submission_id: thetsar1209-llama3-carpm_3381_v1
developer_uid: TheTsar1209
status: inactive
model_repo: TheTsar1209/llama3-carpmuscle-v0.1
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\n{memory}<|im_end|>\n', 'prompt_template': 'Example conversation:\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': False}
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': False}
timestamp: 2024-07-01T16:56:23+00:00
model_name: thetsar1209-llama3-carpm_3381_v1
model_group: TheTsar1209/llama3-carpm
num_battles: 17060
num_wins: 8192
celo_rating: 1165.0
propriety_score: 0.7124183006535948
propriety_total_count: 8109.0
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-carpm_3381_v1
ineligible_reason: None
language_model: TheTsar1209/llama3-carpmuscle-v0.1
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-07-01
win_ratio: 0.4801875732708089
Resubmit model
Running pipeline stage MKMLizer
Starting job with name thetsar1209-llama3-carpm-3381-v1-mkmlizer
Waiting for job on thetsar1209-llama3-carpm-3381-v1-mkmlizer to finish
thetsar1209-llama3-carpm-3381-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
thetsar1209-llama3-carpm-3381-v1-mkmlizer: ║ _____ __ __ ║
thetsar1209-llama3-carpm-3381-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
thetsar1209-llama3-carpm-3381-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
thetsar1209-llama3-carpm-3381-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
thetsar1209-llama3-carpm-3381-v1-mkmlizer: ║ /___/ ║
thetsar1209-llama3-carpm-3381-v1-mkmlizer: ║ ║
thetsar1209-llama3-carpm-3381-v1-mkmlizer: ║ Version: 0.8.14 ║
thetsar1209-llama3-carpm-3381-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
thetsar1209-llama3-carpm-3381-v1-mkmlizer: ║ https://mk1.ai ║
thetsar1209-llama3-carpm-3381-v1-mkmlizer: ║ ║
thetsar1209-llama3-carpm-3381-v1-mkmlizer: ║ The license key for the current software has been verified as ║
thetsar1209-llama3-carpm-3381-v1-mkmlizer: ║ belonging to: ║
thetsar1209-llama3-carpm-3381-v1-mkmlizer: ║ ║
thetsar1209-llama3-carpm-3381-v1-mkmlizer: ║ Chai Research Corp. ║
thetsar1209-llama3-carpm-3381-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
thetsar1209-llama3-carpm-3381-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
thetsar1209-llama3-carpm-3381-v1-mkmlizer: ║ ║
thetsar1209-llama3-carpm-3381-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
thetsar1209-llama3-carpm-3381-v1-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-carpm-3381-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
thetsar1209-llama3-carpm-3381-v1-mkmlizer: Downloaded to shared memory in 35.094s
thetsar1209-llama3-carpm-3381-v1-mkmlizer: quantizing model to /dev/shm/model_cache
thetsar1209-llama3-carpm-3381-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
thetsar1209-llama3-carpm-3381-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:02, 131.66it/s] Loading 0: 11%|█ | 32/291 [00:00<00:01, 147.44it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:01, 157.05it/s] Loading 0: 23%|██▎ | 66/291 [00:00<00:01, 160.16it/s] Loading 0: 29%|██▊ | 83/291 [00:00<00:02, 79.13it/s] Loading 0: 33%|███▎ | 95/291 [00:00<00:02, 86.48it/s] Loading 0: 39%|███▉ | 113/291 [00:01<00:01, 103.34it/s] Loading 0: 45%|████▍ | 130/291 [00:01<00:01, 117.74it/s] Loading 0: 51%|█████ | 148/291 [00:01<00:01, 128.79it/s] Loading 0: 57%|█████▋ | 166/291 [00:01<00:00, 137.33it/s] Loading 0: 63%|██████▎ | 184/291 [00:01<00:00, 147.01it/s] Loading 0: 69%|██████▊ | 200/291 [00:01<00:01, 88.76it/s] Loading 0: 73%|███████▎ | 213/291 [00:01<00:00, 96.23it/s] Loading 0: 79%|███████▊ | 229/291 [00:02<00:00, 107.03it/s] Loading 0: 84%|████████▎ | 243/291 [00:02<00:00, 111.00it/s] Loading 0: 88%|████████▊ | 256/291 [00:02<00:00, 112.83it/s] Loading 0: 92%|█████████▏| 269/291 [00:02<00:00, 114.85it/s] Loading 0: 97%|█████████▋| 282/291 [00:02<00:00, 106.45it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
thetsar1209-llama3-carpm-3381-v1-mkmlizer: quantized model in 23.803s
thetsar1209-llama3-carpm-3381-v1-mkmlizer: Processed model TheTsar1209/llama3-carpmuscle-v0.1 in 61.546s
thetsar1209-llama3-carpm-3381-v1-mkmlizer: creating bucket guanaco-mkml-models
thetsar1209-llama3-carpm-3381-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
thetsar1209-llama3-carpm-3381-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/thetsar1209-llama3-carpm-3381-v1
