meseca-15062024-c1

developer_uid: nguyenzzz

submission_id: meseca-15062024-c1_v2

model_name: meseca-15062024-c1_v2

model_group: meseca/15062024-c1

status: torndown

timestamp: 2024-07-02T02:06:49+00:00

num_battles: 11490

num_wins: 6274

celo_rating: 1207.23

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: meseca-15062024-c1_v2

is_internal_developer: False

language_model: meseca/15062024-c1

model_size: 8B

ranking_group: single

us_pacific_date: 2024-07-01

win_ratio: 0.5460400348128808

generation_params: {'temperature': 1.1, '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}

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-v2-mkmlizer
Waiting for job on meseca-15062024-c1-v2-mkmlizer to finish
meseca-15062024-c1-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
meseca-15062024-c1-v2-mkmlizer: ║     _____            __           __                                ║
meseca-15062024-c1-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
meseca-15062024-c1-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
meseca-15062024-c1-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
meseca-15062024-c1-v2-mkmlizer: ║       /___/                                                         ║
meseca-15062024-c1-v2-mkmlizer: ║                                                                     ║
meseca-15062024-c1-v2-mkmlizer: ║  Version: 0.8.14                                                    ║
meseca-15062024-c1-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
meseca-15062024-c1-v2-mkmlizer: ║  https://mk1.ai                                                     ║
meseca-15062024-c1-v2-mkmlizer: ║                                                                     ║
meseca-15062024-c1-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
meseca-15062024-c1-v2-mkmlizer: ║  belonging to:                                                      ║
meseca-15062024-c1-v2-mkmlizer: ║                                                                     ║
meseca-15062024-c1-v2-mkmlizer: ║  Chai Research Corp.                                                ║
meseca-15062024-c1-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
meseca-15062024-c1-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
meseca-15062024-c1-v2-mkmlizer: ║                                                                     ║
meseca-15062024-c1-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
meseca-15062024-c1-v2-mkmlizer: Downloaded to shared memory in 31.809s
meseca-15062024-c1-v2-mkmlizer: quantizing model to /dev/shm/model_cache
meseca-15062024-c1-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
meseca-15062024-c1-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<10:55,  2.27s/it]
Loading 0:   5%|▌         | 15/291 [00:04<01:02,  4.39it/s]
Loading 0:  11%|█▏        | 33/291 [00:04<00:22, 11.68it/s]
Loading 0:  18%|█▊        | 51/291 [00:04<00:11, 21.01it/s]
Loading 0:  22%|██▏       | 65/291 [00:05<00:08, 25.23it/s]
Loading 0:  27%|██▋       | 78/291 [00:05<00:06, 33.80it/s]
Loading 0:  33%|███▎      | 96/291 [00:05<00:04, 48.56it/s]
Loading 0:  39%|███▉      | 114/291 [00:05<00:02, 64.60it/s]
Loading 0:  45%|████▌     | 132/291 [00:05<00:01, 81.07it/s]
Loading 0:  52%|█████▏    | 150/291 [00:05<00:01, 96.58it/s]
Loading 0:  57%|█████▋    | 166/291 [00:06<00:01, 73.17it/s]
Loading 0:  61%|██████    | 178/291 [00:06<00:01, 79.92it/s]
Loading 0:  67%|██████▋   | 195/291 [00:06<00:01, 94.15it/s]
Loading 0:  73%|███████▎  | 212/291 [00:06<00:00, 108.91it/s]
Loading 0:  79%|███████▊  | 229/291 [00:06<00:00, 122.59it/s]
Loading 0:  85%|████████▍ | 247/291 [00:06<00:00, 132.15it/s]
Loading 0:  91%|█████████ | 265/291 [00:06<00:00, 140.60it/s]
Loading 0:  97%|█████████▋| 281/291 [00:07<00:00, 89.86it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
meseca-15062024-c1-v2-mkmlizer: quantized model in 23.619s
meseca-15062024-c1-v2-mkmlizer: Processed model meseca/15062024-c1 in 55.428s
meseca-15062024-c1-v2-mkmlizer: creating bucket guanaco-mkml-models
meseca-15062024-c1-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
meseca-15062024-c1-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/meseca-15062024-c1-v2
meseca-15062024-c1-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/meseca-15062024-c1-v2/special_tokens_map.json
meseca-15062024-c1-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/meseca-15062024-c1-v2/config.json
meseca-15062024-c1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/meseca-15062024-c1-v2/tokenizer_config.json
meseca-15062024-c1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/meseca-15062024-c1-v2/tokenizer.json
meseca-15062024-c1-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/meseca-15062024-c1-v2/flywheel_model.0.safetensors
