meseca-15062024-c1

developer_uid: nguyenzzz

submission_id: meseca-15062024-c1_v1

model_name: v2-l3-70b-euryale-test-beta-1

model_group: meseca/15062024-c1

status: torndown

timestamp: 2024-06-16T06:11:08+00:00

num_battles: 10829

num_wins: 6103

celo_rating: 1217.97

family_friendly_score: 0.0

submission_type: basic

model_repo: meseca/15062024-c1

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: v2-l3-70b-euryale-test-beta-1

is_internal_developer: False

language_model: meseca/15062024-c1

model_size: 8B

ranking_group: single

us_pacific_date: 2024-06-15

win_ratio: 0.5635792778649922

generation_params: {'temperature': 0.9, 'top_p': 0.95, 'min_p': 0.075, 'top_k': 60, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|end_header_id|>,', '<|eot_id|>,', '\n\n{user_name}'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}

formatter: {'memory_template': "<|begin_of_text|><|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}

model_eval_status: success

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'}

Resubmit model

Running pipeline stage MKMLizer
Starting job with name meseca-15062024-c1-v1-mkmlizer
Waiting for job on meseca-15062024-c1-v1-mkmlizer to finish
meseca-15062024-c1-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
meseca-15062024-c1-v1-mkmlizer: ║     _____            __           __                                ║
meseca-15062024-c1-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
meseca-15062024-c1-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
meseca-15062024-c1-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
meseca-15062024-c1-v1-mkmlizer: ║       /___/                                                         ║
meseca-15062024-c1-v1-mkmlizer: ║                                                                     ║
meseca-15062024-c1-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
meseca-15062024-c1-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
meseca-15062024-c1-v1-mkmlizer: ║  https://mk1.ai                                                     ║
meseca-15062024-c1-v1-mkmlizer: ║                                                                     ║
meseca-15062024-c1-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
meseca-15062024-c1-v1-mkmlizer: ║  belonging to:                                                      ║
meseca-15062024-c1-v1-mkmlizer: ║                                                                     ║
meseca-15062024-c1-v1-mkmlizer: ║  Chai Research Corp.                                                ║
meseca-15062024-c1-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
meseca-15062024-c1-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
meseca-15062024-c1-v1-mkmlizer: ║                                                                     ║
meseca-15062024-c1-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
meseca-15062024-c1-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-15062024-c1-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
meseca-15062024-c1-v1-mkmlizer: Downloaded to shared memory in 46.808s
meseca-15062024-c1-v1-mkmlizer: quantizing model to /dev/shm/model_cache
meseca-15062024-c1-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
meseca-15062024-c1-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:05<12:13,  2.54s/it]
Loading 0:   4%|▍         | 13/291 [00:05<01:22,  3.38it/s]
Loading 0:   8%|▊         | 23/291 [00:05<00:38,  6.97it/s]
Loading 0:  11%|█▏        | 33/291 [00:05<00:22, 11.62it/s]
Loading 0:  17%|█▋        | 49/291 [00:05<00:11, 21.30it/s]
Loading 0:  20%|██        | 59/291 [00:05<00:08, 27.82it/s]
Loading 0:  24%|██▎       | 69/291 [00:06<00:08, 26.81it/s]
Loading 0:  29%|██▊       | 83/291 [00:06<00:05, 38.61it/s]
Loading 0:  32%|███▏      | 93/291 [00:06<00:04, 46.04it/s]
Loading 0:  35%|███▌      | 103/291 [00:06<00:03, 51.53it/s]
Loading 0:  39%|███▉      | 113/291 [00:06<00:02, 59.40it/s]
Loading 0:  42%|████▏     | 123/291 [00:06<00:02, 64.56it/s]
Loading 0:  46%|████▌     | 133/291 [00:06<00:02, 72.02it/s]
Loading 0:  49%|████▉     | 143/291 [00:06<00:01, 76.82it/s]
Loading 0:  53%|█████▎    | 153/291 [00:06<00:01, 80.48it/s]
Loading 0:  56%|█████▌    | 163/291 [00:07<00:01, 84.75it/s]
Loading 0:  59%|█████▉    | 173/291 [00:07<00:02, 53.26it/s]
Loading 0:  63%|██████▎   | 183/291 [00:07<00:01, 61.92it/s]
Loading 0:  66%|██████▋   | 193/291 [00:07<00:01, 67.70it/s]
Loading 0:  70%|██████▉   | 203/291 [00:07<00:01, 73.53it/s]
Loading 0:  73%|███████▎  | 212/291 [00:07<00:01, 77.13it/s]
Loading 0:  76%|███████▌  | 221/291 [00:07<00:00, 78.52it/s]
Loading 0:  79%|███████▉  | 230/291 [00:08<00:00, 79.47it/s]
Loading 0:  82%|████████▏ | 239/291 [00:08<00:00, 82.12it/s]
Loading 0:  86%|████████▌ | 249/291 [00:08<00:00, 83.95it/s]
Loading 0:  90%|█████████ | 262/291 [00:08<00:00, 96.61it/s]
Loading 0:  93%|█████████▎| 272/291 [00:08<00:00, 58.19it/s]
Loading 0:  97%|█████████▋| 283/291 [00:08<00:00, 65.45it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
meseca-15062024-c1-v1-mkmlizer: quantized model in 25.615s
meseca-15062024-c1-v1-mkmlizer: Processed model meseca/15062024-c1 in 74.969s
meseca-15062024-c1-v1-mkmlizer: creating bucket guanaco-mkml-models
meseca-15062024-c1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
meseca-15062024-c1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/meseca-15062024-c1-v1
meseca-15062024-c1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/meseca-15062024-c1-v1/tokenizer_config.json
meseca-15062024-c1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/meseca-15062024-c1-v1/tokenizer.json
meseca-15062024-c1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/meseca-15062024-c1-v1/special_tokens_map.json
meseca-15062024-c1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/meseca-15062024-c1-v1/config.json
meseca-15062024-c1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/meseca-15062024-c1-v1/flywheel_model.0.safetensors
meseca-15062024-c1-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
meseca-15062024-c1-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-15062024-c1-v1-mkmlizer:   warnings.warn(
meseca-15062024-c1-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-15062024-c1-v1-mkmlizer:   warnings.warn(
meseca-15062024-c1-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-15062024-c1-v1-mkmlizer:   warnings.warn(
meseca-15062024-c1-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-15062024-c1-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
meseca-15062024-c1-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
meseca-15062024-c1-v1-mkmlizer: Saving duration: 0.404s
meseca-15062024-c1-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 17.317s
meseca-15062024-c1-v1-mkmlizer: creating bucket guanaco-reward-models
meseca-15062024-c1-v1-mkmlizer: WARNING: Retrying failed request: /?location ([Errno 110] Connection timed out)
meseca-15062024-c1-v1-mkmlizer: WARNING: Waiting 3 sec...
meseca-15062024-c1-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
meseca-15062024-c1-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/meseca-15062024-c1-v1_reward
meseca-15062024-c1-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/meseca-15062024-c1-v1_reward/config.json
meseca-15062024-c1-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/meseca-15062024-c1-v1_reward/special_tokens_map.json
meseca-15062024-c1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/meseca-15062024-c1-v1_reward/tokenizer_config.json
meseca-15062024-c1-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/meseca-15062024-c1-v1_reward/merges.txt
meseca-15062024-c1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/meseca-15062024-c1-v1_reward/tokenizer.json
meseca-15062024-c1-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/meseca-15062024-c1-v1_reward/vocab.json
meseca-15062024-c1-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/meseca-15062024-c1-v1_reward/reward.tensors
Job meseca-15062024-c1-v1-mkmlizer completed after 302.79s with status: succeeded
Stopping job with name meseca-15062024-c1-v1-mkmlizer
Pipeline stage MKMLizer completed in 305.69s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service meseca-15062024-c1-v1
Waiting for inference service meseca-15062024-c1-v1 to be ready
Inference service meseca-15062024-c1-v1 ready after 30.1622257232666s
Pipeline stage ISVCDeployer completed in 37.16s
Running pipeline stage StressChecker
Received healthy response to inference request in 19.20166301727295s
Received healthy response to inference request in 1.3418314456939697s
Received healthy response to inference request in 1.3099393844604492s
Received healthy response to inference request in 1.2659540176391602s
Received healthy response to inference request in 1.3446588516235352s
5 requests
0 failed requests
5th percentile: 1.2747510910034179
10th percentile: 1.2835481643676758
20th percentile: 1.3011423110961915
30th percentile: 1.3163177967071533
40th percentile: 1.3290746212005615
50th percentile: 1.3418314456939697
60th percentile: 1.3429624080657958
70th percentile: 1.3440933704376221
80th percentile: 4.916059684753421
90th percentile: 12.058861351013185
95th percentile: 15.630262184143064
99th percentile: 18.487382850646974
mean time: 4.892809343338013
Pipeline stage StressChecker completed in 25.11s
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-15062024-c1_v1 status is now deployed due to DeploymentManager action
meseca-15062024-c1_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of meseca-15062024-c1_v1
Running pipeline stage ISVCDeleter
Checking if service meseca-15062024-c1-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.39s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key meseca-15062024-c1-v1/config.json from bucket guanaco-mkml-models
Deleting key meseca-15062024-c1-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key meseca-15062024-c1-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key meseca-15062024-c1-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key meseca-15062024-c1-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key meseca-15062024-c1-v1_reward/config.json from bucket guanaco-reward-models
Deleting key meseca-15062024-c1-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key meseca-15062024-c1-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key meseca-15062024-c1-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key meseca-15062024-c1-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key meseca-15062024-c1-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key meseca-15062024-c1-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.11s
meseca-15062024-c1_v1 status is now torndown due to DeploymentManager action