submission_id: pawankrd-cosmosrp_v8
developer_uid: PawanOsman
best_of: 16
celo_rating: 1213.16
display_name: pawankrd-cosmosrp_v7
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': 0.9, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['<', '>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
is_internal_developer: False
language_model: PawanKrd/CosmosRP
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_eval_status: success
model_group: PawanKrd/CosmosRP
model_name: pawankrd-cosmosrp_v7
model_num_parameters: 8030261248.0
model_repo: PawanKrd/CosmosRP
model_size: 8B
num_battles: 13894
num_wins: 7273
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: 2024-06-15T01:30:39+00:00
us_pacific_date: 2024-06-14
win_ratio: 0.5234633654815029
Resubmit model
Running pipeline stage MKMLizer
Starting job with name pawankrd-cosmosrp-v8-mkmlizer
Received score %s for bot %s
Waiting for job on pawankrd-cosmosrp-v8-mkmlizer to finish
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
pawankrd-cosmosrp-v8-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
pawankrd-cosmosrp-v8-mkmlizer: ║     _____            __           __                                ║
pawankrd-cosmosrp-v8-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
pawankrd-cosmosrp-v8-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
pawankrd-cosmosrp-v8-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
pawankrd-cosmosrp-v8-mkmlizer: ║       /___/                                                         ║
pawankrd-cosmosrp-v8-mkmlizer: ║                                                                     ║
pawankrd-cosmosrp-v8-mkmlizer: ║  Version: 0.8.14                                                    ║
pawankrd-cosmosrp-v8-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
pawankrd-cosmosrp-v8-mkmlizer: ║  https://mk1.ai                                                     ║
pawankrd-cosmosrp-v8-mkmlizer: ║                                                                     ║
pawankrd-cosmosrp-v8-mkmlizer: ║  The license key for the current software has been verified as      ║
pawankrd-cosmosrp-v8-mkmlizer: ║  belonging to:                                                      ║
pawankrd-cosmosrp-v8-mkmlizer: ║                                                                     ║
pawankrd-cosmosrp-v8-mkmlizer: ║  Chai Research Corp.                                                ║
pawankrd-cosmosrp-v8-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
pawankrd-cosmosrp-v8-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
pawankrd-cosmosrp-v8-mkmlizer: ║                                                                     ║
pawankrd-cosmosrp-v8-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
pawankrd-cosmosrp-v8-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.
pawankrd-cosmosrp-v8-mkmlizer:   warnings.warn(warning_message, FutureWarning)
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
%s, retrying in %s seconds...
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
pawankrd-cosmosrp-v8-mkmlizer: Downloaded to shared memory in 38.816s
pawankrd-cosmosrp-v8-mkmlizer: quantizing model to /dev/shm/model_cache
pawankrd-cosmosrp-v8-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Received score %s for bot %s
%s, retrying in %s seconds...
Running M-Eval for topic stay_in_character
M-Eval Dataset for topic stay_in_character is loaded
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
pawankrd-cosmosrp-v8-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<10:46,  2.24s/it]
Loading 0:   6%|▌         | 18/291 [00:04<00:50,  5.38it/s]
Loading 0:  11%|█▏        | 33/291 [00:04<00:22, 11.48it/s]
Loading 0:  18%|█▊        | 51/291 [00:04<00:11, 21.02it/s]
Loading 0:  22%|██▏       | 65/291 [00:05<00:08, 25.64it/s]
Loading 0:  27%|██▋       | 80/291 [00:05<00:05, 36.09it/s]
Loading 0:  33%|███▎      | 96/291 [00:05<00:03, 49.13it/s]
Loading 0:  39%|███▉      | 114/291 [00:05<00:02, 65.40it/s]
Loading 0:  45%|████▌     | 132/291 [00:05<00:01, 82.17it/s]
Loading 0:  52%|█████▏    | 150/291 [00:05<00:01, 98.18it/s]
Loading 0:  57%|█████▋    | 166/291 [00:05<00:01, 76.82it/s]
Loading 0:  63%|██████▎   | 184/291 [00:06<00:01, 92.98it/s]
Loading 0:  68%|██████▊   | 199/291 [00:06<00:00, 103.41it/s]
Loading 0:  73%|███████▎  | 213/291 [00:06<00:00, 109.51it/s]
Loading 0:  79%|███████▉  | 231/291 [00:06<00:00, 123.82it/s]
Loading 0:  86%|████████▌ | 249/291 [00:06<00:00, 134.59it/s]
Loading 0:  91%|█████████▏| 266/291 [00:06<00:00, 89.52it/s] 
Loading 0:  98%|█████████▊| 284/291 [00:06<00:00, 105.01it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
pawankrd-cosmosrp-v8-mkmlizer: quantized model in 22.723s
pawankrd-cosmosrp-v8-mkmlizer: Processed model PawanKrd/CosmosRP in 64.009s
pawankrd-cosmosrp-v8-mkmlizer: creating bucket guanaco-mkml-models
pawankrd-cosmosrp-v8-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
pawankrd-cosmosrp-v8-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/pawankrd-cosmosrp-v8
pawankrd-cosmosrp-v8-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v8/config.json
pawankrd-cosmosrp-v8-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v8/special_tokens_map.json
pawankrd-cosmosrp-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v8/tokenizer_config.json
Received score %s for bot %s
pawankrd-cosmosrp-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v8/tokenizer.json
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
pawankrd-cosmosrp-v8-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/pawankrd-cosmosrp-v8/flywheel_model.0.safetensors
pawankrd-cosmosrp-v8-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
pawankrd-cosmosrp-v8-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.
pawankrd-cosmosrp-v8-mkmlizer:   warnings.warn(
pawankrd-cosmosrp-v8-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.
pawankrd-cosmosrp-v8-mkmlizer:   warnings.warn(
pawankrd-cosmosrp-v8-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.
pawankrd-cosmosrp-v8-mkmlizer:   warnings.warn(
pawankrd-cosmosrp-v8-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()
pawankrd-cosmosrp-v8-mkmlizer:   return self.fget.__get__(instance, owner)()
pawankrd-cosmosrp-v8-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Scoring model output for bot %s
pawankrd-cosmosrp-v8-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/pawankrd-cosmosrp-v8_reward/reward.tensors
Scoring model output for bot %s
Job pawankrd-cosmosrp-v8-mkmlizer completed after 93.73s with status: succeeded
Stopping job with name pawankrd-cosmosrp-v8-mkmlizer
Pipeline stage MKMLizer completed in 94.14s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service pawankrd-cosmosrp-v8
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Waiting for inference service pawankrd-cosmosrp-v8 to be ready
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Completed M-Eval for topic stay_in_character, average_score=8.6875
Running M-Eval for topic user_preference
M-Eval Dataset for topic user_preference is loaded
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Inference service pawankrd-cosmosrp-v8 ready after 30.182148456573486s
Pipeline stage ISVCDeployer completed in 36.02s
Running pipeline stage StressChecker
Received score %s for bot %s
Received score %s for bot %s
Received score %s for bot %s
Received healthy response to inference request in 2.1330273151397705s
Received score %s for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Scoring model output for bot %s
Received score %s for bot %s
Received healthy response to inference request in 1.3923838138580322s
Scoring model output for bot %s
Scoring model output for bot %s
Received healthy response to inference request in 1.34885573387146s
Received healthy response to inference request in 1.314058780670166s
Received score %s for bot %s
Received score %s for bot %s
Received healthy response to inference request in 1.2719056606292725s
5 requests
0 failed requests
5th percentile: 1.280336284637451
10th percentile: 1.28876690864563
Received score %s for bot %s
20th percentile: 1.3056281566619874
30th percentile: 1.3210181713104248
40th percentile: 1.3349369525909425
50th percentile: 1.34885573387146
60th percentile: 1.3662669658660889
70th percentile: 1.3836781978607178
80th percentile: 1.54051251411438
90th percentile: 1.8367699146270753
95th percentile: 1.9848986148834227
99th percentile: 2.103401575088501
mean time: 1.4920462608337401
Received score %s for bot %s
Pipeline stage StressChecker completed in 8.70s
Received score %s for bot %s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.11s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.07s
M-Eval Dataset for topic stay_in_character is loaded
pawankrd-cosmosrp_v8 status is now deployed due to DeploymentManager action
pawankrd-cosmosrp_v8 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of pawankrd-cosmosrp_v8
Running pipeline stage ISVCDeleter
Checking if service pawankrd-cosmosrp-v8 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.32s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key pawankrd-cosmosrp-v8/config.json from bucket guanaco-mkml-models
Deleting key pawankrd-cosmosrp-v8/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key pawankrd-cosmosrp-v8/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key pawankrd-cosmosrp-v8/tokenizer.json from bucket guanaco-mkml-models
Deleting key pawankrd-cosmosrp-v8/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key pawankrd-cosmosrp-v8_reward/config.json from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-v8_reward/merges.txt from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-v8_reward/reward.tensors from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-v8_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-v8_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-v8_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-v8_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.81s
pawankrd-cosmosrp_v8 status is now torndown due to DeploymentManager action