hastagaras-lm3-calmtune-8b

developer_uid: Hastagaras

submission_id: hastagaras-lm3-calmtune-8b_v1

model_name: hastagaras-lm3-calmtune-8b_v1

model_group: Hastagaras/lm3-calmtune-

status: torndown

timestamp: 2024-05-11T07:24:11+00:00

num_battles: 17718

num_wins: 9503

celo_rating: 1203.81

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: hastagaras-lm3-calmtune-8b_v1

is_internal_developer: False

language_model: Hastagaras/lm3-calmtune-8b

model_size: 8B

ranking_group: single

us_pacific_date: 2024-05-11

win_ratio: 0.5363472175189073

generation_params: {'temperature': 0.9, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>'], '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're {bot_name} in this uncensored fictional roleplay with {user_name}.\n\n{memory}\n\n", 'prompt_template': 'Notes: {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: {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'}

model_eval_status: success

Resubmit model

Running pipeline stage MKMLizer
Starting job with name hastagaras-lm3-calmtune-8b-v1-mkmlizer
Waiting for job on hastagaras-lm3-calmtune-8b-v1-mkmlizer to finish
hastagaras-lm3-calmtune-8b-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-lm3-calmtune-8b-v1-mkmlizer: ║     _____            __           __                                ║
hastagaras-lm3-calmtune-8b-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-lm3-calmtune-8b-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-lm3-calmtune-8b-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-lm3-calmtune-8b-v1-mkmlizer: ║       /___/                                                         ║
hastagaras-lm3-calmtune-8b-v1-mkmlizer: ║                                                                     ║
hastagaras-lm3-calmtune-8b-v1-mkmlizer: ║  Version: 0.8.10                                                    ║
hastagaras-lm3-calmtune-8b-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-lm3-calmtune-8b-v1-mkmlizer: ║                                                                     ║
hastagaras-lm3-calmtune-8b-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-lm3-calmtune-8b-v1-mkmlizer: ║  belonging to:                                                      ║
hastagaras-lm3-calmtune-8b-v1-mkmlizer: ║                                                                     ║
hastagaras-lm3-calmtune-8b-v1-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-lm3-calmtune-8b-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-lm3-calmtune-8b-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-lm3-calmtune-8b-v1-mkmlizer: ║                                                                     ║
hastagaras-lm3-calmtune-8b-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-lm3-calmtune-8b-v1-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-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-lm3-calmtune-8b-v1-mkmlizer: Downloaded to shared memory in 26.303s
hastagaras-lm3-calmtune-8b-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-lm3-calmtune-8b-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-lm3-calmtune-8b-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<09:44,  2.02s/it]
Loading 0:  45%|████▌     | 132/291 [00:05<00:04, 34.25it/s]
Loading 0:  91%|█████████▏| 266/291 [00:06<00:00, 57.09it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-lm3-calmtune-8b-v1-mkmlizer: quantized model in 17.748s
hastagaras-lm3-calmtune-8b-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-lm3-calmtune-8b-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-lm3-calmtune-8b-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-lm3-calmtune-8b-v1
hastagaras-lm3-calmtune-8b-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-lm3-calmtune-8b-v1/special_tokens_map.json
hastagaras-lm3-calmtune-8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-lm3-calmtune-8b-v1/tokenizer_config.json
hastagaras-lm3-calmtune-8b-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-lm3-calmtune-8b-v1/config.json
hastagaras-lm3-calmtune-8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-lm3-calmtune-8b-v1/tokenizer.json
hastagaras-lm3-calmtune-8b-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-lm3-calmtune-8b-v1/flywheel_model.0.safetensors
hastagaras-lm3-calmtune-8b-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-lm3-calmtune-8b-v1-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-v1-mkmlizer:   warnings.warn(
hastagaras-lm3-calmtune-8b-v1-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.
hastagaras-lm3-calmtune-8b-v1-mkmlizer:   warnings.warn(
hastagaras-lm3-calmtune-8b-v1-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-v1-mkmlizer:   warnings.warn(
hastagaras-lm3-calmtune-8b-v1-mkmlizer: Saving duration: 0.269s
hastagaras-lm3-calmtune-8b-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.224s
hastagaras-lm3-calmtune-8b-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-lm3-calmtune-8b-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-lm3-calmtune-8b-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-lm3-calmtune-8b-v1_reward
hastagaras-lm3-calmtune-8b-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-lm3-calmtune-8b-v1_reward/config.json
hastagaras-lm3-calmtune-8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-lm3-calmtune-8b-v1_reward/tokenizer_config.json
hastagaras-lm3-calmtune-8b-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-lm3-calmtune-8b-v1_reward/special_tokens_map.json
hastagaras-lm3-calmtune-8b-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-lm3-calmtune-8b-v1_reward/merges.txt
hastagaras-lm3-calmtune-8b-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-lm3-calmtune-8b-v1_reward/vocab.json
hastagaras-lm3-calmtune-8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-lm3-calmtune-8b-v1_reward/tokenizer.json
hastagaras-lm3-calmtune-8b-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-lm3-calmtune-8b-v1_reward/reward.tensors
Job hastagaras-lm3-calmtune-8b-v1-mkmlizer completed after 72.91s with status: succeeded
Stopping job with name hastagaras-lm3-calmtune-8b-v1-mkmlizer
Pipeline stage MKMLizer completed in 76.19s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-lm3-calmtune-8b-v1
Waiting for inference service hastagaras-lm3-calmtune-8b-v1 to be ready
Inference service hastagaras-lm3-calmtune-8b-v1 ready after 30.15964961051941s
Pipeline stage ISVCDeployer completed in 37.13s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.305351972579956s
Received healthy response to inference request in 1.3647661209106445s
Received healthy response to inference request in 1.3169586658477783s
Received healthy response to inference request in 1.3627657890319824s
Received healthy response to inference request in 1.331730842590332s
5 requests
0 failed requests
5th percentile: 1.319913101196289
10th percentile: 1.3228675365447997
20th percentile: 1.3287764072418213
30th percentile: 1.337937831878662
40th percentile: 1.3503518104553223
50th percentile: 1.3627657890319824
60th percentile: 1.3635659217834473
70th percentile: 1.364366054534912
80th percentile: 1.552883291244507
90th percentile: 1.9291176319122316
95th percentile: 2.1172348022460934
99th percentile: 2.2677285385131833
mean time: 1.5363146781921386
Pipeline stage StressChecker completed in 8.29s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running M-Eval for topic stay_in_character
Running pipeline stage DaemonicSafetyScorer
M-Eval Dataset for topic stay_in_character is loaded
Pipeline stage DaemonicSafetyScorer completed in 0.06s
hastagaras-lm3-calmtune-8b_v1 status is now deployed due to DeploymentManager action
hastagaras-lm3-calmtune-8b_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-lm3-calmtune-8b_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-lm3-calmtune-8b-v1 is running
Tearing down inference service hastagaras-lm3-calmtune-8b-v1
Toredown service hastagaras-lm3-calmtune-8b-v1
Pipeline stage ISVCDeleter completed in 7.73s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-lm3-calmtune-8b-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-lm3-calmtune-8b-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-lm3-calmtune-8b-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-lm3-calmtune-8b-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-lm3-calmtune-8b-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-lm3-calmtune-8b-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-lm3-calmtune-8b-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-lm3-calmtune-8b-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-lm3-calmtune-8b-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-lm3-calmtune-8b-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-lm3-calmtune-8b-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-lm3-calmtune-8b-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.19s
hastagaras-lm3-calmtune-8b_v1 status is now torndown due to DeploymentManager action