chaiml-exp70-dpo-ftexp13_4591

developer_uid: NischayDnk

submission_id: chaiml-exp70-dpo-ftexp13_4591_v1

model_name: chaiml-exp70-dpo-ftexp13_4591_v1

model_group: ChaiML/exp70-dpo-ftexp13

status: torndown

timestamp: 2025-03-13T08:37:04+00:00

num_battles: 9945

num_wins: 5072

celo_rating: 1288.03

family_friendly_score: 0.5684

family_friendly_standard_error: 0.007004590494811242

submission_type: basic

model_repo: ChaiML/exp70-dpo-ftexp13sft-24B-ssdelfiltered5k

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': 0.3702776183613044, 'latency_mean': 2.700613853931427, 'latency_p50': 2.690152406692505, 'latency_p90': 2.979280424118042}, {'batch_size': 2, 'throughput': 0.5735179816992341, 'latency_mean': 3.4819944036006927, 'latency_p50': 3.476223587989807, 'latency_p90': 3.7952723503112793}, {'batch_size': 3, 'throughput': 0.7305355062951877, 'latency_mean': 4.103095780611039, 'latency_p50': 4.122061252593994, 'latency_p90': 4.51609742641449}, {'batch_size': 4, 'throughput': 0.8418760134591204, 'latency_mean': 4.733058756589889, 'latency_p50': 4.735608339309692, 'latency_p90': 5.208748197555542}, {'batch_size': 5, 'throughput': 0.934472086174281, 'latency_mean': 5.319997849464417, 'latency_p50': 5.2708059549331665, 'latency_p90': 5.9319367647171015}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-exp70-dpo-ftexp13_4591_v1

is_internal_developer: False

language_model: ChaiML/exp70-dpo-ftexp13sft-24B-ssdelfiltered5k

model_size: 24B

ranking_group: single

throughput_3p7s: 0.64

us_pacific_date: 2025-03-13

win_ratio: 0.5100050276520864

generation_params: {'temperature': 0.45, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.45, 'frequency_penalty': 0.45, 'stopping_words': ['You:', '\n', '</s>', '###'], '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-exp70-dpo-ftexp13-4591-v1-mkmlizer
Waiting for job on chaiml-exp70-dpo-ftexp13-4591-v1-mkmlizer to finish
chaiml-exp70-dpo-ftexp13-4591-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-exp70-dpo-ftexp13-4591-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-exp70-dpo-ftexp13-4591-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-exp70-dpo-ftexp13-4591-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-exp70-dpo-ftexp13-4591-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-exp70-dpo-ftexp13-4591-v1-mkmlizer: ║       /___/                                                         ║
chaiml-exp70-dpo-ftexp13-4591-v1-mkmlizer: ║                                                                     ║
chaiml-exp70-dpo-ftexp13-4591-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-exp70-dpo-ftexp13-4591-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-exp70-dpo-ftexp13-4591-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-exp70-dpo-ftexp13-4591-v1-mkmlizer: ║                                                                     ║
chaiml-exp70-dpo-ftexp13-4591-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-exp70-dpo-ftexp13-4591-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-exp70-dpo-ftexp13-4591-v1-mkmlizer: ║                                                                     ║
chaiml-exp70-dpo-ftexp13-4591-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-exp70-dpo-ftexp13-4591-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-exp70-dpo-ftexp13-4591-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
chaiml-exp70-dpo-ftexp13-4591-v1-mkmlizer: ║                                                                     ║
chaiml-exp70-dpo-ftexp13-4591-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-exp70-dpo-ftexp13-4591-v1-mkmlizer: Downloaded to shared memory in 77.099s
chaiml-exp70-dpo-ftexp13-4591-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpv40bzel4, device:0
chaiml-exp70-dpo-ftexp13-4591-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission jellywibble-enzo-mafia-enemy_v12: HTTPConnectionPool(host='jellywibble-enzo-mafia-enemy-v12-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-exp70-dpo-ftexp13-4591-v1-mkmlizer: quantized model in 53.129s
chaiml-exp70-dpo-ftexp13-4591-v1-mkmlizer: Processed model ChaiML/exp70-dpo-ftexp13sft-24B-ssdelfiltered5k in 130.229s
chaiml-exp70-dpo-ftexp13-4591-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-exp70-dpo-ftexp13-4591-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-exp70-dpo-ftexp13-4591-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-exp70-dpo-ftexp13-4591-v1
chaiml-exp70-dpo-ftexp13-4591-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-exp70-dpo-ftexp13-4591-v1/config.json
chaiml-exp70-dpo-ftexp13-4591-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-exp70-dpo-ftexp13-4591-v1/tokenizer_config.json
chaiml-exp70-dpo-ftexp13-4591-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-exp70-dpo-ftexp13-4591-v1/special_tokens_map.json
chaiml-exp70-dpo-ftexp13-4591-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-exp70-dpo-ftexp13-4591-v1/tokenizer.json
chaiml-exp70-dpo-ftexp13-4591-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-exp70-dpo-ftexp13-4591-v1/flywheel_model.1.safetensors
chaiml-exp70-dpo-ftexp13-4591-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-exp70-dpo-ftexp13-4591-v1/flywheel_model.0.safetensors
chaiml-exp70-dpo-ftexp13-4591-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:17, 21.01it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:09, 37.85it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:09, 34.92it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:09, 34.45it/s]
Loading 0:   7%|▋         | 26/363 [00:00<00:09, 35.60it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:08, 40.24it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:13, 24.61it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:14, 22.41it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 29.19it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:11, 27.89it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:09, 30.70it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:10, 28.90it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 29.76it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:10, 26.82it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:12, 22.58it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 27.98it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:09, 28.71it/s]
Loading 0:  24%|██▍       | 87/363 [00:03<00:11, 24.52it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:09, 27.31it/s]
Loading 0:  26%|██▌       | 95/363 [00:03<00:09, 27.30it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:09, 28.75it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:09, 28.00it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:10, 24.38it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:09, 27.15it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:09, 26.72it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 29.78it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 27.76it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 29.80it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:08, 28.47it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:07, 31.22it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:07, 29.53it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:06, 33.39it/s]
Loading 0:  42%|████▏     | 153/363 [00:05<00:09, 21.24it/s]
Loading 0:  43%|████▎     | 157/363 [00:05<00:08, 23.64it/s]
Loading 0:  44%|████▍     | 160/363 [00:05<00:08, 23.85it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:07, 26.97it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:07, 26.21it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 28.84it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 28.03it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:06, 28.71it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:06, 26.41it/s]
Loading 0:  52%|█████▏    | 190/363 [00:06<00:07, 23.82it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:06, 24.59it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 24.78it/s]
Loading 0:  55%|█████▌    | 200/363 [00:21<00:06, 24.78it/s]
Loading 0:  55%|█████▌    | 201/363 [00:21<02:58,  1.10s/it]
Loading 0:  56%|█████▌    | 203/363 [00:21<02:27,  1.09it/s]
Loading 0:  57%|█████▋    | 208/363 [00:21<01:28,  1.75it/s]
Loading 0:  58%|█████▊    | 211/363 [00:21<01:08,  2.22it/s]
Loading 0:  59%|█████▉    | 214/363 [00:21<00:50,  2.93it/s]
Loading 0:  60%|██████    | 218/363 [00:22<00:34,  4.20it/s]
Loading 0:  61%|██████    | 221/363 [00:22<00:26,  5.37it/s]
Loading 0:  62%|██████▏   | 224/363 [00:22<00:21,  6.46it/s]
Loading 0:  63%|██████▎   | 228/363 [00:22<00:14,  9.05it/s]
Loading 0:  64%|██████▎   | 231/363 [00:22<00:12, 10.41it/s]
Loading 0:  65%|██████▌   | 237/363 [00:22<00:08, 15.45it/s]
Loading 0:  66%|██████▌   | 240/363 [00:23<00:07, 16.14it/s]
Loading 0:  68%|██████▊   | 246/363 [00:23<00:05, 21.51it/s]
Loading 0:  69%|██████▉   | 250/363 [00:23<00:05, 22.23it/s]
Loading 0:  70%|███████   | 255/363 [00:23<00:04, 24.97it/s]
Loading 0:  71%|███████▏  | 259/363 [00:23<00:04, 24.83it/s]
Loading 0:  73%|███████▎  | 265/363 [00:23<00:03, 31.71it/s]
Loading 0:  74%|███████▍  | 269/363 [00:24<00:04, 22.09it/s]
Loading 0:  75%|███████▌  | 273/363 [00:24<00:04, 21.89it/s]
Loading 0:  76%|███████▌  | 276/363 [00:24<00:04, 21.16it/s]
Loading 0:  78%|███████▊  | 282/363 [00:24<00:03, 26.25it/s]
Loading 0:  79%|███████▉  | 286/363 [00:24<00:02, 26.00it/s]
Loading 0:  80%|████████  | 291/363 [00:24<00:02, 28.86it/s]
Loading 0:  81%|████████▏ | 295/363 [00:24<00:02, 27.87it/s]
Loading 0:  82%|████████▏ | 299/363 [00:25<00:02, 27.86it/s]
Loading 0:  84%|████████▎ | 304/363 [00:25<00:02, 25.70it/s]
Loading 0:  85%|████████▍ | 307/363 [00:25<00:02, 23.40it/s]
Loading 0:  85%|████████▌ | 310/363 [00:25<00:02, 23.91it/s]
Loading 0:  86%|████████▌ | 313/363 [00:25<00:02, 23.97it/s]
Loading 0:  88%|████████▊ | 318/363 [00:25<00:01, 27.50it/s]
Loading 0:  88%|████████▊ | 321/363 [00:26<00:01, 24.95it/s]
Loading 0:  90%|█████████ | 327/363 [00:26<00:01, 29.19it/s]
Loading 0:  91%|█████████ | 330/363 [00:26<00:01, 26.00it/s]
Loading 0:  92%|█████████▏| 335/363 [00:26<00:00, 28.34it/s]
Loading 0:  93%|█████████▎| 338/363 [00:26<00:00, 26.38it/s]
Loading 0:  94%|█████████▍| 341/363 [00:33<00:13,  1.68it/s]
Loading 0:  96%|█████████▌| 347/363 [00:33<00:05,  2.79it/s]
Loading 0:  96%|█████████▋| 350/363 [00:33<00:03,  3.50it/s]
Loading 0:  98%|█████████▊| 355/363 [00:33<00:01,  5.19it/s]
Loading 0:  99%|█████████▉| 359/363 [00:34<00:00,  6.75it/s]
                                                            
