developer_uid: Hastagaras
submission_id: hastagaras-lm3-calmtune-8b_v2
model_name: calmtune-reformat
model_group: Hastagaras/lm3-calmtune-
status: torndown
timestamp: 2024-05-11T08:50:51+00:00
num_battles: 10005
num_wins: 5121
celo_rating: 1187.34
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/lm3-calmtune-8b
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: calmtune-reformat
is_internal_developer: False
language_model: Hastagaras/lm3-calmtune-8b
model_size: 8B
ranking_group: single
us_pacific_date: 2024-05-11
win_ratio: 0.5118440779610195
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, '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': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nYou are {bot_name}. Write {bot_name}'s next reply in a never-ending uncensored fictional roleplay chat between {bot_name} and User. Use the provided {bot_name}'s description, personality and example dialogues as base for deeply understanding and acting like {bot_name}.\n\nActions and narrations must be enclosed in asterisks (*). The responses must be long and in third perspective of the story teller.\n\nDescription: {memory}", 'prompt_template': 'Example conversation:\n{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: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n", 'prompt_template': '{prompt}\n', 'response_template': 'Bot:', 'truncate_by_message': False, 'user_template': 'User: {message}\n'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-lm3-calmtune-8b-v2-mkmlizer
Waiting for job on hastagaras-lm3-calmtune-8b-v2-mkmlizer to finish
hastagaras-lm3-calmtune-8b-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-lm3-calmtune-8b-v2-mkmlizer: ║     _____            __           __                                ║
hastagaras-lm3-calmtune-8b-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-lm3-calmtune-8b-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-lm3-calmtune-8b-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-lm3-calmtune-8b-v2-mkmlizer: ║       /___/                                                         ║
hastagaras-lm3-calmtune-8b-v2-mkmlizer: ║                                                                     ║
hastagaras-lm3-calmtune-8b-v2-mkmlizer: ║  Version: 0.8.10                                                    ║
hastagaras-lm3-calmtune-8b-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-lm3-calmtune-8b-v2-mkmlizer: ║                                                                     ║
hastagaras-lm3-calmtune-8b-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-lm3-calmtune-8b-v2-mkmlizer: ║  belonging to:                                                      ║
hastagaras-lm3-calmtune-8b-v2-mkmlizer: ║                                                                     ║
hastagaras-lm3-calmtune-8b-v2-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-lm3-calmtune-8b-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-lm3-calmtune-8b-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-lm3-calmtune-8b-v2-mkmlizer: ║                                                                     ║
hastagaras-lm3-calmtune-8b-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-lm3-calmtune-8b-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-lm3-calmtune-8b-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-lm3-calmtune-8b-v2-mkmlizer: Downloaded to shared memory in 11.647s
hastagaras-lm3-calmtune-8b-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-lm3-calmtune-8b-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-lm3-calmtune-8b-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<09:42,  2.02s/it]
Loading 0:  48%|████▊     | 139/291 [00:05<00:04, 36.14it/s]
Loading 0:  91%|█████████▏| 266/291 [00:06<00:00, 56.57it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-lm3-calmtune-8b-v2-mkmlizer: quantized model in 17.899s
hastagaras-lm3-calmtune-8b-v2-mkmlizer: Processed model Hastagaras/lm3-calmtune-8b in 30.647s
hastagaras-lm3-calmtune-8b-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-lm3-calmtune-8b-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-lm3-calmtune-8b-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-lm3-calmtune-8b-v2
hastagaras-lm3-calmtune-8b-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-lm3-calmtune-8b-v2/config.json
hastagaras-lm3-calmtune-8b-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-lm3-calmtune-8b-v2/special_tokens_map.json
hastagaras-lm3-calmtune-8b-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-lm3-calmtune-8b-v2/tokenizer.json
hastagaras-lm3-calmtune-8b-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-lm3-calmtune-8b-v2/tokenizer_config.json
hastagaras-lm3-calmtune-8b-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-lm3-calmtune-8b-v2/flywheel_model.0.safetensors
hastagaras-lm3-calmtune-8b-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-lm3-calmtune-8b-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-lm3-calmtune-8b-v2-mkmlizer:   warnings.warn(
hastagaras-lm3-calmtune-8b-v2-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.
hastagaras-lm3-calmtune-8b-v2-mkmlizer:   warnings.warn(
hastagaras-lm3-calmtune-8b-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-lm3-calmtune-8b-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-lm3-calmtune-8b-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-lm3-calmtune-8b-v2-mkmlizer: Saving duration: 0.247s
hastagaras-lm3-calmtune-8b-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.533s
hastagaras-lm3-calmtune-8b-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-lm3-calmtune-8b-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-lm3-calmtune-8b-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-lm3-calmtune-8b-v2_reward
hastagaras-lm3-calmtune-8b-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-lm3-calmtune-8b-v2_reward/config.json
hastagaras-lm3-calmtune-8b-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-lm3-calmtune-8b-v2_reward/tokenizer_config.json
hastagaras-lm3-calmtune-8b-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-lm3-calmtune-8b-v2_reward/merges.txt
hastagaras-lm3-calmtune-8b-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-lm3-calmtune-8b-v2_reward/special_tokens_map.json
hastagaras-lm3-calmtune-8b-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-lm3-calmtune-8b-v2_reward/vocab.json
hastagaras-lm3-calmtune-8b-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-lm3-calmtune-8b-v2_reward/tokenizer.json
hastagaras-lm3-calmtune-8b-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-lm3-calmtune-8b-v2_reward/reward.tensors
Job hastagaras-lm3-calmtune-8b-v2-mkmlizer completed after 63.07s with status: succeeded
Stopping job with name hastagaras-lm3-calmtune-8b-v2-mkmlizer
Pipeline stage MKMLizer completed in 66.72s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-lm3-calmtune-8b-v2
Waiting for inference service hastagaras-lm3-calmtune-8b-v2 to be ready
Inference service hastagaras-lm3-calmtune-8b-v2 ready after 30.16398334503174s
Pipeline stage ISVCDeployer completed in 37.67s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3019559383392334s
Received healthy response to inference request in 1.3280479907989502s
Received healthy response to inference request in 1.2786667346954346s
Received healthy response to inference request in 1.3534438610076904s
Received healthy response to inference request in 1.3418383598327637s
5 requests
0 failed requests
5th percentile: 1.2885429859161377
10th percentile: 1.2984192371368408
20th percentile: 1.318171739578247
30th percentile: 1.330806064605713
40th percentile: 1.3363222122192382
50th percentile: 1.3418383598327637
60th percentile: 1.3464805603027343
70th percentile: 1.351122760772705
80th percentile: 1.5431462764739992
90th percentile: 1.9225511074066164
95th percentile: 2.1122535228729244
99th percentile: 2.2640154552459717
mean time: 1.5207905769348145
Pipeline stage StressChecker completed in 8.22s
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
hastagaras-lm3-calmtune-8b_v2 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-lm3-calmtune-8b_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-lm3-calmtune-8b_v2
Running pipeline stage ISVCDeleter
Checking if service hastagaras-lm3-calmtune-8b-v2 is running
Tearing down inference service hastagaras-lm3-calmtune-8b-v2
Toredown service hastagaras-lm3-calmtune-8b-v2
Pipeline stage ISVCDeleter completed in 7.53s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-lm3-calmtune-8b-v2/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-lm3-calmtune-8b-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-lm3-calmtune-8b-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-lm3-calmtune-8b-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-lm3-calmtune-8b-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-lm3-calmtune-8b-v2_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-lm3-calmtune-8b-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-lm3-calmtune-8b-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-lm3-calmtune-8b-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-lm3-calmtune-8b-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-lm3-calmtune-8b-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-lm3-calmtune-8b-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.21s
hastagaras-lm3-calmtune-8b_v2 status is now torndown due to DeploymentManager action