submission_id: jellywibble-quantumenigm_5980_v2
developer_uid: Jellywibble
best_of: 16
celo_rating: 1264.5
display_name: quantum-enigma-cp1500
family_friendly_score: 0.0
formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}:', 'truncate_by_message': False}
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.08, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
is_internal_developer: True
language_model: Jellywibble/QuantumEnigma-cp1500
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: Jellywibble/QuantumEnigm
model_name: quantum-enigma-cp1500
model_num_parameters: 8030261248.0
model_repo: Jellywibble/QuantumEnigma-cp1500
model_size: 8B
num_battles: 35775
num_wins: 21658
ranking_group: single
reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}
reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634
status: torndown
submission_type: basic
timestamp: 2024-07-06T22:27:59+00:00
us_pacific_date: 2024-07-06
win_ratio: 0.6053948287910552
Resubmit model
Running pipeline stage MKMLizer
Starting job with name jellywibble-quantumenigm-5980-v2-mkmlizer
Waiting for job on jellywibble-quantumenigm-5980-v2-mkmlizer to finish
jellywibble-quantumenigm-5980-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jellywibble-quantumenigm-5980-v2-mkmlizer: ║     _____            __           __                                ║
jellywibble-quantumenigm-5980-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
jellywibble-quantumenigm-5980-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
jellywibble-quantumenigm-5980-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
jellywibble-quantumenigm-5980-v2-mkmlizer: ║       /___/                                                         ║
jellywibble-quantumenigm-5980-v2-mkmlizer: ║                                                                     ║
jellywibble-quantumenigm-5980-v2-mkmlizer: ║  Version: 0.8.14                                                    ║
jellywibble-quantumenigm-5980-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
jellywibble-quantumenigm-5980-v2-mkmlizer: ║  https://mk1.ai                                                     ║
jellywibble-quantumenigm-5980-v2-mkmlizer: ║                                                                     ║
jellywibble-quantumenigm-5980-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
jellywibble-quantumenigm-5980-v2-mkmlizer: ║  belonging to:                                                      ║
jellywibble-quantumenigm-5980-v2-mkmlizer: ║                                                                     ║
jellywibble-quantumenigm-5980-v2-mkmlizer: ║  Chai Research Corp.                                                ║
jellywibble-quantumenigm-5980-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
jellywibble-quantumenigm-5980-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
jellywibble-quantumenigm-5980-v2-mkmlizer: ║                                                                     ║
jellywibble-quantumenigm-5980-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jellywibble-quantumenigm-5980-v2-mkmlizer: Downloaded to shared memory in 32.714s
jellywibble-quantumenigm-5980-v2-mkmlizer: quantizing model to /dev/shm/model_cache
jellywibble-quantumenigm-5980-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jellywibble-quantumenigm-5980-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/291 [00:00<00:33,  8.65it/s]
Loading 0:   1%|▏         | 4/291 [00:00<00:58,  4.92it/s]
Loading 0:   2%|▏         | 5/291 [00:01<01:12,  3.96it/s]
Loading 0:   3%|▎         | 8/291 [00:01<00:37,  7.65it/s]
Loading 0:   3%|▎         | 10/291 [00:01<00:31,  8.83it/s]
Loading 0:   4%|▍         | 12/291 [00:01<00:36,  7.67it/s]
Loading 0:   5%|▍         | 14/291 [00:01<00:36,  7.67it/s]
Loading 0:   8%|▊         | 23/291 [00:02<00:13, 19.14it/s]
Loading 0:  11%|█▏        | 33/291 [00:02<00:09, 26.43it/s]
Loading 0:  13%|█▎        | 37/291 [00:02<00:08, 28.35it/s]
Loading 0:  14%|█▍        | 41/291 [00:02<00:08, 30.32it/s]
Loading 0:  17%|█▋        | 50/291 [00:02<00:05, 40.25it/s]
Loading 0:  20%|██        | 59/291 [00:02<00:04, 47.99it/s]
Loading 0:  23%|██▎       | 67/291 [00:02<00:04, 54.20it/s]
Loading 0:  25%|██▌       | 74/291 [00:03<00:03, 57.89it/s]
Loading 0:  28%|██▊       | 81/291 [00:03<00:04, 44.88it/s]
Loading 0:  31%|███       | 90/291 [00:03<00:03, 50.90it/s]
Loading 0:  34%|███▍      | 99/291 [00:03<00:03, 55.30it/s]
Loading 0:  37%|███▋      | 108/291 [00:03<00:03, 58.94it/s]
Loading 0:  40%|███▉      | 116/291 [00:03<00:02, 59.61it/s]
Loading 0:  43%|████▎     | 126/291 [00:03<00:02, 64.63it/s]
Loading 0:  46%|████▌     | 133/291 [00:04<00:03, 51.12it/s]
Loading 0:  48%|████▊     | 139/291 [00:04<00:03, 48.75it/s]
Loading 0:  51%|█████     | 148/291 [00:04<00:02, 54.09it/s]
Loading 0:  54%|█████▍    | 157/291 [00:04<00:02, 58.06it/s]
Loading 0:  57%|█████▋    | 166/291 [00:04<00:02, 61.27it/s]
Loading 0:  60%|██████    | 175/291 [00:04<00:01, 63.17it/s]
Loading 0:  64%|██████▍   | 186/291 [00:05<00:01, 57.58it/s]
Loading 0:  66%|██████▋   | 193/291 [00:05<00:01, 51.40it/s]
Loading 0:  69%|██████▉   | 202/291 [00:05<00:01, 55.62it/s]
Loading 0:  73%|███████▎  | 211/291 [00:05<00:01, 59.01it/s]
Loading 0:  76%|███████▌  | 220/291 [00:05<00:01, 61.69it/s]
Loading 0:  78%|███████▊  | 228/291 [00:05<00:01, 61.66it/s]
Loading 0:  81%|████████  | 235/291 [00:05<00:01, 49.56it/s]
Loading 0:  83%|████████▎ | 241/291 [00:06<00:00, 51.00it/s]
Loading 0:  85%|████████▌ | 248/291 [00:06<00:00, 52.28it/s]
