submission_id: thetsar1209-llama3-carp-_4098_v1
developer_uid: TheTsar1209
status: torndown
model_repo: TheTsar1209/llama3-carp-orpo-test-v0.2
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 1.0, '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': False}
reward_formatter: {'memory_template': 'Memory: {memory}\n', 'prompt_template': '{prompt}\n', 'bot_template': 'Bot: {message}\n', 'user_template': 'User: {message}\n', 'response_template': 'Bot:', 'truncate_by_message': False}
timestamp: 2024-04-25T02:39:26+00:00
model_name: thetsar1209-llama3-carp-_4098_v1
model_eval_status: success
model_group: TheTsar1209/llama3-carp-
num_battles: 6847
num_wins: 3261
celo_rating: 1134.66
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-_4098_v1
ineligible_reason: propriety_total_count < 800
language_model: TheTsar1209/llama3-carp-orpo-test-v0.2
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-04-24
win_ratio: 0.47626697823864467
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name thetsar1209-llama3-carp-4098-v1-mkmlizer
Waiting for job on thetsar1209-llama3-carp-4098-v1-mkmlizer to finish
thetsar1209-llama3-carp-4098-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
thetsar1209-llama3-carp-4098-v1-mkmlizer: ║ _____ __ __ ║
thetsar1209-llama3-carp-4098-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
thetsar1209-llama3-carp-4098-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
thetsar1209-llama3-carp-4098-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
thetsar1209-llama3-carp-4098-v1-mkmlizer: ║ /___/ ║
thetsar1209-llama3-carp-4098-v1-mkmlizer: ║ ║
thetsar1209-llama3-carp-4098-v1-mkmlizer: ║ Version: 0.8.10 ║
thetsar1209-llama3-carp-4098-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
thetsar1209-llama3-carp-4098-v1-mkmlizer: ║ ║
thetsar1209-llama3-carp-4098-v1-mkmlizer: ║ The license key for the current software has been verified as ║
thetsar1209-llama3-carp-4098-v1-mkmlizer: ║ belonging to: ║
thetsar1209-llama3-carp-4098-v1-mkmlizer: ║ ║
thetsar1209-llama3-carp-4098-v1-mkmlizer: ║ Chai Research Corp. ║
thetsar1209-llama3-carp-4098-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
thetsar1209-llama3-carp-4098-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
thetsar1209-llama3-carp-4098-v1-mkmlizer: ║ ║
thetsar1209-llama3-carp-4098-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
thetsar1209-llama3-carp-4098-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-carp-4098-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
thetsar1209-llama3-carp-4098-v1-mkmlizer: Downloaded to shared memory in 104.907s
thetsar1209-llama3-carp-4098-v1-mkmlizer: quantizing model to /dev/shm/model_cache
thetsar1209-llama3-carp-4098-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
thetsar1209-llama3-carp-4098-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 51%|█████ | 147/291 [00:01<00:00, 146.14it/s] Loading 0: 99%|█████████▊| 287/291 [00:06<00:00, 36.92it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
thetsar1209-llama3-carp-4098-v1-mkmlizer: quantized model in 17.383s
thetsar1209-llama3-carp-4098-v1-mkmlizer: Processed model TheTsar1209/llama3-carp-orpo-test-v0.2 in 123.246s
thetsar1209-llama3-carp-4098-v1-mkmlizer: creating bucket guanaco-mkml-models
thetsar1209-llama3-carp-4098-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
thetsar1209-llama3-carp-4098-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/thetsar1209-llama3-carp-4098-v1
thetsar1209-llama3-carp-4098-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/thetsar1209-llama3-carp-4098-v1/config.json
thetsar1209-llama3-carp-4098-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/thetsar1209-llama3-carp-4098-v1/special_tokens_map.json
thetsar1209-llama3-carp-4098-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/thetsar1209-llama3-carp-4098-v1/tokenizer_config.json
thetsar1209-llama3-carp-4098-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/thetsar1209-llama3-carp-4098-v1/tokenizer.json
thetsar1209-llama3-carp-4098-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/thetsar1209-llama3-carp-4098-v1/flywheel_model.0.safetensors
thetsar1209-llama3-carp-4098-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
thetsar1209-llama3-carp-4098-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-carp-4098-v1-mkmlizer: warnings.warn(
thetsar1209-llama3-carp-4098-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-carp-4098-v1-mkmlizer: warnings.warn(
thetsar1209-llama3-carp-4098-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-carp-4098-v1-mkmlizer: return self.fget.__get__(instance, owner)()
thetsar1209-llama3-carp-4098-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
thetsar1209-llama3-carp-4098-v1-mkmlizer: Saving duration: 0.227s
thetsar1209-llama3-carp-4098-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.821s
thetsar1209-llama3-carp-4098-v1-mkmlizer: creating bucket guanaco-reward-models
thetsar1209-llama3-carp-4098-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
thetsar1209-llama3-carp-4098-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/thetsar1209-llama3-carp-4098-v1_reward
thetsar1209-llama3-carp-4098-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/thetsar1209-llama3-carp-4098-v1_reward/special_tokens_map.json
thetsar1209-llama3-carp-4098-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/thetsar1209-llama3-carp-4098-v1_reward/config.json
thetsar1209-llama3-carp-4098-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/thetsar1209-llama3-carp-4098-v1_reward/tokenizer_config.json
thetsar1209-llama3-carp-4098-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/thetsar1209-llama3-carp-4098-v1_reward/merges.txt
thetsar1209-llama3-carp-4098-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/thetsar1209-llama3-carp-4098-v1_reward/vocab.json
thetsar1209-llama3-carp-4098-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/thetsar1209-llama3-carp-4098-v1_reward/tokenizer.json
thetsar1209-llama3-carp-4098-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/thetsar1209-llama3-carp-4098-v1_reward/reward.tensors
Job thetsar1209-llama3-carp-4098-v1-mkmlizer completed after 146.17s with status: succeeded
Stopping job with name thetsar1209-llama3-carp-4098-v1-mkmlizer
Pipeline stage MKMLizer completed in 149.04s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service thetsar1209-llama3-carp-4098-v1
Waiting for inference service thetsar1209-llama3-carp-4098-v1 to be ready
Inference service thetsar1209-llama3-carp-4098-v1 ready after 40.6359543800354s
Pipeline stage ISVCDeployer completed in 48.02s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0346546173095703s
Received healthy response to inference request in 1.2300000190734863s
Received healthy response to inference request in 1.2266559600830078s
Received healthy response to inference request in 1.2181994915008545s
Received healthy response to inference request in 1.2386136054992676s
5 requests
0 failed requests
5th percentile: 1.2198907852172851
10th percentile: 1.2215820789337157
20th percentile: 1.2249646663665772
30th percentile: 1.2273247718811036
40th percentile: 1.2286623954772948
50th percentile: 1.2300000190734863
60th percentile: 1.2334454536437989
70th percentile: 1.2368908882141114
80th percentile: 1.3978218078613283
90th percentile: 1.7162382125854494
95th percentile: 1.8754464149475096
99th percentile: 2.0028129768371583
mean time: 1.3896247386932372
Pipeline stage StressChecker completed in 7.57s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.04s
M-Eval Dataset for topic stay_in_character is loaded
thetsar1209-llama3-carp-_4098_v1 status is now deployed due to DeploymentManager action
thetsar1209-llama3-carp-_4098_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of thetsar1209-llama3-carp-_4098_v1
Running pipeline stage ISVCDeleter
Checking if service thetsar1209-llama3-carp-4098-v1 is running
Tearing down inference service thetsar1209-llama3-carp-4098-v1
Toredown service thetsar1209-llama3-carp-4098-v1
Pipeline stage ISVCDeleter completed in 4.62s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key thetsar1209-llama3-carp-4098-v1/config.json from bucket guanaco-mkml-models
Deleting key thetsar1209-llama3-carp-4098-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key thetsar1209-llama3-carp-4098-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key thetsar1209-llama3-carp-4098-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key thetsar1209-llama3-carp-4098-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key thetsar1209-llama3-carp-4098-v1_reward/config.json from bucket guanaco-reward-models
Deleting key thetsar1209-llama3-carp-4098-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key thetsar1209-llama3-carp-4098-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key thetsar1209-llama3-carp-4098-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key thetsar1209-llama3-carp-4098-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key thetsar1209-llama3-carp-4098-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key thetsar1209-llama3-carp-4098-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.83s
thetsar1209-llama3-carp-_4098_v1 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics