hastagaras-l3-malmer-8b

developer_uid: Hastagaras

submission_id: hastagaras-l3-malmer-8b_v1

model_name: hastagaras-l3-malmer-8b_v1

model_group: Hastagaras/L3-Malmer-8B

status: torndown

timestamp: 2024-04-25T12:48:45+00:00

num_battles: 5730

num_wins: 3199

celo_rating: 1193.33

family_friendly_score: 0.0

submission_type: basic

model_repo: Hastagaras/L3-Malmer-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-l3-malmer-8b_v1

is_internal_developer: False

language_model: Hastagaras/L3-Malmer-8B

model_size: 8B

ranking_group: single

us_pacific_date: 2024-04-25

win_ratio: 0.5582897033158813

generation_params: {'temperature': 0.85, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 1.1, 'stopping_words': ['\n', '</s>', '###', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}

formatter: {'memory_template': 'Respond as {bot_name} in a roleplay chat with {user_name}. Use *asterisks* for actions/gestures and `backticks` for thoughts/inner monologue.\n{memory}', 'prompt_template': '\n### Response:\n{bot_name}: {prompt}', 'bot_template': '\n### Response:\n{bot_name}: {message}', 'user_template': '\n### Instruction:\n{user_name}: {message}', 'response_template': '\n### Response:\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': '{bot_name}: {prompt}\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 hastagaras-l3-malmer-8b-v1-mkmlizer
Waiting for job on hastagaras-l3-malmer-8b-v1-mkmlizer to finish
hastagaras-l3-malmer-8b-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-l3-malmer-8b-v1-mkmlizer: ║     _____            __           __                                ║
hastagaras-l3-malmer-8b-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-l3-malmer-8b-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-l3-malmer-8b-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-l3-malmer-8b-v1-mkmlizer: ║       /___/                                                         ║
hastagaras-l3-malmer-8b-v1-mkmlizer: ║                                                                     ║
hastagaras-l3-malmer-8b-v1-mkmlizer: ║  Version: 0.8.10                                                    ║
hastagaras-l3-malmer-8b-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-l3-malmer-8b-v1-mkmlizer: ║                                                                     ║
hastagaras-l3-malmer-8b-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-l3-malmer-8b-v1-mkmlizer: ║  belonging to:                                                      ║
hastagaras-l3-malmer-8b-v1-mkmlizer: ║                                                                     ║
hastagaras-l3-malmer-8b-v1-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-l3-malmer-8b-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-l3-malmer-8b-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-l3-malmer-8b-v1-mkmlizer: ║                                                                     ║
hastagaras-l3-malmer-8b-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-l3-malmer-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-l3-malmer-8b-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-l3-malmer-8b-v1-mkmlizer: Downloaded to shared memory in 28.140s
hastagaras-l3-malmer-8b-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-l3-malmer-8b-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-l3-malmer-8b-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:05<13:19,  2.77s/it]
Loading 0:  24%|██▍       | 71/291 [00:06<00:15, 14.44it/s]
Loading 0:  51%|█████     | 149/291 [00:07<00:04, 28.80it/s]
Loading 0:  79%|███████▉  | 230/291 [00:08<00:01, 41.45it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-l3-malmer-8b-v1-mkmlizer: quantized model in 22.329s
hastagaras-l3-malmer-8b-v1-mkmlizer: Processed model Hastagaras/L3-Malmer-8B in 52.324s
hastagaras-l3-malmer-8b-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-l3-malmer-8b-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-l3-malmer-8b-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-l3-malmer-8b-v1
hastagaras-l3-malmer-8b-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-l3-malmer-8b-v1/special_tokens_map.json
hastagaras-l3-malmer-8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-l3-malmer-8b-v1/tokenizer_config.json
hastagaras-l3-malmer-8b-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-l3-malmer-8b-v1/config.json
hastagaras-l3-malmer-8b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-l3-malmer-8b-v1/tokenizer.json
hastagaras-l3-malmer-8b-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-l3-malmer-8b-v1/flywheel_model.0.safetensors
hastagaras-l3-malmer-8b-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-l3-malmer-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-l3-malmer-8b-v1-mkmlizer:   warnings.warn(
hastagaras-l3-malmer-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-l3-malmer-8b-v1-mkmlizer:   warnings.warn(
hastagaras-l3-malmer-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-l3-malmer-8b-v1-mkmlizer:   warnings.warn(
hastagaras-l3-malmer-8b-v1-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-l3-malmer-8b-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-l3-malmer-8b-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-l3-malmer-8b-v1-mkmlizer: Saving duration: 0.273s
hastagaras-l3-malmer-8b-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.914s
hastagaras-l3-malmer-8b-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-l3-malmer-8b-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-l3-malmer-8b-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-l3-malmer-8b-v1_reward
hastagaras-l3-malmer-8b-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-l3-malmer-8b-v1_reward/special_tokens_map.json
hastagaras-l3-malmer-8b-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-l3-malmer-8b-v1_reward/vocab.json
hastagaras-l3-malmer-8b-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-l3-malmer-8b-v1_reward/config.json
hastagaras-l3-malmer-8b-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-l3-malmer-8b-v1_reward/merges.txt
hastagaras-l3-malmer-8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-l3-malmer-8b-v1_reward/tokenizer_config.json
hastagaras-l3-malmer-8b-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-l3-malmer-8b-v1_reward/tokenizer.json
hastagaras-l3-malmer-8b-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-l3-malmer-8b-v1_reward/reward.tensors
Job hastagaras-l3-malmer-8b-v1-mkmlizer completed after 83.86s with status: succeeded
Stopping job with name hastagaras-l3-malmer-8b-v1-mkmlizer
Pipeline stage MKMLizer completed in 87.16s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-l3-malmer-8b-v1
Waiting for inference service hastagaras-l3-malmer-8b-v1 to be ready
Inference service hastagaras-l3-malmer-8b-v1 ready after 30.16705060005188s
Pipeline stage ISVCDeployer completed in 37.50s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1280510425567627s
Received healthy response to inference request in 1.2642805576324463s
Received healthy response to inference request in 1.2725868225097656s
Received healthy response to inference request in 1.2678139209747314s
Received healthy response to inference request in 1.2532637119293213s
5 requests
0 failed requests
5th percentile: 1.2554670810699462
10th percentile: 1.2576704502105713
20th percentile: 1.2620771884918214
30th percentile: 1.2649872303009033
40th percentile: 1.2664005756378174
50th percentile: 1.2678139209747314
60th percentile: 1.269723081588745
70th percentile: 1.2716322422027588
80th percentile: 1.4436796665191651
90th percentile: 1.785865354537964
95th percentile: 1.9569581985473632
99th percentile: 2.093832473754883
mean time: 1.4371992111206056
Pipeline stage StressChecker completed in 7.83s
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
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-l3-malmer-8b_v1 status is now deployed due to DeploymentManager action
hastagaras-l3-malmer-8b_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-l3-malmer-8b_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-l3-malmer-8b-v1 is running
Tearing down inference service hastagaras-l3-malmer-8b-v1
Toredown service hastagaras-l3-malmer-8b-v1
Pipeline stage ISVCDeleter completed in 3.62s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-l3-malmer-8b-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-malmer-8b-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-l3-malmer-8b-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-malmer-8b-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-l3-malmer-8b-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-l3-malmer-8b-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-malmer-8b-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-l3-malmer-8b-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-l3-malmer-8b-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-malmer-8b-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-malmer-8b-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-l3-malmer-8b-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.35s
hastagaras-l3-malmer-8b_v1 status is now torndown due to DeploymentManager action