cgato-thesalt-rp-l3-8b-d_9840

submission_id: cgato-thesalt-rp-l3-8b-d_9840_v1

developer_uid: c.gato

best_of: 16

celo_rating: 1201.7

display_name: cgato-thesalt-rp-l3-8b-d_9840_v1

family_friendly_score: 0.0

formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{bot_name}:', 'truncate_by_message': True}

generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '\\r', '\\r\n', '\n\n', 'You:'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}

is_internal_developer: False

language_model: cgato/TheSalt-RP-L3-8b-DPO-v0.3.2-e0.10.2

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_group: cgato/TheSalt-RP-L3-8b-D

model_name: cgato-thesalt-rp-l3-8b-d_9840_v1

model_num_parameters: 8030294016.0

model_repo: cgato/TheSalt-RP-L3-8b-DPO-v0.3.2-e0.10.2

model_size: 8B

num_battles: 34763

num_wins: 18284

ranking_group: single

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': True, 'user_template': '{user_name}: {message}\n'}

reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2

status: torndown

submission_type: basic

timestamp: 2024-07-05T15:38:31+00:00

us_pacific_date: 2024-07-05

win_ratio: 0.5259615108017145

Resubmit model

Running pipeline stage MKMLizer
Starting job with name cgato-thesalt-rp-l3-8b-d-9840-v1-mkmlizer
Waiting for job on cgato-thesalt-rp-l3-8b-d-9840-v1-mkmlizer to finish
cgato-thesalt-rp-l3-8b-d-9840-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-thesalt-rp-l3-8b-d-9840-v1-mkmlizer: ║     _____            __           __                                ║
cgato-thesalt-rp-l3-8b-d-9840-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cgato-thesalt-rp-l3-8b-d-9840-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cgato-thesalt-rp-l3-8b-d-9840-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cgato-thesalt-rp-l3-8b-d-9840-v1-mkmlizer: ║       /___/                                                         ║
cgato-thesalt-rp-l3-8b-d-9840-v1-mkmlizer: ║                                                                     ║
cgato-thesalt-rp-l3-8b-d-9840-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
cgato-thesalt-rp-l3-8b-d-9840-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cgato-thesalt-rp-l3-8b-d-9840-v1-mkmlizer: ║  https://mk1.ai                                                     ║
cgato-thesalt-rp-l3-8b-d-9840-v1-mkmlizer: ║                                                                     ║
cgato-thesalt-rp-l3-8b-d-9840-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
cgato-thesalt-rp-l3-8b-d-9840-v1-mkmlizer: ║  belonging to:                                                      ║
cgato-thesalt-rp-l3-8b-d-9840-v1-mkmlizer: ║                                                                     ║
cgato-thesalt-rp-l3-8b-d-9840-v1-mkmlizer: ║  Chai Research Corp.                                                ║
cgato-thesalt-rp-l3-8b-d-9840-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cgato-thesalt-rp-l3-8b-d-9840-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
cgato-thesalt-rp-l3-8b-d-9840-v1-mkmlizer: ║                                                                     ║
cgato-thesalt-rp-l3-8b-d-9840-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
cgato-thesalt-rp-l3-8b-d-9840-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   5%|▍         | 14/291 [00:00<00:02, 129.80it/s]
Loading 0:  11%|█         | 32/291 [00:00<00:01, 145.70it/s]
Loading 0:  17%|█▋        | 49/291 [00:00<00:01, 155.82it/s]
Loading 0:  23%|██▎       | 67/291 [00:00<00:01, 156.82it/s]
Loading 0:  29%|██▊       | 83/291 [00:00<00:02, 79.56it/s] 
Loading 0:  33%|███▎      | 95/291 [00:00<00:02, 86.55it/s]
Loading 0:  38%|███▊      | 112/291 [00:01<00:01, 104.60it/s]
Loading 0:  44%|████▍     | 129/291 [00:01<00:01, 119.96it/s]
Loading 0:  49%|████▉     | 144/291 [00:01<00:01, 126.93it/s]
Loading 0:  55%|█████▍    | 159/291 [00:01<00:01, 130.40it/s]
Loading 0:  62%|██████▏   | 179/291 [00:01<00:00, 144.65it/s]
Loading 0:  67%|██████▋   | 195/291 [00:01<00:01, 83.45it/s] 
Loading 0:  73%|███████▎  | 212/291 [00:01<00:00, 96.63it/s]
Loading 0:  79%|███████▉  | 230/291 [00:02<00:00, 110.24it/s]
Loading 0:  85%|████████▍ | 247/291 [00:02<00:00, 123.16it/s]
Loading 0:  91%|█████████ | 265/291 [00:02<00:00, 132.10it/s]
Loading 0:  97%|█████████▋| 281/291 [00:02<00:00, 138.88it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cgato-thesalt-rp-l3-8b-d-9840-v1-mkmlizer: quantized model in 23.353s
cgato-thesalt-rp-l3-8b-d-9840-v1-mkmlizer: Processed model cgato/TheSalt-RP-L3-8b-DPO-v0.3.2-e0.10.2 in 59.604s
cgato-thesalt-rp-l3-8b-d-9840-v1-mkmlizer: creating bucket guanaco-mkml-models
cgato-thesalt-rp-l3-8b-d-9840-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-thesalt-rp-l3-8b-d-9840-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-9840-v1
cgato-thesalt-rp-l3-8b-d-9840-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-9840-v1/config.json
cgato-thesalt-rp-l3-8b-d-9840-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-9840-v1/special_tokens_map.json
cgato-thesalt-rp-l3-8b-d-9840-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-9840-v1/tokenizer_config.json
