submission_id: thetsar1209-llama3-carp-v0-4_v4
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': 1.0, 'min_p': 0.1, '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\\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': '<|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}
timestamp: 2024-05-21T23:00:10+00:00
model_name: thetsar1209-llama3-carp-v0-4_v1
model_eval_status: success
model_group: TheTsar1209/llama3-carp-
num_battles: 11342
num_wins: 5859
celo_rating: 1180.23
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: 0.5165755598659848
Resubmit model
Running pipeline stage MKMLizer
Starting job with name thetsar1209-llama3-carp-v0-4-v4-mkmlizer
Waiting for job on thetsar1209-llama3-carp-v0-4-v4-mkmlizer to finish
thetsar1209-llama3-carp-v0-4-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
thetsar1209-llama3-carp-v0-4-v4-mkmlizer: ║ _____ __ __ ║
thetsar1209-llama3-carp-v0-4-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
thetsar1209-llama3-carp-v0-4-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
thetsar1209-llama3-carp-v0-4-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
thetsar1209-llama3-carp-v0-4-v4-mkmlizer: ║ /___/ ║
thetsar1209-llama3-carp-v0-4-v4-mkmlizer: ║ ║
thetsar1209-llama3-carp-v0-4-v4-mkmlizer: ║ Version: 0.8.14 ║
thetsar1209-llama3-carp-v0-4-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
thetsar1209-llama3-carp-v0-4-v4-mkmlizer: ║ https://mk1.ai ║
thetsar1209-llama3-carp-v0-4-v4-mkmlizer: ║ ║
thetsar1209-llama3-carp-v0-4-v4-mkmlizer: ║ The license key for the current software has been verified as ║
thetsar1209-llama3-carp-v0-4-v4-mkmlizer: ║ belonging to: ║
thetsar1209-llama3-carp-v0-4-v4-mkmlizer: ║ ║
thetsar1209-llama3-carp-v0-4-v4-mkmlizer: ║ Chai Research Corp. ║
thetsar1209-llama3-carp-v0-4-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
thetsar1209-llama3-carp-v0-4-v4-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
thetsar1209-llama3-carp-v0-4-v4-mkmlizer: ║ ║
thetsar1209-llama3-carp-v0-4-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
thetsar1209-llama3-carp-v0-4-v4-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-v4-mkmlizer: warnings.warn(warning_message, FutureWarning)
thetsar1209-llama3-carp-v0-4-v4-mkmlizer: Downloaded to shared memory in 31.646s
thetsar1209-llama3-carp-v0-4-v4-mkmlizer: quantizing model to /dev/shm/model_cache
thetsar1209-llama3-carp-v0-4-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
thetsar1209-llama3-carp-v0-4-v4-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 7%|▋ | 21/291 [00:00<00:01, 206.05it/s] Loading 0: 14%|█▍ | 42/291 [00:00<00:01, 194.60it/s] Loading 0: 23%|██▎ | 66/291 [00:00<00:01, 205.43it/s] Loading 0: 30%|██▉ | 87/291 [00:00<00:02, 90.72it/s] Loading 0: 38%|███▊ | 111/291 [00:00<00:01, 117.50it/s] Loading 0: 45%|████▍ | 130/291 [00:00<00:01, 132.51it/s] Loading 0: 51%|█████ | 149/291 [00:01<00:00, 144.79it/s] Loading 0: 59%|█████▉ | 173/291 [00:01<00:00, 165.16it/s] Loading 0: 66%|██████▋ | 193/291 [00:01<00:00, 101.37it/s] Loading 0: 74%|███████▍ | 215/291 [00:01<00:00, 121.85it/s] Loading 0: 80%|███████▉ | 232/291 [00:01<00:00, 127.51it/s] Loading 0: 86%|████████▌ | 249/291 [00:01<00:00, 121.42it/s] Loading 0: 91%|█████████ | 265/291 [00:02<00:00, 128.84it/s] Loading 0: 98%|█████████▊| 284/291 [00:02<00:00, 143.05it/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-v4-mkmlizer: quantized model in 17.972s
thetsar1209-llama3-carp-v0-4-v4-mkmlizer: Processed model TheTsar1209/llama3-carp-v0.4 in 50.633s
thetsar1209-llama3-carp-v0-4-v4-mkmlizer: creating bucket guanaco-mkml-models
thetsar1209-llama3-carp-v0-4-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
thetsar1209-llama3-carp-v0-4-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/thetsar1209-llama3-carp-v0-4-v4
thetsar1209-llama3-carp-v0-4-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/thetsar1209-llama3-carp-v0-4-v4/tokenizer_config.json
thetsar1209-llama3-carp-v0-4-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/thetsar1209-llama3-carp-v0-4-v4/config.json
thetsar1209-llama3-carp-v0-4-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/thetsar1209-llama3-carp-v0-4-v4/special_tokens_map.json
thetsar1209-llama3-carp-v0-4-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/thetsar1209-llama3-carp-v0-4-v4/tokenizer.json
thetsar1209-llama3-carp-v0-4-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/thetsar1209-llama3-carp-v0-4-v4/flywheel_model.0.safetensors
thetsar1209-llama3-carp-v0-4-v4-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
thetsar1209-llama3-carp-v0-4-v4-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-v4-mkmlizer: warnings.warn(
thetsar1209-llama3-carp-v0-4-v4-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-v4-mkmlizer: warnings.warn(
thetsar1209-llama3-carp-v0-4-v4-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-v4-mkmlizer: warnings.warn(
thetsar1209-llama3-carp-v0-4-v4-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-v4-mkmlizer: return self.fget.__get__(instance, owner)()
thetsar1209-llama3-carp-v0-4-v4-mkmlizer: creating bucket guanaco-reward-models
thetsar1209-llama3-carp-v0-4-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
thetsar1209-llama3-carp-v0-4-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-4-v4_reward
thetsar1209-llama3-carp-v0-4-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-4-v4_reward/tokenizer_config.json
thetsar1209-llama3-carp-v0-4-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-4-v4_reward/config.json
thetsar1209-llama3-carp-v0-4-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-4-v4_reward/merges.txt
thetsar1209-llama3-carp-v0-4-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-4-v4_reward/vocab.json
thetsar1209-llama3-carp-v0-4-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-4-v4_reward/special_tokens_map.json
thetsar1209-llama3-carp-v0-4-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-4-v4_reward/tokenizer.json
thetsar1209-llama3-carp-v0-4-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-4-v4_reward/reward.tensors
Job thetsar1209-llama3-carp-v0-4-v4-mkmlizer completed after 83.29s with status: succeeded
Stopping job with name thetsar1209-llama3-carp-v0-4-v4-mkmlizer
Pipeline stage MKMLizer completed in 87.17s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service thetsar1209-llama3-carp-v0-4-v4
Waiting for inference service thetsar1209-llama3-carp-v0-4-v4 to be ready
Inference service thetsar1209-llama3-carp-v0-4-v4 ready after 30.18824052810669s
Pipeline stage ISVCDeployer completed in 37.41s
Running pipeline stage StressChecker
Received healthy response to inference request in 4.845568656921387s
Received healthy response to inference request in 1.2857327461242676s
Received healthy response to inference request in 1.2818350791931152s
Received healthy response to inference request in 1.2989144325256348s
Received healthy response to inference request in 1.351283311843872s
5 requests
0 failed requests
5th percentile: 1.2826146125793456
10th percentile: 1.2833941459655762
20th percentile: 1.2849532127380372
30th percentile: 1.288369083404541
40th percentile: 1.2936417579650878
50th percentile: 1.2989144325256348
60th percentile: 1.3198619842529298
70th percentile: 1.3408095359802246
80th percentile: 2.050140380859376
90th percentile: 3.447854518890381
95th percentile: 4.146711587905883
99th percentile: 4.705797243118286
mean time: 2.012666845321655
Pipeline stage StressChecker completed in 10.70s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
Running M-Eval for topic stay_in_character
thetsar1209-llama3-carp-v0-4_v4 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
thetsar1209-llama3-carp-v0-4_v4 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics