alexxi19-ft-v1-violet

developer_uid: leosheng

submission_id: alexxi19-ft-v1-violet_v3

model_name: alexxi19-ft-v1-violet_v1

model_group: alexxi19/ft-v1-violet

status: torndown

timestamp: 2025-02-03T16:36:54+00:00

num_battles: 6452

num_wins: 2808

celo_rating: 1228.03

family_friendly_score: 0.5731999999999999

family_friendly_standard_error: 0.00699488041355962

submission_type: basic

model_repo: alexxi19/ft-v1-violet

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

display_name: alexxi19-ft-v1-violet_v1

is_internal_developer: False

language_model: alexxi19/ft-v1-violet

model_size: 13B

ranking_group: single

us_pacific_date: 2025-02-03

win_ratio: 0.43521388716677

generation_params: {'temperature': 0.95, 'top_p': 0.87, 'min_p': 0.05, 'top_k': 15, 'presence_penalty': 0.0, 'frequency_penalty': 0.35, 'stopping_words': ['\n', '<|im_end|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{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 alexxi19-ft-v1-violet-v3-mkmlizer
Waiting for job on alexxi19-ft-v1-violet-v3-mkmlizer to finish
alexxi19-ft-v1-violet-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alexxi19-ft-v1-violet-v3-mkmlizer: ║     _____            __           __                                ║
alexxi19-ft-v1-violet-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
alexxi19-ft-v1-violet-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
alexxi19-ft-v1-violet-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
alexxi19-ft-v1-violet-v3-mkmlizer: ║       /___/                                                         ║
alexxi19-ft-v1-violet-v3-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-violet-v3-mkmlizer: ║  Version: 0.11.12                                                   ║
alexxi19-ft-v1-violet-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
alexxi19-ft-v1-violet-v3-mkmlizer: ║  https://mk1.ai                                                     ║
alexxi19-ft-v1-violet-v3-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-violet-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
alexxi19-ft-v1-violet-v3-mkmlizer: ║  belonging to:                                                      ║
alexxi19-ft-v1-violet-v3-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-violet-v3-mkmlizer: ║  Chai Research Corp.                                                ║
alexxi19-ft-v1-violet-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
alexxi19-ft-v1-violet-v3-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
alexxi19-ft-v1-violet-v3-mkmlizer: ║                                                                     ║
alexxi19-ft-v1-violet-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alexxi19-ft-v1-violet-v3-mkmlizer: Downloaded to shared memory in 35.180s
alexxi19-ft-v1-violet-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpehyom__6, device:0
alexxi19-ft-v1-violet-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alexxi19-ft-v1-violet-v3-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.
alexxi19-ft-v1-violet-v3-mkmlizer:   tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
alexxi19-ft-v1-violet-v3-mkmlizer: quantized model in 35.752s
alexxi19-ft-v1-violet-v3-mkmlizer: Processed model alexxi19/ft-v1-violet in 70.932s
alexxi19-ft-v1-violet-v3-mkmlizer: creating bucket guanaco-mkml-models
alexxi19-ft-v1-violet-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alexxi19-ft-v1-violet-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alexxi19-ft-v1-violet-v3
alexxi19-ft-v1-violet-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alexxi19-ft-v1-violet-v3/tokenizer.json
alexxi19-ft-v1-violet-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alexxi19-ft-v1-violet-v3/flywheel_model.0.safetensors
alexxi19-ft-v1-violet-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:07, 48.68it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:05, 62.76it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:04, 68.72it/s]
Loading 0:   9%|▉         | 34/363 [00:00<00:04, 74.86it/s]
Loading 0:  12%|█▏        | 43/363 [00:00<00:04, 78.01it/s]
Loading 0:  14%|█▍        | 52/363 [00:00<00:04, 77.48it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:16, 18.63it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:11, 24.68it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:08, 31.59it/s]
Loading 0:  24%|██▍       | 88/363 [00:02<00:07, 39.22it/s]
Loading 0:  27%|██▋       | 97/363 [00:02<00:05, 46.79it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:04, 53.43it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:04, 57.94it/s]
Loading 0:  34%|███▍      | 124/363 [00:02<00:03, 60.52it/s]
Loading 0:  37%|███▋      | 133/363 [00:02<00:03, 66.21it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:11, 19.18it/s]
Loading 0:  42%|████▏     | 151/363 [00:04<00:08, 24.79it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:06, 31.44it/s]
Loading 0:  47%|████▋     | 169/363 [00:04<00:05, 37.92it/s]
Loading 0:  49%|████▉     | 178/363 [00:04<00:04, 42.94it/s]
Loading 0:  52%|█████▏    | 187/363 [00:04<00:03, 48.16it/s]
Loading 0:  54%|█████▍    | 196/363 [00:04<00:03, 55.03it/s]
Loading 0:  56%|█████▋    | 205/363 [00:04<00:02, 61.16it/s]
Loading 0:  59%|█████▉    | 214/363 [00:05<00:02, 65.22it/s]
Loading 0:  61%|██████▏   | 223/363 [00:06<00:07, 19.84it/s]
Loading 0:  66%|██████▌   | 238/363 [00:06<00:04, 29.97it/s]
Loading 0:  69%|██████▉   | 250/363 [00:06<00:02, 37.73it/s]
Loading 0:  71%|███████▏  | 259/363 [00:06<00:02, 43.02it/s]
Loading 0:  74%|███████▍  | 268/363 [00:06<00:01, 49.73it/s]
Loading 0:  78%|███████▊  | 283/363 [00:06<00:01, 62.62it/s]
Loading 0:  81%|████████▏ | 295/363 [00:07<00:01, 67.55it/s]
Loading 0:  84%|████████▎ | 304/363 [00:08<00:02, 23.35it/s]
Loading 0:  86%|████████▌ | 313/363 [00:08<00:01, 28.73it/s]
Loading 0:  89%|████████▉ | 323/363 [00:08<00:01, 36.33it/s]
Loading 0:  93%|█████████▎| 337/363 [00:08<00:00, 47.53it/s]
Loading 0:  95%|█████████▌| 346/363 [00:08<00:00, 53.39it/s]
Loading 0:  98%|█████████▊| 355/363 [00:08<00:00, 58.88it/s]
                                                            
Job alexxi19-ft-v1-violet-v3-mkmlizer completed after 93.74s with status: succeeded
Stopping job with name alexxi19-ft-v1-violet-v3-mkmlizer
Pipeline stage MKMLizer completed in 94.23s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service alexxi19-ft-v1-violet-v3
Waiting for inference service alexxi19-ft-v1-violet-v3 to be ready
Inference service alexxi19-ft-v1-violet-v3 ready after 160.52388978004456s
Pipeline stage MKMLDeployer completed in 161.03s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8589973449707031s
Received healthy response to inference request in 1.8515245914459229s
Received healthy response to inference request in 1.6395223140716553s
Received healthy response to inference request in 1.625605821609497s
Received healthy response to inference request in 1.8348960876464844s
5 requests
0 failed requests
5th percentile: 1.6283891201019287
10th percentile: 1.6311724185943604
20th percentile: 1.6367390155792236
30th percentile: 1.6785970687866212
40th percentile: 1.7567465782165528
50th percentile: 1.8348960876464844
60th percentile: 1.8415474891662598
70th percentile: 1.8481988906860352
80th percentile: 1.8530191421508788
90th percentile: 1.856008243560791
95th percentile: 1.8575027942657472
99th percentile: 1.858698434829712
mean time: 1.7621092319488525
Pipeline stage StressChecker completed in 10.26s
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 0.64s
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
alexxi19-ft-v1-violet_v3 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 2645.28s
Shutdown handler de-registered
alexxi19-ft-v1-violet_v3 status is now inactive due to auto deactivation removed underperforming models
alexxi19-ft-v1-violet_v3 status is now torndown due to DeploymentManager action