developer_uid: PawanOsman
submission_id: pawankrd-cosmosrp_v6
model_name: pawankrd-cosmosrp_v6
model_group: PawanKrd/CosmosRP
status: torndown
timestamp: 2024-06-14T11:53:08+00:00
num_battles: 34634
num_wins: 18417
celo_rating: 1205.29
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_v6
is_internal_developer: False
language_model: PawanKrd/CosmosRP
model_size: 8B
ranking_group: single
us_pacific_date: 2024-06-14
win_ratio: 0.5317606975804123
generation_params: {'temperature': 0.9, 'top_p': 1.0, '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}
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'}
model_eval_status: success
Resubmit model
Running pipeline stage MKMLizer
Starting job with name pawankrd-cosmosrp-v6-mkmlizer
Waiting for job on pawankrd-cosmosrp-v6-mkmlizer to finish
pawankrd-cosmosrp-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
pawankrd-cosmosrp-v6-mkmlizer: ║ _____ __ __ ║
pawankrd-cosmosrp-v6-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
pawankrd-cosmosrp-v6-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
pawankrd-cosmosrp-v6-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
pawankrd-cosmosrp-v6-mkmlizer: ║ /___/ ║
pawankrd-cosmosrp-v6-mkmlizer: ║ ║
pawankrd-cosmosrp-v6-mkmlizer: ║ Version: 0.8.14 ║
pawankrd-cosmosrp-v6-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
pawankrd-cosmosrp-v6-mkmlizer: ║ https://mk1.ai ║
pawankrd-cosmosrp-v6-mkmlizer: ║ ║
pawankrd-cosmosrp-v6-mkmlizer: ║ The license key for the current software has been verified as ║
pawankrd-cosmosrp-v6-mkmlizer: ║ belonging to: ║
pawankrd-cosmosrp-v6-mkmlizer: ║ ║
pawankrd-cosmosrp-v6-mkmlizer: ║ Chai Research Corp. ║
pawankrd-cosmosrp-v6-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
pawankrd-cosmosrp-v6-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
pawankrd-cosmosrp-v6-mkmlizer: ║ ║
pawankrd-cosmosrp-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
pawankrd-cosmosrp-v6-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-v6-mkmlizer: warnings.warn(warning_message, FutureWarning)
pawankrd-cosmosrp-v6-mkmlizer: Downloaded to shared memory in 31.606s
pawankrd-cosmosrp-v6-mkmlizer: quantizing model to /dev/shm/model_cache
pawankrd-cosmosrp-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
pawankrd-cosmosrp-v6-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<10:53, 2.26s/it] Loading 0: 5%|▌ | 15/291 [00:04<01:02, 4.40it/s] Loading 0: 11%|█▏ | 33/291 [00:04<00:22, 11.69it/s] Loading 0: 18%|█▊ | 51/291 [00:04<00:11, 21.01it/s] Loading 0: 22%|██▏ | 65/291 [00:05<00:09, 24.73it/s] Loading 0: 27%|██▋ | 78/291 [00:05<00:06, 33.03it/s] Loading 0: 33%|███▎ | 95/291 [00:05<00:04, 47.06it/s] Loading 0: 39%|███▉ | 113/291 [00:05<00:02, 62.27it/s] Loading 0: 45%|████▍ | 130/291 [00:05<00:02, 77.68it/s] Loading 0: 50%|█████ | 146/291 [00:05<00:01, 92.10it/s] Loading 0: 55%|█████▌ | 161/291 [00:05<00:01, 102.68it/s] Loading 0: 60%|██████ | 176/291 [00:06<00:01, 65.84it/s] Loading 0: 66%|██████▋ | 193/291 [00:06<00:01, 81.57it/s] Loading 0: 73%|███████▎ | 211/291 [00:06<00:00, 96.95it/s] Loading 0: 79%|███████▊ | 229/291 [00:06<00:00, 111.07it/s] Loading 0: 85%|████████▍ | 247/291 [00:06<00:00, 122.46it/s] Loading 0: 91%|█████████ | 265/291 [00:06<00:00, 131.50it/s] Loading 0: 97%|█████████▋| 281/291 [00:07<00:00, 85.33it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
pawankrd-cosmosrp-v6-mkmlizer: quantized model in 23.363s
pawankrd-cosmosrp-v6-mkmlizer: Processed model PawanKrd/CosmosRP in 57.670s
pawankrd-cosmosrp-v6-mkmlizer: creating bucket guanaco-mkml-models
pawankrd-cosmosrp-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
pawankrd-cosmosrp-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/pawankrd-cosmosrp-v6
pawankrd-cosmosrp-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v6/config.json
pawankrd-cosmosrp-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v6/special_tokens_map.json
pawankrd-cosmosrp-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v6/tokenizer_config.json
pawankrd-cosmosrp-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v6/tokenizer.json
pawankrd-cosmosrp-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/pawankrd-cosmosrp-v6/flywheel_model.0.safetensors
pawankrd-cosmosrp-v6-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
pawankrd-cosmosrp-v6-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-v6-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v6-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-v6-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v6-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-v6-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v6-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-v6-mkmlizer: return self.fget.__get__(instance, owner)()
pawankrd-cosmosrp-v6-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
pawankrd-cosmosrp-v6-mkmlizer: Saving duration: 0.449s
pawankrd-cosmosrp-v6-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.882s
pawankrd-cosmosrp-v6-mkmlizer: creating bucket guanaco-reward-models
pawankrd-cosmosrp-v6-mkmlizer: Bucket 's3://guanaco-reward-models/' created
pawankrd-cosmosrp-v6-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/pawankrd-cosmosrp-v6_reward
pawankrd-cosmosrp-v6-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/pawankrd-cosmosrp-v6_reward/config.json
pawankrd-cosmosrp-v6-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/pawankrd-cosmosrp-v6_reward/special_tokens_map.json
pawankrd-cosmosrp-v6-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/pawankrd-cosmosrp-v6_reward/tokenizer_config.json
pawankrd-cosmosrp-v6-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/pawankrd-cosmosrp-v6_reward/tokenizer.json
pawankrd-cosmosrp-v6-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/pawankrd-cosmosrp-v6_reward/merges.txt
pawankrd-cosmosrp-v6-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/pawankrd-cosmosrp-v6_reward/vocab.json
pawankrd-cosmosrp-v6-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/pawankrd-cosmosrp-v6_reward/reward.tensors
Job pawankrd-cosmosrp-v6-mkmlizer completed after 83.73s with status: succeeded
Stopping job with name pawankrd-cosmosrp-v6-mkmlizer
Pipeline stage MKMLizer completed in 87.09s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service pawankrd-cosmosrp-v6
Waiting for inference service pawankrd-cosmosrp-v6 to be ready
Inference service pawankrd-cosmosrp-v6 ready after 40.24582386016846s
Pipeline stage ISVCDeployer completed in 47.45s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1754472255706787s
Received healthy response to inference request in 1.3837230205535889s
Received healthy response to inference request in 1.338149070739746s
Received healthy response to inference request in 1.310103178024292s
Received healthy response to inference request in 1.272171974182129s
5 requests
0 failed requests
5th percentile: 1.2797582149505615
10th percentile: 1.2873444557189941
20th percentile: 1.3025169372558594
30th percentile: 1.3157123565673827
40th percentile: 1.3269307136535644
50th percentile: 1.338149070739746
60th percentile: 1.3563786506652833
70th percentile: 1.3746082305908203
80th percentile: 1.542067861557007
90th percentile: 1.8587575435638428
95th percentile: 2.0171023845672607
99th percentile: 2.1437782573699953
mean time: 1.4959188938140868
Pipeline stage StressChecker completed in 8.12s
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_v6 status is now deployed due to DeploymentManager action
pawankrd-cosmosrp_v6 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of pawankrd-cosmosrp_v6
Running pipeline stage ISVCDeleter
Checking if service pawankrd-cosmosrp-v6 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 3.85s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key pawankrd-cosmosrp-v6/config.json from bucket guanaco-mkml-models
Deleting key pawankrd-cosmosrp-v6/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key pawankrd-cosmosrp-v6/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key pawankrd-cosmosrp-v6/tokenizer.json from bucket guanaco-mkml-models
Deleting key pawankrd-cosmosrp-v6/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key pawankrd-cosmosrp-v6_reward/config.json from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-v6_reward/merges.txt from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-v6_reward/reward.tensors from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-v6_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-v6_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-v6_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key pawankrd-cosmosrp-v6_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.93s
pawankrd-cosmosrp_v6 status is now torndown due to DeploymentManager action