developer_uid: Nitral-AI
submission_id: nitral-ai-pp-1-4-phase1_v6
model_name: nitral-ai-pp-1-4-phase1_v6
model_group: Nitral-AI/Pp-1.4-Phase1
status: torndown
timestamp: 2024-06-02T02:17:04+00:00
num_battles: 8112
num_wins: 4436
celo_rating: 1215.49
family_friendly_score: 0.0
submission_type: basic
model_repo: Nitral-AI/Pp-1.4-Phase1
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: nitral-ai-pp-1-4-phase1_v6
is_internal_developer: False
language_model: Nitral-AI/Pp-1.4-Phase1
model_size: 8B
ranking_group: single
us_pacific_date: 2024-06-01
win_ratio: 0.546844181459566
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.08, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], '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 nitral-ai-pp-1-4-phase1-v6-mkmlizer
Waiting for job on nitral-ai-pp-1-4-phase1-v6-mkmlizer to finish
Stopping job with name nitral-ai-pp-1-4-phase1-v6-mkmlizer
%s, retrying in %s seconds...
Starting job with name nitral-ai-pp-1-4-phase1-v6-mkmlizer
Waiting for job on nitral-ai-pp-1-4-phase1-v6-mkmlizer to finish
nitral-ai-pp-1-4-phase1-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-pp-1-4-phase1-v6-mkmlizer: ║ _____ __ __ ║
nitral-ai-pp-1-4-phase1-v6-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nitral-ai-pp-1-4-phase1-v6-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nitral-ai-pp-1-4-phase1-v6-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nitral-ai-pp-1-4-phase1-v6-mkmlizer: ║ /___/ ║
nitral-ai-pp-1-4-phase1-v6-mkmlizer: ║ ║
nitral-ai-pp-1-4-phase1-v6-mkmlizer: ║ Version: 0.8.14 ║
nitral-ai-pp-1-4-phase1-v6-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nitral-ai-pp-1-4-phase1-v6-mkmlizer: ║ https://mk1.ai ║
nitral-ai-pp-1-4-phase1-v6-mkmlizer: ║ ║
nitral-ai-pp-1-4-phase1-v6-mkmlizer: ║ The license key for the current software has been verified as ║
nitral-ai-pp-1-4-phase1-v6-mkmlizer: ║ belonging to: ║
nitral-ai-pp-1-4-phase1-v6-mkmlizer: ║ ║
nitral-ai-pp-1-4-phase1-v6-mkmlizer: ║ Chai Research Corp. ║
nitral-ai-pp-1-4-phase1-v6-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nitral-ai-pp-1-4-phase1-v6-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
nitral-ai-pp-1-4-phase1-v6-mkmlizer: ║ ║
nitral-ai-pp-1-4-phase1-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nitral-ai-pp-1-4-phase1-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.
nitral-ai-pp-1-4-phase1-v6-mkmlizer: warnings.warn(warning_message, FutureWarning)
nitral-ai-pp-1-4-phase1-v6-mkmlizer: Downloaded to shared memory in 16.516s
nitral-ai-pp-1-4-phase1-v6-mkmlizer: quantizing model to /dev/shm/model_cache
nitral-ai-pp-1-4-phase1-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nitral-ai-pp-1-4-phase1-v6-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:01, 2.29s/it] Loading 0: 5%|▌ | 15/291 [00:04<01:03, 4.35it/s] Loading 0: 11%|█▏ | 33/291 [00:04<00:22, 11.56it/s] Loading 0: 18%|█▊ | 51/291 [00:04<00:11, 20.78it/s] Loading 0: 22%|██▏ | 65/291 [00:05<00:09, 24.64it/s] Loading 0: 27%|██▋ | 78/291 [00:05<00:06, 32.98it/s] Loading 0: 33%|███▎ | 95/291 [00:05<00:04, 46.93it/s] Loading 0: 39%|███▉ | 113/291 [00:05<00:02, 62.76it/s] Loading 0: 45%|████▌ | 131/291 [00:05<00:02, 78.90it/s] Loading 0: 50%|█████ | 146/291 [00:05<00:01, 91.23it/s] Loading 0: 55%|█████▌ | 161/291 [00:05<00:01, 102.36it/s] Loading 0: 60%|██████ | 176/291 [00:06<00:01, 67.22it/s] Loading 0: 67%|██████▋ | 194/291 [00:06<00:01, 83.53it/s] Loading 0: 73%|███████▎ | 212/291 [00:06<00:00, 99.15it/s] Loading 0: 79%|███████▉ | 230/291 [00:06<00:00, 112.98it/s] Loading 0: 85%|████████▌ | 248/291 [00:06<00:00, 124.06it/s] Loading 0: 91%|█████████▏| 266/291 [00:07<00:00, 81.50it/s] Loading 0: 98%|█████████▊| 284/291 [00:07<00:00, 96.31it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
nitral-ai-pp-1-4-phase1-v6-mkmlizer: quantized model in 23.641s
nitral-ai-pp-1-4-phase1-v6-mkmlizer: Processed model Nitral-AI/Pp-1.4-Phase1 in 42.829s
nitral-ai-pp-1-4-phase1-v6-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-pp-1-4-phase1-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-pp-1-4-phase1-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-pp-1-4-phase1-v6
nitral-ai-pp-1-4-phase1-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-pp-1-4-phase1-v6/config.json
nitral-ai-pp-1-4-phase1-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-pp-1-4-phase1-v6/special_tokens_map.json
nitral-ai-pp-1-4-phase1-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-pp-1-4-phase1-v6/tokenizer_config.json
nitral-ai-pp-1-4-phase1-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-pp-1-4-phase1-v6/tokenizer.json
nitral-ai-pp-1-4-phase1-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nitral-ai-pp-1-4-phase1-v6/flywheel_model.0.safetensors
nitral-ai-pp-1-4-phase1-v6-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
nitral-ai-pp-1-4-phase1-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.
nitral-ai-pp-1-4-phase1-v6-mkmlizer: warnings.warn(
nitral-ai-pp-1-4-phase1-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.
nitral-ai-pp-1-4-phase1-v6-mkmlizer: warnings.warn(
nitral-ai-pp-1-4-phase1-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.
nitral-ai-pp-1-4-phase1-v6-mkmlizer: warnings.warn(
nitral-ai-pp-1-4-phase1-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()
nitral-ai-pp-1-4-phase1-v6-mkmlizer: return self.fget.__get__(instance, owner)()
nitral-ai-pp-1-4-phase1-v6-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nitral-ai-pp-1-4-phase1-v6-mkmlizer: Saving duration: 0.466s
nitral-ai-pp-1-4-phase1-v6-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.247s
nitral-ai-pp-1-4-phase1-v6-mkmlizer: creating bucket guanaco-reward-models
nitral-ai-pp-1-4-phase1-v6-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nitral-ai-pp-1-4-phase1-v6-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nitral-ai-pp-1-4-phase1-v6_reward
nitral-ai-pp-1-4-phase1-v6-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nitral-ai-pp-1-4-phase1-v6_reward/config.json
nitral-ai-pp-1-4-phase1-v6-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nitral-ai-pp-1-4-phase1-v6_reward/tokenizer_config.json
nitral-ai-pp-1-4-phase1-v6-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nitral-ai-pp-1-4-phase1-v6_reward/merges.txt
nitral-ai-pp-1-4-phase1-v6-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nitral-ai-pp-1-4-phase1-v6_reward/vocab.json
nitral-ai-pp-1-4-phase1-v6-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nitral-ai-pp-1-4-phase1-v6_reward/special_tokens_map.json
nitral-ai-pp-1-4-phase1-v6-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nitral-ai-pp-1-4-phase1-v6_reward/tokenizer.json
nitral-ai-pp-1-4-phase1-v6-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nitral-ai-pp-1-4-phase1-v6_reward/reward.tensors
Job nitral-ai-pp-1-4-phase1-v6-mkmlizer completed after 73.27s with status: succeeded
Stopping job with name nitral-ai-pp-1-4-phase1-v6-mkmlizer
Pipeline stage MKMLizer completed in 76.67s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service nitral-ai-pp-1-4-phase1-v6
Waiting for inference service nitral-ai-pp-1-4-phase1-v6 to be ready
Inference service nitral-ai-pp-1-4-phase1-v6 ready after 40.214778423309326s
Pipeline stage ISVCDeployer completed in 46.98s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.145704507827759s
Received healthy response to inference request in 1.3463408946990967s
Received healthy response to inference request in 1.3479809761047363s
Received healthy response to inference request in 1.3060176372528076s
Received healthy response to inference request in 1.237522840499878s
5 requests
0 failed requests
5th percentile: 1.2512217998504638
10th percentile: 1.2649207592010498
20th percentile: 1.2923186779022218
30th percentile: 1.3140822887420653
40th percentile: 1.330211591720581
50th percentile: 1.3463408946990967
60th percentile: 1.3469969272613525
70th percentile: 1.3476529598236084
80th percentile: 1.507525682449341
90th percentile: 1.8266150951385498
95th percentile: 1.986159801483154
99th percentile: 2.1137955665588377
mean time: 1.4767133712768554
Pipeline stage StressChecker completed in 8.03s
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 0.03s
M-Eval Dataset for topic stay_in_character is loaded
nitral-ai-pp-1-4-phase1_v6 status is now deployed due to DeploymentManager action
nitral-ai-pp-1-4-phase1_v6 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of nitral-ai-pp-1-4-phase1_v6
Running pipeline stage ISVCDeleter
Checking if service nitral-ai-pp-1-4-phase1-v6 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.21s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key nitral-ai-pp-1-4-phase1-v6/config.json from bucket guanaco-mkml-models
Deleting key nitral-ai-pp-1-4-phase1-v6/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key nitral-ai-pp-1-4-phase1-v6/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key nitral-ai-pp-1-4-phase1-v6/tokenizer.json from bucket guanaco-mkml-models
Deleting key nitral-ai-pp-1-4-phase1-v6/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key nitral-ai-pp-1-4-phase1-v6_reward/config.json from bucket guanaco-reward-models
Deleting key nitral-ai-pp-1-4-phase1-v6_reward/merges.txt from bucket guanaco-reward-models
Deleting key nitral-ai-pp-1-4-phase1-v6_reward/reward.tensors from bucket guanaco-reward-models
Deleting key nitral-ai-pp-1-4-phase1-v6_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key nitral-ai-pp-1-4-phase1-v6_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key nitral-ai-pp-1-4-phase1-v6_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key nitral-ai-pp-1-4-phase1-v6_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.16s
nitral-ai-pp-1-4-phase1_v6 status is now torndown due to DeploymentManager action