thetsar1209-llama3-carpm-3381-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/thetsar1209-llama3-carpm-3381-v1/special_tokens_map.json
thetsar1209-llama3-carpm-3381-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/thetsar1209-llama3-carpm-3381-v1/tokenizer_config.json
thetsar1209-llama3-carpm-3381-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/thetsar1209-llama3-carpm-3381-v1/config.json
thetsar1209-llama3-carpm-3381-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/thetsar1209-llama3-carpm-3381-v1/tokenizer.json
thetsar1209-llama3-carpm-3381-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/thetsar1209-llama3-carpm-3381-v1/flywheel_model.0.safetensors
thetsar1209-llama3-carpm-3381-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
thetsar1209-llama3-carpm-3381-v1-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-carpm-3381-v1-mkmlizer: warnings.warn(
thetsar1209-llama3-carpm-3381-v1-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-carpm-3381-v1-mkmlizer: warnings.warn(
thetsar1209-llama3-carpm-3381-v1-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-carpm-3381-v1-mkmlizer: warnings.warn(
thetsar1209-llama3-carpm-3381-v1-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-carpm-3381-v1-mkmlizer: return self.fget.__get__(instance, owner)()
thetsar1209-llama3-carpm-3381-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
thetsar1209-llama3-carpm-3381-v1-mkmlizer: Saving duration: 0.414s
thetsar1209-llama3-carpm-3381-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.319s
thetsar1209-llama3-carpm-3381-v1-mkmlizer: creating bucket guanaco-reward-models
thetsar1209-llama3-carpm-3381-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
thetsar1209-llama3-carpm-3381-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/thetsar1209-llama3-carpm-3381-v1_reward
thetsar1209-llama3-carpm-3381-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/thetsar1209-llama3-carpm-3381-v1_reward/config.json
thetsar1209-llama3-carpm-3381-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/thetsar1209-llama3-carpm-3381-v1_reward/special_tokens_map.json
thetsar1209-llama3-carpm-3381-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/thetsar1209-llama3-carpm-3381-v1_reward/tokenizer_config.json
thetsar1209-llama3-carpm-3381-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/thetsar1209-llama3-carpm-3381-v1_reward/merges.txt
thetsar1209-llama3-carpm-3381-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/thetsar1209-llama3-carpm-3381-v1_reward/vocab.json
thetsar1209-llama3-carpm-3381-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/thetsar1209-llama3-carpm-3381-v1_reward/tokenizer.json
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Job thetsar1209-llama3-carpm-3381-v1-mkmlizer completed after 94.3s with status: succeeded
Stopping job with name thetsar1209-llama3-carpm-3381-v1-mkmlizer
Pipeline stage MKMLizer completed in 95.32s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service thetsar1209-llama3-carpm-3381-v1
Waiting for inference service thetsar1209-llama3-carpm-3381-v1 to be ready
Inference service thetsar1209-llama3-carpm-3381-v1 ready after 40.26384496688843s
Pipeline stage ISVCDeployer completed in 47.32s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2363784313201904s
Received healthy response to inference request in 1.2919626235961914s
Received healthy response to inference request in 1.2746295928955078s
Received healthy response to inference request in 1.2728297710418701s
Received healthy response to inference request in 1.287471055984497s
5 requests
0 failed requests
5th percentile: 1.2731897354125976
10th percentile: 1.273549699783325
20th percentile: 1.2742696285247803
30th percentile: 1.2771978855133057
40th percentile: 1.2823344707489013
50th percentile: 1.287471055984497
60th percentile: 1.2892676830291747
70th percentile: 1.2910643100738526
80th percentile: 1.4808457851409913
90th percentile: 1.8586121082305909
95th percentile: 2.0474952697753905
99th percentile: 2.1986017990112305
mean time: 1.4726542949676513
Pipeline stage StressChecker completed in 8.20s
thetsar1209-llama3-carpm_3381_v1 status is now deployed due to DeploymentManager action
thetsar1209-llama3-carpm_3381_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics