submission_id: cgato-blopblip-l3-8b-v0-1-1_v1
developer_uid: c.gato
best_of: 16
display_name: cgato-blopblip-l3-8b-v0-1-1_v1
family_friendly_score: 0.0
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': True}
generation_params: {'temperature': 0.9, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 200, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', 'You:'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
ineligible_reason: model is not deployable
is_internal_developer: False
language_model: cgato/BlopBlip-L3-8b-v0.1.1
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_eval_status: error
model_group: cgato/BlopBlip-L3-8b-v0.
model_name: cgato-blopblip-l3-8b-v0-1-1_v1
model_num_parameters: 8030261248.0
model_repo: cgato/BlopBlip-L3-8b-v0.1.1
model_size: 8B
num_battles: 233
num_wins: 102
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': True, 'user_template': '{user_name}: {message}\n'}
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
status: rejected
submission_type: basic
timestamp: 2024-06-15T02:29:39+00:00
us_pacific_date: 2024-06-14
win_ratio: 0.43776824034334766
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-blopblip-l3-8b-v0-1-1-v1-mkmlizer
Waiting for job on cgato-blopblip-l3-8b-v0-1-1-v1-mkmlizer to finish
Stopping job with name cgato-blopblip-l3-8b-v0-1-1-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name cgato-blopblip-l3-8b-v0-1-1-v1-mkmlizer
Waiting for job on cgato-blopblip-l3-8b-v0-1-1-v1-mkmlizer to finish
cgato-blopblip-l3-8b-v0-1-1-v1-mkmlizer: Downloaded to shared memory in 41.616s
cgato-blopblip-l3-8b-v0-1-1-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-blopblip-l3-8b-v0-1-1-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-blopblip-l3-8b-v0-1-1-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   5%|▍         | 14/291 [00:00<00:02, 129.12it/s]
Loading 0:  11%|█         | 32/291 [00:00<00:01, 146.27it/s]
Loading 0:  17%|█▋        | 49/291 [00:00<00:01, 156.35it/s]
Loading 0:  23%|██▎       | 66/291 [00:00<00:01, 156.97it/s]
Loading 0:  28%|██▊       | 82/291 [00:00<00:01, 140.08it/s]
Loading 0:  33%|███▎      | 97/291 [00:00<00:02, 71.29it/s] 
Loading 0:  39%|███▉      | 113/291 [00:01<00:02, 85.76it/s]
Loading 0:  45%|████▍     | 130/291 [00:01<00:01, 102.46it/s]
Loading 0:  51%|█████     | 147/291 [00:01<00:01, 117.32it/s]
Loading 0:  56%|█████▌    | 162/291 [00:01<00:01, 124.22it/s]
Loading 0:  62%|██████▏   | 180/291 [00:01<00:00, 133.69it/s]
Loading 0:  67%|██████▋   | 195/291 [00:01<00:01, 81.55it/s] 
Loading 0:  73%|███████▎  | 212/291 [00:02<00:00, 95.77it/s]
Loading 0:  79%|███████▉  | 230/291 [00:02<00:00, 110.73it/s]
Loading 0:  85%|████████▍ | 247/291 [00:02<00:00, 123.40it/s]
Loading 0:  91%|█████████ | 265/291 [00:02<00:00, 133.97it/s]
Loading 0:  97%|█████████▋| 282/291 [00:02<00:00, 138.57it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cgato-blopblip-l3-8b-v0-1-1-v1-mkmlizer: quantized model in 23.494s
cgato-blopblip-l3-8b-v0-1-1-v1-mkmlizer: Processed model cgato/BlopBlip-L3-8b-v0.1.1 in 67.716s
cgato-blopblip-l3-8b-v0-1-1-v1-mkmlizer: creating bucket guanaco-mkml-models
cgato-blopblip-l3-8b-v0-1-1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-blopblip-l3-8b-v0-1-1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-blopblip-l3-8b-v0-1-1-v1
cgato-blopblip-l3-8b-v0-1-1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-blopblip-l3-8b-v0-1-1-v1/special_tokens_map.json
cgato-blopblip-l3-8b-v0-1-1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-blopblip-l3-8b-v0-1-1-v1/config.json
cgato-blopblip-l3-8b-v0-1-1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-blopblip-l3-8b-v0-1-1-v1/tokenizer_config.json
cgato-blopblip-l3-8b-v0-1-1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-blopblip-l3-8b-v0-1-1-v1/tokenizer.json
cgato-blopblip-l3-8b-v0-1-1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-blopblip-l3-8b-v0-1-1-v1/flywheel_model.0.safetensors
cgato-blopblip-l3-8b-v0-1-1-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-blopblip-l3-8b-v0-1-1-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.
cgato-blopblip-l3-8b-v0-1-1-v1-mkmlizer:   warnings.warn(
cgato-blopblip-l3-8b-v0-1-1-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.
cgato-blopblip-l3-8b-v0-1-1-v1-mkmlizer:   warnings.warn(
cgato-blopblip-l3-8b-v0-1-1-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()
cgato-blopblip-l3-8b-v0-1-1-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
cgato-blopblip-l3-8b-v0-1-1-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-blopblip-l3-8b-v0-1-1-v1-mkmlizer: Saving duration: 0.432s
cgato-blopblip-l3-8b-v0-1-1-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.516s
cgato-blopblip-l3-8b-v0-1-1-v1-mkmlizer: creating bucket guanaco-reward-models
cgato-blopblip-l3-8b-v0-1-1-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-blopblip-l3-8b-v0-1-1-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-blopblip-l3-8b-v0-1-1-v1_reward
cgato-blopblip-l3-8b-v0-1-1-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-blopblip-l3-8b-v0-1-1-v1_reward/special_tokens_map.json
cgato-blopblip-l3-8b-v0-1-1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-blopblip-l3-8b-v0-1-1-v1_reward/tokenizer_config.json
cgato-blopblip-l3-8b-v0-1-1-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-blopblip-l3-8b-v0-1-1-v1_reward/config.json
cgato-blopblip-l3-8b-v0-1-1-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-blopblip-l3-8b-v0-1-1-v1_reward/vocab.json
cgato-blopblip-l3-8b-v0-1-1-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-blopblip-l3-8b-v0-1-1-v1_reward/merges.txt
cgato-blopblip-l3-8b-v0-1-1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-blopblip-l3-8b-v0-1-1-v1_reward/tokenizer.json
cgato-blopblip-l3-8b-v0-1-1-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-blopblip-l3-8b-v0-1-1-v1_reward/reward.tensors
Job cgato-blopblip-l3-8b-v0-1-1-v1-mkmlizer completed after 138.48s with status: succeeded
Stopping job with name cgato-blopblip-l3-8b-v0-1-1-v1-mkmlizer
Pipeline stage MKMLizer completed in 139.89s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cgato-blopblip-l3-8b-v0-1-1-v1
Waiting for inference service cgato-blopblip-l3-8b-v0-1-1-v1 to be ready
Inference service cgato-blopblip-l3-8b-v0-1-1-v1 ready after 40.28810214996338s
Pipeline stage ISVCDeployer completed in 46.03s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.191699743270874s
Received healthy response to inference request in 1.2425696849822998s
Received healthy response to inference request in 1.253234624862671s
Received healthy response to inference request in 1.2309141159057617s
Received healthy response to inference request in 1.2349944114685059s
5 requests
0 failed requests
5th percentile: 1.2317301750183105
10th percentile: 1.2325462341308593
20th percentile: 1.234178352355957
30th percentile: 1.2365094661712646
40th percentile: 1.2395395755767822
50th percentile: 1.2425696849822998
60th percentile: 1.2468356609344482
70th percentile: 1.2511016368865966
80th percentile: 1.4409276485443117
90th percentile: 1.816313695907593
95th percentile: 2.004006719589233
99th percentile: 2.154161138534546
mean time: 1.4306825160980225
Pipeline stage StressChecker completed in 7.75s
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
M-Eval Dataset for topic stay_in_character is loaded
cgato-blopblip-l3-8b-v0-1-1_v1 status is now deployed due to DeploymentManager action
cgato-blopblip-l3-8b-v0-1-1_v1 status is now rejected due to a failure to get M-Eval score. Please try again in five minutes.