:  40%|████      | 204/508 [00:20<02:21,  2.14it/s]
Loading 0:  42%|████▏     | 211/508 [00:20<01:29,  3.33it/s]
Loading 0:  43%|████▎     | 216/508 [00:20<01:07,  4.31it/s]
Loading 0:  43%|████▎     | 219/508 [00:20<00:56,  5.15it/s]
Loading 0:  44%|████▍     | 224/508 [00:20<00:39,  7.16it/s]
Loading 0:  46%|████▌     | 232/508 [00:20<00:24, 11.30it/s]
Loading 0:  47%|████▋     | 237/508 [00:21<00:20, 13.46it/s]
Loading 0:  48%|████▊     | 245/508 [00:21<00:13, 19.01it/s]
Loading 0:  49%|████▉     | 250/508 [00:21<00:11, 22.34it/s]
Loading 0:  50%|█████     | 255/508 [00:21<00:10, 24.12it/s]
Loading 0:  51%|█████     | 260/508 [00:21<00:09, 26.53it/s]
Loading 0:  52%|█████▏    | 264/508 [00:21<00:10, 23.45it/s]
Loading 0:  53%|█████▎    | 268/508 [00:22<00:09, 25.96it/s]
Loading 0:  54%|█████▍    | 276/508 [00:22<00:06, 33.59it/s]
Loading 0:  55%|█████▌    | 281/508 [00:22<00:07, 31.68it/s]
Loading 0:  57%|█████▋    | 289/508 [00:22<00:06, 36.06it/s]
Loading 0:  58%|█████▊    | 293/508 [00:22<00:05, 36.38it/s]
Loading 0:  59%|█████▉    | 300/508 [00:22<00:05, 38.69it/s]
Loading 0:  60%|██████    | 305/508 [00:22<00:05, 40.50it/s]
Loading 0:  61%|██████    | 311/508 [00:22<00:04, 44.24it/s]
Loading 0:  62%|██████▏   | 316/508 [00:23<00:06, 28.64it/s]
Loading 0:  63%|██████▎   | 322/508 [00:23<00:05, 33.97it/s]
Loading 0:  64%|██████▍   | 327/508 [00:23<00:04, 36.64it/s]
Loading 0:  66%|██████▌   | 333/508 [00:23<00:04, 37.29it/s]
Loading 0:  67%|██████▋   | 338/508 [00:23<00:04, 39.68it/s]
Loading 0:  68%|██████▊   | 344/508 [00:23<00:04, 39.86it/s]
Loading 0:  69%|██████▊   | 349/508 [00:24<00:03, 41.59it/s]
Loading 0:  70%|██████▉   | 354/508 [00:24<00:03, 38.58it/s]
Loading 0:  71%|███████   | 359/508 [00:24<00:04, 31.25it/s]
Loading 0:  71%|███████▏  | 363/508 [00:24<00:04, 32.77it/s]
Loading 0:  72%|███████▏  | 367/508 [00:24<00:04, 34.38it/s]
Loading 0:  74%|███████▍  | 375/508 [00:24<00:03, 41.66it/s]
Loading 0:  75%|███████▍  | 380/508 [00:24<00:03, 36.58it/s]
Loading 0:  76%|███████▋  | 388/508 [00:25<00:02, 41.87it/s]
Loading 0:  77%|███████▋  | 393/508 [00:25<00:02, 43.45it/s]
Loading 0:  78%|███████▊  | 398/508 [00:25<00:02, 40.55it/s]
Loading 0:  79%|███████▉  | 403/508 [00:25<00:02, 40.03it/s]
Loading 0:  80%|████████  | 408/508 [00:25<00:03, 33.05it/s]
Loading 0:  81%|████████  | 412/508 [00:25<00:03, 31.10it/s]
Loading 0:  83%|████████▎ | 421/508 [00:26<00:02, 38.50it/s]
Loading 0:  84%|████████▎ | 425/508 [00:26<00:02, 38.49it/s]
Loading 0:  85%|████████▌ | 432/508 [00:26<00:01, 41.41it/s]
Loading 0:  86%|████████▌ | 437/508 [00:26<00:01, 42.72it/s]
Loading 0:  87%|████████▋ | 443/508 [00:26<00:01, 39.28it/s]
Loading 0:  88%|████████▊ | 448/508 [00:26<00:01, 40.94it/s]
Loading 0:  89%|████████▉ | 451/508 [00:41<00:01, 40.94it/s]
Loading 0:  89%|████████▉ | 452/508 [00:41<00:49,  1.14it/s]
Loading 0:  90%|████████▉ | 456/508 [00:41<00:34,  1.51it/s]
Loading 0:  91%|█████████ | 460/508 [00:41<00:24,  1.96it/s]
Loading 0:  92%|█████████▏| 466/508 [00:41<00:13,  3.02it/s]
Loading 0:  93%|█████████▎| 474/508 [00:41<00:06,  4.90it/s]
Loading 0:  94%|█████████▍| 479/508 [00:42<00:04,  6.27it/s]
Loading 0:  96%|█████████▌| 487/508 [00:42<00:02,  9.38it/s]
Loading 0:  97%|█████████▋| 492/508 [00:42<00:01, 11.76it/s]
Loading 0:  98%|█████████▊| 497/508 [00:42<00:00, 14.17it/s]
Loading 0:  99%|█████████▉| 502/508 [00:42<00:00, 15.62it/s]
Loading 0: 100%|█████████▉| 506/508 [00:42<00:00, 18.10it/s]
                                                            
Job chaiml-gemma-exp3-dpo-s-66157-v2-mkmlizer completed after 186.27s with status: succeeded
Stopping job with name chaiml-gemma-exp3-dpo-s-66157-v2-mkmlizer
Pipeline stage MKMLizer completed in 186.79s
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-gemma-exp3-dpo-s-66157-v2
Waiting for inference service chaiml-gemma-exp3-dpo-s-66157-v2 to be ready
Inference service chaiml-gemma-exp3-dpo-s-66157-v2 ready after 110.38957786560059s
Pipeline stage MKMLDeployer completed in 110.88s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 4.516860008239746s
Received healthy response to inference request in 3.3335866928100586s
Received healthy response to inference request in 3.358349084854126s
Received healthy response to inference request in 3.28372859954834s
Received healthy response to inference request in 3.5817487239837646s
5 requests
0 failed requests
5th percentile: 3.2937002182006836
10th percentile: 3.3036718368530273
20th percentile: 3.323615074157715
30th percentile: 3.338539171218872
40th percentile: 3.348444128036499
50th percentile: 3.358349084854126
60th percentile: 3.4477089405059815
70th percentile: 3.537068796157837
80th percentile: 3.768770980834961
90th percentile: 4.142815494537354
95th percentile: 4.32983775138855
99th percentile: 4.479455556869507
mean time: 3.614854621887207
Pipeline stage StressChecker completed in 19.34s
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 0.65s
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 0.65s
Shutdown handler de-registered
chaiml-gemma-exp3-dpo-s_66157_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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-gemma-exp3-dpo-s-66157-v2-profiler
Waiting for inference service chaiml-gemma-exp3-dpo-s-66157-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 6040.84s
Shutdown handler de-registered
chaiml-gemma-exp3-dpo-s_66157_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-gemma-exp3-dpo-s_66157_v2 status is now torndown due to DeploymentManager action