developer_uid: rinen0721
submission_id: rinen0721-mistral-dpo-0213_v1
model_name: rinen0721-mistral-dpo-0213_v1
model_group: rinen0721/Mistral-dpo-02
status: torndown
timestamp: 2025-02-13T03:00:38+00:00
num_battles: 6341
num_wins: 2768
celo_rating: 1235.06
family_friendly_score: 0.5558000000000001
family_friendly_standard_error: 0.0070268963276826565
submission_type: basic
model_repo: rinen0721/Mistral-dpo-0213
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_v1
is_internal_developer: False
language_model: rinen0721/Mistral-dpo-0213
model_size: 13B
ranking_group: single
us_pacific_date: 2025-02-12
win_ratio: 0.43652420753824317
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-v1-mkmlizer
Waiting for job on rinen0721-mistral-dpo-0213-v1-mkmlizer to finish
rinen0721-mistral-dpo-0213-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rinen0721-mistral-dpo-0213-v1-mkmlizer: ║ _____ __ __ ║
rinen0721-mistral-dpo-0213-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rinen0721-mistral-dpo-0213-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rinen0721-mistral-dpo-0213-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rinen0721-mistral-dpo-0213-v1-mkmlizer: ║ /___/ ║
rinen0721-mistral-dpo-0213-v1-mkmlizer: ║ ║
rinen0721-mistral-dpo-0213-v1-mkmlizer: ║ Version: 0.12.8 ║
rinen0721-mistral-dpo-0213-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rinen0721-mistral-dpo-0213-v1-mkmlizer: ║ https://mk1.ai ║
rinen0721-mistral-dpo-0213-v1-mkmlizer: ║ ║
rinen0721-mistral-dpo-0213-v1-mkmlizer: ║ The license key for the current software has been verified as ║
rinen0721-mistral-dpo-0213-v1-mkmlizer: ║ belonging to: ║
rinen0721-mistral-dpo-0213-v1-mkmlizer: ║ ║
rinen0721-mistral-dpo-0213-v1-mkmlizer: ║ Chai Research Corp. ║
rinen0721-mistral-dpo-0213-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rinen0721-mistral-dpo-0213-v1-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
rinen0721-mistral-dpo-0213-v1-mkmlizer: ║ ║
rinen0721-mistral-dpo-0213-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rinen0721-mistral-dpo-0213-v1-mkmlizer: Downloaded to shared memory in 51.651s
rinen0721-mistral-dpo-0213-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmptsb295mz, device:0
rinen0721-mistral-dpo-0213-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rinen0721-mistral-dpo-0213-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-v1-mkmlizer: tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
Failed to get response for submission dtnewman-daniel-2025021_12303_v6: HTTPConnectionPool(host='dtnewman-daniel-2025021-12303-v6-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
rinen0721-mistral-dpo-0213-v1-mkmlizer: quantized model in 36.055s
rinen0721-mistral-dpo-0213-v1-mkmlizer: Processed model rinen0721/Mistral-dpo-0213 in 87.706s
rinen0721-mistral-dpo-0213-v1-mkmlizer: creating bucket guanaco-mkml-models
rinen0721-mistral-dpo-0213-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rinen0721-mistral-dpo-0213-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rinen0721-mistral-dpo-0213-v1
rinen0721-mistral-dpo-0213-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rinen0721-mistral-dpo-0213-v1/config.json
rinen0721-mistral-dpo-0213-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rinen0721-mistral-dpo-0213-v1/special_tokens_map.json
rinen0721-mistral-dpo-0213-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rinen0721-mistral-dpo-0213-v1/tokenizer_config.json
rinen0721-mistral-dpo-0213-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rinen0721-mistral-dpo-0213-v1/tokenizer.json
rinen0721-mistral-dpo-0213-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rinen0721-mistral-dpo-0213-v1/flywheel_model.0.safetensors
rinen0721-mistral-dpo-0213-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 2%|▏ | 7/363 [00:00<00:07, 48.15it/s] Loading 0: 4%|▍ | 16/363 [00:00<00:05, 68.50it/s] Loading 0: 7%|▋ | 25/363 [00:00<00:04, 71.90it/s] Loading 0: 9%|▉ | 34/363 [00:00<00:04, 67.03it/s] Loading 0: 12%|█▏ | 43/363 [00:00<00:04, 72.46it/s] Loading 0: 14%|█▍ | 52/363 [00:00<00:04, 75.85it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:15, 19.01it/s] Loading 0: 19%|█▉ | 70/363 [00:02<00:11, 24.97it/s] Loading 0: 22%|██▏ | 79/363 [00:02<00:08, 32.03it/s] Loading 0: 24%|██▍ | 88/363 [00:02<00:06, 39.54it/s] Loading 0: 27%|██▋ | 97/363 [00:02<00:05, 46.98it/s] Loading 0: 29%|██▉ | 106/363 [00:02<00:05, 50.78it/s] Loading 0: 32%|███▏ | 115/363 [00:02<00:04, 57.06it/s] Loading 0: 34%|███▍ | 124/363 [00:02<00:03, 62.95it/s] Loading 0: 37%|███▋ | 133/363 [00:02<00:03, 68.01it/s] Loading 0: 39%|███▉ | 142/363 [00:04<00:11, 19.46it/s] Loading 0: 42%|████▏ | 151/363 [00:04<00:08, 25.22it/s] Loading 0: 44%|████▍ | 160/363 [00:04<00:06, 31.86it/s] Loading 0: 47%|████▋ | 169/363 [00:04<00:04, 38.82it/s] Loading 0: 49%|████▉ | 178/363 [00:04<00:04, 44.32it/s] Loading 0: 52%|█████▏ | 187/363 [00:04<00:03, 48.96it/s] Loading 0: 54%|█████▍ | 196/363 [00:04<00:03, 55.64it/s] Loading 0: 56%|█████▋ | 205/363 [00:04<00:02, 61.56it/s] Loading 0: 59%|█████▉ | 214/363 [00:05<00:02, 64.78it/s] Loading 0: 61%|██████▏ | 223/363 [00:06<00:07, 19.75it/s] Loading 0: 64%|██████▍ | 232/363 [00:06<00:05, 25.52it/s] Loading 0: 66%|██████▋ | 241/363 [00:06<00:03, 32.21it/s] Loading 0: 68%|██████▊ | 248/363 [00:06<00:03, 37.16it/s] Loading 0: 71%|███████ | 256/363 [00:06<00:02, 41.37it/s] Loading 0: 73%|███████▎ | 265/363 [00:06<00:02, 48.87it/s] Loading 0: 75%|███████▌ | 274/363 [00:06<00:01, 56.22it/s] Loading 0: 78%|███████▊ | 283/363 [00:07<00:01, 62.23it/s] Loading 0: 80%|████████ | 292/363 [00:07<00:01, 64.92it/s] Loading 0: 83%|████████▎ | 301/363 [00:07<00:00, 68.11it/s] Loading 0: 85%|████████▌ | 309/363 [00:08<00:02, 21.23it/s] Loading 0: 87%|████████▋ | 315/363 [00:08<00:01, 24.77it/s] Loading 0: 89%|████████▊ | 322/363 [00:08<00:01, 29.79it/s] Loading 0: 91%|█████████ | 331/363 [00:08<00:00, 37.18it/s] Loading 0: 94%|█████████▎| 340/363 [00:08<00:00, 43.99it/s] Loading 0: 96%|█████████▌| 349/363 [00:08<00:00, 51.74it/s] Loading 0: 99%|█████████▊| 358/363 [00:08<00:00, 58.60it/s]
Job rinen0721-mistral-dpo-0213-v1-mkmlizer completed after 114.25s with status: succeeded
Stopping job with name rinen0721-mistral-dpo-0213-v1-mkmlizer
Pipeline stage MKMLizer completed in 114.74s
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 rinen0721-mistral-dpo-0213-v1
Waiting for inference service rinen0721-mistral-dpo-0213-v1 to be ready
Failed to get response for submission dtnewman-daniel-2025021_12303_v6: HTTPConnectionPool(host='dtnewman-daniel-2025021-12303-v6-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission dtnewman-daniel-2025021_12303_v7: HTTPConnectionPool(host='dtnewman-daniel-2025021-12303-v7-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service rinen0721-mistral-dpo-0213-v1 ready after 160.60859656333923s
Pipeline stage MKMLDeployer completed in 161.12s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.7532169818878174s
Received healthy response to inference request in 1.413771629333496s
Received healthy response to inference request in 1.5211858749389648s
Received healthy response to inference request in 1.397242784500122s
Received healthy response to inference request in 1.1654162406921387s
5 requests
0 failed requests
5th percentile: 1.2117815494537354
10th percentile: 1.2581468582153321
20th percentile: 1.3508774757385253
30th percentile: 1.400548553466797
40th percentile: 1.4071600914001465
50th percentile: 1.413771629333496
60th percentile: 1.4567373275756836
70th percentile: 1.4997030258178712
80th percentile: 1.5675920963287353
90th percentile: 1.6604045391082765
95th percentile: 1.706810760498047
99th percentile: 1.7439357376098632
mean time: 1.4501667022705078
Pipeline stage StressChecker completed in 8.56s
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 0.94s
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
rinen0721-mistral-dpo-0213_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 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rinen0721-mistral-dpo-0213-v1-profiler
Waiting for inference service rinen0721-mistral-dpo-0213-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 2610.42s
Shutdown handler de-registered
rinen0721-mistral-dpo-0213_v1 status is now inactive due to auto deactivation removed underperforming models
rinen0721-mistral-dpo-0213_v1 status is now torndown due to DeploymentManager action
rinen0721-mistral-dpo-0213_v1 status is now torndown due to DeploymentManager action
rinen0721-mistral-dpo-0213_v1 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1