submission_id: cgato-thesalt-rp-l3-8b-d_1440_v2
developer_uid: c.gato
status: inactive
model_repo: cgato/TheSalt-RP-L3-8b-DPO-v0.3.2-e0.13.2
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
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'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
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': False}
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': False}
timestamp: 2024-07-08T00:41:18+00:00
model_name: cgato-thesalt-rp-l3-8b-d_1440_v2
model_group: cgato/TheSalt-RP-L3-8b-D
num_battles: 29099
num_wins: 14956
celo_rating: 1197.4
alignment_score: None
alignment_samples: 0
propriety_score: 0.7063913470993117
propriety_total_count: 5085.0
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_1440_v2
ineligible_reason: None
language_model: cgato/TheSalt-RP-L3-8b-DPO-v0.3.2-e0.13.2
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-07-07
win_ratio: 0.5139695522182893
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-thesalt-rp-l3-8b-d-1440-v2-mkmlizer
Waiting for job on cgato-thesalt-rp-l3-8b-d-1440-v2-mkmlizer to finish
cgato-thesalt-rp-l3-8b-d-1440-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-thesalt-rp-l3-8b-d-1440-v2-mkmlizer: ║ _____ __ __ ║
cgato-thesalt-rp-l3-8b-d-1440-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-thesalt-rp-l3-8b-d-1440-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-thesalt-rp-l3-8b-d-1440-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-thesalt-rp-l3-8b-d-1440-v2-mkmlizer: ║ /___/ ║
cgato-thesalt-rp-l3-8b-d-1440-v2-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-1440-v2-mkmlizer: ║ Version: 0.8.14 ║
cgato-thesalt-rp-l3-8b-d-1440-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-thesalt-rp-l3-8b-d-1440-v2-mkmlizer: ║ https://mk1.ai ║
cgato-thesalt-rp-l3-8b-d-1440-v2-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-1440-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-thesalt-rp-l3-8b-d-1440-v2-mkmlizer: ║ belonging to: ║
cgato-thesalt-rp-l3-8b-d-1440-v2-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-1440-v2-mkmlizer: ║ Chai Research Corp. ║
cgato-thesalt-rp-l3-8b-d-1440-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-thesalt-rp-l3-8b-d-1440-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-thesalt-rp-l3-8b-d-1440-v2-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-1440-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-thesalt-rp-l3-8b-d-1440-v2-mkmlizer: Downloaded to shared memory in 14.319s
cgato-thesalt-rp-l3-8b-d-1440-v2-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-thesalt-rp-l3-8b-d-1440-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-thesalt-rp-l3-8b-d-1440-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:02, 127.86it/s] Loading 0: 11%|█ | 31/291 [00:00<00:01, 145.76it/s] Loading 0: 16%|█▋ | 48/291 [00:00<00:01, 152.94it/s] Loading 0: 22%|██▏ | 64/291 [00:00<00:01, 153.19it/s] Loading 0: 27%|██▋ | 80/291 [00:00<00:01, 147.19it/s] Loading 0: 33%|███▎ | 95/291 [00:00<00:02, 87.47it/s] Loading 0: 38%|███▊ | 112/291 [00:00<00:01, 104.29it/s] Loading 0: 44%|████▍ | 129/291 [00:01<00:01, 117.99it/s] Loading 0: 49%|████▉ | 144/291 [00:01<00:01, 124.31it/s] Loading 0: 55%|█████▍ | 159/291 [00:01<00:01, 127.33it/s] Loading 0: 61%|██████ | 177/291 [00:01<00:00, 140.87it/s] Loading 0: 66%|██████▋ | 193/291 [00:01<00:01, 92.73it/s] Loading 0: 72%|███████▏ | 210/291 [00:01<00:00, 107.71it/s] Loading 0: 77%|███████▋ | 225/291 [00:01<00:00, 116.56it/s] Loading 0: 82%|████████▏ | 239/291 [00:02<00:00, 120.46it/s] Loading 0: 88%|████████▊ | 256/291 [00:02<00:00, 132.23it/s] Loading 0: 94%|█████████▍| 273/291 [00:02<00:00, 141.51it/s] Loading 0: 99%|█████████▉| 289/291 [00:07<00:00, 10.04it/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-1440-v2-mkmlizer: quantized model in 18.736s
cgato-thesalt-rp-l3-8b-d-1440-v2-mkmlizer: Processed model cgato/TheSalt-RP-L3-8b-DPO-v0.3.2-e0.13.2 in 33.054s
cgato-thesalt-rp-l3-8b-d-1440-v2-mkmlizer: creating bucket guanaco-mkml-models
cgato-thesalt-rp-l3-8b-d-1440-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-thesalt-rp-l3-8b-d-1440-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-1440-v2
cgato-thesalt-rp-l3-8b-d-1440-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-1440-v2/special_tokens_map.json
cgato-thesalt-rp-l3-8b-d-1440-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-1440-v2/config.json
cgato-thesalt-rp-l3-8b-d-1440-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-1440-v2/tokenizer_config.json
cgato-thesalt-rp-l3-8b-d-1440-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-1440-v2/tokenizer.json
cgato-thesalt-rp-l3-8b-d-1440-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-1440-v2/flywheel_model.0.safetensors
cgato-thesalt-rp-l3-8b-d-1440-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-thesalt-rp-l3-8b-d-1440-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.
cgato-thesalt-rp-l3-8b-d-1440-v2-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-d-1440-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`.
cgato-thesalt-rp-l3-8b-d-1440-v2-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-d-1440-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.
cgato-thesalt-rp-l3-8b-d-1440-v2-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-d-1440-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.
cgato-thesalt-rp-l3-8b-d-1440-v2-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-d-1440-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()
cgato-thesalt-rp-l3-8b-d-1440-v2-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-thesalt-rp-l3-8b-d-1440-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-thesalt-rp-l3-8b-d-1440-v2-mkmlizer: Saving duration: 0.227s
cgato-thesalt-rp-l3-8b-d-1440-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.607s
cgato-thesalt-rp-l3-8b-d-1440-v2-mkmlizer: creating bucket guanaco-reward-models
cgato-thesalt-rp-l3-8b-d-1440-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-thesalt-rp-l3-8b-d-1440-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-1440-v2_reward
cgato-thesalt-rp-l3-8b-d-1440-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-1440-v2_reward/config.json
cgato-thesalt-rp-l3-8b-d-1440-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-1440-v2_reward/tokenizer_config.json
cgato-thesalt-rp-l3-8b-d-1440-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-1440-v2_reward/special_tokens_map.json
cgato-thesalt-rp-l3-8b-d-1440-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-1440-v2_reward/merges.txt
cgato-thesalt-rp-l3-8b-d-1440-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-1440-v2_reward/vocab.json
cgato-thesalt-rp-l3-8b-d-1440-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-1440-v2_reward/tokenizer.json
cgato-thesalt-rp-l3-8b-d-1440-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-1440-v2_reward/reward.tensors
Job cgato-thesalt-rp-l3-8b-d-1440-v2-mkmlizer completed after 76.35s with status: succeeded
Stopping job with name cgato-thesalt-rp-l3-8b-d-1440-v2-mkmlizer
Pipeline stage MKMLizer completed in 77.28s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service cgato-thesalt-rp-l3-8b-d-1440-v2
Waiting for inference service cgato-thesalt-rp-l3-8b-d-1440-v2 to be ready
Failed to get response for submission blend_pefis_2024-07-04: ('http://mistralai-mixtral-8x7b-3473-v33-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', '{"error":"TypeError : SamplingParameters.__init__() got an unexpected keyword argument \'min_p\'"}')
Inference service cgato-thesalt-rp-l3-8b-d-1440-v2 ready after 50.24726605415344s
Pipeline stage ISVCDeployer completed in 57.32s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0457704067230225s
Received healthy response to inference request in 1.2750439643859863s
Received healthy response to inference request in 1.268578290939331s
Received healthy response to inference request in 1.2716715335845947s
Received healthy response to inference request in 1.2695081233978271s
5 requests
0 failed requests
5th percentile: 1.2687642574310303
10th percentile: 1.2689502239227295
20th percentile: 1.269322156906128
30th percentile: 1.2699408054351806
40th percentile: 1.2708061695098878
50th percentile: 1.2716715335845947
60th percentile: 1.2730205059051514
70th percentile: 1.274369478225708
80th percentile: 1.4291892528533936
90th percentile: 1.7374798297882081
95th percentile: 1.8916251182556152
99th percentile: 2.014941349029541
mean time: 1.4261144638061523
Pipeline stage StressChecker completed in 7.93s
cgato-thesalt-rp-l3-8b-d_1440_v2 status is now deployed due to DeploymentManager action
cgato-thesalt-rp-l3-8b-d_1440_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics