developer_uid: c.gato
submission_id: cgato-l3-1-thespice-v0-9_1055_v2
model_name: cgato-l3-1-thespice-v0-9_1055_v2
model_group: cgato/L3.1-TheSpice-V0.9
status: torndown
timestamp: 2024-10-12T02:27:48+00:00
num_battles: 5843
num_wins: 2754
celo_rating: 1234.95
family_friendly_score: 0.5399701046337818
family_friendly_standard_error: 0.006641295274386603
submission_type: basic
model_repo: cgato/L3.1-TheSpice-V0.9-MiniTune-v0.1
model_architecture: LlamaForCausalLM
model_num_parameters: 8030294016.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
display_name: cgato-l3-1-thespice-v0-9_1055_v2
is_internal_developer: False
language_model: cgato/L3.1-TheSpice-V0.9-MiniTune-v0.1
model_size: 8B
ranking_group: single
us_pacific_date: 2024-10-11
win_ratio: 0.47133321923669347
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': '<|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 cgato-l3-1-thespice-v0-9-1055-v2-mkmlizer
Waiting for job on cgato-l3-1-thespice-v0-9-1055-v2-mkmlizer to finish
cgato-l3-1-thespice-v0-9-1055-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-1-thespice-v0-9-1055-v2-mkmlizer: ║ _____ __ __ ║
cgato-l3-1-thespice-v0-9-1055-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-l3-1-thespice-v0-9-1055-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-l3-1-thespice-v0-9-1055-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-l3-1-thespice-v0-9-1055-v2-mkmlizer: ║ /___/ ║
cgato-l3-1-thespice-v0-9-1055-v2-mkmlizer: ║ ║
cgato-l3-1-thespice-v0-9-1055-v2-mkmlizer: ║ Version: 0.11.12 ║
cgato-l3-1-thespice-v0-9-1055-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-l3-1-thespice-v0-9-1055-v2-mkmlizer: ║ https://mk1.ai ║
cgato-l3-1-thespice-v0-9-1055-v2-mkmlizer: ║ ║
cgato-l3-1-thespice-v0-9-1055-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-l3-1-thespice-v0-9-1055-v2-mkmlizer: ║ belonging to: ║
cgato-l3-1-thespice-v0-9-1055-v2-mkmlizer: ║ ║
cgato-l3-1-thespice-v0-9-1055-v2-mkmlizer: ║ Chai Research Corp. ║
cgato-l3-1-thespice-v0-9-1055-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-l3-1-thespice-v0-9-1055-v2-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
cgato-l3-1-thespice-v0-9-1055-v2-mkmlizer: ║ ║
cgato-l3-1-thespice-v0-9-1055-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-1-thespice-v0-9-1055-v2-mkmlizer: Downloaded to shared memory in 23.273s
cgato-l3-1-thespice-v0-9-1055-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp9ry8onaa, device:0
cgato-l3-1-thespice-v0-9-1055-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-l3-1-thespice-v0-9-1055-v2-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.
cgato-l3-1-thespice-v0-9-1055-v2-mkmlizer: tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
cgato-l3-1-thespice-v0-9-1055-v2-mkmlizer: quantized model in 26.040s
cgato-l3-1-thespice-v0-9-1055-v2-mkmlizer: Processed model cgato/L3.1-TheSpice-V0.9-MiniTune-v0.1 in 49.313s
cgato-l3-1-thespice-v0-9-1055-v2-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-1-thespice-v0-9-1055-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-l3-1-thespice-v0-9-1055-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-l3-1-thespice-v0-9-1055-v2
cgato-l3-1-thespice-v0-9-1055-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-l3-1-thespice-v0-9-1055-v2/config.json
cgato-l3-1-thespice-v0-9-1055-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-l3-1-thespice-v0-9-1055-v2/special_tokens_map.json
cgato-l3-1-thespice-v0-9-1055-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-l3-1-thespice-v0-9-1055-v2/tokenizer_config.json
cgato-l3-1-thespice-v0-9-1055-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-l3-1-thespice-v0-9-1055-v2/tokenizer.json
cgato-l3-1-thespice-v0-9-1055-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-1-thespice-v0-9-1055-v2/flywheel_model.0.safetensors
Job cgato-l3-1-thespice-v0-9-1055-v2-mkmlizer completed after 74.11s with status: succeeded
Stopping job with name cgato-l3-1-thespice-v0-9-1055-v2-mkmlizer
Pipeline stage MKMLizer completed in 74.75s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.21s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cgato-l3-1-thespice-v0-9-1055-v2
Waiting for inference service cgato-l3-1-thespice-v0-9-1055-v2 to be ready
Inference service cgato-l3-1-thespice-v0-9-1055-v2 ready after 150.57410550117493s
Pipeline stage MKMLDeployer completed in 151.37s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0915863513946533s
Received healthy response to inference request in 1.5312931537628174s
Received healthy response to inference request in 1.4899344444274902s
Received healthy response to inference request in 1.4248948097229004s
Received healthy response to inference request in 1.504225492477417s
5 requests
0 failed requests
5th percentile: 1.4379027366638184
10th percentile: 1.4509106636047364
20th percentile: 1.4769265174865722
30th percentile: 1.4927926540374756
40th percentile: 1.4985090732574462
50th percentile: 1.504225492477417
60th percentile: 1.5150525569915771
70th percentile: 1.5258796215057373
80th percentile: 1.6433517932891846
90th percentile: 1.867469072341919
95th percentile: 1.9795277118682861
99th percentile: 2.06917462348938
mean time: 1.6083868503570558
Pipeline stage StressChecker completed in 9.43s
Shutdown handler de-registered
cgato-l3-1-thespice-v0-9_1055_v2 status is now deployed due to DeploymentManager action
cgato-l3-1-thespice-v0-9_1055_v2 status is now inactive due to auto deactivation removed underperforming models
cgato-l3-1-thespice-v0-9_1055_v2 status is now torndown due to DeploymentManager action