Job chaiml-exp70-dpo-ftexp13-4591-v1-mkmlizer completed after 165.31s with status: succeeded
Stopping job with name chaiml-exp70-dpo-ftexp13-4591-v1-mkmlizer
Pipeline stage MKMLizer completed in 165.81s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-exp70-dpo-ftexp13-4591-v1
Waiting for inference service chaiml-exp70-dpo-ftexp13-4591-v1 to be ready
Failed to get response for submission jellywibble-enzo-mafia-enemy_v12: HTTPConnectionPool(host='jellywibble-enzo-mafia-enemy-v12-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission jellywibble-enzo-mafia-enemy_v12: HTTPConnectionPool(host='jellywibble-enzo-mafia-enemy-v12-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service chaiml-exp70-dpo-ftexp13-4591-v1 ready after 100.40073609352112s
Pipeline stage MKMLDeployer completed in 100.95s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.1019842624664307s
Received healthy response to inference request in 2.49662709236145s
Received healthy response to inference request in 2.416668176651001s
Received healthy response to inference request in 2.3192975521087646s
Received healthy response to inference request in 2.3437788486480713s
5 requests
0 failed requests
5th percentile: 2.324193811416626
10th percentile: 2.3290900707244875
20th percentile: 2.33888258934021
30th percentile: 2.3583567142486572
40th percentile: 2.387512445449829
50th percentile: 2.416668176651001
60th percentile: 2.448651742935181
70th percentile: 2.4806353092193603
80th percentile: 2.6176985263824464
90th percentile: 2.8598413944244383
95th percentile: 2.9809128284454345
99th percentile: 3.0777699756622314
mean time: 2.5356711864471437
Pipeline stage StressChecker completed in 14.07s
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 0.69s
Shutdown handler de-registered
chaiml-exp70-dpo-ftexp13_4591_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 0.11s
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-exp70-dpo-ftexp13-4591-v1-profiler
Waiting for inference service chaiml-exp70-dpo-ftexp13-4591-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 4887.70s
Shutdown handler de-registered
chaiml-exp70-dpo-ftexp13_4591_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-exp70-dpo-ftexp13_4591_v1 status is now torndown due to DeploymentManager action