meseca-15062024-c1-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
meseca-15062024-c1-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:919: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
meseca-15062024-c1-v2-mkmlizer:   warnings.warn(
meseca-15062024-c1-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
meseca-15062024-c1-v2-mkmlizer:   warnings.warn(
meseca-15062024-c1-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:769: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
meseca-15062024-c1-v2-mkmlizer:   warnings.warn(
meseca-15062024-c1-v2-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-v2-mkmlizer:   warnings.warn(
meseca-15062024-c1-v2-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-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
meseca-15062024-c1-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
meseca-15062024-c1-v2-mkmlizer: Saving duration: 1.593s
meseca-15062024-c1-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.781s
meseca-15062024-c1-v2-mkmlizer: creating bucket guanaco-reward-models
meseca-15062024-c1-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
meseca-15062024-c1-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/meseca-15062024-c1-v2_reward
meseca-15062024-c1-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/meseca-15062024-c1-v2_reward/config.json
meseca-15062024-c1-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/meseca-15062024-c1-v2_reward/special_tokens_map.json
meseca-15062024-c1-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/meseca-15062024-c1-v2_reward/tokenizer_config.json
meseca-15062024-c1-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/meseca-15062024-c1-v2_reward/vocab.json
meseca-15062024-c1-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/meseca-15062024-c1-v2_reward/merges.txt
meseca-15062024-c1-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/meseca-15062024-c1-v2_reward/tokenizer.json
meseca-15062024-c1-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/meseca-15062024-c1-v2_reward/reward.tensors
Job meseca-15062024-c1-v2-mkmlizer completed after 144.88s with status: succeeded
Stopping job with name meseca-15062024-c1-v2-mkmlizer
Pipeline stage MKMLizer completed in 145.85s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service meseca-15062024-c1-v2
Waiting for inference service meseca-15062024-c1-v2 to be ready
Inference service meseca-15062024-c1-v2 ready after 50.32623887062073s
Pipeline stage ISVCDeployer completed in 57.14s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.210901975631714s
Received healthy response to inference request in 1.3735911846160889s
Received healthy response to inference request in 1.3532969951629639s
Received healthy response to inference request in 1.3172836303710938s
Received healthy response to inference request in 1.4556810855865479s
5 requests
0 failed requests
5th percentile: 1.3244863033294678
10th percentile: 1.3316889762878419
20th percentile: 1.3460943222045898
30th percentile: 1.3573558330535889
40th percentile: 1.3654735088348389
50th percentile: 1.3735911846160889
60th percentile: 1.4064271450042725
70th percentile: 1.439263105392456
80th percentile: 1.606725263595581
90th percentile: 1.9088136196136476
95th percentile: 2.0598577976226804
99th percentile: 2.180693140029907
mean time: 1.5421509742736816
Pipeline stage StressChecker completed in 8.52s
meseca-15062024-c1_v2 status is now deployed due to DeploymentManager action
meseca-15062024-c1_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of meseca-15062024-c1_v2
Running pipeline stage ISVCDeleter
Checking if service meseca-15062024-c1-v2 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 3.88s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key meseca-15062024-c1-v2/config.json from bucket guanaco-mkml-models
Deleting key meseca-15062024-c1-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key meseca-15062024-c1-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key meseca-15062024-c1-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key meseca-15062024-c1-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key meseca-15062024-c1-v2_reward/config.json from bucket guanaco-reward-models
Deleting key meseca-15062024-c1-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key meseca-15062024-c1-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key meseca-15062024-c1-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key meseca-15062024-c1-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key meseca-15062024-c1-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key meseca-15062024-c1-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.50s
meseca-15062024-c1_v2 status is now torndown due to DeploymentManager action