submission_id: thetsar1209-llama3-carp-v0-4_v9
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: {prompt}\n', 'bot_template': 'Bot: {message}\n', 'user_template': 'User: {message}\n', 'response_template': 'Bot:', 'truncate_by_message': True}
timestamp: 2024-07-01T16:58:00+00:00
model_name: thetsar1209-llama3-carp-v0-4_v1
model_group: TheTsar1209/llama3-carp-
num_battles: 16589
num_wins: 8756
celo_rating: 1194.99
propriety_score: 0.7272272272272272
propriety_total_count: 7992.0
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: 2024-07-01
win_ratio: 0.527819639520164
Resubmit model
Running pipeline stage MKMLizer
Starting job with name thetsar1209-llama3-carp-v0-4-v9-mkmlizer
Waiting for job on thetsar1209-llama3-carp-v0-4-v9-mkmlizer to finish
thetsar1209-llama3-carp-v0-4-v9-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
thetsar1209-llama3-carp-v0-4-v9-mkmlizer: ║ _____ __ __ ║
thetsar1209-llama3-carp-v0-4-v9-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
thetsar1209-llama3-carp-v0-4-v9-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
thetsar1209-llama3-carp-v0-4-v9-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
thetsar1209-llama3-carp-v0-4-v9-mkmlizer: ║ /___/ ║
thetsar1209-llama3-carp-v0-4-v9-mkmlizer: ║ ║
thetsar1209-llama3-carp-v0-4-v9-mkmlizer: ║ Version: 0.8.14 ║
thetsar1209-llama3-carp-v0-4-v9-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
thetsar1209-llama3-carp-v0-4-v9-mkmlizer: ║ https://mk1.ai ║
thetsar1209-llama3-carp-v0-4-v9-mkmlizer: ║ ║
thetsar1209-llama3-carp-v0-4-v9-mkmlizer: ║ The license key for the current software has been verified as ║
thetsar1209-llama3-carp-v0-4-v9-mkmlizer: ║ belonging to: ║
thetsar1209-llama3-carp-v0-4-v9-mkmlizer: ║ ║
thetsar1209-llama3-carp-v0-4-v9-mkmlizer: ║ Chai Research Corp. ║
thetsar1209-llama3-carp-v0-4-v9-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
thetsar1209-llama3-carp-v0-4-v9-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
thetsar1209-llama3-carp-v0-4-v9-mkmlizer: ║ ║
thetsar1209-llama3-carp-v0-4-v9-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
thetsar1209-llama3-carp-v0-4-v9-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-v9-mkmlizer: warnings.warn(warning_message, FutureWarning)
thetsar1209-llama3-carp-v0-4-v9-mkmlizer: Downloaded to shared memory in 43.776s
thetsar1209-llama3-carp-v0-4-v9-mkmlizer: quantizing model to /dev/shm/model_cache
thetsar1209-llama3-carp-v0-4-v9-mkmlizer: Saving flywheel model at /dev/shm/model_cache
thetsar1209-llama3-carp-v0-4-v9-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:02, 132.08it/s] Loading 0: 11%|█ | 32/291 [00:00<00:01, 148.10it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:01, 155.89it/s] Loading 0: 23%|██▎ | 66/291 [00:00<00:01, 156.56it/s] Loading 0: 29%|██▊ | 83/291 [00:00<00:02, 81.74it/s] Loading 0: 33%|███▎ | 95/291 [00:00<00:02, 83.28it/s] Loading 0: 38%|███▊ | 112/291 [00:01<00:01, 99.69it/s] Loading 0: 44%|████▍ | 129/291 [00:01<00:01, 114.86it/s] Loading 0: 50%|████▉ | 145/291 [00:01<00:01, 125.78it/s] Loading 0: 55%|█████▍ | 160/291 [00:01<00:01, 129.85it/s] Loading 0: 62%|██████▏ | 179/291 [00:01<00:00, 142.60it/s] Loading 0: 67%|██████▋ | 195/291 [00:01<00:01, 84.12it/s] Loading 0: 73%|███████▎ | 212/291 [00:01<00:00, 97.76it/s] Loading 0: 79%|███████▉ | 230/291 [00:02<00:00, 111.22it/s] Loading 0: 84%|████████▍ | 244/291 [00:02<00:00, 109.63it/s] Loading 0: 89%|████████▉ | 259/291 [00:02<00:00, 118.48it/s] Loading 0: 95%|█████████▍| 275/291 [00:02<00:00, 125.12it/s] Loading 0: 99%|█████████▉| 289/291 [00:08<00:00, 8.62it/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-v9-mkmlizer: quantized model in 23.728s
thetsar1209-llama3-carp-v0-4-v9-mkmlizer: Processed model TheTsar1209/llama3-carp-v0.4 in 70.146s
thetsar1209-llama3-carp-v0-4-v9-mkmlizer: creating bucket guanaco-mkml-models
thetsar1209-llama3-carp-v0-4-v9-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
thetsar1209-llama3-carp-v0-4-v9-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/thetsar1209-llama3-carp-v0-4-v9
thetsar1209-llama3-carp-v0-4-v9-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/thetsar1209-llama3-carp-v0-4-v9/config.json
thetsar1209-llama3-carp-v0-4-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/thetsar1209-llama3-carp-v0-4-v9/tokenizer_config.json
thetsar1209-llama3-carp-v0-4-v9-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/thetsar1209-llama3-carp-v0-4-v9/special_tokens_map.json
thetsar1209-llama3-carp-v0-4-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/thetsar1209-llama3-carp-v0-4-v9/tokenizer.json
thetsar1209-llama3-carp-v0-4-v9-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/thetsar1209-llama3-carp-v0-4-v9/flywheel_model.0.safetensors
thetsar1209-llama3-carp-v0-4-v9-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
thetsar1209-llama3-carp-v0-4-v9-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-v9-mkmlizer: warnings.warn(
thetsar1209-llama3-carp-v0-4-v9-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-v9-mkmlizer: warnings.warn(
thetsar1209-llama3-carp-v0-4-v9-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-v9-mkmlizer: warnings.warn(
thetsar1209-llama3-carp-v0-4-v9-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-v9-mkmlizer: return self.fget.__get__(instance, owner)()
thetsar1209-llama3-carp-v0-4-v9-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
thetsar1209-llama3-carp-v0-4-v9-mkmlizer: Saving duration: 0.405s
thetsar1209-llama3-carp-v0-4-v9-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.939s
thetsar1209-llama3-carp-v0-4-v9-mkmlizer: creating bucket guanaco-reward-models
thetsar1209-llama3-carp-v0-4-v9-mkmlizer: Bucket 's3://guanaco-reward-models/' created
thetsar1209-llama3-carp-v0-4-v9-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-4-v9_reward
thetsar1209-llama3-carp-v0-4-v9-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-4-v9_reward/config.json
thetsar1209-llama3-carp-v0-4-v9-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-4-v9_reward/tokenizer_config.json
thetsar1209-llama3-carp-v0-4-v9-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-4-v9_reward/merges.txt
thetsar1209-llama3-carp-v0-4-v9-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-4-v9_reward/special_tokens_map.json
thetsar1209-llama3-carp-v0-4-v9-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-4-v9_reward/vocab.json
thetsar1209-llama3-carp-v0-4-v9-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-4-v9_reward/tokenizer.json
thetsar1209-llama3-carp-v0-4-v9-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/thetsar1209-llama3-carp-v0-4-v9_reward/reward.tensors
Job thetsar1209-llama3-carp-v0-4-v9-mkmlizer completed after 94.02s with status: succeeded
Stopping job with name thetsar1209-llama3-carp-v0-4-v9-mkmlizer
Pipeline stage MKMLizer completed in 95.08s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.32s
Running pipeline stage ISVCDeployer
Creating inference service thetsar1209-llama3-carp-v0-4-v9
Waiting for inference service thetsar1209-llama3-carp-v0-4-v9 to be ready
Inference service thetsar1209-llama3-carp-v0-4-v9 ready after 40.311789989471436s
Pipeline stage ISVCDeployer completed in 47.37s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.210343360900879s
Received healthy response to inference request in 1.2794198989868164s
Received healthy response to inference request in 1.2887494564056396s
Received healthy response to inference request in 1.281092643737793s
Received healthy response to inference request in 1.284989356994629s
5 requests
0 failed requests
5th percentile: 1.2797544479370118
10th percentile: 1.2800889968872071
20th percentile: 1.2807580947875976
30th percentile: 1.2818719863891601
40th percentile: 1.2834306716918946
50th percentile: 1.284989356994629
60th percentile: 1.2864933967590333
70th percentile: 1.2879974365234375
80th percentile: 1.4730682373046877
90th percentile: 1.8417057991027832
95th percentile: 2.026024580001831
99th percentile: 2.173479604721069
mean time: 1.4689189434051513
Pipeline stage StressChecker completed in 8.13s
thetsar1209-llama3-carp-v0-4_v9 status is now deployed due to DeploymentManager action
thetsar1209-llama3-carp-v0-4_v9 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics