developer_uid: huohuo12
submission_id: alexxi19-ft-v1-violet_v12
model_name: alexxi19-ft-v1-violet_v8
model_group: alexxi19/ft-v1-violet
status: torndown
timestamp: 2025-02-11T07:39:15+00:00
num_battles: 5386
num_wins: 2596
celo_rating: 1235.92
family_friendly_score: 0.5871999999999999
family_friendly_standard_error: 0.006962702923434261
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_v8
is_internal_developer: False
language_model: alexxi19/ft-v1-violet
model_size: 13B
ranking_group: single
us_pacific_date: 2025-02-10
win_ratio: 0.48199034533976975
generation_params: {'temperature': 0.7, 'top_p': 0.8, 'min_p': 0.02, 'top_k': 69, 'presence_penalty': 0.8, 'frequency_penalty': 0.4, '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 alexxi19-ft-v1-violet-v12-mkmlizer
Waiting for job on alexxi19-ft-v1-violet-v12-mkmlizer to finish
alexxi19-ft-v1-violet-v12-mkmlizer: Downloaded to shared memory in 31.186s
alexxi19-ft-v1-violet-v12-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpujn7xi82, device:0
alexxi19-ft-v1-violet-v12-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alexxi19-ft-v1-violet-v12-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-v12-mkmlizer:   tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
alexxi19-ft-v1-violet-v12-mkmlizer: quantized model in 38.080s
alexxi19-ft-v1-violet-v12-mkmlizer: Processed model alexxi19/ft-v1-violet in 69.267s
alexxi19-ft-v1-violet-v12-mkmlizer: creating bucket guanaco-mkml-models
alexxi19-ft-v1-violet-v12-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alexxi19-ft-v1-violet-v12-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alexxi19-ft-v1-violet-v12
alexxi19-ft-v1-violet-v12-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alexxi19-ft-v1-violet-v12/tokenizer_config.json
alexxi19-ft-v1-violet-v12-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alexxi19-ft-v1-violet-v12/tokenizer.json
alexxi19-ft-v1-violet-v12-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/alexxi19-ft-v1-violet-v12/flywheel_model.0.safetensors
alexxi19-ft-v1-violet-v12-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:06, 51.09it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:05, 67.12it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:05, 62.87it/s]
Loading 0:   9%|▉         | 34/363 [00:00<00:04, 69.78it/s]
Loading 0:  12%|█▏        | 43/363 [00:00<00:04, 74.11it/s]
Loading 0:  14%|█▍        | 52/363 [00:00<00:04, 73.39it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:15, 19.59it/s]
Loading 0:  19%|█▊        | 68/363 [00:01<00:12, 24.22it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:10, 27.89it/s]
Loading 0:  22%|██▏       | 80/363 [00:02<00:09, 29.38it/s]
Loading 0:  24%|██▍       | 88/363 [00:02<00:07, 34.95it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:06, 41.98it/s]
Loading 0:  28%|██▊       | 102/363 [00:02<00:05, 45.30it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:05, 42.79it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:05, 45.43it/s]
Loading 0:  34%|███▍      | 124/363 [00:03<00:04, 49.50it/s]
Loading 0:  36%|███▌      | 131/363 [00:03<00:04, 53.07it/s]
Loading 0:  38%|███▊      | 137/363 [00:03<00:04, 51.91it/s]
Loading 0:  39%|███▉      | 143/363 [00:04<00:18, 11.62it/s]
Loading 0:  42%|████▏     | 151/363 [00:05<00:13, 15.58it/s]
Loading 0:  43%|████▎     | 157/363 [00:05<00:10, 19.37it/s]
Loading 0:  45%|████▍     | 162/363 [00:05<00:09, 22.07it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:07, 26.79it/s]
Loading 0:  49%|████▉     | 177/363 [00:05<00:05, 34.07it/s]
Loading 0:  50%|█████     | 183/363 [00:05<00:04, 38.37it/s]
Loading 0:  52%|█████▏    | 189/363 [00:05<00:04, 35.09it/s]
Loading 0:  54%|█████▍    | 196/363 [00:06<00:04, 38.72it/s]
Loading 0:  56%|█████▋    | 205/363 [00:06<00:03, 44.65it/s]
Loading 0:  59%|█████▉    | 214/363 [00:06<00:02, 51.30it/s]
Loading 0:  61%|██████▏   | 223/363 [00:07<00:07, 17.56it/s]
Loading 0:  64%|██████▍   | 232/363 [00:07<00:05, 22.53it/s]
Loading 0:  66%|██████▋   | 241/363 [00:07<00:04, 28.51it/s]
Loading 0:  69%|██████▉   | 250/363 [00:07<00:03, 34.58it/s]
Loading 0:  71%|███████▏  | 259/363 [00:08<00:02, 39.36it/s]
Loading 0:  74%|███████▍  | 268/363 [00:08<00:02, 44.61it/s]
Loading 0:  76%|███████▋  | 277/363 [00:08<00:01, 49.01it/s]
Loading 0:  79%|███████▉  | 286/363 [00:08<00:01, 50.49it/s]
Loading 0:  81%|████████▏ | 295/363 [00:08<00:01, 55.47it/s]
Loading 0:  84%|████████▎ | 304/363 [00:09<00:02, 19.95it/s]
Loading 0:  86%|████████▌ | 313/363 [00:09<00:01, 25.14it/s]
Loading 0:  89%|████████▊ | 322/363 [00:10<00:01, 30.43it/s]
Loading 0:  91%|█████████ | 331/363 [00:10<00:00, 35.87it/s]
Loading 0:  94%|█████████▎| 340/363 [00:10<00:00, 40.99it/s]
Loading 0:  96%|█████████▌| 349/363 [00:10<00:00, 44.53it/s]
Loading 0:  99%|█████████▊| 358/363 [00:10<00:00, 47.24it/s]
                                                            

Job alexxi19-ft-v1-violet-v12-mkmlizer completed after 102.87s with status: succeeded
Stopping job with name alexxi19-ft-v1-violet-v12-mkmlizer
Pipeline stage MKMLizer completed in 103.31s
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 alexxi19-ft-v1-violet-v12
Waiting for inference service alexxi19-ft-v1-violet-v12 to be ready
Inference service alexxi19-ft-v1-violet-v12 ready after 201.01417469978333s
Pipeline stage MKMLDeployer completed in 201.60s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.039771795272827s
Received healthy response to inference request in 1.2414939403533936s
Received healthy response to inference request in 1.0719656944274902s
Received healthy response to inference request in 1.154097080230713s
Received healthy response to inference request in 1.3887925148010254s
5 requests
0 failed requests
5th percentile: 1.0883919715881347
10th percentile: 1.1048182487487792
20th percentile: 1.1376708030700684
30th percentile: 1.171576452255249
40th percentile: 1.2065351963043214
50th percentile: 1.2414939403533936
60th percentile: 1.3004133701324463
70th percentile: 1.359332799911499
80th percentile: 1.5189883708953857
90th percentile: 1.7793800830841064
95th percentile: 1.9095759391784668
99th percentile: 2.0137326240539553
mean time: 1.3792242050170898
Pipeline stage StressChecker completed in 8.16s
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 0.68s
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 0.63s
Shutdown handler de-registered
alexxi19-ft-v1-violet_v12 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 2657.10s
Shutdown handler de-registered
alexxi19-ft-v1-violet_v12 status is now inactive due to auto deactivation removed underperforming models
alexxi19-ft-v1-violet_v12 status is now torndown due to DeploymentManager action
alexxi19-ft-v1-violet_v12 status is now torndown due to DeploymentManager action
alexxi19-ft-v1-violet_v12 status is now torndown due to DeploymentManager action