rica40325-mistral-13b-2452

developer_uid: rica40325

submission_id: rica40325-mistral-13b-2452_v5

model_name: rica40325-1000dpo_v1

model_group: rica40325/mistral-13B-24

status: torndown

timestamp: 2025-03-18T08:44:38+00:00

num_battles: 6737

num_wins: 3147

celo_rating: 1255.53

family_friendly_score: 0.5904

family_friendly_standard_error: 0.006954535786089536

submission_type: basic

model_repo: rica40325/mistral-13B-2452

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6070471398878549, 'latency_mean': 1.6472554540634154, 'latency_p50': 1.654995083808899, 'latency_p90': 1.8070890188217164}, {'batch_size': 3, 'throughput': 1.1178997334662035, 'latency_mean': 2.6802190101146697, 'latency_p50': 2.678210496902466, 'latency_p90': 2.9351965188980103}, {'batch_size': 5, 'throughput': 1.3497971288355979, 'latency_mean': 3.6847093653678895, 'latency_p50': 3.6716811656951904, 'latency_p90': 4.133521223068238}, {'batch_size': 6, 'throughput': 1.4295660121654032, 'latency_mean': 4.181218054294586, 'latency_p50': 4.180471181869507, 'latency_p90': 4.738634419441223}, {'batch_size': 8, 'throughput': 1.4963419347868279, 'latency_mean': 5.30425641655922, 'latency_p50': 5.25636088848114, 'latency_p90': 6.046286463737488}, {'batch_size': 10, 'throughput': 1.519604967719874, 'latency_mean': 6.531267719268799, 'latency_p50': 6.516230463981628, 'latency_p90': 7.400650691986084}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: rica40325-1000dpo_v1

is_internal_developer: False

language_model: rica40325/mistral-13B-2452

model_size: 13B

ranking_group: single

throughput_3p7s: 1.36

us_pacific_date: 2025-03-18

win_ratio: 0.46712186433130476

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 rica40325-mistral-13b-2452-v5-mkmlizer
Waiting for job on rica40325-mistral-13b-2452-v5-mkmlizer to finish
rica40325-mistral-13b-2452-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rica40325-mistral-13b-2452-v5-mkmlizer: ║     _____            __           __                                ║
rica40325-mistral-13b-2452-v5-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rica40325-mistral-13b-2452-v5-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rica40325-mistral-13b-2452-v5-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rica40325-mistral-13b-2452-v5-mkmlizer: ║       /___/                                                         ║
rica40325-mistral-13b-2452-v5-mkmlizer: ║                                                                     ║
rica40325-mistral-13b-2452-v5-mkmlizer: ║  Version: 0.12.8                                                    ║
rica40325-mistral-13b-2452-v5-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rica40325-mistral-13b-2452-v5-mkmlizer: ║  https://mk1.ai                                                     ║
rica40325-mistral-13b-2452-v5-mkmlizer: ║                                                                     ║
rica40325-mistral-13b-2452-v5-mkmlizer: ║  The license key for the current software has been verified as      ║
rica40325-mistral-13b-2452-v5-mkmlizer: ║  belonging to:                                                      ║
rica40325-mistral-13b-2452-v5-mkmlizer: ║                                                                     ║
rica40325-mistral-13b-2452-v5-mkmlizer: ║  Chai Research Corp.                                                ║
rica40325-mistral-13b-2452-v5-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rica40325-mistral-13b-2452-v5-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
rica40325-mistral-13b-2452-v5-mkmlizer: ║                                                                     ║
rica40325-mistral-13b-2452-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rica40325-mistral-13b-2452-v5-mkmlizer: Downloaded to shared memory in 42.777s
rica40325-mistral-13b-2452-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpsxvv8glz, device:0
rica40325-mistral-13b-2452-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rica40325-mistral-13b-2452-v5-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.
rica40325-mistral-13b-2452-v5-mkmlizer:   tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
rica40325-mistral-13b-2452-v5-mkmlizer: quantized model in 39.460s
rica40325-mistral-13b-2452-v5-mkmlizer: Processed model rica40325/mistral-13B-2452 in 82.238s
rica40325-mistral-13b-2452-v5-mkmlizer: creating bucket guanaco-mkml-models
rica40325-mistral-13b-2452-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rica40325-mistral-13b-2452-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rica40325-mistral-13b-2452-v5
rica40325-mistral-13b-2452-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rica40325-mistral-13b-2452-v5/config.json
rica40325-mistral-13b-2452-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rica40325-mistral-13b-2452-v5/special_tokens_map.json
rica40325-mistral-13b-2452-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rica40325-mistral-13b-2452-v5/tokenizer_config.json
rica40325-mistral-13b-2452-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rica40325-mistral-13b-2452-v5/tokenizer.json
rica40325-mistral-13b-2452-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rica40325-mistral-13b-2452-v5/flywheel_model.0.safetensors
rica40325-mistral-13b-2452-v5-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:10, 35.24it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 48.32it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:06, 52.25it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 53.68it/s]
Loading 0:  11%|█         | 40/363 [00:00<00:06, 53.25it/s]
Loading 0:  13%|█▎        | 49/363 [00:00<00:05, 52.51it/s]
Loading 0:  16%|█▌        | 58/363 [00:01<00:05, 51.36it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:19, 15.30it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:16, 17.79it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:12, 23.45it/s]
Loading 0:  24%|██▍       | 88/363 [00:02<00:09, 28.41it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:08, 32.99it/s]
Loading 0:  29%|██▉       | 106/363 [00:03<00:06, 37.01it/s]
Loading 0:  32%|███▏      | 115/363 [00:03<00:06, 39.66it/s]
Loading 0:  34%|███▍      | 124/363 [00:03<00:05, 41.44it/s]
Loading 0:  37%|███▋      | 133/363 [00:03<00:05, 43.36it/s]
Loading 0:  38%|███▊      | 139/363 [00:03<00:04, 46.10it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:14, 15.48it/s]
Loading 0:  42%|████▏     | 151/363 [00:05<00:11, 19.11it/s]
Loading 0:  44%|████▍     | 160/363 [00:05<00:07, 26.45it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:05, 34.18it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:04, 41.88it/s]
Loading 0:  52%|█████▏    | 187/363 [00:05<00:03, 48.47it/s]
Loading 0:  54%|█████▍    | 196/363 [00:05<00:03, 54.41it/s]
Loading 0:  56%|█████▋    | 205/363 [00:05<00:02, 53.91it/s]
Loading 0:  58%|█████▊    | 212/363 [00:06<00:02, 55.21it/s]
Loading 0:  60%|██████    | 219/363 [00:06<00:02, 57.36it/s]
Loading 0:  62%|██████▏   | 226/363 [00:07<00:08, 15.83it/s]
Loading 0:  64%|██████▍   | 232/363 [00:07<00:07, 18.54it/s]
Loading 0:  66%|██████▋   | 241/363 [00:07<00:05, 24.06it/s]
Loading 0:  69%|██████▊   | 249/363 [00:07<00:03, 30.60it/s]
Loading 0:  71%|███████   | 256/363 [00:08<00:03, 33.45it/s]
Loading 0:  73%|███████▎  | 265/363 [00:08<00:02, 38.65it/s]
Loading 0:  75%|███████▌  | 274/363 [00:08<00:02, 41.66it/s]
Loading 0:  77%|███████▋  | 280/363 [00:08<00:01, 44.02it/s]
Loading 0:  79%|███████▉  | 286/363 [00:08<00:01, 40.57it/s]
Loading 0:  81%|████████▏ | 295/363 [00:08<00:01, 43.75it/s]
Loading 0:  83%|████████▎ | 302/363 [00:08<00:01, 48.76it/s]
Loading 0:  85%|████████▍ | 308/363 [00:10<00:03, 15.41it/s]
Loading 0:  86%|████████▌ | 313/363 [00:10<00:02, 17.22it/s]
Loading 0:  88%|████████▊ | 319/363 [00:10<00:02, 21.40it/s]
Loading 0:  89%|████████▉ | 324/363 [00:10<00:01, 25.02it/s]
Loading 0:  91%|█████████ | 331/363 [00:10<00:01, 28.59it/s]
Loading 0:  94%|█████████▎| 340/363 [00:10<00:00, 33.95it/s]
Loading 0:  96%|█████████▌| 347/363 [00:11<00:00, 39.83it/s]
Loading 0:  98%|█████████▊| 355/363 [00:11<00:00, 42.11it/s]
Loading 0: 100%|██████████| 363/363 [00:17<00:00,  3.60it/s]
                                                            
Job rica40325-mistral-13b-2452-v5-mkmlizer completed after 114.36s with status: succeeded
Stopping job with name rica40325-mistral-13b-2452-v5-mkmlizer
Pipeline stage MKMLizer completed in 114.86s
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 rica40325-mistral-13b-2452-v5
Waiting for inference service rica40325-mistral-13b-2452-v5 to be ready
Inference service rica40325-mistral-13b-2452-v5 ready after 90.33782029151917s
Pipeline stage MKMLDeployer completed in 90.90s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6062943935394287s
Received healthy response to inference request in 1.6724750995635986s
Received healthy response to inference request in 1.511559009552002s
Received healthy response to inference request in 1.6216864585876465s
Received healthy response to inference request in 1.9616124629974365s
5 requests
0 failed requests
5th percentile: 1.5335844993591308
10th percentile: 1.5556099891662598
20th percentile: 1.5996609687805177
30th percentile: 1.6318441867828368
40th percentile: 1.6521596431732177
50th percentile: 1.6724750995635986
60th percentile: 1.7881300449371338
70th percentile: 1.903784990310669
80th percentile: 2.090548849105835
90th percentile: 2.3484216213226317
95th percentile: 2.47735800743103
99th percentile: 2.580507116317749
mean time: 1.8747254848480224
Pipeline stage StressChecker completed in 10.73s
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 0.74s
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 0.71s
Shutdown handler de-registered
rica40325-mistral-13b-2452_v5 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 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rica40325-mistral-13b-2452-v5-profiler
Waiting for inference service rica40325-mistral-13b-2452-v5-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 2691.29s
Shutdown handler de-registered
rica40325-mistral-13b-2452_v5 status is now inactive due to auto deactivation removed underperforming models
rica40325-mistral-13b-2452_v5 status is now torndown due to DeploymentManager action