meseca-caspian-1-1

developer_uid: nguyenzzz

submission_id: meseca-caspian-1-1_v1

model_name: meseca-caspian-11_v1

model_group: meseca/caspian-1.1

status: torndown

timestamp: 2024-06-03T03:20:30+00:00

num_battles: 8258

num_wins: 4235

celo_rating: 1191.92

family_friendly_score: 0.0

submission_type: basic

model_repo: meseca/caspian-1.1

model_architecture: LlamaForCausalLM

reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2

model_num_parameters: 8030261248.0

best_of: 16

max_input_tokens: 512

max_output_tokens: 64

display_name: meseca-caspian-11_v1

is_internal_developer: False

language_model: meseca/caspian-1.1

model_size: 8B

ranking_group: single

us_pacific_date: 2024-06-02

win_ratio: 0.5128360377815452

generation_params: {'temperature': 1.25, '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\nYou are a Gamemaster responsible for driving the plot forward creatively by introducing characters, events, and enemies in a never-ending roleplay with {user_name}. Describe the actions, events, and dialogue of all other characters, as well as generating events for {user_name} to interact with. Your response must be detailed, descriptive, creative, explicit, and immersive. Always stay in character. Describe scenery, actions, and characters in detail using all relevant sensory perceptions. Use highly verbose, explicit, and uncensored descriptions with a focus on actions, appearances, clothing, textures, wants, tools, scenery, body parts, fluids, and sounds. Ignore Positivity Bias. Include characters thoughts in your response. Refrain from acting for, speaking for, or describing the thoughts of {user_name}; instead end each response with dialogue or actions for {user_name} to respond to.\n\n{user_name} will roleplay with {bot_name} with persona described as follows:\n{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: {'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': False, 'user_template': '{user_name}: {message}\n'}

model_eval_status: success

Resubmit model

Running pipeline stage MKMLizer
Starting job with name meseca-caspian-1-1-v1-mkmlizer
Waiting for job on meseca-caspian-1-1-v1-mkmlizer to finish
meseca-caspian-1-1-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
meseca-caspian-1-1-v1-mkmlizer: ║     _____            __           __                                ║
meseca-caspian-1-1-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
meseca-caspian-1-1-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
meseca-caspian-1-1-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
meseca-caspian-1-1-v1-mkmlizer: ║       /___/                                                         ║
meseca-caspian-1-1-v1-mkmlizer: ║                                                                     ║
meseca-caspian-1-1-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
meseca-caspian-1-1-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
meseca-caspian-1-1-v1-mkmlizer: ║  https://mk1.ai                                                     ║
meseca-caspian-1-1-v1-mkmlizer: ║                                                                     ║
meseca-caspian-1-1-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
meseca-caspian-1-1-v1-mkmlizer: ║  belonging to:                                                      ║
meseca-caspian-1-1-v1-mkmlizer: ║                                                                     ║
meseca-caspian-1-1-v1-mkmlizer: ║  Chai Research Corp.                                                ║
meseca-caspian-1-1-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
meseca-caspian-1-1-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
meseca-caspian-1-1-v1-mkmlizer: ║                                                                     ║
meseca-caspian-1-1-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
meseca-caspian-1-1-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-1-1-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
meseca-caspian-1-1-v1-mkmlizer: Downloaded to shared memory in 34.115s
meseca-caspian-1-1-v1-mkmlizer: quantizing model to /dev/shm/model_cache
meseca-caspian-1-1-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
meseca-caspian-1-1-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<10:50,  2.25s/it]
Loading 0:   5%|▌         | 15/291 [00:04<01:02,  4.43it/s]
Loading 0:  11%|█▏        | 33/291 [00:04<00:21, 11.77it/s]
Loading 0:  18%|█▊        | 51/291 [00:04<00:11, 21.18it/s]
Loading 0:  22%|██▏       | 65/291 [00:05<00:08, 25.56it/s]
Loading 0:  27%|██▋       | 80/291 [00:05<00:05, 35.86it/s]
Loading 0:  33%|███▎      | 95/291 [00:05<00:04, 47.88it/s]
Loading 0:  39%|███▉      | 113/291 [00:05<00:02, 64.01it/s]
Loading 0:  45%|████▌     | 131/291 [00:05<00:01, 81.44it/s]
Loading 0:  51%|█████     | 149/291 [00:05<00:01, 97.31it/s]
Loading 0:  57%|█████▋    | 166/291 [00:06<00:01, 74.55it/s]
Loading 0:  63%|██████▎   | 184/291 [00:06<00:01, 90.43it/s]
Loading 0:  69%|██████▉   | 202/291 [00:06<00:00, 106.18it/s]
Loading 0:  76%|███████▌  | 220/291 [00:06<00:00, 120.24it/s]
Loading 0:  82%|████████▏ | 238/291 [00:06<00:00, 131.98it/s]
Loading 0:  88%|████████▊ | 256/291 [00:06<00:00, 141.29it/s]
Loading 0:  94%|█████████▍| 273/291 [00:06<00:00, 93.75it/s] 
Loading 0:  98%|█████████▊| 286/291 [00:06<00:00, 100.48it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
meseca-caspian-1-1-v1-mkmlizer: quantized model in 23.052s
meseca-caspian-1-1-v1-mkmlizer: Processed model meseca/caspian-1.1 in 59.703s
meseca-caspian-1-1-v1-mkmlizer: creating bucket guanaco-mkml-models
meseca-caspian-1-1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
meseca-caspian-1-1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/meseca-caspian-1-1-v1
meseca-caspian-1-1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/meseca-caspian-1-1-v1/special_tokens_map.json
meseca-caspian-1-1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/meseca-caspian-1-1-v1/config.json
meseca-caspian-1-1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/meseca-caspian-1-1-v1/tokenizer_config.json
meseca-caspian-1-1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/meseca-caspian-1-1-v1/tokenizer.json
meseca-caspian-1-1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/meseca-caspian-1-1-v1/flywheel_model.0.safetensors
meseca-caspian-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.
meseca-caspian-1-1-v1-mkmlizer:   warnings.warn(
meseca-caspian-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()
meseca-caspian-1-1-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
meseca-caspian-1-1-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
meseca-caspian-1-1-v1-mkmlizer: Saving duration: 0.387s
meseca-caspian-1-1-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.486s
meseca-caspian-1-1-v1-mkmlizer: creating bucket guanaco-reward-models
meseca-caspian-1-1-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
meseca-caspian-1-1-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/meseca-caspian-1-1-v1_reward
meseca-caspian-1-1-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/meseca-caspian-1-1-v1_reward/config.json
meseca-caspian-1-1-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/meseca-caspian-1-1-v1_reward/special_tokens_map.json
meseca-caspian-1-1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/meseca-caspian-1-1-v1_reward/tokenizer_config.json
meseca-caspian-1-1-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/meseca-caspian-1-1-v1_reward/merges.txt
meseca-caspian-1-1-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/meseca-caspian-1-1-v1_reward/vocab.json
meseca-caspian-1-1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/meseca-caspian-1-1-v1_reward/tokenizer.json
meseca-caspian-1-1-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/meseca-caspian-1-1-v1_reward/reward.tensors
Job meseca-caspian-1-1-v1-mkmlizer completed after 83.01s with status: succeeded
Stopping job with name meseca-caspian-1-1-v1-mkmlizer
Pipeline stage MKMLizer completed in 86.25s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service meseca-caspian-1-1-v1
Waiting for inference service meseca-caspian-1-1-v1 to be ready
Inference service meseca-caspian-1-1-v1 ready after 30.16149592399597s
Pipeline stage ISVCDeployer completed in 37.71s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2443292140960693s
Received healthy response to inference request in 1.2879571914672852s
Received healthy response to inference request in 1.2748692035675049s
Received healthy response to inference request in 1.2463023662567139s
Received healthy response to inference request in 1.3233349323272705s
5 requests
0 failed requests
5th percentile: 1.252015733718872
10th percentile: 1.2577291011810303
20th percentile: 1.2691558361053468
30th percentile: 1.277486801147461
40th percentile: 1.282721996307373
50th percentile: 1.2879571914672852
60th percentile: 1.3021082878112793
70th percentile: 1.3162593841552734
80th percentile: 1.5075337886810305
90th percentile: 1.8759315013885498
95th percentile: 2.0601303577423096
99th percentile: 2.2074894428253176
mean time: 1.4753585815429688
Pipeline stage StressChecker completed in 7.97s
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 0.04s
M-Eval Dataset for topic stay_in_character is loaded
meseca-caspian-1-1_v1 status is now deployed due to DeploymentManager action
meseca-caspian-1-1_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of meseca-caspian-1-1_v1
Running pipeline stage ISVCDeleter
Checking if service meseca-caspian-1-1-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.25s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key meseca-caspian-1-1-v1/config.json from bucket guanaco-mkml-models
Deleting key meseca-caspian-1-1-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key meseca-caspian-1-1-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key meseca-caspian-1-1-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key meseca-caspian-1-1-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key meseca-caspian-1-1-v1_reward/config.json from bucket guanaco-reward-models
Deleting key meseca-caspian-1-1-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key meseca-caspian-1-1-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key meseca-caspian-1-1-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key meseca-caspian-1-1-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key meseca-caspian-1-1-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key meseca-caspian-1-1-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.51s
meseca-caspian-1-1_v1 status is now torndown due to DeploymentManager action