cgato-thesalt-rp-l3-8b-d-9840-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-9840-v1/tokenizer.json
cgato-thesalt-rp-l3-8b-d-9840-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-9840-v1/flywheel_model.0.safetensors
cgato-thesalt-rp-l3-8b-d-9840-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-thesalt-rp-l3-8b-d-9840-v1-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.
cgato-thesalt-rp-l3-8b-d-9840-v1-mkmlizer:   warnings.warn(
cgato-thesalt-rp-l3-8b-d-9840-v1-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`.
cgato-thesalt-rp-l3-8b-d-9840-v1-mkmlizer:   warnings.warn(
cgato-thesalt-rp-l3-8b-d-9840-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.
cgato-thesalt-rp-l3-8b-d-9840-v1-mkmlizer:   warnings.warn(
cgato-thesalt-rp-l3-8b-d-9840-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()
cgato-thesalt-rp-l3-8b-d-9840-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
cgato-thesalt-rp-l3-8b-d-9840-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-thesalt-rp-l3-8b-d-9840-v1-mkmlizer: Saving duration: 0.402s
cgato-thesalt-rp-l3-8b-d-9840-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 8.150s
cgato-thesalt-rp-l3-8b-d-9840-v1-mkmlizer: creating bucket guanaco-reward-models
cgato-thesalt-rp-l3-8b-d-9840-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-thesalt-rp-l3-8b-d-9840-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-9840-v1_reward
cgato-thesalt-rp-l3-8b-d-9840-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-9840-v1_reward/config.json
cgato-thesalt-rp-l3-8b-d-9840-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-9840-v1_reward/special_tokens_map.json
cgato-thesalt-rp-l3-8b-d-9840-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-9840-v1_reward/tokenizer_config.json
cgato-thesalt-rp-l3-8b-d-9840-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-9840-v1_reward/merges.txt
cgato-thesalt-rp-l3-8b-d-9840-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-9840-v1_reward/vocab.json
cgato-thesalt-rp-l3-8b-d-9840-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-9840-v1_reward/tokenizer.json
cgato-thesalt-rp-l3-8b-d-9840-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-9840-v1_reward/reward.tensors
Job cgato-thesalt-rp-l3-8b-d-9840-v1-mkmlizer completed after 94.0s with status: succeeded
Stopping job with name cgato-thesalt-rp-l3-8b-d-9840-v1-mkmlizer
Pipeline stage MKMLizer completed in 94.95s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service cgato-thesalt-rp-l3-8b-d-9840-v1
Waiting for inference service cgato-thesalt-rp-l3-8b-d-9840-v1 to be ready
Inference service cgato-thesalt-rp-l3-8b-d-9840-v1 ready after 40.203054666519165s
Pipeline stage ISVCDeployer completed in 47.44s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.074385643005371s
Received healthy response to inference request in 1.2968220710754395s
Received healthy response to inference request in 1.3041479587554932s
Received healthy response to inference request in 1.289308786392212s
Received healthy response to inference request in 1.2804229259490967s
5 requests
0 failed requests
5th percentile: 1.2822000980377197
10th percentile: 1.2839772701263428
20th percentile: 1.2875316143035889
30th percentile: 1.2908114433288573
40th percentile: 1.2938167572021484
50th percentile: 1.2968220710754395
60th percentile: 1.299752426147461
70th percentile: 1.3026827812194823
80th percentile: 1.4581954956054688
90th percentile: 1.76629056930542
95th percentile: 1.9203381061553955
99th percentile: 2.043576135635376
mean time: 1.4490174770355224
Pipeline stage StressChecker completed in 7.93s
cgato-thesalt-rp-l3-8b-d_9840_v1 status is now deployed due to DeploymentManager action
cgato-thesalt-rp-l3-8b-d_9840_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cgato-thesalt-rp-l3-8b-d_9840_v1
Running pipeline stage ISVCDeleter
Checking if service cgato-thesalt-rp-l3-8b-d-9840-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 5.21s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cgato-thesalt-rp-l3-8b-d-9840-v1/config.json from bucket guanaco-mkml-models
Deleting key cgato-thesalt-rp-l3-8b-d-9840-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cgato-thesalt-rp-l3-8b-d-9840-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cgato-thesalt-rp-l3-8b-d-9840-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key cgato-thesalt-rp-l3-8b-d-9840-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cgato-thesalt-rp-l3-8b-d-9840-v1_reward/config.json from bucket guanaco-reward-models
Deleting key cgato-thesalt-rp-l3-8b-d-9840-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key cgato-thesalt-rp-l3-8b-d-9840-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cgato-thesalt-rp-l3-8b-d-9840-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cgato-thesalt-rp-l3-8b-d-9840-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cgato-thesalt-rp-l3-8b-d-9840-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cgato-thesalt-rp-l3-8b-d-9840-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.40s
cgato-thesalt-rp-l3-8b-d_9840_v1 status is now torndown due to DeploymentManager action