submission_id: meseca-caspian-1_v1
developer_uid: nguyenzzz
status: inactive
model_repo: meseca/caspian-1
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.1, 'top_p': 1.0, 'min_p': 0.08, 'top_k': 50, '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': "<|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}
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: 2024-06-02T16:05:56+00:00
model_name: meseca-caspian-1_v1
model_eval_status: success
model_group: meseca/caspian-1
num_battles: 10282
num_wins: 5684
celo_rating: 1199.2
safety_score: 0.96
propriety_score: 0.6736842105263158
propriety_total_count: 190.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: meseca-caspian-1_v1
ineligible_reason: propriety_total_count < 5000
language_model: meseca/caspian-1
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-02
win_ratio: 0.5528107372106594
Resubmit model
Running pipeline stage MKMLizer
Starting job with name meseca-caspian-1-v1-mkmlizer
Waiting for job on meseca-caspian-1-v1-mkmlizer to finish
meseca-caspian-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.
meseca-caspian-1-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
meseca-caspian-1-v1-mkmlizer: Downloaded to shared memory in 31.070s
meseca-caspian-1-v1-mkmlizer: quantizing model to /dev/shm/model_cache
meseca-caspian-1-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
meseca-caspian-1-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<09:55, 2.06s/it] Loading 0: 8%|▊ | 23/291 [00:04<00:35, 7.48it/s] Loading 0: 15%|█▌ | 45/291 [00:04<00:14, 17.16it/s] Loading 0: 21%|██▏ | 62/291 [00:04<00:09, 23.00it/s] Loading 0: 29%|██▉ | 85/291 [00:04<00:05, 37.49it/s] Loading 0: 36%|███▌ | 105/291 [00:04<00:03, 51.90it/s] Loading 0: 45%|████▍ | 130/291 [00:04<00:02, 74.58it/s] Loading 0: 52%|█████▏ | 150/291 [00:05<00:01, 92.03it/s] Loading 0: 58%|█████▊ | 170/291 [00:05<00:01, 79.47it/s] Loading 0: 67%|██████▋ | 194/291 [00:05<00:00, 101.91it/s] Loading 0: 74%|███████▍ | 216/291 [00:05<00:00, 121.66it/s] Loading 0: 82%|████████▏ | 239/291 [00:05<00:00, 140.17it/s] Loading 0: 91%|█████████ | 264/291 [00:05<00:00, 163.86it/s] Loading 0: 98%|█████████▊| 286/291 [00:06<00:00, 103.14it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
meseca-caspian-1-v1-mkmlizer: quantized model in 17.054s
meseca-caspian-1-v1-mkmlizer: Processed model meseca/caspian-1 in 49.024s
meseca-caspian-1-v1-mkmlizer: creating bucket guanaco-mkml-models
meseca-caspian-1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
meseca-caspian-1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/meseca-caspian-1-v1
meseca-caspian-1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/meseca-caspian-1-v1/config.json
meseca-caspian-1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/meseca-caspian-1-v1/tokenizer_config.json
meseca-caspian-1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/meseca-caspian-1-v1/special_tokens_map.json
meseca-caspian-1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/meseca-caspian-1-v1/tokenizer.json
meseca-caspian-1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/meseca-caspian-1-v1/flywheel_model.0.safetensors
meseca-caspian-1-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
meseca-caspian-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.
meseca-caspian-1-v1-mkmlizer: warnings.warn(
meseca-caspian-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.
meseca-caspian-1-v1-mkmlizer: warnings.warn(
meseca-caspian-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.
meseca-caspian-1-v1-mkmlizer: warnings.warn(
meseca-caspian-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()
meseca-caspian-1-v1-mkmlizer: return self.fget.__get__(instance, owner)()
meseca-caspian-1-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
meseca-caspian-1-v1-mkmlizer: creating bucket guanaco-reward-models
meseca-caspian-1-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
meseca-caspian-1-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/meseca-caspian-1-v1_reward
meseca-caspian-1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/meseca-caspian-1-v1_reward/tokenizer_config.json
meseca-caspian-1-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/meseca-caspian-1-v1_reward/merges.txt
meseca-caspian-1-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/meseca-caspian-1-v1_reward/vocab.json
meseca-caspian-1-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/meseca-caspian-1-v1_reward/config.json
meseca-caspian-1-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/meseca-caspian-1-v1_reward/special_tokens_map.json
meseca-caspian-1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/meseca-caspian-1-v1_reward/tokenizer.json
meseca-caspian-1-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/meseca-caspian-1-v1_reward/reward.tensors
Job meseca-caspian-1-v1-mkmlizer completed after 215.39s with status: succeeded
Stopping job with name meseca-caspian-1-v1-mkmlizer
Pipeline stage MKMLizer completed in 218.44s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service meseca-caspian-1-v1
Waiting for inference service meseca-caspian-1-v1 to be ready
Inference service meseca-caspian-1-v1 ready after 50.297157287597656s
Pipeline stage ISVCDeployer completed in 57.33s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.203388214111328s
Received healthy response to inference request in 1.3072102069854736s
Received healthy response to inference request in 1.3120102882385254s
Received healthy response to inference request in 1.264465093612671s
Received healthy response to inference request in 1.251589298248291s
5 requests
0 failed requests
5th percentile: 1.254164457321167
10th percentile: 1.256739616394043
20th percentile: 1.261889934539795
30th percentile: 1.2730141162872315
40th percentile: 1.2901121616363525
50th percentile: 1.3072102069854736
60th percentile: 1.3091302394866944
70th percentile: 1.3110502719879151
80th percentile: 1.4902858734130862
90th percentile: 1.846837043762207
95th percentile: 2.0251126289367676
99th percentile: 2.167733097076416
mean time: 1.4677326202392578
Pipeline stage StressChecker completed in 7.92s
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
meseca-caspian-1_v1 status is now deployed due to DeploymentManager action
meseca-caspian-1_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics