submission_id: hastagaras-llama-3-8b-cl_3476_v1
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Llama-3-8b-ClauAS-Alpha
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.85, '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': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
reward_formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
timestamp: 2024-05-06T05:09:46+00:00
model_name: hastagaras-llama-3-8b-cl_3476_v1
model_eval_status: success
double_thumbs_up: 1519
thumbs_up: 2391
thumbs_down: 1446
num_battles: 141605
num_wins: 68822
celo_rating: 1174.05
entertaining: 6.96
stay_in_character: 8.48
user_preference: 7.2
safety_score: 0.9
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: hastagaras-llama-3-8b-cl_3476_v1
double_thumbs_up_ratio: 0.2836071695294996
feedback_count: 5356
ineligible_reason: None
language_model: Hastagaras/Llama-3-8b-ClauAS-Alpha
model_score: 7.546666666666667
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
single_thumbs_up_ratio: 0.4464152352501867
thumbs_down_ratio: 0.26997759522031367
thumbs_up_ratio: 0.7300224047796864
us_pacific_date: 2024-05-05
win_ratio: 0.48601391193813775
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-llama-3-8b-cl-3476-v1-mkmlizer
Waiting for job on hastagaras-llama-3-8b-cl-3476-v1-mkmlizer to finish
hastagaras-llama-3-8b-cl-3476-v1-mkmlizer: Downloaded to shared memory in 28.463s
hastagaras-llama-3-8b-cl-3476-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-llama-3-8b-cl-3476-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-llama-3-8b-cl-3476-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  38%|███▊      | 111/291 [00:00<00:01, 111.04it/s]
Loading 0:  78%|███████▊  | 228/291 [00:02<00:00, 114.20it/s]
Loading 0:  99%|█████████▊| 287/291 [00:07<00:00, 27.43it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-llama-3-8b-cl-3476-v1-mkmlizer: quantized model in 23.398s
hastagaras-llama-3-8b-cl-3476-v1-mkmlizer: Processed model Hastagaras/Llama-3-8b-ClauAS-Alpha in 54.495s
hastagaras-llama-3-8b-cl-3476-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-llama-3-8b-cl-3476-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-llama-3-8b-cl-3476-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-llama-3-8b-cl-3476-v1
hastagaras-llama-3-8b-cl-3476-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-cl-3476-v1/special_tokens_map.json
hastagaras-llama-3-8b-cl-3476-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-cl-3476-v1/config.json
hastagaras-llama-3-8b-cl-3476-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-cl-3476-v1/tokenizer_config.json
hastagaras-llama-3-8b-cl-3476-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-llama-3-8b-cl-3476-v1/tokenizer.json
hastagaras-llama-3-8b-cl-3476-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-llama-3-8b-cl-3476-v1/flywheel_model.0.safetensors
hastagaras-llama-3-8b-cl-3476-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-llama-3-8b-cl-3476-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-llama-3-8b-cl-3476-v1-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-cl-3476-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-llama-3-8b-cl-3476-v1-mkmlizer:   warnings.warn(
hastagaras-llama-3-8b-cl-3476-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-llama-3-8b-cl-3476-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-llama-3-8b-cl-3476-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-llama-3-8b-cl-3476-v1-mkmlizer: Saving duration: 0.397s
hastagaras-llama-3-8b-cl-3476-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.028s
hastagaras-llama-3-8b-cl-3476-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-llama-3-8b-cl-3476-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-llama-3-8b-cl-3476-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-llama-3-8b-cl-3476-v1_reward
hastagaras-llama-3-8b-cl-3476-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-cl-3476-v1_reward/config.json
hastagaras-llama-3-8b-cl-3476-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-llama-3-8b-cl-3476-v1_reward/tokenizer_config.json
hastagaras-llama-3-8b-cl-3476-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-llama-3-8b-cl-3476-v1_reward/special_tokens_map.json
hastagaras-llama-3-8b-cl-3476-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-llama-3-8b-cl-3476-v1_reward/vocab.json
hastagaras-llama-3-8b-cl-3476-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-llama-3-8b-cl-3476-v1_reward/merges.txt
hastagaras-llama-3-8b-cl-3476-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-llama-3-8b-cl-3476-v1_reward/tokenizer.json
hastagaras-llama-3-8b-cl-3476-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-llama-3-8b-cl-3476-v1_reward/reward.tensors
Job hastagaras-llama-3-8b-cl-3476-v1-mkmlizer completed after 163.93s with status: succeeded
Stopping job with name hastagaras-llama-3-8b-cl-3476-v1-mkmlizer
Pipeline stage MKMLizer completed in 168.69s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-llama-3-8b-cl-3476-v1
Waiting for inference service hastagaras-llama-3-8b-cl-3476-v1 to be ready
Inference service hastagaras-llama-3-8b-cl-3476-v1 ready after 40.22613191604614s
Pipeline stage ISVCDeployer completed in 47.61s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1932015419006348s
Received healthy response to inference request in 1.2688381671905518s
Received healthy response to inference request in 1.2581536769866943s
Received healthy response to inference request in 1.2726778984069824s
Received healthy response to inference request in 1.2596936225891113s
5 requests
0 failed requests
5th percentile: 1.2584616661071777
10th percentile: 1.258769655227661
20th percentile: 1.259385633468628
30th percentile: 1.2615225315093994
40th percentile: 1.2651803493499756
50th percentile: 1.2688381671905518
60th percentile: 1.270374059677124
70th percentile: 1.2719099521636963
80th percentile: 1.4567826271057132
90th percentile: 1.824992084503174
95th percentile: 2.009096813201904
99th percentile: 2.1563805961608886
mean time: 1.450512981414795
Pipeline stage StressChecker completed in 7.90s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
Running M-Eval for topic stay_in_character
hastagaras-llama-3-8b-cl_3476_v1 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-llama-3-8b-cl_3476_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics