submission_id: cycy233-l3-exp-v0-e3-0_v1
developer_uid: shiroe40
status: inactive
model_repo: cycy233/L3-exp-v0-e3.0
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], '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}
timestamp: 2024-06-26T02:15:13+00:00
model_name: auto
model_group: cycy233/L3-exp-v0-e3.0
num_battles: 19604
num_wins: 9306
celo_rating: 1162.06
propriety_score: 0.7158452226545612
propriety_total_count: 9252.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: auto
ineligible_reason: None
language_model: cycy233/L3-exp-v0-e3.0
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-25
win_ratio: 0.47469904101203836
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-l3-exp-v0-e3-0-v1-mkmlizer
Waiting for job on cycy233-l3-exp-v0-e3-0-v1-mkmlizer to finish
cycy233-l3-exp-v0-e3-0-v1-mkmlizer: Downloaded to shared memory in 62.037s
cycy233-l3-exp-v0-e3-0-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-l3-exp-v0-e3-0-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-exp-v0-e3-0-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:02, 70.22it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 83.52it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 120.74it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-exp-v0-e3-0-v1-mkmlizer: quantized model in 23.523s
cycy233-l3-exp-v0-e3-0-v1-mkmlizer: Processed model cycy233/L3-exp-v0-e3.0 in 88.039s
cycy233-l3-exp-v0-e3-0-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-exp-v0-e3-0-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-exp-v0-e3-0-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-exp-v0-e3-0-v1
cycy233-l3-exp-v0-e3-0-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-exp-v0-e3-0-v1/config.json
cycy233-l3-exp-v0-e3-0-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-exp-v0-e3-0-v1/special_tokens_map.json
cycy233-l3-exp-v0-e3-0-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-exp-v0-e3-0-v1/tokenizer_config.json
cycy233-l3-exp-v0-e3-0-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-exp-v0-e3-0-v1/tokenizer.json
cycy233-l3-exp-v0-e3-0-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-exp-v0-e3-0-v1/flywheel_model.0.safetensors
cycy233-l3-exp-v0-e3-0-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-l3-exp-v0-e3-0-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.
cycy233-l3-exp-v0-e3-0-v1-mkmlizer: warnings.warn(
cycy233-l3-exp-v0-e3-0-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.
cycy233-l3-exp-v0-e3-0-v1-mkmlizer: warnings.warn(
cycy233-l3-exp-v0-e3-0-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.
cycy233-l3-exp-v0-e3-0-v1-mkmlizer: warnings.warn(
cycy233-l3-exp-v0-e3-0-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()
cycy233-l3-exp-v0-e3-0-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-l3-exp-v0-e3-0-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-exp-v0-e3-0-v1-mkmlizer: Saving duration: 0.475s
cycy233-l3-exp-v0-e3-0-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.289s
cycy233-l3-exp-v0-e3-0-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-exp-v0-e3-0-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-exp-v0-e3-0-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-exp-v0-e3-0-v1_reward
cycy233-l3-exp-v0-e3-0-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-exp-v0-e3-0-v1_reward/config.json
cycy233-l3-exp-v0-e3-0-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-exp-v0-e3-0-v1_reward/tokenizer_config.json
cycy233-l3-exp-v0-e3-0-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-exp-v0-e3-0-v1_reward/special_tokens_map.json
cycy233-l3-exp-v0-e3-0-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-exp-v0-e3-0-v1_reward/vocab.json
cycy233-l3-exp-v0-e3-0-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-exp-v0-e3-0-v1_reward/merges.txt
cycy233-l3-exp-v0-e3-0-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-exp-v0-e3-0-v1_reward/tokenizer.json
cycy233-l3-exp-v0-e3-0-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-exp-v0-e3-0-v1_reward/reward.tensors
Job cycy233-l3-exp-v0-e3-0-v1-mkmlizer completed after 149.49s with status: succeeded
Stopping job with name cycy233-l3-exp-v0-e3-0-v1-mkmlizer
Pipeline stage MKMLizer completed in 149.94s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-exp-v0-e3-0-v1
Waiting for inference service cycy233-l3-exp-v0-e3-0-v1 to be ready
Inference service cycy233-l3-exp-v0-e3-0-v1 ready after 40.30186867713928s
Pipeline stage ISVCDeployer completed in 46.15s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1468143463134766s
Received healthy response to inference request in 1.2312607765197754s
Received healthy response to inference request in 1.2206766605377197s
Received healthy response to inference request in 1.2396376132965088s
Received healthy response to inference request in 1.2091782093048096s
5 requests
0 failed requests
5th percentile: 1.2114778995513915
10th percentile: 1.2137775897979737
20th percentile: 1.2183769702911378
30th percentile: 1.2227934837341308
40th percentile: 1.227027130126953
50th percentile: 1.2312607765197754
60th percentile: 1.2346115112304688
70th percentile: 1.237962245941162
80th percentile: 1.4210729598999026
90th percentile: 1.7839436531066895
95th percentile: 1.9653789997100828
99th percentile: 2.110527276992798
mean time: 1.409513521194458
Pipeline stage StressChecker completed in 7.98s
cycy233-l3-exp-v0-e3-0_v1 status is now deployed due to DeploymentManager action
cycy233-l3-exp-v0-e3-0_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics