submission_id: hastagaras-llama3-8b-ese_7365_v2
developer_uid: Hastagaras
best_of: 16
celo_rating: 1207.34
display_name: damn-its-so-bad
family_friendly_score: 0.0
formatter: {'memory_template': "<|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': 1.0, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 200, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
is_internal_developer: False
language_model: Hastagaras/llama3-8b-esekuhhwell
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_eval_status: success
model_group: Hastagaras/llama3-8b-ese
model_name: damn-its-so-bad
model_num_parameters: 8030261248.0
model_repo: Hastagaras/llama3-8b-esekuhhwell
model_size: 8B
num_battles: 20408
num_wins: 11085
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/reward_gpt2_medium_preference_24m_e2
status: torndown
submission_type: basic
timestamp: 2024-05-18T03:28:13+00:00
us_pacific_date: 2024-05-17
win_ratio: 0.5431693453547628
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-llama3-8b-ese-7365-v2-mkmlizer
Waiting for job on hastagaras-llama3-8b-ese-7365-v2-mkmlizer to finish
Failed to get response for submission mistralai-mixtral-8x7b-_3473_v33: ('http://mistralai-mixtral-8x7b-3473-v33-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:42298->127.0.0.1:8080: read: connection reset by peer\n')
hastagaras-llama3-8b-ese-7365-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-llama3-8b-ese-7365-v2-mkmlizer: ║     _____            __           __                                ║
hastagaras-llama3-8b-ese-7365-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-llama3-8b-ese-7365-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-llama3-8b-ese-7365-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-llama3-8b-ese-7365-v2-mkmlizer: ║       /___/                                                         ║
hastagaras-llama3-8b-ese-7365-v2-mkmlizer: ║                                                                     ║
hastagaras-llama3-8b-ese-7365-v2-mkmlizer: ║  Version: 0.8.14                                                    ║
hastagaras-llama3-8b-ese-7365-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-llama3-8b-ese-7365-v2-mkmlizer: ║  https://mk1.ai                                                     ║
hastagaras-llama3-8b-ese-7365-v2-mkmlizer: ║                                                                     ║
hastagaras-llama3-8b-ese-7365-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-llama3-8b-ese-7365-v2-mkmlizer: ║  belonging to:                                                      ║
hastagaras-llama3-8b-ese-7365-v2-mkmlizer: ║                                                                     ║
hastagaras-llama3-8b-ese-7365-v2-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-llama3-8b-ese-7365-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-llama3-8b-ese-7365-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-llama3-8b-ese-7365-v2-mkmlizer: ║                                                                     ║
hastagaras-llama3-8b-ese-7365-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-llama3-8b-ese-7365-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_deprecation.py:131: FutureWarning: 'list_files_info' (from 'huggingface_hub.hf_api') is deprecated and will be removed from version '0.23'. Use `list_repo_tree` and `get_paths_info` instead.
hastagaras-llama3-8b-ese-7365-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-llama3-8b-ese-7365-v2-mkmlizer: Downloaded to shared memory in 20.007s
hastagaras-llama3-8b-ese-7365-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-llama3-8b-ese-7365-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-llama3-8b-ese-7365-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:05<12:44,  2.65s/it]
Loading 0:   5%|▍         | 14/291 [00:05<01:18,  3.52it/s]
Loading 0:  10%|▉         | 29/291 [00:05<00:29,  8.81it/s]
Loading 0:  14%|█▍        | 41/291 [00:05<00:17, 14.25it/s]
Loading 0:  20%|█▉        | 57/291 [00:05<00:09, 23.79it/s]
Loading 0:  24%|██▍       | 70/291 [00:06<00:09, 24.39it/s]
Loading 0:  29%|██▊       | 83/291 [00:06<00:06, 33.15it/s]
Loading 0:  33%|███▎      | 95/291 [00:06<00:04, 42.10it/s]
Loading 0:  37%|███▋      | 109/291 [00:06<00:03, 54.54it/s]
Loading 0:  42%|████▏     | 121/291 [00:06<00:02, 64.79it/s]
Loading 0:  46%|████▌     | 133/291 [00:06<00:02, 74.60it/s]
Loading 0:  50%|████▉     | 145/291 [00:06<00:01, 83.03it/s]
Loading 0:  54%|█████▍    | 157/291 [00:06<00:01, 88.54it/s]
Loading 0:  58%|█████▊    | 169/291 [00:07<00:02, 54.33it/s]
Loading 0:  64%|██████▎   | 185/291 [00:07<00:01, 69.86it/s]
Loading 0:  69%|██████▉   | 202/291 [00:07<00:01, 85.98it/s]
Loading 0:  74%|███████▎  | 214/291 [00:07<00:00, 92.08it/s]
Loading 0:  79%|███████▉  | 230/291 [00:07<00:00, 103.61it/s]
Loading 0:  84%|████████▎ | 243/291 [00:07<00:00, 107.16it/s]
Loading 0:  88%|████████▊ | 257/291 [00:08<00:00, 111.19it/s]
Loading 0:  93%|█████████▎| 270/291 [00:08<00:00, 65.00it/s] 
Loading 0:  98%|█████████▊| 284/291 [00:08<00:00, 75.53it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-llama3-8b-ese-7365-v2-mkmlizer: quantized model in 20.908s
hastagaras-llama3-8b-ese-7365-v2-mkmlizer: Processed model Hastagaras/llama3-8b-esekuhhwell in 42.084s
hastagaras-llama3-8b-ese-7365-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-llama3-8b-ese-7365-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-llama3-8b-ese-7365-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-llama3-8b-ese-7365-v2
hastagaras-llama3-8b-ese-7365-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-llama3-8b-ese-7365-v2/config.json
hastagaras-llama3-8b-ese-7365-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-llama3-8b-ese-7365-v2/tokenizer_config.json
hastagaras-llama3-8b-ese-7365-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-llama3-8b-ese-7365-v2/special_tokens_map.json
hastagaras-llama3-8b-ese-7365-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-llama3-8b-ese-7365-v2/tokenizer.json
hastagaras-llama3-8b-ese-7365-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-llama3-8b-ese-7365-v2/flywheel_model.0.safetensors
hastagaras-llama3-8b-ese-7365-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-llama3-8b-ese-7365-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:913: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
hastagaras-llama3-8b-ese-7365-v2-mkmlizer:   warnings.warn(
hastagaras-llama3-8b-ese-7365-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:757: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
hastagaras-llama3-8b-ese-7365-v2-mkmlizer:   warnings.warn(
hastagaras-llama3-8b-ese-7365-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/torch/_utils.py:831: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly.  To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
hastagaras-llama3-8b-ese-7365-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-llama3-8b-ese-7365-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-llama3-8b-ese-7365-v2-mkmlizer: Saving duration: 0.255s
hastagaras-llama3-8b-ese-7365-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.001s
hastagaras-llama3-8b-ese-7365-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-llama3-8b-ese-7365-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-llama3-8b-ese-7365-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-llama3-8b-ese-7365-v2_reward
hastagaras-llama3-8b-ese-7365-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-llama3-8b-ese-7365-v2_reward/tokenizer_config.json
hastagaras-llama3-8b-ese-7365-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-llama3-8b-ese-7365-v2_reward/special_tokens_map.json
hastagaras-llama3-8b-ese-7365-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-llama3-8b-ese-7365-v2_reward/config.json
hastagaras-llama3-8b-ese-7365-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-llama3-8b-ese-7365-v2_reward/vocab.json
hastagaras-llama3-8b-ese-7365-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-llama3-8b-ese-7365-v2_reward/merges.txt
hastagaras-llama3-8b-ese-7365-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-llama3-8b-ese-7365-v2_reward/tokenizer.json
hastagaras-llama3-8b-ese-7365-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-llama3-8b-ese-7365-v2_reward/reward.tensors
Job hastagaras-llama3-8b-ese-7365-v2-mkmlizer completed after 63.31s with status: succeeded
Stopping job with name hastagaras-llama3-8b-ese-7365-v2-mkmlizer
Pipeline stage MKMLizer completed in 66.93s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-llama3-8b-ese-7365-v2
Waiting for inference service hastagaras-llama3-8b-ese-7365-v2 to be ready
Inference service hastagaras-llama3-8b-ese-7365-v2 ready after 30.270925760269165s
Pipeline stage ISVCDeployer completed in 37.15s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1044657230377197s
Received healthy response to inference request in 1.3297059535980225s
Received healthy response to inference request in 1.3332676887512207s
Received healthy response to inference request in 1.2985327243804932s
Received healthy response to inference request in 1.3394899368286133s
5 requests
0 failed requests
5th percentile: 1.304767370223999
10th percentile: 1.3110020160675049
20th percentile: 1.3234713077545166
30th percentile: 1.330418300628662
40th percentile: 1.3318429946899415
50th percentile: 1.3332676887512207
60th percentile: 1.3357565879821778
70th percentile: 1.3382454872131349
80th percentile: 1.4924850940704346
90th percentile: 1.7984754085540773
95th percentile: 1.9514705657958984
99th percentile: 2.0738666915893553
mean time: 1.4810924053192138
Pipeline stage StressChecker completed in 8.16s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.04s
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-llama3-8b-ese_7365_v2 status is now deployed due to DeploymentManager action
hastagaras-llama3-8b-ese_7365_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-llama3-8b-ese_7365_v2
Running pipeline stage ISVCDeleter
Checking if service hastagaras-llama3-8b-ese-7365-v2 is running
Tearing down inference service hastagaras-llama3-8b-ese-7365-v2
Toredown service hastagaras-llama3-8b-ese-7365-v2
Pipeline stage ISVCDeleter completed in 4.32s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-llama3-8b-ese-7365-v2/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-8b-ese-7365-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-8b-ese-7365-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-8b-ese-7365-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-llama3-8b-ese-7365-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-llama3-8b-ese-7365-v2_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-ese-7365-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-ese-7365-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-ese-7365-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-ese-7365-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-ese-7365-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-llama3-8b-ese-7365-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 4.25s
hastagaras-llama3-8b-ese_7365_v2 status is now torndown due to DeploymentManager action