developer_uid: rinen0721
submission_id: rinen0721-mistral-dpo-0213-m3_v1
model_name: rinen0721-mistral-dpo-0213-m3_v1
model_group: rinen0721/Mistral-dpo-02
status: torndown
timestamp: 2025-02-13T10:54:43+00:00
num_battles: 6742
num_wins: 3020
celo_rating: 1241.52
family_friendly_score: 0.5851999999999999
family_friendly_standard_error: 0.006967653263474008
submission_type: basic
model_repo: rinen0721/Mistral-dpo-0213-m3
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
display_name: rinen0721-mistral-dpo-0213-m3_v1
is_internal_developer: False
language_model: rinen0721/Mistral-dpo-0213-m3
model_size: 13B
ranking_group: single
us_pacific_date: 2025-02-13
win_ratio: 0.44793829724117473
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-0213-m3-v1-mkmlizer
Waiting for job on rinen0721-mistral-dpo-0213-m3-v1-mkmlizer to finish
rinen0721-mistral-dpo-0213-m3-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rinen0721-mistral-dpo-0213-m3-v1-mkmlizer: ║ _____ __ __ ║
rinen0721-mistral-dpo-0213-m3-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rinen0721-mistral-dpo-0213-m3-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rinen0721-mistral-dpo-0213-m3-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rinen0721-mistral-dpo-0213-m3-v1-mkmlizer: ║ /___/ ║
rinen0721-mistral-dpo-0213-m3-v1-mkmlizer: ║ ║
rinen0721-mistral-dpo-0213-m3-v1-mkmlizer: ║ Version: 0.12.8 ║
rinen0721-mistral-dpo-0213-m3-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rinen0721-mistral-dpo-0213-m3-v1-mkmlizer: ║ https://mk1.ai ║
rinen0721-mistral-dpo-0213-m3-v1-mkmlizer: ║ ║
rinen0721-mistral-dpo-0213-m3-v1-mkmlizer: ║ The license key for the current software has been verified as ║
rinen0721-mistral-dpo-0213-m3-v1-mkmlizer: ║ belonging to: ║
rinen0721-mistral-dpo-0213-m3-v1-mkmlizer: ║ ║
rinen0721-mistral-dpo-0213-m3-v1-mkmlizer: ║ Chai Research Corp. ║
rinen0721-mistral-dpo-0213-m3-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rinen0721-mistral-dpo-0213-m3-v1-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
rinen0721-mistral-dpo-0213-m3-v1-mkmlizer: ║ ║
rinen0721-mistral-dpo-0213-m3-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rinen0721-mistral-dpo-0213-m3-v1-mkmlizer: Downloaded to shared memory in 57.713s
rinen0721-mistral-dpo-0213-m3-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpfqhdatz9, device:0
rinen0721-mistral-dpo-0213-m3-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rinen0721-mistral-dpo-0213-m3-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-0213-m3-v1-mkmlizer: tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
rinen0721-mistral-dpo-0213-m3-v1-mkmlizer: quantized model in 35.579s
rinen0721-mistral-dpo-0213-m3-v1-mkmlizer: Processed model rinen0721/Mistral-dpo-0213-m3 in 93.292s
rinen0721-mistral-dpo-0213-m3-v1-mkmlizer: creating bucket guanaco-mkml-models
rinen0721-mistral-dpo-0213-m3-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rinen0721-mistral-dpo-0213-m3-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rinen0721-mistral-dpo-0213-m3-v1
rinen0721-mistral-dpo-0213-m3-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rinen0721-mistral-dpo-0213-m3-v1/config.json
rinen0721-mistral-dpo-0213-m3-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rinen0721-mistral-dpo-0213-m3-v1/special_tokens_map.json
rinen0721-mistral-dpo-0213-m3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rinen0721-mistral-dpo-0213-m3-v1/tokenizer_config.json
rinen0721-mistral-dpo-0213-m3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rinen0721-mistral-dpo-0213-m3-v1/tokenizer.json
rinen0721-mistral-dpo-0213-m3-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rinen0721-mistral-dpo-0213-m3-v1/flywheel_model.0.safetensors
rinen0721-mistral-dpo-0213-m3-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 2%|▏ | 7/363 [00:00<00:07, 46.83it/s] Loading 0: 4%|▍ | 16/363 [00:00<00:05, 65.44it/s] Loading 0: 7%|▋ | 26/363 [00:00<00:04, 78.39it/s] Loading 0: 10%|▉ | 35/363 [00:00<00:04, 81.56it/s] Loading 0: 12%|█▏ | 44/363 [00:00<00:03, 83.89it/s] Loading 0: 15%|█▍ | 53/363 [00:00<00:03, 79.32it/s] Loading 0: 17%|█▋ | 62/363 [00:01<00:14, 20.62it/s] Loading 0: 20%|█▉ | 71/363 [00:01<00:10, 27.25it/s] Loading 0: 22%|██▏ | 79/363 [00:01<00:08, 33.62it/s] Loading 0: 24%|██▍ | 88/363 [00:02<00:06, 41.65it/s] Loading 0: 27%|██▋ | 97/363 [00:02<00:05, 48.44it/s] Loading 0: 29%|██▉ | 106/363 [00:02<00:04, 54.31it/s] Loading 0: 32%|███▏ | 115/363 [00:02<00:04, 61.30it/s] Loading 0: 34%|███▍ | 124/363 [00:02<00:03, 67.31it/s] Loading 0: 37%|███▋ | 133/363 [00:02<00:03, 71.03it/s] Loading 0: 39%|███▉ | 142/363 [00:03<00:10, 20.43it/s] Loading 0: 42%|████▏ | 151/363 [00:03<00:08, 26.47it/s] Loading 0: 44%|████▍ | 160/363 [00:04<00:06, 33.50it/s] Loading 0: 47%|████▋ | 169/363 [00:04<00:04, 41.06it/s] Loading 0: 49%|████▉ | 178/363 [00:04<00:03, 47.49it/s] Loading 0: 52%|█████▏ | 187/363 [00:04<00:03, 52.46it/s] Loading 0: 54%|█████▍ | 196/363 [00:04<00:02, 56.99it/s] Loading 0: 56%|█████▋ | 205/363 [00:04<00:02, 62.97it/s] Loading 0: 59%|█████▉ | 214/363 [00:04<00:02, 68.05it/s] Loading 0: 61%|██████▏ | 223/363 [00:05<00:06, 20.63it/s] Loading 0: 64%|██████▍ | 232/363 [00:05<00:04, 26.48it/s] Loading 0: 66%|██████▋ | 241/363 [00:06<00:03, 33.25it/s] Loading 0: 69%|██████▉ | 250/363 [00:06<00:02, 40.62it/s] Loading 0: 71%|███████▏ | 259/363 [00:06<00:02, 46.65it/s] Loading 0: 74%|███████▍ | 268/363 [00:06<00:01, 52.42it/s] Loading 0: 76%|███████▋ | 277/363 [00:06<00:01, 59.44it/s] Loading 0: 79%|███████▉ | 286/363 [00:06<00:01, 63.40it/s] Loading 0: 81%|████████▏ | 295/363 [00:06<00:00, 68.66it/s] Loading 0: 84%|████████▎ | 304/363 [00:07<00:02, 20.58it/s] Loading 0: 86%|████████▌ | 313/363 [00:08<00:01, 26.36it/s] Loading 0: 89%|████████▊ | 322/363 [00:08<00:01, 32.96it/s] Loading 0: 91%|█████████ | 331/363 [00:08<00:00, 40.00it/s] Loading 0: 93%|█████████▎| 339/363 [00:08<00:00, 46.00it/s] Loading 0: 96%|█████████▌| 347/363 [00:08<00:00, 50.29it/s] Loading 0: 98%|█████████▊| 355/363 [00:08<00:00, 55.44it/s] Loading 0: 100%|██████████| 363/363 [00:14<00:00, 4.13it/s]
Job rinen0721-mistral-dpo-0213-m3-v1-mkmlizer completed after 124.26s with status: succeeded
Stopping job with name rinen0721-mistral-dpo-0213-m3-v1-mkmlizer
Pipeline stage MKMLizer completed in 124.77s
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-v1
Waiting for inference service rinen0721-mistral-dpo-0213-m3-v1 to be ready
Inference service rinen0721-mistral-dpo-0213-m3-v1 ready after 170.61610174179077s
Pipeline stage MKMLDeployer completed in 171.16s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0983338356018066s
Failed to get response for submission dtnewman-20250212-c-4ep_25732_v1: HTTPConnectionPool(host='dtnewman-20250212-c-4ep-25732-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Received healthy response to inference request in 1.455744981765747s
Received healthy response to inference request in 1.7967545986175537s
Received healthy response to inference request in 1.6104300022125244s
Received healthy response to inference request in 1.7805769443511963s
5 requests
0 failed requests
5th percentile: 1.4866819858551026
10th percentile: 1.517618989944458
20th percentile: 1.579492998123169
30th percentile: 1.6444593906402587
40th percentile: 1.7125181674957275
50th percentile: 1.7805769443511963
60th percentile: 1.7870480060577392
70th percentile: 1.7935190677642823
80th percentile: 1.8570704460144043
90th percentile: 1.9777021408081055
95th percentile: 2.038017988204956
99th percentile: 2.0862706661224366
mean time: 1.7483680725097657
Pipeline stage StressChecker completed in 9.83s
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 0.65s
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 0.62s
Shutdown handler de-registered
rinen0721-mistral-dpo-0213-m3_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-0213-m3-v1-profiler
Waiting for inference service rinen0721-mistral-dpo-0213-m3-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 4685.36s
Shutdown handler de-registered
rinen0721-mistral-dpo-0213-m3_v1 status is now inactive due to auto deactivation removed underperforming models
rinen0721-mistral-dpo-0213-m3_v1 status is now torndown due to DeploymentManager action
rinen0721-mistral-dpo-0213-m3_v1 status is now torndown due to DeploymentManager action
rinen0721-mistral-dpo-0213-m3_v1 status is now torndown due to DeploymentManager action