developer_uid: rinen0721
submission_id: rinen0721-mistral-dpo-0114_v1
model_name: rinen0721-mistral-dpo-0114_v1
model_group: rinen0721/Mistral-dpo-01
status: torndown
timestamp: 2025-01-14T02:35:23+00:00
num_battles: 9151
num_wins: 4331
celo_rating: 1242.93
family_friendly_score: 0.5962000000000001
family_friendly_standard_error: 0.006938956117457438
submission_type: basic
model_repo: rinen0721/Mistral-dpo-0114
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6167125765535587, 'latency_mean': 1.62141419172287, 'latency_p50': 1.6162569522857666, 'latency_p90': 1.793293333053589}, {'batch_size': 3, 'throughput': 1.1368742119639352, 'latency_mean': 2.629801905155182, 'latency_p50': 2.6336774826049805, 'latency_p90': 2.9357689142227175}, {'batch_size': 5, 'throughput': 1.3808978069582265, 'latency_mean': 3.5981808459758757, 'latency_p50': 3.5906715393066406, 'latency_p90': 4.0540180683135985}, {'batch_size': 6, 'throughput': 1.459301129550464, 'latency_mean': 4.095665336847305, 'latency_p50': 4.081437587738037, 'latency_p90': 4.5381287097930905}, {'batch_size': 8, 'throughput': 1.5263470584929713, 'latency_mean': 5.20199407696724, 'latency_p50': 5.183534622192383, 'latency_p90': 5.943047046661377}, {'batch_size': 10, 'throughput': 1.5618022825173266, 'latency_mean': 6.36476501584053, 'latency_p50': 6.44098174571991, 'latency_p90': 7.168021607398987}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: rinen0721-mistral-dpo-0114_v1
is_internal_developer: False
language_model: rinen0721/Mistral-dpo-0114
model_size: 13B
ranking_group: single
throughput_3p7s: 1.41
us_pacific_date: 2025-01-13
win_ratio: 0.47328160856736967
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{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 rinen0721-mistral-dpo-0114-v1-mkmlizer
Waiting for job on rinen0721-mistral-dpo-0114-v1-mkmlizer to finish
rinen0721-mistral-dpo-0114-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rinen0721-mistral-dpo-0114-v1-mkmlizer: ║     _____            __           __                                ║
rinen0721-mistral-dpo-0114-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rinen0721-mistral-dpo-0114-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rinen0721-mistral-dpo-0114-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rinen0721-mistral-dpo-0114-v1-mkmlizer: ║       /___/                                                         ║
rinen0721-mistral-dpo-0114-v1-mkmlizer: ║                                                                     ║
rinen0721-mistral-dpo-0114-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
rinen0721-mistral-dpo-0114-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rinen0721-mistral-dpo-0114-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rinen0721-mistral-dpo-0114-v1-mkmlizer: ║                                                                     ║
rinen0721-mistral-dpo-0114-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rinen0721-mistral-dpo-0114-v1-mkmlizer: ║  belonging to:                                                      ║
rinen0721-mistral-dpo-0114-v1-mkmlizer: ║                                                                     ║
rinen0721-mistral-dpo-0114-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rinen0721-mistral-dpo-0114-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rinen0721-mistral-dpo-0114-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
rinen0721-mistral-dpo-0114-v1-mkmlizer: ║                                                                     ║
rinen0721-mistral-dpo-0114-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rinen0721-mistral-dpo-0114-v1-mkmlizer: Downloaded to shared memory in 51.260s
rinen0721-mistral-dpo-0114-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp8p55wczf, device:0
rinen0721-mistral-dpo-0114-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rinen0721-mistral-dpo-0114-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/mk1/flywheel/functional/loader.py:55: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
rinen0721-mistral-dpo-0114-v1-mkmlizer:   tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
rinen0721-mistral-dpo-0114-v1-mkmlizer: quantized model in 35.945s
rinen0721-mistral-dpo-0114-v1-mkmlizer: Processed model rinen0721/Mistral-dpo-0114 in 87.205s
rinen0721-mistral-dpo-0114-v1-mkmlizer: creating bucket guanaco-mkml-models
rinen0721-mistral-dpo-0114-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rinen0721-mistral-dpo-0114-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rinen0721-mistral-dpo-0114-v1
rinen0721-mistral-dpo-0114-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rinen0721-mistral-dpo-0114-v1/config.json
rinen0721-mistral-dpo-0114-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rinen0721-mistral-dpo-0114-v1/special_tokens_map.json
rinen0721-mistral-dpo-0114-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rinen0721-mistral-dpo-0114-v1/tokenizer_config.json
rinen0721-mistral-dpo-0114-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rinen0721-mistral-dpo-0114-v1/tokenizer.json
rinen0721-mistral-dpo-0114-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rinen0721-mistral-dpo-0114-v1/flywheel_model.0.safetensors
rinen0721-mistral-dpo-0114-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:07, 50.00it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:04, 83.44it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:03, 83.66it/s]
Loading 0:  12%|█▏        | 43/363 [00:00<00:03, 83.98it/s]
Loading 0:  16%|█▌        | 58/363 [00:00<00:03, 91.97it/s]
Loading 0:  19%|█▊        | 68/363 [00:01<00:12, 24.35it/s]
Loading 0:  21%|██        | 76/363 [00:01<00:10, 28.22it/s]
Loading 0:  23%|██▎       | 85/363 [00:02<00:07, 35.08it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:05, 45.28it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:05, 50.69it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:04, 56.22it/s]
Loading 0:  34%|███▍      | 124/363 [00:02<00:03, 61.77it/s]
Loading 0:  37%|███▋      | 135/363 [00:02<00:03, 72.32it/s]
Loading 0:  40%|███▉      | 144/363 [00:03<00:09, 23.20it/s]
Loading 0:  42%|████▏     | 151/363 [00:03<00:07, 27.19it/s]
Loading 0:  44%|████▍     | 160/363 [00:03<00:05, 34.38it/s]
Loading 0:  47%|████▋     | 170/363 [00:04<00:04, 43.70it/s]
Loading 0:  51%|█████     | 184/363 [00:04<00:03, 56.01it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:02, 59.65it/s]
Loading 0:  56%|█████▌    | 202/363 [00:04<00:02, 63.92it/s]
Loading 0:  58%|█████▊    | 212/363 [00:04<00:02, 71.77it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:06, 22.80it/s]
Loading 0:  64%|██████▍   | 232/363 [00:05<00:04, 28.20it/s]
Loading 0:  66%|██████▋   | 241/363 [00:05<00:03, 34.82it/s]
Loading 0:  69%|██████▉   | 250/363 [00:05<00:02, 42.01it/s]
Loading 0:  71%|███████▏  | 259/363 [00:06<00:02, 49.38it/s]
Loading 0:  74%|███████▍  | 268/363 [00:06<00:01, 53.58it/s]
Loading 0:  76%|███████▋  | 277/363 [00:06<00:01, 59.39it/s]
Loading 0:  79%|███████▉  | 286/363 [00:06<00:01, 65.11it/s]
Loading 0:  81%|████████▏ | 295/363 [00:06<00:00, 70.10it/s]
Loading 0:  84%|████████▎ | 304/363 [00:07<00:02, 21.20it/s]
Loading 0:  86%|████████▌ | 313/363 [00:07<00:01, 27.37it/s]
Loading 0:  89%|████████▊ | 322/363 [00:07<00:01, 34.52it/s]
Loading 0:  91%|█████████▏| 332/363 [00:07<00:00, 43.54it/s]
Loading 0:  94%|█████████▍| 341/363 [00:08<00:00, 50.31it/s]
Loading 0:  96%|█████████▋| 350/363 [00:08<00:00, 55.88it/s]
Loading 0:  99%|█████████▊| 358/363 [00:08<00:00, 60.74it/s]
                                                            

Job rinen0721-mistral-dpo-0114-v1-mkmlizer completed after 114.59s with status: succeeded
Stopping job with name rinen0721-mistral-dpo-0114-v1-mkmlizer
Pipeline stage MKMLizer completed in 115.10s
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 rinen0721-mistral-dpo-0114-v1
Waiting for inference service rinen0721-mistral-dpo-0114-v1 to be ready
Inference service rinen0721-mistral-dpo-0114-v1 ready after 381.4398584365845s
Pipeline stage MKMLDeployer completed in 382.00s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.024132251739502s
Received healthy response to inference request in 1.4835269451141357s
Received healthy response to inference request in 1.206214189529419s
Received healthy response to inference request in 1.492295742034912s
Received healthy response to inference request in 2.21429181098938s
5 requests
0 failed requests
5th percentile: 1.2616767406463623
10th percentile: 1.3171392917633056
20th percentile: 1.4280643939971924
30th percentile: 1.485280704498291
40th percentile: 1.4887882232666017
50th percentile: 1.492295742034912
60th percentile: 1.705030345916748
70th percentile: 1.9177649497985838
80th percentile: 2.0621641635894776
90th percentile: 2.1382279872894285
95th percentile: 2.176259899139404
99th percentile: 2.2066854286193847
mean time: 1.6840921878814696
Pipeline stage StressChecker completed in 9.69s
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 0.70s
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 0.61s
Shutdown handler de-registered
rinen0721-mistral-dpo-0114_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 0.09s
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 rinen0721-mistral-dpo-0114-v1-profiler
Waiting for inference service rinen0721-mistral-dpo-0114-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
Pipeline stage OfflineFamilyFriendlyScorer completed in 2878.47s
Shutdown handler de-registered
rinen0721-mistral-dpo-0114_v1 status is now inactive due to auto deactivation removed underperforming models
rinen0721-mistral-dpo-0114_v1 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1