submission_id: thetsar1209-llama3-carp-v0-4_v6
developer_uid: TheTsar1209
status: inactive
model_repo: TheTsar1209/llama3-carp-v0.4
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['<|im_end|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': '<|im_start|>system\nYou are {bot_name}\nDescription : {memory}\n', 'prompt_template': 'Example conversation:\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n', 'truncate_by_message': True}
reward_formatter: {'memory_template': 'Memory: {memory}\n', 'prompt_template': '{prompt}\n', 'bot_template': 'Bot: {message}\n', 'user_template': 'User: {message}\n', 'response_template': 'Bot:', 'truncate_by_message': True}
timestamp: 2024-05-21T23:37:10+00:00
model_name: thetsar1209-llama3-carp-v0-4_v1
model_eval_status: success
model_group: TheTsar1209/llama3-carp-
num_battles: 12633
num_wins: 6608
celo_rating: 1187.75
safety_score: 0.96
propriety_score: 0.0
propriety_total_count: 0.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: thetsar1209-llama3-carp-v0-4_v1
ineligible_reason: propriety_total_count < 5000
language_model: TheTsar1209/llama3-carp-v0.4
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-05-21
win_ratio: 0.5230744874534948
Resubmit model
Running pipeline stage MKMLizer
Starting job with name thetsar1209-llama3-carp-v0-4-v6-mkmlizer
Waiting for job on thetsar1209-llama3-carp-v0-4-v6-mkmlizer to finish
thetsar1209-llama3-carp-v0-4-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
thetsar1209-llama3-carp-v0-4-v6-mkmlizer: ║ _____ __ __ ║
thetsar1209-llama3-carp-v0-4-v6-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
thetsar1209-llama3-carp-v0-4-v6-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
thetsar1209-llama3-carp-v0-4-v6-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
thetsar1209-llama3-carp-v0-4-v6-mkmlizer: ║ /___/ ║
thetsar1209-llama3-carp-v0-4-v6-mkmlizer: ║ ║
thetsar1209-llama3-carp-v0-4-v6-mkmlizer: ║ Version: 0.8.14 ║
thetsar1209-llama3-carp-v0-4-v6-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
thetsar1209-llama3-carp-v0-4-v6-mkmlizer: ║ https://mk1.ai ║
thetsar1209-llama3-carp-v0-4-v6-mkmlizer: ║ ║
thetsar1209-llama3-carp-v0-4-v6-mkmlizer: ║ The license key for the current software has been verified as ║
thetsar1209-llama3-carp-v0-4-v6-mkmlizer: ║ belonging to: ║
thetsar1209-llama3-carp-v0-4-v6-mkmlizer: ║ ║
thetsar1209-llama3-carp-v0-4-v6-mkmlizer: ║ Chai Research Corp. ║
thetsar1209-llama3-carp-v0-4-v6-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
thetsar1209-llama3-carp-v0-4-v6-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
thetsar1209-llama3-carp-v0-4-v6-mkmlizer: ║ ║
thetsar1209-llama3-carp-v0-4-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
thetsar1209-llama3-carp-v0-4-v6-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_deprecation.py:131: FutureWarning: 'list_files_info' (from 'huggingface_hub.hf_api') is deprecated and will be removed from version '0.23'. Use `list_repo_tree` and `get_paths_info` instead.
thetsar1209-llama3-carp-v0-4-v6-mkmlizer: warnings.warn(warning_message, FutureWarning)
thetsar1209-llama3-carp-v0-4-v6-mkmlizer: Downloaded to shared memory in 13.024s
thetsar1209-llama3-carp-v0-4-v6-mkmlizer: quantizing model to /dev/shm/model_cache
thetsar1209-llama3-carp-v0-4-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
thetsar1209-llama3-carp-v0-4-v6-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 7%|▋ | 21/291 [00:00<00:01, 206.91it/s] Loading 0: 14%|█▍ | 42/291 [00:00<00:01, 193.12it/s] Loading 0: 23%|██▎ | 66/291 [00:00<00:01, 205.73it/s] Loading 0: 30%|██▉ | 87/291 [00:00<00:02, 97.50it/s] Loading 0: 38%|███▊ | 111/291 [00:00<00:01, 123.59it/s] Loading 0: 45%|████▍ | 130/291 [00:00<00:01, 137.35it/s] Loading 0: 51%|█████ | 149/291 [00:01<00:00, 148.71it/s] Loading 0: 59%|█████▉ | 172/291 [00:01<00:00, 168.92it/s] Loading 0: 66%|██████▌ | 192/291 [00:01<00:00, 105.38it/s] Loading 0: 73%|███████▎ | 212/291 [00:01<00:00, 120.40it/s] Loading 0: 81%|████████▏ | 237/291 [00:01<00:00, 144.94it/s] Loading 0: 88%|████████▊ | 257/291 [00:01<00:00, 154.02it/s] Loading 0: 97%|█████████▋| 281/291 [00:01<00:00, 171.43it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
thetsar1209-llama3-carp-v0-4-v6-mkmlizer: quantized model in 16.747s
thetsar1209-llama3-carp-v0-4-v6-mkmlizer: Processed model TheTsar1209/llama3-carp-v0.4 in 30.752s
thetsar1209-llama3-carp-v0-4-v6-mkmlizer: creating bucket guanaco-mkml-models
thetsar1209-llama3-carp-v0-4-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
thetsar1209-llama3-carp-v0-4-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/thetsar1209-llama3-carp-v0-4-v6
thetsar1209-llama3-carp-v0-4-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/thetsar1209-llama3-carp-v0-4-v6/tokenizer_config.json
thetsar1209-llama3-carp-v0-4-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/thetsar1209-llama3-carp-v0-4-v6/special_tokens_map.json
thetsar1209-llama3-carp-v0-4-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/thetsar1209-llama3-carp-v0-4-v6/config.json
thetsar1209-llama3-carp-v0-4-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/thetsar1209-llama3-carp-v0-4-v6/tokenizer.json
thetsar1209-llama3-carp-v0-4-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/thetsar1209-llama3-carp-v0-4-v6/flywheel_model.0.safetensors
thetsar1209-llama3-carp-v0-4-v6-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
thetsar1209-llama3-carp-v0-4-v6-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.
thetsar1209-llama3-carp-v0-4-v6-mkmlizer: warnings.warn(
thetsar1209-llama3-carp-v0-4-v6-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.
thetsar1209-llama3-carp-v0-4-v6-mkmlizer: warnings.warn(
thetsar1209-llama3-carp-v0-4-v6-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.
thetsar1209-llama3-carp-v0-4-v6-mkmlizer: warnings.warn(
thetsar1209-llama3-carp-v0-4-v6-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()
thetsar1209-llama3-carp-v0-4-v6-mkmlizer: return self.fget.__get__(instance, owner)()
thetsar1209-llama3-carp-v0-4-v6-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
thetsar1209-llama3-carp-v0-4-v6-mkmlizer: Saving duration: 1.535s
thetsar1209-llama3-carp-v0-4-v6-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.289s
thetsar1209-llama3-carp-v0-4-v6-mkmlizer: creating bucket guanaco-reward-models
thetsar1209-llama3-carp-v0-4-v6-mkmlizer: Bucket 's3://guanaco-reward-models/' created
thetsar1209-llama3-carp-v0-4-v6-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-4-v6_reward
thetsar1209-llama3-carp-v0-4-v6-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-4-v6_reward/special_tokens_map.json
thetsar1209-llama3-carp-v0-4-v6-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-4-v6_reward/vocab.json
thetsar1209-llama3-carp-v0-4-v6-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-4-v6_reward/tokenizer_config.json
thetsar1209-llama3-carp-v0-4-v6-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-4-v6_reward/merges.txt
thetsar1209-llama3-carp-v0-4-v6-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-4-v6_reward/config.json
thetsar1209-llama3-carp-v0-4-v6-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-4-v6_reward/tokenizer.json
thetsar1209-llama3-carp-v0-4-v6-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-4-v6_reward/reward.tensors
Job thetsar1209-llama3-carp-v0-4-v6-mkmlizer completed after 297.14s with status: succeeded
Stopping job with name thetsar1209-llama3-carp-v0-4-v6-mkmlizer
Pipeline stage MKMLizer completed in 300.40s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service thetsar1209-llama3-carp-v0-4-v6
Waiting for inference service thetsar1209-llama3-carp-v0-4-v6 to be ready
Inference service thetsar1209-llama3-carp-v0-4-v6 ready after 30.218483686447144s
Pipeline stage ISVCDeployer completed in 37.24s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0678014755249023s
Received healthy response to inference request in 1.2605185508728027s
Received healthy response to inference request in 1.254370927810669s
Received healthy response to inference request in 1.2601463794708252s
Received healthy response to inference request in 1.2464401721954346s
5 requests
0 failed requests
5th percentile: 1.2480263233184814
10th percentile: 1.2496124744415282
20th percentile: 1.2527847766876221
30th percentile: 1.2555260181427002
40th percentile: 1.2578361988067628
50th percentile: 1.2601463794708252
60th percentile: 1.2602952480316163
70th percentile: 1.2604441165924072
80th percentile: 1.4219751358032229
90th percentile: 1.7448883056640625
95th percentile: 1.9063448905944822
99th percentile: 2.0355101585388184
mean time: 1.4178555011749268
Pipeline stage StressChecker completed in 7.70s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.04s
M-Eval Dataset for topic stay_in_character is loaded
thetsar1209-llama3-carp-v0-4_v6 status is now deployed due to DeploymentManager action
thetsar1209-llama3-carp-v0-4_v6 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics