submission_id: cgato-thesalt-rp-l3-8b-d_1612_v1
developer_uid: c.gato
status: inactive
model_repo: cgato/TheSalt-RP-L3-8b-DPO-v0.3.2-e0.6.2
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 100, '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': '<|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: 2024-07-03T03:43:34+00:00
model_name: cgato-thesalt-rp-l3-8b-d_1612_v1
model_group: cgato/TheSalt-RP-L3-8b-D
num_battles: 17698
num_wins: 9564
celo_rating: 1203.76
propriety_score: 0.71007458269208
propriety_total_count: 8447.0
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_1612_v1
ineligible_reason: None
language_model: cgato/TheSalt-RP-L3-8b-DPO-v0.3.2-e0.6.2
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-07-02
win_ratio: 0.5404000452028478
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-thesalt-rp-l3-8b-d-1612-v1-mkmlizer
Waiting for job on cgato-thesalt-rp-l3-8b-d-1612-v1-mkmlizer to finish
cgato-thesalt-rp-l3-8b-d-1612-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-thesalt-rp-l3-8b-d-1612-v1-mkmlizer: ║ _____ __ __ ║
cgato-thesalt-rp-l3-8b-d-1612-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-thesalt-rp-l3-8b-d-1612-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-thesalt-rp-l3-8b-d-1612-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-thesalt-rp-l3-8b-d-1612-v1-mkmlizer: ║ /___/ ║
cgato-thesalt-rp-l3-8b-d-1612-v1-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-1612-v1-mkmlizer: ║ Version: 0.8.14 ║
cgato-thesalt-rp-l3-8b-d-1612-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-thesalt-rp-l3-8b-d-1612-v1-mkmlizer: ║ https://mk1.ai ║
cgato-thesalt-rp-l3-8b-d-1612-v1-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-1612-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-thesalt-rp-l3-8b-d-1612-v1-mkmlizer: ║ belonging to: ║
cgato-thesalt-rp-l3-8b-d-1612-v1-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-1612-v1-mkmlizer: ║ Chai Research Corp. ║
cgato-thesalt-rp-l3-8b-d-1612-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-thesalt-rp-l3-8b-d-1612-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-thesalt-rp-l3-8b-d-1612-v1-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-1612-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-thesalt-rp-l3-8b-d-1612-v1-mkmlizer: Downloaded to shared memory in 54.878s
cgato-thesalt-rp-l3-8b-d-1612-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-thesalt-rp-l3-8b-d-1612-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-thesalt-rp-l3-8b-d-1612-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 124.30it/s] Loading 0: 10%|█ | 30/291 [00:00<00:01, 139.14it/s] Loading 0: 15%|█▌ | 44/291 [00:00<00:01, 134.69it/s] Loading 0: 20%|█▉ | 58/291 [00:00<00:01, 133.66it/s] Loading 0: 25%|██▌ | 73/291 [00:00<00:01, 138.83it/s] Loading 0: 30%|██▉ | 87/291 [00:00<00:02, 69.62it/s] Loading 0: 35%|███▌ | 102/291 [00:01<00:02, 83.70it/s] Loading 0: 39%|███▉ | 114/291 [00:01<00:01, 90.53it/s] Loading 0: 45%|████▍ | 130/291 [00:01<00:01, 103.15it/s] Loading 0: 51%|█████ | 147/291 [00:01<00:01, 116.71it/s] Loading 0: 55%|█████▌ | 161/291 [00:01<00:01, 118.72it/s] Loading 0: 60%|██████ | 176/291 [00:01<00:00, 125.69it/s] Loading 0: 65%|██████▌ | 190/291 [00:01<00:01, 79.05it/s] Loading 0: 70%|██████▉ | 203/291 [00:02<00:01, 85.92it/s] Loading 0: 76%|███████▌ | 220/291 [00:02<00:00, 100.54it/s] Loading 0: 81%|████████▏ | 237/291 [00:02<00:00, 112.48it/s] Loading 0: 86%|████████▌ | 250/291 [00:02<00:00, 116.20it/s] Loading 0: 91%|█████████ | 265/291 [00:02<00:00, 121.58it/s] Loading 0: 97%|█████████▋| 281/291 [00:02<00:00, 127.24it/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-1612-v1-mkmlizer: quantized model in 23.118s
cgato-thesalt-rp-l3-8b-d-1612-v1-mkmlizer: Processed model cgato/TheSalt-RP-L3-8b-DPO-v0.3.2-e0.6.2 in 77.996s
cgato-thesalt-rp-l3-8b-d-1612-v1-mkmlizer: creating bucket guanaco-mkml-models
cgato-thesalt-rp-l3-8b-d-1612-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-thesalt-rp-l3-8b-d-1612-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-1612-v1
cgato-thesalt-rp-l3-8b-d-1612-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-1612-v1/config.json
cgato-thesalt-rp-l3-8b-d-1612-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-1612-v1/tokenizer_config.json
cgato-thesalt-rp-l3-8b-d-1612-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-1612-v1/special_tokens_map.json
cgato-thesalt-rp-l3-8b-d-1612-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-1612-v1/tokenizer.json
cgato-thesalt-rp-l3-8b-d-1612-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-1612-v1/flywheel_model.0.safetensors
cgato-thesalt-rp-l3-8b-d-1612-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-thesalt-rp-l3-8b-d-1612-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-1612-v1-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-d-1612-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-1612-v1-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-d-1612-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-1612-v1-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-d-1612-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-1612-v1-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-d-1612-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-1612-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-thesalt-rp-l3-8b-d-1612-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-thesalt-rp-l3-8b-d-1612-v1-mkmlizer: Saving duration: 0.396s
cgato-thesalt-rp-l3-8b-d-1612-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 22.325s
cgato-thesalt-rp-l3-8b-d-1612-v1-mkmlizer: creating bucket guanaco-reward-models
cgato-thesalt-rp-l3-8b-d-1612-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-thesalt-rp-l3-8b-d-1612-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-1612-v1_reward
cgato-thesalt-rp-l3-8b-d-1612-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-1612-v1_reward/tokenizer_config.json
cgato-thesalt-rp-l3-8b-d-1612-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-1612-v1_reward/special_tokens_map.json
cgato-thesalt-rp-l3-8b-d-1612-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-1612-v1_reward/config.json
cgato-thesalt-rp-l3-8b-d-1612-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-1612-v1_reward/vocab.json
cgato-thesalt-rp-l3-8b-d-1612-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-1612-v1_reward/merges.txt
cgato-thesalt-rp-l3-8b-d-1612-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-1612-v1_reward/tokenizer.json
cgato-thesalt-rp-l3-8b-d-1612-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-1612-v1_reward/reward.tensors
Failed to get response for submission mistralai-mixtral-8x7b-_3473_v33: ('http://mistralai-mixtral-8x7b-3473-v33-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:54400->127.0.0.1:8080: read: connection reset by peer\n')
Job cgato-thesalt-rp-l3-8b-d-1612-v1-mkmlizer completed after 209.26s with status: succeeded
Stopping job with name cgato-thesalt-rp-l3-8b-d-1612-v1-mkmlizer
Pipeline stage MKMLizer completed in 210.17s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service cgato-thesalt-rp-l3-8b-d-1612-v1
Waiting for inference service cgato-thesalt-rp-l3-8b-d-1612-v1 to be ready
Inference service cgato-thesalt-rp-l3-8b-d-1612-v1 ready after 50.27278542518616s
Pipeline stage ISVCDeployer completed in 57.30s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0105371475219727s
Received healthy response to inference request in 1.2800970077514648s
Received healthy response to inference request in 1.1916916370391846s
Received healthy response to inference request in 1.2846705913543701s
Received healthy response to inference request in 1.2295575141906738s
5 requests
0 failed requests
5th percentile: 1.1992648124694825
10th percentile: 1.2068379878997804
20th percentile: 1.221984338760376
30th percentile: 1.239665412902832
40th percentile: 1.2598812103271484
50th percentile: 1.2800970077514648
60th percentile: 1.281926441192627
70th percentile: 1.2837558746337892
80th percentile: 1.4298439025878908
90th percentile: 1.7201905250549316
95th percentile: 1.865363836288452
99th percentile: 1.9815024852752685
mean time: 1.3993107795715332
Pipeline stage StressChecker completed in 8.23s
cgato-thesalt-rp-l3-8b-d_1612_v1 status is now deployed due to DeploymentManager action
cgato-thesalt-rp-l3-8b-d_1612_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics