submission_id: cgato-smallsmorts-l3-8b-v0-1_v1
developer_uid: c.gato
best_of: 16
display_name: cgato-blopblip-l3-8b-v0-2-1_v1
family_friendly_score: 0.0
formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{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/SmallSmorts-L3-8b-v0.1
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_eval_status: error
model_group: cgato/SmallSmorts-L3-8b-
model_name: cgato-blopblip-l3-8b-v0-2-1_v1
model_num_parameters: 8030294016.0
model_repo: cgato/SmallSmorts-L3-8b-v0.1
model_size: 8B
num_battles: 81
num_wins: 39
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: 2024-06-16T07:32:20+00:00
us_pacific_date: 2024-06-16
win_ratio: 0.48148148148148145
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-smallsmorts-l3-8b-v0-1-v1-mkmlizer
Waiting for job on cgato-smallsmorts-l3-8b-v0-1-v1-mkmlizer to finish
cgato-smallsmorts-l3-8b-v0-1-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-smallsmorts-l3-8b-v0-1-v1-mkmlizer: ║ _____ __ __ ║
cgato-smallsmorts-l3-8b-v0-1-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-smallsmorts-l3-8b-v0-1-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-smallsmorts-l3-8b-v0-1-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-smallsmorts-l3-8b-v0-1-v1-mkmlizer: ║ /___/ ║
cgato-smallsmorts-l3-8b-v0-1-v1-mkmlizer: ║ ║
cgato-smallsmorts-l3-8b-v0-1-v1-mkmlizer: ║ Version: 0.8.14 ║
cgato-smallsmorts-l3-8b-v0-1-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-smallsmorts-l3-8b-v0-1-v1-mkmlizer: ║ https://mk1.ai ║
cgato-smallsmorts-l3-8b-v0-1-v1-mkmlizer: ║ ║
cgato-smallsmorts-l3-8b-v0-1-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-smallsmorts-l3-8b-v0-1-v1-mkmlizer: ║ belonging to: ║
cgato-smallsmorts-l3-8b-v0-1-v1-mkmlizer: ║ ║
cgato-smallsmorts-l3-8b-v0-1-v1-mkmlizer: ║ Chai Research Corp. ║
cgato-smallsmorts-l3-8b-v0-1-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-smallsmorts-l3-8b-v0-1-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-smallsmorts-l3-8b-v0-1-v1-mkmlizer: ║ ║
cgato-smallsmorts-l3-8b-v0-1-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-smallsmorts-l3-8b-v0-1-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.
cgato-smallsmorts-l3-8b-v0-1-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-smallsmorts-l3-8b-v0-1-v1-mkmlizer: Downloaded to shared memory in 45.239s
cgato-smallsmorts-l3-8b-v0-1-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-smallsmorts-l3-8b-v0-1-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-smallsmorts-l3-8b-v0-1-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 3%|▎ | 8/291 [00:00<00:03, 76.22it/s] Loading 0: 7%|▋ | 20/291 [00:00<00:02, 101.39it/s] Loading 0: 11%|█ | 31/291 [00:00<00:02, 91.61it/s] Loading 0: 14%|█▍ | 41/291 [00:00<00:02, 92.43it/s] Loading 0: 19%|█▊ | 54/291 [00:00<00:02, 103.69it/s] Loading 0: 22%|██▏ | 65/291 [00:00<00:02, 102.15it/s] Loading 0: 26%|██▌ | 76/291 [00:00<00:02, 87.84it/s] Loading 0: 30%|██▉ | 86/291 [00:01<00:04, 45.49it/s] Loading 0: 33%|███▎ | 95/291 [00:01<00:03, 50.29it/s] Loading 0: 36%|███▌ | 104/291 [00:01<00:03, 54.26it/s] Loading 0: 41%|████ | 120/291 [00:01<00:02, 72.02it/s] Loading 0: 45%|████▍ | 130/291 [00:01<00:02, 77.38it/s] Loading 0: 48%|████▊ | 140/291 [00:01<00:01, 81.40it/s] Loading 0: 54%|█████▎ | 156/291 [00:02<00:01, 95.70it/s] Loading 0: 57%|█████▋ | 167/291 [00:02<00:01, 90.72it/s] Loading 0: 62%|██████▏ | 179/291 [00:02<00:01, 96.88it/s] Loading 0: 65%|██████▌ | 190/291 [00:02<00:01, 53.18it/s] Loading 0: 68%|██████▊ | 198/291 [00:02<00:01, 55.15it/s] Loading 0: 72%|███████▏ | 210/291 [00:02<00:01, 65.97it/s] Loading 0: 75%|███████▌ | 219/291 [00:03<00:01, 67.36it/s] Loading 0: 79%|███████▊ | 229/291 [00:03<00:00, 72.09it/s] Loading 0: 82%|████████▏ | 239/291 [00:03<00:00, 76.23it/s] Loading 0: 85%|████████▌ | 248/291 [00:03<00:00, 77.81it/s] Loading 0: 91%|█████████ | 264/291 [00:03<00:00, 92.76it/s] Loading 0: 94%|█████████▍| 274/291 [00:03<00:00, 87.41it/s] Loading 0: 98%|█████████▊| 284/291 [00:03<00:00, 89.92it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cgato-smallsmorts-l3-8b-v0-1-v1-mkmlizer: quantized model in 25.560s
cgato-smallsmorts-l3-8b-v0-1-v1-mkmlizer: Processed model cgato/SmallSmorts-L3-8b-v0.1 in 73.571s
cgato-smallsmorts-l3-8b-v0-1-v1-mkmlizer: creating bucket guanaco-mkml-models
cgato-smallsmorts-l3-8b-v0-1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-smallsmorts-l3-8b-v0-1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-smallsmorts-l3-8b-v0-1-v1
cgato-smallsmorts-l3-8b-v0-1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-smallsmorts-l3-8b-v0-1-v1/special_tokens_map.json
cgato-smallsmorts-l3-8b-v0-1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-smallsmorts-l3-8b-v0-1-v1/tokenizer.json
cgato-smallsmorts-l3-8b-v0-1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-smallsmorts-l3-8b-v0-1-v1/config.json
cgato-smallsmorts-l3-8b-v0-1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-smallsmorts-l3-8b-v0-1-v1/tokenizer_config.json
cgato-smallsmorts-l3-8b-v0-1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-smallsmorts-l3-8b-v0-1-v1/flywheel_model.0.safetensors
cgato-smallsmorts-l3-8b-v0-1-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-smallsmorts-l3-8b-v0-1-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-smallsmorts-l3-8b-v0-1-v1-mkmlizer: warnings.warn(
cgato-smallsmorts-l3-8b-v0-1-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.
cgato-smallsmorts-l3-8b-v0-1-v1-mkmlizer: warnings.warn(
cgato-smallsmorts-l3-8b-v0-1-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-smallsmorts-l3-8b-v0-1-v1-mkmlizer: warnings.warn(
cgato-smallsmorts-l3-8b-v0-1-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-smallsmorts-l3-8b-v0-1-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-smallsmorts-l3-8b-v0-1-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-smallsmorts-l3-8b-v0-1-v1-mkmlizer: Saving duration: 0.481s
cgato-smallsmorts-l3-8b-v0-1-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.777s
cgato-smallsmorts-l3-8b-v0-1-v1-mkmlizer: creating bucket guanaco-reward-models
cgato-smallsmorts-l3-8b-v0-1-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-smallsmorts-l3-8b-v0-1-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-smallsmorts-l3-8b-v0-1-v1_reward
cgato-smallsmorts-l3-8b-v0-1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-smallsmorts-l3-8b-v0-1-v1_reward/tokenizer_config.json
cgato-smallsmorts-l3-8b-v0-1-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-smallsmorts-l3-8b-v0-1-v1_reward/special_tokens_map.json
cgato-smallsmorts-l3-8b-v0-1-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-smallsmorts-l3-8b-v0-1-v1_reward/merges.txt
cgato-smallsmorts-l3-8b-v0-1-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-smallsmorts-l3-8b-v0-1-v1_reward/config.json
cgato-smallsmorts-l3-8b-v0-1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-smallsmorts-l3-8b-v0-1-v1_reward/tokenizer.json
cgato-smallsmorts-l3-8b-v0-1-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-smallsmorts-l3-8b-v0-1-v1_reward/vocab.json
cgato-smallsmorts-l3-8b-v0-1-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-smallsmorts-l3-8b-v0-1-v1_reward/reward.tensors
Job cgato-smallsmorts-l3-8b-v0-1-v1-mkmlizer completed after 154.56s with status: succeeded
Stopping job with name cgato-smallsmorts-l3-8b-v0-1-v1-mkmlizer
Pipeline stage MKMLizer completed in 158.76s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cgato-smallsmorts-l3-8b-v0-1-v1
Waiting for inference service cgato-smallsmorts-l3-8b-v0-1-v1 to be ready
Inference service cgato-smallsmorts-l3-8b-v0-1-v1 ready after 140.67542958259583s
Pipeline stage ISVCDeployer completed in 148.27s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0793662071228027s
Received healthy response to inference request in 1.289886474609375s
Received healthy response to inference request in 1.1620392799377441s
Received healthy response to inference request in 1.2657756805419922s
Received healthy response to inference request in 1.2433009147644043s
5 requests
0 failed requests
5th percentile: 1.1782916069030762
10th percentile: 1.1945439338684083
20th percentile: 1.2270485877990722
30th percentile: 1.247795867919922
40th percentile: 1.256785774230957
50th percentile: 1.2657756805419922
60th percentile: 1.2754199981689454
70th percentile: 1.2850643157958985
80th percentile: 1.4477824211120607
90th percentile: 1.7635743141174318
95th percentile: 1.921470260620117
99th percentile: 2.0477870178222655
mean time: 1.4080737113952637
Pipeline stage StressChecker completed in 7.69s
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 0.03s
M-Eval Dataset for topic stay_in_character is loaded
cgato-smallsmorts-l3-8b-v0-1_v1 status is now deployed due to DeploymentManager action
cgato-smallsmorts-l3-8b-v0-1_v1 status is now rejected due to a failure to get M-Eval score. Please try again in five minutes.