submission_id: thetsar1209-llama3-carpm_3381_v2
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\nYou are {bot_name}\nDescription : {memory}\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: 2024-07-01T17:00:01+00:00
model_name: thetsar1209-llama3carpm_3381_v1
model_group: TheTsar1209/llama3-carpm
num_battles: 16432
num_wins: 7812
celo_rating: 1162.36
propriety_score: 0.7161834206156598
propriety_total_count: 7829.0
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-llama3carpm_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: 0.4754138266796495
Resubmit model
Running pipeline stage MKMLizer
Starting job with name thetsar1209-llama3-carpm-3381-v2-mkmlizer
Waiting for job on thetsar1209-llama3-carpm-3381-v2-mkmlizer to finish
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
thetsar1209-llama3-carpm-3381-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
thetsar1209-llama3-carpm-3381-v2-mkmlizer: ║ _____ __ __ ║
thetsar1209-llama3-carpm-3381-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
thetsar1209-llama3-carpm-3381-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
thetsar1209-llama3-carpm-3381-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
thetsar1209-llama3-carpm-3381-v2-mkmlizer: ║ /___/ ║
thetsar1209-llama3-carpm-3381-v2-mkmlizer: ║ ║
thetsar1209-llama3-carpm-3381-v2-mkmlizer: ║ Version: 0.8.14 ║
thetsar1209-llama3-carpm-3381-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
thetsar1209-llama3-carpm-3381-v2-mkmlizer: ║ https://mk1.ai ║
thetsar1209-llama3-carpm-3381-v2-mkmlizer: ║ ║
thetsar1209-llama3-carpm-3381-v2-mkmlizer: ║ The license key for the current software has been verified as ║
thetsar1209-llama3-carpm-3381-v2-mkmlizer: ║ belonging to: ║
thetsar1209-llama3-carpm-3381-v2-mkmlizer: ║ ║
thetsar1209-llama3-carpm-3381-v2-mkmlizer: ║ Chai Research Corp. ║
thetsar1209-llama3-carpm-3381-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
thetsar1209-llama3-carpm-3381-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
thetsar1209-llama3-carpm-3381-v2-mkmlizer: ║ ║
thetsar1209-llama3-carpm-3381-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
thetsar1209-llama3-carpm-3381-v2-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-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
thetsar1209-llama3-carpm-3381-v2-mkmlizer: Downloaded to shared memory in 20.713s
thetsar1209-llama3-carpm-3381-v2-mkmlizer: quantizing model to /dev/shm/model_cache
thetsar1209-llama3-carpm-3381-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Retrying (%r) after connection broken by '%r': %s
thetsar1209-llama3-carpm-3381-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:02, 128.72it/s] Loading 0: 11%|█ | 31/291 [00:00<00:01, 150.89it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:01, 154.88it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:01, 157.45it/s] Loading 0: 29%|██▊ | 83/291 [00:00<00:02, 82.37it/s] Loading 0: 33%|███▎ | 95/291 [00:00<00:02, 87.47it/s] Loading 0: 38%|███▊ | 112/291 [00:01<00:01, 105.51it/s] Loading 0: 45%|████▍ | 130/291 [00:01<00:01, 119.43it/s] Loading 0: 51%|█████ | 148/291 [00:01<00:01, 130.22it/s] Loading 0: 57%|█████▋ | 166/291 [00:01<00:00, 137.69it/s] Loading 0: 63%|██████▎ | 184/291 [00:01<00:00, 147.10it/s] Loading 0: 69%|██████▊ | 200/291 [00:01<00:01, 88.86it/s] Loading 0: 73%|███████▎ | 213/291 [00:01<00:00, 96.26it/s] Loading 0: 79%|███████▉ | 230/291 [00:02<00:00, 108.90it/s] Loading 0: 85%|████████▌ | 248/291 [00:02<00:00, 121.47it/s] Loading 0: 91%|█████████▏| 266/291 [00:02<00:00, 132.18it/s] Loading 0: 97%|█████████▋| 282/291 [00:02<00:00, 138.81it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
thetsar1209-llama3-carpm-3381-v2-mkmlizer: quantized model in 23.641s
thetsar1209-llama3-carpm-3381-v2-mkmlizer: Processed model TheTsar1209/llama3-carpmuscle-v0.1 in 47.074s
thetsar1209-llama3-carpm-3381-v2-mkmlizer: creating bucket guanaco-mkml-models
thetsar1209-llama3-carpm-3381-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
thetsar1209-llama3-carpm-3381-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/thetsar1209-llama3-carpm-3381-v2
thetsar1209-llama3-carpm-3381-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/thetsar1209-llama3-carpm-3381-v2/config.json
thetsar1209-llama3-carpm-3381-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/thetsar1209-llama3-carpm-3381-v2/special_tokens_map.json
thetsar1209-llama3-carpm-3381-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/thetsar1209-llama3-carpm-3381-v2/tokenizer_config.json
thetsar1209-llama3-carpm-3381-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/thetsar1209-llama3-carpm-3381-v2/tokenizer.json
thetsar1209-llama3-carpm-3381-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/thetsar1209-llama3-carpm-3381-v2/flywheel_model.0.safetensors
thetsar1209-llama3-carpm-3381-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
thetsar1209-llama3-carpm-3381-v2-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-v2-mkmlizer: warnings.warn(
thetsar1209-llama3-carpm-3381-v2-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-v2-mkmlizer: warnings.warn(
thetsar1209-llama3-carpm-3381-v2-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-v2-mkmlizer: warnings.warn(
thetsar1209-llama3-carpm-3381-v2-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-v2-mkmlizer: return self.fget.__get__(instance, owner)()
thetsar1209-llama3-carpm-3381-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
thetsar1209-llama3-carpm-3381-v2-mkmlizer: Saving duration: 0.415s
thetsar1209-llama3-carpm-3381-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.263s
thetsar1209-llama3-carpm-3381-v2-mkmlizer: creating bucket guanaco-reward-models
thetsar1209-llama3-carpm-3381-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
thetsar1209-llama3-carpm-3381-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/thetsar1209-llama3-carpm-3381-v2_reward
thetsar1209-llama3-carpm-3381-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/thetsar1209-llama3-carpm-3381-v2_reward/special_tokens_map.json
thetsar1209-llama3-carpm-3381-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/thetsar1209-llama3-carpm-3381-v2_reward/config.json
thetsar1209-llama3-carpm-3381-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/thetsar1209-llama3-carpm-3381-v2_reward/tokenizer_config.json
thetsar1209-llama3-carpm-3381-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/thetsar1209-llama3-carpm-3381-v2_reward/vocab.json
thetsar1209-llama3-carpm-3381-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/thetsar1209-llama3-carpm-3381-v2_reward/merges.txt
thetsar1209-llama3-carpm-3381-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/thetsar1209-llama3-carpm-3381-v2_reward/tokenizer.json
thetsar1209-llama3-carpm-3381-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/thetsar1209-llama3-carpm-3381-v2_reward/reward.tensors
Job thetsar1209-llama3-carpm-3381-v2-mkmlizer completed after 73.58s with status: succeeded
Stopping job with name thetsar1209-llama3-carpm-3381-v2-mkmlizer
Pipeline stage MKMLizer completed in 75.09s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service thetsar1209-llama3-carpm-3381-v2
Waiting for inference service thetsar1209-llama3-carpm-3381-v2 to be ready
Connection pool is full, discarding connection: %s
Inference service thetsar1209-llama3-carpm-3381-v2 ready after 40.263684034347534s
Pipeline stage ISVCDeployer completed in 47.32s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2065837383270264s
Received healthy response to inference request in 1.305858850479126s
Received healthy response to inference request in 1.4436674118041992s
Received healthy response to inference request in 1.270864486694336s
Received healthy response to inference request in 1.2986726760864258s
5 requests
0 failed requests
5th percentile: 1.276426124572754
10th percentile: 1.281987762451172
20th percentile: 1.2931110382080078
30th percentile: 1.3001099109649659
40th percentile: 1.3029843807220458
50th percentile: 1.305858850479126
60th percentile: 1.3609822750091554
70th percentile: 1.4161056995391845
80th percentile: 1.5962506771087648
90th percentile: 1.9014172077178957
95th percentile: 2.0540004730224606
99th percentile: 2.176067085266113
mean time: 1.5051294326782227
Pipeline stage StressChecker completed in 8.38s
thetsar1209-llama3-carpm_3381_v2 status is now deployed due to DeploymentManager action
thetsar1209-llama3-carpm_3381_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics