leosheng-no-repeat-write

developer_uid: leosheng

submission_id: leosheng-no-repeat-write_v1

model_name: leosheng-no-repeat-write_v1

model_group: leosheng/no-repeat-write

status: torndown

timestamp: 2025-01-24T04:28:55+00:00

num_battles: 6428

num_wins: 2857

celo_rating: 1206.87

family_friendly_score: 0.591

family_friendly_standard_error: 0.006952970588173086

submission_type: basic

model_repo: leosheng/no-repeat-write

model_architecture: LlamaForCausalLM

model_num_parameters: 8030261248.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

display_name: leosheng-no-repeat-write_v1

is_internal_developer: False

language_model: leosheng/no-repeat-write

model_size: 8B

ranking_group: single

us_pacific_date: 2025-01-23

win_ratio: 0.4444617299315495

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 leosheng-no-repeat-write-v1-mkmlizer
Waiting for job on leosheng-no-repeat-write-v1-mkmlizer to finish
leosheng-no-repeat-write-v1-mkmlizer: Downloaded to shared memory in 32.236s
leosheng-no-repeat-write-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp47vep5f4, device:0
leosheng-no-repeat-write-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
leosheng-no-repeat-write-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.
leosheng-no-repeat-write-v1-mkmlizer:   tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
leosheng-no-repeat-write-v1-mkmlizer: quantized model in 27.481s
leosheng-no-repeat-write-v1-mkmlizer: Processed model leosheng/no-repeat-write in 59.717s
leosheng-no-repeat-write-v1-mkmlizer: creating bucket guanaco-mkml-models
leosheng-no-repeat-write-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
leosheng-no-repeat-write-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/leosheng-no-repeat-write-v1
leosheng-no-repeat-write-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/leosheng-no-repeat-write-v1/config.json
leosheng-no-repeat-write-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/leosheng-no-repeat-write-v1/special_tokens_map.json
leosheng-no-repeat-write-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/leosheng-no-repeat-write-v1/tokenizer_config.json
leosheng-no-repeat-write-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/leosheng-no-repeat-write-v1/tokenizer.json
leosheng-no-repeat-write-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/leosheng-no-repeat-write-v1/flywheel_model.0.safetensors
leosheng-no-repeat-write-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:05, 51.41it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:03, 68.99it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:03, 73.40it/s]
Loading 0:  12%|█▏        | 34/291 [00:00<00:03, 70.45it/s]
Loading 0:  15%|█▍        | 43/291 [00:00<00:03, 70.98it/s]
Loading 0:  18%|█▊        | 52/291 [00:00<00:03, 74.65it/s]
Loading 0:  21%|██        | 61/291 [00:00<00:03, 74.52it/s]
Loading 0:  24%|██▍       | 70/291 [00:00<00:03, 70.32it/s]
Loading 0:  27%|██▋       | 79/291 [00:01<00:03, 68.02it/s]
Loading 0:  30%|██▉       | 86/291 [00:02<00:10, 19.53it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:07, 25.01it/s]
Loading 0:  35%|███▌      | 103/291 [00:02<00:05, 32.02it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:04, 39.23it/s]
Loading 0:  42%|████▏     | 121/291 [00:02<00:03, 46.87it/s]
Loading 0:  45%|████▍     | 130/291 [00:02<00:02, 53.93it/s]
Loading 0:  48%|████▊     | 139/291 [00:02<00:02, 60.13it/s]
Loading 0:  51%|█████     | 148/291 [00:03<00:02, 62.46it/s]
Loading 0:  54%|█████▍    | 157/291 [00:03<00:02, 63.15it/s]
Loading 0:  57%|█████▋    | 166/291 [00:03<00:02, 61.67it/s]
Loading 0:  60%|██████    | 175/291 [00:03<00:01, 61.84it/s]
Loading 0:  63%|██████▎   | 184/291 [00:03<00:01, 62.32it/s]
Loading 0:  66%|██████▌   | 191/291 [00:05<00:06, 15.92it/s]
Loading 0:  67%|██████▋   | 196/291 [00:05<00:05, 18.06it/s]
Loading 0:  70%|███████   | 205/291 [00:05<00:03, 23.77it/s]
Loading 0:  74%|███████▎  | 214/291 [00:05<00:02, 30.08it/s]
Loading 0:  77%|███████▋  | 223/291 [00:05<00:01, 35.27it/s]
Loading 0:  80%|███████▉  | 232/291 [00:05<00:01, 40.16it/s]
Loading 0:  83%|████████▎ | 241/291 [00:05<00:01, 42.98it/s]
Loading 0:  86%|████████▌ | 250/291 [00:06<00:00, 45.90it/s]
Loading 0:  88%|████████▊ | 256/291 [00:06<00:00, 47.16it/s]
Loading 0:  90%|█████████ | 262/291 [00:06<00:00, 45.89it/s]
Loading 0:  92%|█████████▏| 268/291 [00:06<00:00, 42.98it/s]
Loading 0:  94%|█████████▍| 274/291 [00:06<00:00, 46.41it/s]
Loading 0:  97%|█████████▋| 283/291 [00:06<00:00, 49.81it/s]
Loading 0:  99%|█████████▉| 289/291 [00:07<00:00, 26.84it/s]
                                                            
Job leosheng-no-repeat-write-v1-mkmlizer completed after 93.31s with status: succeeded
Stopping job with name leosheng-no-repeat-write-v1-mkmlizer
Pipeline stage MKMLizer completed in 93.77s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service leosheng-no-repeat-write-v1
Waiting for inference service leosheng-no-repeat-write-v1 to be ready
Inference service leosheng-no-repeat-write-v1 ready after 150.6889202594757s
Pipeline stage MKMLDeployer completed in 151.27s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.5347225666046143s
Received healthy response to inference request in 1.7120678424835205s
Received healthy response to inference request in 1.7071928977966309s
Received healthy response to inference request in 1.5518643856048584s
Received healthy response to inference request in 2.197922706604004s
5 requests
0 failed requests
5th percentile: 1.538150930404663
10th percentile: 1.541579294204712
20th percentile: 1.5484360218048097
30th percentile: 1.582930088043213
40th percentile: 1.6450614929199219
50th percentile: 1.7071928977966309
60th percentile: 1.7091428756713867
70th percentile: 1.7110928535461425
80th percentile: 1.8092388153076173
90th percentile: 2.0035807609558107
95th percentile: 2.1007517337799073
99th percentile: 2.1784885120391846
mean time: 1.7407540798187255
Pipeline stage StressChecker completed in 10.05s
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 0.67s
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 0.64s
Shutdown handler de-registered
leosheng-no-repeat-write_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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.07s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service leosheng-no-repeat-write-v1-profiler
Waiting for inference service leosheng-no-repeat-write-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 3000.26s
Shutdown handler de-registered
leosheng-no-repeat-write_v1 status is now inactive due to auto deactivation removed underperforming models
leosheng-no-repeat-write_v1 status is now torndown due to DeploymentManager action