rieofawox-l3-er-v0-2-8b-ex

submission_id: rieofawox-l3-er-v0-2-8b-ex_v1

developer_uid: la.fey

best_of: 16

celo_rating: 1207.58

display_name: rieofawox-l3-er-v0-2-8b-ex_v1

family_friendly_score: 0.0

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}

generation_params: {'temperature': 0.75, 'top_p': 1.0, 'min_p': 0.08, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>', '<|end_header_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}

is_internal_developer: False

language_model: Rieofawox/L3-ER-v0.2-8B-EX

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_eval_status: success

model_group: Rieofawox/L3-ER-v0.2-8B-

model_name: rieofawox-l3-er-v0-2-8b-ex_v1

model_num_parameters: 8030261248.0

model_repo: Rieofawox/L3-ER-v0.2-8B-EX

model_size: 8B

num_battles: 28819

num_wins: 15544

ranking_group: single

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'}

reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2

status: torndown

submission_type: basic

timestamp: 2024-06-12T19:21:44+00:00

us_pacific_date: 2024-06-12

win_ratio: 0.5393663902286686

Resubmit model

Running pipeline stage MKMLizer
Starting job with name rieofawox-l3-er-v0-2-8b-ex-v1-mkmlizer
Waiting for job on rieofawox-l3-er-v0-2-8b-ex-v1-mkmlizer to finish
rieofawox-l3-er-v0-2-8b-ex-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rieofawox-l3-er-v0-2-8b-ex-v1-mkmlizer: ║     _____            __           __                                ║
rieofawox-l3-er-v0-2-8b-ex-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rieofawox-l3-er-v0-2-8b-ex-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rieofawox-l3-er-v0-2-8b-ex-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rieofawox-l3-er-v0-2-8b-ex-v1-mkmlizer: ║       /___/                                                         ║
rieofawox-l3-er-v0-2-8b-ex-v1-mkmlizer: ║                                                                     ║
rieofawox-l3-er-v0-2-8b-ex-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
rieofawox-l3-er-v0-2-8b-ex-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rieofawox-l3-er-v0-2-8b-ex-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rieofawox-l3-er-v0-2-8b-ex-v1-mkmlizer: ║                                                                     ║
rieofawox-l3-er-v0-2-8b-ex-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rieofawox-l3-er-v0-2-8b-ex-v1-mkmlizer: ║  belonging to:                                                      ║
rieofawox-l3-er-v0-2-8b-ex-v1-mkmlizer: ║                                                                     ║
rieofawox-l3-er-v0-2-8b-ex-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rieofawox-l3-er-v0-2-8b-ex-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rieofawox-l3-er-v0-2-8b-ex-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
rieofawox-l3-er-v0-2-8b-ex-v1-mkmlizer: ║                                                                     ║
rieofawox-l3-er-v0-2-8b-ex-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rieofawox-l3-er-v0-2-8b-ex-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.
rieofawox-l3-er-v0-2-8b-ex-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
rieofawox-l3-er-v0-2-8b-ex-v1-mkmlizer: Downloaded to shared memory in 64.369s
rieofawox-l3-er-v0-2-8b-ex-v1-mkmlizer: quantizing model to /dev/shm/model_cache
rieofawox-l3-er-v0-2-8b-ex-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rieofawox-l3-er-v0-2-8b-ex-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<11:25,  2.37s/it]
Loading 0:   1%|          | 3/291 [00:04<06:57,  1.45s/it]
Loading 0:   6%|▌         | 18/291 [00:05<00:41,  6.58it/s]
Loading 0:  11%|█▏        | 33/291 [00:05<00:18, 14.22it/s]
Loading 0:  15%|█▌        | 44/291 [00:05<00:12, 19.76it/s]
Loading 0:  21%|██        | 60/291 [00:05<00:07, 31.75it/s]
Loading 0:  27%|██▋       | 78/291 [00:05<00:04, 47.41it/s]
Loading 0:  31%|███▏      | 91/291 [00:05<00:03, 51.61it/s]
Loading 0:  37%|███▋      | 108/291 [00:05<00:02, 68.33it/s]
Loading 0:  42%|████▏     | 123/291 [00:06<00:02, 66.86it/s]
Loading 0:  48%|████▊     | 141/291 [00:06<00:01, 83.99it/s]
Loading 0:  55%|█████▍    | 159/291 [00:06<00:01, 100.55it/s]
Loading 0:  59%|█████▉    | 173/291 [00:06<00:01, 88.87it/s] 
Loading 0:  65%|██████▌   | 190/291 [00:06<00:00, 104.22it/s]
Loading 0:  70%|███████   | 204/291 [00:06<00:00, 88.00it/s] 
Loading 0:  76%|███████▋  | 222/291 [00:06<00:00, 105.12it/s]
Loading 0:  82%|████████▏ | 240/291 [00:07<00:00, 119.90it/s]
Loading 0:  88%|████████▊ | 255/291 [00:07<00:00, 103.01it/s]
Loading 0:  93%|█████████▎| 270/291 [00:07<00:00, 112.53it/s]
Loading 0:  98%|█████████▊| 285/291 [00:07<00:00, 91.98it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
rieofawox-l3-er-v0-2-8b-ex-v1-mkmlizer: quantized model in 23.493s
rieofawox-l3-er-v0-2-8b-ex-v1-mkmlizer: Processed model Rieofawox/L3-ER-v0.2-8B-EX in 90.693s
rieofawox-l3-er-v0-2-8b-ex-v1-mkmlizer: creating bucket guanaco-mkml-models
rieofawox-l3-er-v0-2-8b-ex-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rieofawox-l3-er-v0-2-8b-ex-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rieofawox-l3-er-v0-2-8b-ex-v1
rieofawox-l3-er-v0-2-8b-ex-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rieofawox-l3-er-v0-2-8b-ex-v1/special_tokens_map.json
rieofawox-l3-er-v0-2-8b-ex-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rieofawox-l3-er-v0-2-8b-ex-v1/config.json
rieofawox-l3-er-v0-2-8b-ex-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rieofawox-l3-er-v0-2-8b-ex-v1/tokenizer_config.json
rieofawox-l3-er-v0-2-8b-ex-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rieofawox-l3-er-v0-2-8b-ex-v1/tokenizer.json
rieofawox-l3-er-v0-2-8b-ex-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rieofawox-l3-er-v0-2-8b-ex-v1/flywheel_model.0.safetensors
rieofawox-l3-er-v0-2-8b-ex-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
rieofawox-l3-er-v0-2-8b-ex-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.
rieofawox-l3-er-v0-2-8b-ex-v1-mkmlizer:   warnings.warn(
rieofawox-l3-er-v0-2-8b-ex-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.
rieofawox-l3-er-v0-2-8b-ex-v1-mkmlizer:   warnings.warn(
rieofawox-l3-er-v0-2-8b-ex-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.
rieofawox-l3-er-v0-2-8b-ex-v1-mkmlizer:   warnings.warn(
rieofawox-l3-er-v0-2-8b-ex-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()
rieofawox-l3-er-v0-2-8b-ex-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
rieofawox-l3-er-v0-2-8b-ex-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
rieofawox-l3-er-v0-2-8b-ex-v1-mkmlizer: Saving duration: 0.399s
rieofawox-l3-er-v0-2-8b-ex-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.289s
rieofawox-l3-er-v0-2-8b-ex-v1-mkmlizer: creating bucket guanaco-reward-models
rieofawox-l3-er-v0-2-8b-ex-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
rieofawox-l3-er-v0-2-8b-ex-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/rieofawox-l3-er-v0-2-8b-ex-v1_reward
rieofawox-l3-er-v0-2-8b-ex-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/rieofawox-l3-er-v0-2-8b-ex-v1_reward/config.json
rieofawox-l3-er-v0-2-8b-ex-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/rieofawox-l3-er-v0-2-8b-ex-v1_reward/special_tokens_map.json
rieofawox-l3-er-v0-2-8b-ex-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/rieofawox-l3-er-v0-2-8b-ex-v1_reward/tokenizer_config.json
rieofawox-l3-er-v0-2-8b-ex-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/rieofawox-l3-er-v0-2-8b-ex-v1_reward/merges.txt
rieofawox-l3-er-v0-2-8b-ex-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/rieofawox-l3-er-v0-2-8b-ex-v1_reward/vocab.json
rieofawox-l3-er-v0-2-8b-ex-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/rieofawox-l3-er-v0-2-8b-ex-v1_reward/tokenizer.json
rieofawox-l3-er-v0-2-8b-ex-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/rieofawox-l3-er-v0-2-8b-ex-v1_reward/reward.tensors
Job rieofawox-l3-er-v0-2-8b-ex-v1-mkmlizer completed after 124.22s with status: succeeded
Stopping job with name rieofawox-l3-er-v0-2-8b-ex-v1-mkmlizer
Pipeline stage MKMLizer completed in 128.51s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service rieofawox-l3-er-v0-2-8b-ex-v1
Waiting for inference service rieofawox-l3-er-v0-2-8b-ex-v1 to be ready
Inference service rieofawox-l3-er-v0-2-8b-ex-v1 ready after 40.256661891937256s
Pipeline stage ISVCDeployer completed in 47.87s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.219989538192749s
Received healthy response to inference request in 1.3738226890563965s
Received healthy response to inference request in 1.330317735671997s
Received healthy response to inference request in 1.298574686050415s
Received healthy response to inference request in 1.2805800437927246s
5 requests
0 failed requests
5th percentile: 1.2841789722442627
10th percentile: 1.2877779006958008
20th percentile: 1.294975757598877
30th percentile: 1.3049232959747314
40th percentile: 1.3176205158233643
50th percentile: 1.330317735671997
60th percentile: 1.3477197170257569
70th percentile: 1.3651216983795167
80th percentile: 1.5430560588836673
90th percentile: 1.8815227985382081
95th percentile: 2.0507561683654782
99th percentile: 2.186142864227295
mean time: 1.5006569385528565
Pipeline stage StressChecker completed in 8.14s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
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
rieofawox-l3-er-v0-2-8b-ex_v1 status is now deployed due to DeploymentManager action
rieofawox-l3-er-v0-2-8b-ex_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of rieofawox-l3-er-v0-2-8b-ex_v1
Running pipeline stage ISVCDeleter
Checking if service rieofawox-l3-er-v0-2-8b-ex-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 3.77s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key rieofawox-l3-er-v0-2-8b-ex-v1/config.json from bucket guanaco-mkml-models
Deleting key rieofawox-l3-er-v0-2-8b-ex-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key rieofawox-l3-er-v0-2-8b-ex-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key rieofawox-l3-er-v0-2-8b-ex-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key rieofawox-l3-er-v0-2-8b-ex-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key rieofawox-l3-er-v0-2-8b-ex-v1_reward/config.json from bucket guanaco-reward-models
Deleting key rieofawox-l3-er-v0-2-8b-ex-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key rieofawox-l3-er-v0-2-8b-ex-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key rieofawox-l3-er-v0-2-8b-ex-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key rieofawox-l3-er-v0-2-8b-ex-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key rieofawox-l3-er-v0-2-8b-ex-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key rieofawox-l3-er-v0-2-8b-ex-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.38s
rieofawox-l3-er-v0-2-8b-ex_v1 status is now torndown due to DeploymentManager action