submission_id: cgato-thesalt-rp-l3-8b-v0-3-2_v7
developer_uid: c.gato
status: inactive
model_repo: cgato/TheSalt-RP-L3-8b-v0.3.2
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.9, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 200, '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}\n', 'prompt_template': '{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: 2024-06-19T19:42:29+00:00
model_name: cgato-thesalt-rp-l3-8b-v0-3-2_v7
model_group: cgato/TheSalt-RP-L3-8b-v
num_battles: 20745
num_wins: 10932
celo_rating: 1197.64
propriety_score: 0.7207916792891043
propriety_total_count: 9903.0
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-v0-3-2_v7
ineligible_reason: None
language_model: cgato/TheSalt-RP-L3-8b-v0.3.2
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-19
win_ratio: 0.5269703543022415
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-thesalt-rp-l3-8b-v0-3-2-v7-mkmlizer
Waiting for job on cgato-thesalt-rp-l3-8b-v0-3-2-v7-mkmlizer to finish
Stopping job with name cgato-thesalt-rp-l3-8b-v0-3-2-v7-mkmlizer
%s, retrying in %s seconds...
Starting job with name cgato-thesalt-rp-l3-8b-v0-3-2-v7-mkmlizer
Waiting for job on cgato-thesalt-rp-l3-8b-v0-3-2-v7-mkmlizer to finish
Stopping job with name cgato-thesalt-rp-l3-8b-v0-3-2-v7-mkmlizer
%s, retrying in %s seconds...
Starting job with name cgato-thesalt-rp-l3-8b-v0-3-2-v7-mkmlizer
Waiting for job on cgato-thesalt-rp-l3-8b-v0-3-2-v7-mkmlizer to finish
cgato-thesalt-rp-l3-8b-v0-3-2-v7-mkmlizer: Downloaded to shared memory in 28.545s
cgato-thesalt-rp-l3-8b-v0-3-2-v7-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-thesalt-rp-l3-8b-v0-3-2-v7-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-thesalt-rp-l3-8b-v0-3-2-v7-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:02, 125.97it/s] Loading 0: 11%|█ | 31/291 [00:00<00:01, 147.40it/s] Loading 0: 16%|█▋ | 48/291 [00:00<00:01, 154.63it/s] Loading 0: 22%|██▏ | 64/291 [00:00<00:01, 154.09it/s] Loading 0: 27%|██▋ | 80/291 [00:00<00:01, 148.71it/s] Loading 0: 33%|███▎ | 95/291 [00:00<00:02, 70.75it/s] Loading 0: 38%|███▊ | 112/291 [00:01<00:02, 87.86it/s] Loading 0: 44%|████▍ | 129/291 [00:01<00:01, 103.57it/s] Loading 0: 49%|████▉ | 144/291 [00:01<00:01, 113.11it/s] Loading 0: 55%|█████▍ | 159/291 [00:01<00:01, 119.48it/s] Loading 0: 62%|██████▏ | 179/291 [00:01<00:00, 135.25it/s] Loading 0: 67%|██████▋ | 195/291 [00:01<00:01, 75.74it/s] Loading 0: 73%|███████▎ | 211/291 [00:02<00:00, 89.18it/s] Loading 0: 78%|███████▊ | 228/291 [00:02<00:00, 103.75it/s] Loading 0: 84%|████████▎ | 243/291 [00:02<00:00, 113.04it/s] Loading 0: 89%|████████▊ | 258/291 [00:02<00:00, 119.21it/s] Loading 0: 94%|█████████▍| 274/291 [00:02<00:00, 128.77it/s] Loading 0: 99%|█████████▉| 289/291 [00:07<00:00, 9.59it/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-v0-3-2-v7-mkmlizer: quantized model in 19.168s
cgato-thesalt-rp-l3-8b-v0-3-2-v7-mkmlizer: Processed model cgato/TheSalt-RP-L3-8b-v0.3.2 in 48.773s
cgato-thesalt-rp-l3-8b-v0-3-2-v7-mkmlizer: creating bucket guanaco-mkml-models
cgato-thesalt-rp-l3-8b-v0-3-2-v7-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-thesalt-rp-l3-8b-v0-3-2-v7-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-v0-3-2-v7
cgato-thesalt-rp-l3-8b-v0-3-2-v7-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-v0-3-2-v7/special_tokens_map.json
cgato-thesalt-rp-l3-8b-v0-3-2-v7-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-v0-3-2-v7/config.json
cgato-thesalt-rp-l3-8b-v0-3-2-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-v0-3-2-v7/tokenizer_config.json
cgato-thesalt-rp-l3-8b-v0-3-2-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-v0-3-2-v7/tokenizer.json
cgato-thesalt-rp-l3-8b-v0-3-2-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-v0-3-2-v7/flywheel_model.0.safetensors
cgato-thesalt-rp-l3-8b-v0-3-2-v7-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-thesalt-rp-l3-8b-v0-3-2-v7-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:913: 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-v0-3-2-v7-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-v0-3-2-v7-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:757: 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-v0-3-2-v7-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-v0-3-2-v7-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-v0-3-2-v7-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-v0-3-2-v7-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-v0-3-2-v7-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-thesalt-rp-l3-8b-v0-3-2-v7-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-thesalt-rp-l3-8b-v0-3-2-v7-mkmlizer: Saving duration: 0.282s
cgato-thesalt-rp-l3-8b-v0-3-2-v7-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.798s
cgato-thesalt-rp-l3-8b-v0-3-2-v7-mkmlizer: creating bucket guanaco-reward-models
cgato-thesalt-rp-l3-8b-v0-3-2-v7-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-thesalt-rp-l3-8b-v0-3-2-v7-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-v0-3-2-v7_reward
cgato-thesalt-rp-l3-8b-v0-3-2-v7-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-v0-3-2-v7_reward/config.json
cgato-thesalt-rp-l3-8b-v0-3-2-v7-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-v0-3-2-v7_reward/special_tokens_map.json
cgato-thesalt-rp-l3-8b-v0-3-2-v7-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-v0-3-2-v7_reward/tokenizer_config.json
cgato-thesalt-rp-l3-8b-v0-3-2-v7-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-v0-3-2-v7_reward/merges.txt
cgato-thesalt-rp-l3-8b-v0-3-2-v7-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-v0-3-2-v7_reward/vocab.json
cgato-thesalt-rp-l3-8b-v0-3-2-v7-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-v0-3-2-v7_reward/tokenizer.json
cgato-thesalt-rp-l3-8b-v0-3-2-v7-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-v0-3-2-v7_reward/reward.tensors
Job cgato-thesalt-rp-l3-8b-v0-3-2-v7-mkmlizer completed after 87.3s with status: succeeded
Stopping job with name cgato-thesalt-rp-l3-8b-v0-3-2-v7-mkmlizer
Pipeline stage MKMLizer completed in 95.25s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cgato-thesalt-rp-l3-8b-v0-3-2-v7
Waiting for inference service cgato-thesalt-rp-l3-8b-v0-3-2-v7 to be ready
Inference service cgato-thesalt-rp-l3-8b-v0-3-2-v7 ready after 50.30650186538696s
Pipeline stage ISVCDeployer completed in 58.06s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9042258262634277s
Received healthy response to inference request in 0.9552409648895264s
Received healthy response to inference request in 1.0446927547454834s
Received healthy response to inference request in 1.021862506866455s
Received healthy response to inference request in 1.0213501453399658s
5 requests
0 failed requests
5th percentile: 0.9684628009796142
10th percentile: 0.9816846370697021
20th percentile: 1.0081283092498778
30th percentile: 1.0214526176452636
40th percentile: 1.0216575622558595
50th percentile: 1.021862506866455
60th percentile: 1.0309946060180664
70th percentile: 1.0401267051696776
80th percentile: 1.2165993690490724
90th percentile: 1.5604125976562502
95th percentile: 1.7323192119598387
99th percentile: 1.86984450340271
mean time: 1.1894744396209718
Pipeline stage StressChecker completed in 6.60s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
cgato-thesalt-rp-l3-8b-v0-3-2_v7 status is now deployed due to DeploymentManager action
cgato-thesalt-rp-l3-8b-v0-3-2_v7 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics