submission_id: thetsar1209-llama3-carp-v0-4_v8
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': ['\n'], '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: {prompt}\n', 'bot_template': 'Bot: {message}\n', 'user_template': 'User: {message}\n', 'response_template': 'Bot:', 'truncate_by_message': True}
timestamp: 2024-06-21T17:25:49+00:00
model_name: thetsar1209-llama3-carp-v0-4_v1
model_group: TheTsar1209/llama3-carp-
num_battles: 36024
num_wins: 19358
celo_rating: 1193.44
propriety_score: 0.7186693432750215
propriety_total_count: 17435.0
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: None
language_model: TheTsar1209/llama3-carp-v0.4
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-21
win_ratio: 0.5373639795691761
Resubmit model
Running pipeline stage MKMLizer
Starting job with name thetsar1209-llama3-carp-v0-4-v8-mkmlizer
Waiting for job on thetsar1209-llama3-carp-v0-4-v8-mkmlizer to finish
thetsar1209-llama3-carp-v0-4-v8-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
thetsar1209-llama3-carp-v0-4-v8-mkmlizer: ║ _____ __ __ ║
thetsar1209-llama3-carp-v0-4-v8-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
thetsar1209-llama3-carp-v0-4-v8-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
thetsar1209-llama3-carp-v0-4-v8-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
thetsar1209-llama3-carp-v0-4-v8-mkmlizer: ║ /___/ ║
thetsar1209-llama3-carp-v0-4-v8-mkmlizer: ║ ║
thetsar1209-llama3-carp-v0-4-v8-mkmlizer: ║ Version: 0.8.14 ║
thetsar1209-llama3-carp-v0-4-v8-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
thetsar1209-llama3-carp-v0-4-v8-mkmlizer: ║ https://mk1.ai ║
thetsar1209-llama3-carp-v0-4-v8-mkmlizer: ║ ║
thetsar1209-llama3-carp-v0-4-v8-mkmlizer: ║ The license key for the current software has been verified as ║
thetsar1209-llama3-carp-v0-4-v8-mkmlizer: ║ belonging to: ║
thetsar1209-llama3-carp-v0-4-v8-mkmlizer: ║ ║
thetsar1209-llama3-carp-v0-4-v8-mkmlizer: ║ Chai Research Corp. ║
thetsar1209-llama3-carp-v0-4-v8-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
thetsar1209-llama3-carp-v0-4-v8-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
thetsar1209-llama3-carp-v0-4-v8-mkmlizer: ║ ║
thetsar1209-llama3-carp-v0-4-v8-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
thetsar1209-llama3-carp-v0-4-v8-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-v8-mkmlizer: warnings.warn(warning_message, FutureWarning)
thetsar1209-llama3-carp-v0-4-v8-mkmlizer: Downloaded to shared memory in 38.079s
thetsar1209-llama3-carp-v0-4-v8-mkmlizer: quantizing model to /dev/shm/model_cache
thetsar1209-llama3-carp-v0-4-v8-mkmlizer: Saving flywheel model at /dev/shm/model_cache
thetsar1209-llama3-carp-v0-4-v8-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:02, 121.84it/s] Loading 0: 11%|█ | 31/291 [00:00<00:01, 141.75it/s] Loading 0: 16%|█▋ | 48/291 [00:00<00:01, 150.56it/s] Loading 0: 22%|██▏ | 64/291 [00:00<00:01, 150.97it/s] Loading 0: 27%|██▋ | 80/291 [00:00<00:01, 146.42it/s] Loading 0: 33%|███▎ | 95/291 [00:01<00:02, 69.65it/s] Loading 0: 38%|███▊ | 112/291 [00:01<00:02, 86.81it/s] Loading 0: 44%|████▍ | 129/291 [00:01<00:01, 102.86it/s] Loading 0: 49%|████▉ | 144/291 [00:01<00:01, 112.68it/s] Loading 0: 55%|█████▍ | 159/291 [00:01<00:01, 119.15it/s] Loading 0: 62%|██████▏ | 179/291 [00:01<00:00, 134.78it/s] Loading 0: 67%|██████▋ | 195/291 [00:01<00:01, 74.22it/s] Loading 0: 73%|███████▎ | 211/291 [00:02<00:00, 88.05it/s] Loading 0: 78%|███████▊ | 228/291 [00:02<00:00, 103.25it/s] Loading 0: 84%|████████▎ | 243/291 [00:02<00:00, 112.84it/s] Loading 0: 89%|████████▊ | 258/291 [00:02<00:00, 119.81it/s] Loading 0: 95%|█████████▍| 275/291 [00:02<00:00, 127.35it/s] Loading 0: 100%|█████████▉| 290/291 [00:07<00:00, 9.83it/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-v8-mkmlizer: quantized model in 19.466s
thetsar1209-llama3-carp-v0-4-v8-mkmlizer: Processed model TheTsar1209/llama3-carp-v0.4 in 58.654s
thetsar1209-llama3-carp-v0-4-v8-mkmlizer: creating bucket guanaco-mkml-models
thetsar1209-llama3-carp-v0-4-v8-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
thetsar1209-llama3-carp-v0-4-v8-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/thetsar1209-llama3-carp-v0-4-v8
thetsar1209-llama3-carp-v0-4-v8-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/thetsar1209-llama3-carp-v0-4-v8/config.json
thetsar1209-llama3-carp-v0-4-v8-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/thetsar1209-llama3-carp-v0-4-v8/special_tokens_map.json
thetsar1209-llama3-carp-v0-4-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/thetsar1209-llama3-carp-v0-4-v8/tokenizer_config.json
thetsar1209-llama3-carp-v0-4-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/thetsar1209-llama3-carp-v0-4-v8/tokenizer.json
thetsar1209-llama3-carp-v0-4-v8-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/thetsar1209-llama3-carp-v0-4-v8/flywheel_model.0.safetensors
thetsar1209-llama3-carp-v0-4-v8-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
thetsar1209-llama3-carp-v0-4-v8-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-v8-mkmlizer: warnings.warn(
thetsar1209-llama3-carp-v0-4-v8-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-v8-mkmlizer: warnings.warn(
thetsar1209-llama3-carp-v0-4-v8-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-v8-mkmlizer: warnings.warn(
thetsar1209-llama3-carp-v0-4-v8-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-v8-mkmlizer: return self.fget.__get__(instance, owner)()
thetsar1209-llama3-carp-v0-4-v8-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
thetsar1209-llama3-carp-v0-4-v8-mkmlizer: Saving duration: 0.305s
thetsar1209-llama3-carp-v0-4-v8-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.984s
thetsar1209-llama3-carp-v0-4-v8-mkmlizer: creating bucket guanaco-reward-models
thetsar1209-llama3-carp-v0-4-v8-mkmlizer: Bucket 's3://guanaco-reward-models/' created
thetsar1209-llama3-carp-v0-4-v8-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-4-v8_reward
thetsar1209-llama3-carp-v0-4-v8-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-4-v8_reward/config.json
thetsar1209-llama3-carp-v0-4-v8-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-4-v8_reward/special_tokens_map.json
thetsar1209-llama3-carp-v0-4-v8-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-4-v8_reward/tokenizer_config.json
thetsar1209-llama3-carp-v0-4-v8-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-4-v8_reward/merges.txt
thetsar1209-llama3-carp-v0-4-v8-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-4-v8_reward/vocab.json
thetsar1209-llama3-carp-v0-4-v8-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-4-v8_reward/tokenizer.json
thetsar1209-llama3-carp-v0-4-v8-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-4-v8_reward/reward.tensors
Job thetsar1209-llama3-carp-v0-4-v8-mkmlizer completed after 94.24s with status: succeeded
Stopping job with name thetsar1209-llama3-carp-v0-4-v8-mkmlizer
Pipeline stage MKMLizer completed in 94.64s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service thetsar1209-llama3-carp-v0-4-v8
Waiting for inference service thetsar1209-llama3-carp-v0-4-v8 to be ready
Inference service thetsar1209-llama3-carp-v0-4-v8 ready after 50.22613072395325s
Pipeline stage ISVCDeployer completed in 56.21s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.888777017593384s
Received healthy response to inference request in 3.8101961612701416s
Received healthy response to inference request in 2.4353199005126953s
Received healthy response to inference request in 1.2918288707733154s
Received healthy response to inference request in 2.7867257595062256s
5 requests
0 failed requests
5th percentile: 1.5205270767211914
10th percentile: 1.7492252826690673
20th percentile: 2.206621694564819
30th percentile: 2.5056010723114013
40th percentile: 2.6461634159088137
50th percentile: 2.7867257595062256
60th percentile: 2.827546262741089
70th percentile: 2.868366765975952
80th percentile: 3.0730608463287354
90th percentile: 3.4416285037994387
95th percentile: 3.62591233253479
99th percentile: 3.773339395523071
mean time: 2.6425695419311523
Pipeline stage StressChecker completed in 13.82s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
thetsar1209-llama3-carp-v0-4_v8 status is now deployed due to DeploymentManager action
thetsar1209-llama3-carp-v0-4_v8 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics