developer_uid: azuruce
submission_id: rinen0721-mistral-dpo-0213-m3_v2
model_name: rinen0721-mistral-dpo-0213-m3_v2
model_group: rinen0721/Mistral-dpo-02
status: torndown
timestamp: 2025-02-15T00:46:06+00:00
num_battles: 6815
num_wins: 3133
celo_rating: 1235.83
family_friendly_score: 0.5860000000000001
family_friendly_standard_error: 0.006965687331484238
submission_type: basic
model_repo: rinen0721/Mistral-dpo-0213-m3
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 768
max_output_tokens: 64
display_name: rinen0721-mistral-dpo-0213-m3_v2
is_internal_developer: True
language_model: rinen0721/Mistral-dpo-0213-m3
model_size: 13B
ranking_group: single
us_pacific_date: 2025-02-14
win_ratio: 0.45972120322817317
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', '</s>', '###', '####', '<|eot_id|>', '<|end_of_text|>', '<|im_end|>', 'You:', 'Bot:', 'User:', 'Me:'], 'max_input_tokens': 768, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '', 'prompt_template': '', '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-0213-m3-v2-mkmlizer
Waiting for job on rinen0721-mistral-dpo-0213-m3-v2-mkmlizer to finish
rinen0721-mistral-dpo-0213-m3-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rinen0721-mistral-dpo-0213-m3-v2-mkmlizer: ║     _____            __           __                                ║
rinen0721-mistral-dpo-0213-m3-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rinen0721-mistral-dpo-0213-m3-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rinen0721-mistral-dpo-0213-m3-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rinen0721-mistral-dpo-0213-m3-v2-mkmlizer: ║       /___/                                                         ║
rinen0721-mistral-dpo-0213-m3-v2-mkmlizer: ║                                                                     ║
rinen0721-mistral-dpo-0213-m3-v2-mkmlizer: ║  Version: 0.12.8                                                    ║
rinen0721-mistral-dpo-0213-m3-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rinen0721-mistral-dpo-0213-m3-v2-mkmlizer: ║  https://mk1.ai                                                     ║
rinen0721-mistral-dpo-0213-m3-v2-mkmlizer: ║                                                                     ║
rinen0721-mistral-dpo-0213-m3-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
rinen0721-mistral-dpo-0213-m3-v2-mkmlizer: ║  belonging to:                                                      ║
rinen0721-mistral-dpo-0213-m3-v2-mkmlizer: ║                                                                     ║
rinen0721-mistral-dpo-0213-m3-v2-mkmlizer: ║  Chai Research Corp.                                                ║
rinen0721-mistral-dpo-0213-m3-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rinen0721-mistral-dpo-0213-m3-v2-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
rinen0721-mistral-dpo-0213-m3-v2-mkmlizer: ║                                                                     ║
rinen0721-mistral-dpo-0213-m3-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rinen0721-mistral-dpo-0213-m3-v2-mkmlizer: Downloaded to shared memory in 41.304s
rinen0721-mistral-dpo-0213-m3-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpwhi7uvff, device:0
rinen0721-mistral-dpo-0213-m3-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rinen0721-mistral-dpo-0213-m3-v2-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-0213-m3-v2-mkmlizer:   tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
rinen0721-mistral-dpo-0213-m3-v2-mkmlizer: quantized model in 38.236s
rinen0721-mistral-dpo-0213-m3-v2-mkmlizer: Processed model rinen0721/Mistral-dpo-0213-m3 in 79.541s
rinen0721-mistral-dpo-0213-m3-v2-mkmlizer: creating bucket guanaco-mkml-models
rinen0721-mistral-dpo-0213-m3-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rinen0721-mistral-dpo-0213-m3-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rinen0721-mistral-dpo-0213-m3-v2
rinen0721-mistral-dpo-0213-m3-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rinen0721-mistral-dpo-0213-m3-v2/config.json
rinen0721-mistral-dpo-0213-m3-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rinen0721-mistral-dpo-0213-m3-v2/special_tokens_map.json
rinen0721-mistral-dpo-0213-m3-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rinen0721-mistral-dpo-0213-m3-v2/tokenizer_config.json
rinen0721-mistral-dpo-0213-m3-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rinen0721-mistral-dpo-0213-m3-v2/tokenizer.json
rinen0721-mistral-dpo-0213-m3-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 38.05it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:06, 51.67it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:06, 56.01it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:05, 60.76it/s]
Loading 0:  11%|█         | 40/363 [00:00<00:05, 61.12it/s]
Loading 0:  13%|█▎        | 49/363 [00:00<00:05, 60.27it/s]
Loading 0:  16%|█▌        | 58/363 [00:00<00:05, 60.80it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:16, 18.43it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:14, 20.13it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 27.00it/s]
Loading 0:  24%|██▍       | 88/363 [00:02<00:08, 33.90it/s]
Loading 0:  27%|██▋       | 97/363 [00:02<00:06, 39.32it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:05, 45.13it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:04, 50.52it/s]
Loading 0:  34%|███▎      | 122/363 [00:03<00:04, 54.34it/s]
Loading 0:  36%|███▌      | 129/363 [00:03<00:04, 55.89it/s]
Loading 0:  37%|███▋      | 136/363 [00:03<00:04, 52.72it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:14, 15.12it/s]
Loading 0:  42%|████▏     | 151/363 [00:04<00:10, 20.30it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:07, 26.05it/s]
Loading 0:  47%|████▋     | 169/363 [00:04<00:06, 32.03it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:04, 37.32it/s]
Loading 0:  52%|█████▏    | 187/363 [00:05<00:04, 42.11it/s]
Loading 0:  54%|█████▍    | 196/363 [00:05<00:03, 46.59it/s]
Loading 0:  56%|█████▋    | 205/363 [00:05<00:03, 50.46it/s]
Loading 0:  59%|█████▊    | 213/363 [00:05<00:02, 56.05it/s]
Loading 0:  61%|██████    | 220/363 [00:05<00:02, 53.69it/s]
Loading 0:  62%|██████▏   | 226/363 [00:06<00:08, 17.04it/s]
Loading 0:  64%|██████▍   | 232/363 [00:07<00:06, 19.86it/s]
Loading 0:  66%|██████▋   | 241/363 [00:07<00:04, 25.99it/s]
Loading 0:  69%|██████▉   | 250/363 [00:07<00:03, 32.17it/s]
Loading 0:  71%|███████▏  | 259/363 [00:07<00:02, 38.24it/s]
Loading 0:  74%|███████▍  | 268/363 [00:07<00:02, 40.51it/s]
Loading 0:  76%|███████▋  | 277/363 [00:07<00:01, 44.29it/s]
Loading 0:  79%|███████▉  | 286/363 [00:08<00:01, 48.47it/s]
Loading 0:  81%|████████▏ | 295/363 [00:08<00:01, 49.69it/s]
Loading 0:  84%|████████▎ | 304/363 [00:09<00:03, 19.21it/s]
Loading 0:  86%|████████▌ | 313/363 [00:09<00:02, 24.10it/s]
Loading 0:  89%|████████▊ | 322/363 [00:09<00:01, 28.92it/s]
Loading 0:  91%|█████████ | 331/363 [00:09<00:00, 34.25it/s]
Loading 0:  94%|█████████▎| 340/363 [00:09<00:00, 38.91it/s]
Loading 0:  96%|█████████▌| 349/363 [00:10<00:00, 42.05it/s]
Loading 0:  99%|█████████▊| 358/363 [00:10<00:00, 46.14it/s]
                                                            

Job rinen0721-mistral-dpo-0213-m3-v2-mkmlizer completed after 216.51s with status: succeeded
Stopping job with name rinen0721-mistral-dpo-0213-m3-v2-mkmlizer
Pipeline stage MKMLizer completed in 217.00s
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 rinen0721-mistral-dpo-0213-m3-v2
Waiting for inference service rinen0721-mistral-dpo-0213-m3-v2 to be ready
Inference service rinen0721-mistral-dpo-0213-m3-v2 ready after 200.7625274658203s
Pipeline stage MKMLDeployer completed in 201.26s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.5406713485717773s
Received healthy response to inference request in 1.8660492897033691s
Received healthy response to inference request in 1.165642499923706s
Received healthy response to inference request in 1.341501235961914s
Received healthy response to inference request in 1.4107599258422852s
5 requests
0 failed requests
5th percentile: 1.2008142471313477
10th percentile: 1.2359859943389893
20th percentile: 1.3063294887542725
30th percentile: 1.3553529739379884
40th percentile: 1.3830564498901368
50th percentile: 1.4107599258422852
60th percentile: 1.462724494934082
70th percentile: 1.514689064025879
80th percentile: 1.6057469367980957
90th percentile: 1.7358981132507325
95th percentile: 1.8009737014770508
99th percentile: 1.8530341720581054
mean time: 1.4649248600006104
Pipeline stage StressChecker completed in 8.83s
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 0.61s
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-0213-m3_v2 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
Pipeline stage OfflineFamilyFriendlyScorer completed in 2502.26s
Shutdown handler de-registered
rinen0721-mistral-dpo-0213-m3_v2 status is now inactive due to auto deactivation removed underperforming models
rinen0721-mistral-dpo-0213-m3_v2 status is now torndown due to DeploymentManager action
rinen0721-mistral-dpo-0213-m3_v2 status is now torndown due to DeploymentManager action
rinen0721-mistral-dpo-0213-m3_v2 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1