Loading 0:  88%|████████▊ | 257/291 [00:06<00:00, 56.95it/s]
Loading 0:  91%|█████████▏| 266/291 [00:06<00:00, 59.99it/s]
Loading 0:  94%|█████████▍| 274/291 [00:06<00:00, 64.60it/s]
Loading 0:  97%|█████████▋| 282/291 [00:06<00:00, 68.21it/s]
Loading 0: 100%|█████████▉| 290/291 [00:11<00:00,  4.89it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
jellywibble-quantumenigm-5980-v2-mkmlizer: quantized model in 65.072s
jellywibble-quantumenigm-5980-v2-mkmlizer: Processed model Jellywibble/QuantumEnigma-cp1500 in 97.786s
jellywibble-quantumenigm-5980-v2-mkmlizer: creating bucket guanaco-mkml-models
jellywibble-quantumenigm-5980-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jellywibble-quantumenigm-5980-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jellywibble-quantumenigm-5980-v2
jellywibble-quantumenigm-5980-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jellywibble-quantumenigm-5980-v2/config.json
jellywibble-quantumenigm-5980-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jellywibble-quantumenigm-5980-v2/tokenizer_config.json
jellywibble-quantumenigm-5980-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jellywibble-quantumenigm-5980-v2/special_tokens_map.json
jellywibble-quantumenigm-5980-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jellywibble-quantumenigm-5980-v2/tokenizer.json
jellywibble-quantumenigm-5980-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jellywibble-quantumenigm-5980-v2/flywheel_model.0.safetensors
jellywibble-quantumenigm-5980-v2-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
jellywibble-quantumenigm-5980-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:919: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
jellywibble-quantumenigm-5980-v2-mkmlizer:   warnings.warn(
jellywibble-quantumenigm-5980-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
jellywibble-quantumenigm-5980-v2-mkmlizer:   warnings.warn(
jellywibble-quantumenigm-5980-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:769: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
jellywibble-quantumenigm-5980-v2-mkmlizer:   warnings.warn(
jellywibble-quantumenigm-5980-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:468: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
jellywibble-quantumenigm-5980-v2-mkmlizer:   warnings.warn(
jellywibble-quantumenigm-5980-v2-mkmlizer: 
Downloading shards:   0%|          | 0/2 [00:00<?, ?it/s]
Downloading shards:  50%|█████     | 1/2 [00:03<00:03,  3.84s/it]
Downloading shards: 100%|██████████| 2/2 [00:05<00:00,  2.55s/it]
Downloading shards: 100%|██████████| 2/2 [00:05<00:00,  2.74s/it]
Job jellywibble-quantumenigm-5980-v2-mkmlizer completed after 143.68s with status: succeeded
Stopping job with name jellywibble-quantumenigm-5980-v2-mkmlizer
Pipeline stage MKMLizer completed in 144.49s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service jellywibble-quantumenigm-5980-v2
Waiting for inference service jellywibble-quantumenigm-5980-v2 to be ready
Inference service jellywibble-quantumenigm-5980-v2 ready after 50.295782804489136s
Pipeline stage ISVCDeployer completed in 57.10s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3037452697753906s
Received healthy response to inference request in 1.5780980587005615s
Received healthy response to inference request in 1.5533897876739502s
Received healthy response to inference request in 1.5140650272369385s
Received healthy response to inference request in 1.6040849685668945s
5 requests
0 failed requests
5th percentile: 1.5219299793243408
10th percentile: 1.5297949314117432
20th percentile: 1.5455248355865479
30th percentile: 1.5583314418792724
40th percentile: 1.568214750289917
50th percentile: 1.5780980587005615
60th percentile: 1.5884928226470947
70th percentile: 1.5988875865936278
80th percentile: 1.7440170288085939
90th percentile: 2.0238811492919924
95th percentile: 2.163813209533691
99th percentile: 2.275758857727051
mean time: 1.710676622390747
Pipeline stage StressChecker completed in 9.36s
jellywibble-quantumenigm_5980_v2 status is now deployed due to DeploymentManager action
jellywibble-quantumenigm_5980_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of jellywibble-quantumenigm_5980_v2
Running pipeline stage ISVCDeleter
Checking if service jellywibble-quantumenigm-5980-v2 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.68s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key jellywibble-quantumenigm-5980-v2/config.json from bucket guanaco-mkml-models
Deleting key jellywibble-quantumenigm-5980-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key jellywibble-quantumenigm-5980-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key jellywibble-quantumenigm-5980-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key jellywibble-quantumenigm-5980-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key jellywibble-quantumenigm-5980-v2_reward/config.json from bucket guanaco-reward-models
Deleting key jellywibble-quantumenigm-5980-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key jellywibble-quantumenigm-5980-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key jellywibble-quantumenigm-5980-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key jellywibble-quantumenigm-5980-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key jellywibble-quantumenigm-5980-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key jellywibble-quantumenigm-5980-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.50s
jellywibble-quantumenigm_5980_v2 status is now torndown due to DeploymentManager action