developer_uid: PawanOsman
submission_id: pawankrd-cosmosrp_v9
model_name: pawankrd-cosmosrp_v9
model_group: PawanKrd/CosmosRP
status: torndown
timestamp: 2024-06-15T17:43:51+00:00
num_battles: 11911
num_wins: 6625
celo_rating: 1208.27
family_friendly_score: 0.0
submission_type: basic
model_repo: PawanKrd/CosmosRP
model_architecture: LlamaForCausalLM
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: pawankrd-cosmosrp_v9
is_internal_developer: False
language_model: PawanKrd/CosmosRP
model_size: 8B
ranking_group: single
us_pacific_date: 2024-06-15
win_ratio: 0.5562085467215179
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}
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}
model_eval_status: success
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'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name pawankrd-cosmosrp-v9-mkmlizer
Waiting for job on pawankrd-cosmosrp-v9-mkmlizer to finish
pawankrd-cosmosrp-v9-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
pawankrd-cosmosrp-v9-mkmlizer: ║ _____ __ __ ║
pawankrd-cosmosrp-v9-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
pawankrd-cosmosrp-v9-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
pawankrd-cosmosrp-v9-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
pawankrd-cosmosrp-v9-mkmlizer: ║ /___/ ║
pawankrd-cosmosrp-v9-mkmlizer: ║ ║
pawankrd-cosmosrp-v9-mkmlizer: ║ Version: 0.8.14 ║
pawankrd-cosmosrp-v9-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
pawankrd-cosmosrp-v9-mkmlizer: ║ https://mk1.ai ║
pawankrd-cosmosrp-v9-mkmlizer: ║ ║
pawankrd-cosmosrp-v9-mkmlizer: ║ The license key for the current software has been verified as ║
pawankrd-cosmosrp-v9-mkmlizer: ║ belonging to: ║
pawankrd-cosmosrp-v9-mkmlizer: ║ ║
pawankrd-cosmosrp-v9-mkmlizer: ║ Chai Research Corp. ║
pawankrd-cosmosrp-v9-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
pawankrd-cosmosrp-v9-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
pawankrd-cosmosrp-v9-mkmlizer: ║ ║
pawankrd-cosmosrp-v9-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
pawankrd-cosmosrp-v9-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-v9-mkmlizer: warnings.warn(warning_message, FutureWarning)
pawankrd-cosmosrp-v9-mkmlizer: Downloaded to shared memory in 228.599s
pawankrd-cosmosrp-v9-mkmlizer: quantizing model to /dev/shm/model_cache
pawankrd-cosmosrp-v9-mkmlizer: Saving flywheel model at /dev/shm/model_cache
pawankrd-cosmosrp-v9-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:06, 43.08it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:04, 62.91it/s] Loading 0: 7%|▋ | 21/291 [00:00<00:03, 70.13it/s] Loading 0: 10%|▉ | 29/291 [00:00<00:03, 73.30it/s] Loading 0: 13%|█▎ | 37/291 [00:00<00:03, 66.61it/s] Loading 0: 15%|█▌ | 44/291 [00:00<00:06, 39.23it/s] Loading 0: 17%|█▋ | 50/291 [00:01<00:05, 42.86it/s] Loading 0: 19%|█▉ | 56/291 [00:01<00:05, 43.39it/s] Loading 0: 21%|██▏ | 62/291 [00:01<00:04, 46.45it/s] Loading 0: 24%|██▍ | 70/291 [00:01<00:04, 53.60it/s] Loading 0: 26%|██▌ | 76/291 [00:01<00:04, 50.38it/s] Loading 0: 28%|██▊ | 82/291 [00:01<00:04, 49.09it/s] Loading 0: 31%|███ | 89/291 [00:01<00:03, 52.24it/s] Loading 0: 33%|███▎ | 96/291 [00:02<00:05, 37.19it/s] Loading 0: 35%|███▍ | 101/291 [00:02<00:04, 38.24it/s] Loading 0: 36%|███▋ | 106/291 [00:02<00:04, 38.65it/s] Loading 0: 38%|███▊ | 112/291 [00:02<00:04, 43.09it/s] Loading 0: 41%|████ | 120/291 [00:02<00:03, 51.28it/s] Loading 0: 43%|████▎ | 126/291 [00:02<00:03, 52.80it/s] Loading 0: 45%|████▌ | 132/291 [00:02<00:03, 52.13it/s] Loading 0: 47%|████▋ | 138/291 [00:02<00:02, 53.36it/s] Loading 0: 49%|████▉ | 144/291 [00:03<00:04, 34.97it/s] Loading 0: 51%|█████ | 149/291 [00:03<00:03, 36.56it/s] Loading 0: 54%|█████▍ | 157/291 [00:03<00:02, 45.07it/s] Loading 0: 57%|█████▋ | 165/291 [00:03<00:02, 52.05it/s] Loading 0: 59%|█████▉ | 171/291 [00:03<00:02, 53.49it/s] Loading 0: 61%|██████ | 177/291 [00:03<00:02, 52.04it/s] Loading 0: 63%|██████▎ | 184/291 [00:03<00:01, 55.60it/s] Loading 0: 66%|██████▌ | 191/291 [00:03<00:01, 58.21it/s] Loading 0: 68%|██████▊ | 198/291 [00:04<00:02, 36.86it/s] Loading 0: 70%|██████▉ | 203/291 [00:04<00:02, 37.99it/s] Loading 0: 73%|███████▎ | 211/291 [00:04<00:01, 46.43it/s] Loading 0: 75%|███████▌ | 219/291 [00:04<00:01, 53.02it/s] Loading 0: 78%|███████▊ | 226/291 [00:04<00:01, 56.79it/s] Loading 0: 80%|████████ | 233/291 [00:04<00:01, 56.23it/s] Loading 0: 82%|████████▏ | 240/291 [00:04<00:00, 56.34it/s] Loading 0: 86%|████████▌ | 249/291 [00:05<00:00, 42.66it/s] Loading 0: 88%|████████▊ | 255/291 [00:05<00:00, 41.89it/s] Loading 0: 90%|█████████ | 262/291 [00:05<00:00, 47.48it/s] Loading 0: 92%|█████████▏| 268/291 [00:05<00:00, 48.77it/s] Loading 0: 95%|█████████▍| 275/291 [00:05<00:00, 49.82it/s] Loading 0: 97%|█████████▋| 283/291 [00:05<00:00, 56.80it/s] Loading 0: 100%|██████████| 291/291 [00:11<00:00, 4.06it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
pawankrd-cosmosrp-v9-mkmlizer: quantized model in 27.653s
pawankrd-cosmosrp-v9-mkmlizer: Processed model PawanKrd/CosmosRP in 261.616s
pawankrd-cosmosrp-v9-mkmlizer: creating bucket guanaco-mkml-models
pawankrd-cosmosrp-v9-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
pawankrd-cosmosrp-v9-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/pawankrd-cosmosrp-v9
pawankrd-cosmosrp-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v9/tokenizer_config.json
pawankrd-cosmosrp-v9-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v9/special_tokens_map.json
pawankrd-cosmosrp-v9-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v9/config.json
pawankrd-cosmosrp-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v9/tokenizer.json
pawankrd-cosmosrp-v9-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/pawankrd-cosmosrp-v9/flywheel_model.0.safetensors
pawankrd-cosmosrp-v9-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
pawankrd-cosmosrp-v9-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-v9-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v9-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-v9-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v9-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-v9-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v9-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-v9-mkmlizer: return self.fget.__get__(instance, owner)()
pawankrd-cosmosrp-v9-mkmlizer: Saving duration: 0.424s
pawankrd-cosmosrp-v9-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.333s
pawankrd-cosmosrp-v9-mkmlizer: creating bucket guanaco-reward-models
pawankrd-cosmosrp-v9-mkmlizer: Bucket 's3://guanaco-reward-models/' created
pawankrd-cosmosrp-v9-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/pawankrd-cosmosrp-v9_reward
pawankrd-cosmosrp-v9-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/pawankrd-cosmosrp-v9_reward/tokenizer_config.json
pawankrd-cosmosrp-v9-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/pawankrd-cosmosrp-v9_reward/special_tokens_map.json
pawankrd-cosmosrp-v9-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/pawankrd-cosmosrp-v9_reward/config.json
pawankrd-cosmosrp-v9-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/pawankrd-cosmosrp-v9_reward/merges.txt
pawankrd-cosmosrp-v9-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/pawankrd-cosmosrp-v9_reward/vocab.json
pawankrd-cosmosrp-v9-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/pawankrd-cosmosrp-v9_reward/tokenizer.json
pawankrd-cosmosrp-v9-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/pawankrd-cosmosrp-v9_reward/reward.tensors
Job pawankrd-cosmosrp-v9-mkmlizer completed after 299.71s with status: succeeded
Stopping job with name pawankrd-cosmosrp-v9-mkmlizer
Pipeline stage MKMLizer completed in 304.49s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service pawankrd-cosmosrp-v9
Waiting for inference service pawankrd-cosmosrp-v9 to be ready
Inference service pawankrd-cosmosrp-v9 ready after 40.2588164806366s
Pipeline stage ISVCDeployer completed in 47.64s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.206267833709717s
Received healthy response to inference request in 1.3937468528747559s
Received healthy response to inference request in 1.8165993690490723s
Received healthy response to inference request in 2.136587142944336s
Received healthy response to inference request in 1.6594979763031006s
5 requests
0 failed requests
5th percentile: 1.4468970775604248
10th percentile: 1.5000473022460938
20th percentile: 1.6063477516174316
30th percentile: 1.690918254852295
40th percentile: 1.7537588119506835
50th percentile: 1.8165993690490723
60th percentile: 1.9445944786071778
70th percentile: 2.072589588165283
80th percentile: 2.150523281097412
90th percentile: 2.1783955574035643
95th percentile: 2.1923316955566405
99th percentile: 2.2034806060791015
mean time: 1.8425398349761963
Pipeline stage StressChecker completed in 9.92s
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 0.05s
M-Eval Dataset for topic stay_in_character is loaded
pawankrd-cosmosrp_v9 status is now deployed due to DeploymentManager action
pawankrd-cosmosrp_v9 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of pawankrd-cosmosrp_v9
Running pipeline stage ISVCDeleter
Checking if service pawankrd-cosmosrp-v9 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.11s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key pawankrd-cosmosrp-v9/config.json from bucket guanaco-mkml-models
Deleting key pawankrd-cosmosrp-v9/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key pawankrd-cosmosrp-v9/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key pawankrd-cosmosrp-v9/tokenizer.json from bucket guanaco-mkml-models
Deleting key pawankrd-cosmosrp-v9/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key pawankrd-cosmosrp-v9_reward/config.json from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-v9_reward/merges.txt from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-v9_reward/reward.tensors from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-v9_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-v9_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-v9_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-v9_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.10s
pawankrd-cosmosrp_v9 status is now torndown due to DeploymentManager action