submission_id: cgato-thesalt-rp-l3-8b-d_5769_v1
developer_uid: c.gato
status: inactive
model_repo: cgato/TheSalt-RP-L3-8b-DPO-v0.3.2-e0.12.2
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 0.9, 'min_p': 0.05, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '\n\n', 'You:'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
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}
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': True}
timestamp: 2024-07-07T17:33:21+00:00
model_name: cgato-thesalt-rp-l3-8b-d_5769_v1
model_group: cgato/TheSalt-RP-L3-8b-D
num_battles: 43828
num_wins: 22607
celo_rating: 1203.32
propriety_score: 0.705936312409907
propriety_total_count: 7631.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030294016.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: cgato-thesalt-rp-l3-8b-d_5769_v1
ineligible_reason: None
language_model: cgato/TheSalt-RP-L3-8b-DPO-v0.3.2-e0.12.2
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-07-07
win_ratio: 0.5158118098019531
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-thesalt-rp-l3-8b-d-5769-v1-mkmlizer
Waiting for job on cgato-thesalt-rp-l3-8b-d-5769-v1-mkmlizer to finish
cgato-thesalt-rp-l3-8b-d-5769-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-thesalt-rp-l3-8b-d-5769-v1-mkmlizer: ║ _____ __ __ ║
cgato-thesalt-rp-l3-8b-d-5769-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-thesalt-rp-l3-8b-d-5769-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-thesalt-rp-l3-8b-d-5769-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-thesalt-rp-l3-8b-d-5769-v1-mkmlizer: ║ /___/ ║
cgato-thesalt-rp-l3-8b-d-5769-v1-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-5769-v1-mkmlizer: ║ Version: 0.8.14 ║
cgato-thesalt-rp-l3-8b-d-5769-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-thesalt-rp-l3-8b-d-5769-v1-mkmlizer: ║ https://mk1.ai ║
cgato-thesalt-rp-l3-8b-d-5769-v1-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-5769-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-thesalt-rp-l3-8b-d-5769-v1-mkmlizer: ║ belonging to: ║
cgato-thesalt-rp-l3-8b-d-5769-v1-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-5769-v1-mkmlizer: ║ Chai Research Corp. ║
cgato-thesalt-rp-l3-8b-d-5769-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-thesalt-rp-l3-8b-d-5769-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-thesalt-rp-l3-8b-d-5769-v1-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-5769-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-thesalt-rp-l3-8b-d-5769-v1-mkmlizer: Downloaded to shared memory in 33.109s
cgato-thesalt-rp-l3-8b-d-5769-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-thesalt-rp-l3-8b-d-5769-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-thesalt-rp-l3-8b-d-5769-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:02, 116.05it/s] Loading 0: 8%|▊ | 24/291 [00:00<00:02, 103.64it/s] Loading 0: 13%|█▎ | 39/291 [00:00<00:02, 116.32it/s] Loading 0: 18%|█▊ | 51/291 [00:00<00:02, 109.35it/s] Loading 0: 23%|██▎ | 66/291 [00:00<00:01, 117.36it/s] Loading 0: 27%|██▋ | 78/291 [00:00<00:01, 110.10it/s] Loading 0: 31%|███ | 90/291 [00:01<00:03, 62.38it/s] Loading 0: 35%|███▌ | 102/291 [00:01<00:02, 72.94it/s] Loading 0: 38%|███▊ | 112/291 [00:01<00:02, 78.09it/s] Loading 0: 43%|████▎ | 124/291 [00:01<00:01, 87.54it/s] Loading 0: 47%|████▋ | 138/291 [00:01<00:01, 96.30it/s] Loading 0: 51%|█████ | 149/291 [00:01<00:01, 93.96it/s] Loading 0: 57%|█████▋ | 165/291 [00:01<00:01, 106.21it/s] Loading 0: 62%|██████▏ | 179/291 [00:01<00:01, 111.10it/s] Loading 0: 66%|██████▌ | 191/291 [00:02<00:01, 68.60it/s] Loading 0: 69%|██████▉ | 201/291 [00:02<00:01, 74.04it/s] Loading 0: 73%|███████▎ | 211/291 [00:02<00:01, 78.77it/s] Loading 0: 76%|███████▌ | 221/291 [00:02<00:00, 83.01it/s] Loading 0: 81%|████████▏ | 237/291 [00:02<00:00, 97.00it/s] Loading 0: 85%|████████▌ | 248/291 [00:02<00:00, 93.97it/s] Loading 0: 91%|█████████ | 264/291 [00:02<00:00, 105.03it/s] Loading 0: 95%|█████████▍| 276/291 [00:03<00:00, 101.78it/s] Loading 0: 99%|█████████▊| 287/291 [00:08<00:00, 6.69it/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-5769-v1-mkmlizer: quantized model in 25.113s
cgato-thesalt-rp-l3-8b-d-5769-v1-mkmlizer: Processed model cgato/TheSalt-RP-L3-8b-DPO-v0.3.2-e0.12.2 in 58.222s
cgato-thesalt-rp-l3-8b-d-5769-v1-mkmlizer: creating bucket guanaco-mkml-models
cgato-thesalt-rp-l3-8b-d-5769-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-thesalt-rp-l3-8b-d-5769-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-5769-v1
cgato-thesalt-rp-l3-8b-d-5769-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-5769-v1/config.json
cgato-thesalt-rp-l3-8b-d-5769-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-5769-v1/special_tokens_map.json
cgato-thesalt-rp-l3-8b-d-5769-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-5769-v1/tokenizer_config.json
cgato-thesalt-rp-l3-8b-d-5769-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-5769-v1/tokenizer.json
cgato-thesalt-rp-l3-8b-d-5769-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-5769-v1/flywheel_model.0.safetensors
cgato-thesalt-rp-l3-8b-d-5769-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-thesalt-rp-l3-8b-d-5769-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-5769-v1-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-d-5769-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-5769-v1-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-d-5769-v1-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.
cgato-thesalt-rp-l3-8b-d-5769-v1-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-d-5769-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-5769-v1-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-d-5769-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-5769-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-thesalt-rp-l3-8b-d-5769-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-thesalt-rp-l3-8b-d-5769-v1-mkmlizer: Saving duration: 0.382s
cgato-thesalt-rp-l3-8b-d-5769-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.371s
cgato-thesalt-rp-l3-8b-d-5769-v1-mkmlizer: creating bucket guanaco-reward-models
cgato-thesalt-rp-l3-8b-d-5769-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-thesalt-rp-l3-8b-d-5769-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-5769-v1_reward
cgato-thesalt-rp-l3-8b-d-5769-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-5769-v1_reward/config.json
cgato-thesalt-rp-l3-8b-d-5769-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-5769-v1_reward/tokenizer_config.json
cgato-thesalt-rp-l3-8b-d-5769-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-5769-v1_reward/special_tokens_map.json
cgato-thesalt-rp-l3-8b-d-5769-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-5769-v1_reward/merges.txt
cgato-thesalt-rp-l3-8b-d-5769-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-5769-v1_reward/vocab.json
cgato-thesalt-rp-l3-8b-d-5769-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-5769-v1_reward/tokenizer.json
cgato-thesalt-rp-l3-8b-d-5769-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-5769-v1_reward/reward.tensors
Job cgato-thesalt-rp-l3-8b-d-5769-v1-mkmlizer completed after 83.91s with status: succeeded
Stopping job with name cgato-thesalt-rp-l3-8b-d-5769-v1-mkmlizer
Pipeline stage MKMLizer completed in 84.74s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service cgato-thesalt-rp-l3-8b-d-5769-v1
Waiting for inference service cgato-thesalt-rp-l3-8b-d-5769-v1 to be ready
Inference service cgato-thesalt-rp-l3-8b-d-5769-v1 ready after 60.28141474723816s
Pipeline stage ISVCDeployer completed in 67.23s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.124408483505249s
Received healthy response to inference request in 1.3132085800170898s
Received healthy response to inference request in 1.3096590042114258s
Received healthy response to inference request in 1.384392261505127s
Received healthy response to inference request in 1.2735748291015625s
5 requests
0 failed requests
5th percentile: 1.280791664123535
10th percentile: 1.2880084991455079
20th percentile: 1.3024421691894532
30th percentile: 1.3103689193725585
40th percentile: 1.3117887496948242
50th percentile: 1.3132085800170898
60th percentile: 1.3416820526123048
70th percentile: 1.3701555252075195
80th percentile: 1.5323955059051515
90th percentile: 1.8284019947052004
95th percentile: 1.9764052391052245
99th percentile: 2.094807834625244
mean time: 1.4810486316680909
Pipeline stage StressChecker completed in 8.15s
cgato-thesalt-rp-l3-8b-d_5769_v1 status is now deployed due to DeploymentManager action
cgato-thesalt-rp-l3-8b-d_5769_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics