submission_id: thetsar1209-llama3-carp-_3165_v3
developer_uid: TheTsar1209
status: torndown
model_repo: TheTsar1209/llama3-carp-orpo-test-v0.1
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: 2024-04-24T13:09:57+00:00
model_name: thetsar1209-llama3-carp-3165_v1
model_eval_status: pending
model_group: TheTsar1209/llama3-carp-
num_battles: 8134
num_wins: 3942
celo_rating: 1144.0
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-3165_v1
ineligible_reason: propriety_total_count < 800
language_model: TheTsar1209/llama3-carp-orpo-test-v0.1
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-04-24
win_ratio: 0.4846324071797394
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name thetsar1209-llama3-carp-3165-v3-mkmlizer
Waiting for job on thetsar1209-llama3-carp-3165-v3-mkmlizer to finish
Stopping job with name thetsar1209-llama3-carp-3165-v3-mkmlizer
%s, retrying in %s seconds...
Starting job with name thetsar1209-llama3-carp-3165-v3-mkmlizer
Waiting for job on thetsar1209-llama3-carp-3165-v3-mkmlizer to finish
thetsar1209-llama3-carp-3165-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
thetsar1209-llama3-carp-3165-v3-mkmlizer: ║ _____ __ __ ║
thetsar1209-llama3-carp-3165-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
thetsar1209-llama3-carp-3165-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
thetsar1209-llama3-carp-3165-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
thetsar1209-llama3-carp-3165-v3-mkmlizer: ║ /___/ ║
thetsar1209-llama3-carp-3165-v3-mkmlizer: ║ ║
thetsar1209-llama3-carp-3165-v3-mkmlizer: ║ Version: 0.8.10 ║
thetsar1209-llama3-carp-3165-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
thetsar1209-llama3-carp-3165-v3-mkmlizer: ║ ║
thetsar1209-llama3-carp-3165-v3-mkmlizer: ║ The license key for the current software has been verified as ║
thetsar1209-llama3-carp-3165-v3-mkmlizer: ║ belonging to: ║
thetsar1209-llama3-carp-3165-v3-mkmlizer: ║ ║
thetsar1209-llama3-carp-3165-v3-mkmlizer: ║ Chai Research Corp. ║
thetsar1209-llama3-carp-3165-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
thetsar1209-llama3-carp-3165-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
thetsar1209-llama3-carp-3165-v3-mkmlizer: ║ ║
thetsar1209-llama3-carp-3165-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
thetsar1209-llama3-carp-3165-v3-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-3165-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
thetsar1209-llama3-carp-3165-v3-mkmlizer: Downloaded to shared memory in 30.739s
thetsar1209-llama3-carp-3165-v3-mkmlizer: quantizing model to /dev/shm/model_cache
thetsar1209-llama3-carp-3165-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
thetsar1209-llama3-carp-3165-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 45%|████▍ | 130/291 [00:01<00:01, 129.62it/s] Loading 0: 91%|█████████ | 265/291 [00:02<00:00, 132.72it/s] Loading 0: 99%|█████████▊| 287/291 [00:07<00:00, 29.02it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
thetsar1209-llama3-carp-3165-v3-mkmlizer: quantized model in 17.567s
thetsar1209-llama3-carp-3165-v3-mkmlizer: Processed model TheTsar1209/llama3-carp-orpo-test-v0.1 in 49.392s
thetsar1209-llama3-carp-3165-v3-mkmlizer: creating bucket guanaco-mkml-models
thetsar1209-llama3-carp-3165-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
thetsar1209-llama3-carp-3165-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/thetsar1209-llama3-carp-3165-v3
thetsar1209-llama3-carp-3165-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/thetsar1209-llama3-carp-3165-v3/special_tokens_map.json
thetsar1209-llama3-carp-3165-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/thetsar1209-llama3-carp-3165-v3/config.json
thetsar1209-llama3-carp-3165-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/thetsar1209-llama3-carp-3165-v3/tokenizer_config.json
thetsar1209-llama3-carp-3165-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/thetsar1209-llama3-carp-3165-v3/tokenizer.json
thetsar1209-llama3-carp-3165-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/thetsar1209-llama3-carp-3165-v3/flywheel_model.0.safetensors
thetsar1209-llama3-carp-3165-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
thetsar1209-llama3-carp-3165-v3-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-3165-v3-mkmlizer: warnings.warn(
thetsar1209-llama3-carp-3165-v3-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-3165-v3-mkmlizer: warnings.warn(
thetsar1209-llama3-carp-3165-v3-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-3165-v3-mkmlizer: warnings.warn(
thetsar1209-llama3-carp-3165-v3-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-3165-v3-mkmlizer: return self.fget.__get__(instance, owner)()
thetsar1209-llama3-carp-3165-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
thetsar1209-llama3-carp-3165-v3-mkmlizer: Saving duration: 0.262s
thetsar1209-llama3-carp-3165-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 9.552s
thetsar1209-llama3-carp-3165-v3-mkmlizer: creating bucket guanaco-reward-models
thetsar1209-llama3-carp-3165-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
thetsar1209-llama3-carp-3165-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/thetsar1209-llama3-carp-3165-v3_reward
thetsar1209-llama3-carp-3165-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/thetsar1209-llama3-carp-3165-v3_reward/special_tokens_map.json
thetsar1209-llama3-carp-3165-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/thetsar1209-llama3-carp-3165-v3_reward/tokenizer_config.json
thetsar1209-llama3-carp-3165-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/thetsar1209-llama3-carp-3165-v3_reward/config.json
thetsar1209-llama3-carp-3165-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/thetsar1209-llama3-carp-3165-v3_reward/merges.txt
thetsar1209-llama3-carp-3165-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/thetsar1209-llama3-carp-3165-v3_reward/vocab.json
thetsar1209-llama3-carp-3165-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/thetsar1209-llama3-carp-3165-v3_reward/tokenizer.json
Job thetsar1209-llama3-carp-3165-v3-mkmlizer completed after 198.53s with status: succeeded
Stopping job with name thetsar1209-llama3-carp-3165-v3-mkmlizer
Pipeline stage MKMLizer completed in 203.02s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service thetsar1209-llama3-carp-3165-v3
Waiting for inference service thetsar1209-llama3-carp-3165-v3 to be ready
Inference service thetsar1209-llama3-carp-3165-v3 ready after 30.257807970046997s
Pipeline stage ISVCDeployer completed in 37.57s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.7216720581054688s
Received healthy response to inference request in 1.2567431926727295s
Received healthy response to inference request in 1.2144103050231934s
Received healthy response to inference request in 1.253310203552246s
Received healthy response to inference request in 1.2664875984191895s
5 requests
0 failed requests
5th percentile: 1.2221902847290038
10th percentile: 1.2299702644348145
20th percentile: 1.2455302238464356
30th percentile: 1.2539968013763427
40th percentile: 1.2553699970245362
50th percentile: 1.2567431926727295
60th percentile: 1.2606409549713136
70th percentile: 1.2645387172698974
80th percentile: 1.5575244903564456
90th percentile: 2.1395982742309574
95th percentile: 2.4306351661682126
99th percentile: 2.6634646797180177
mean time: 1.5425246715545655
Pipeline stage StressChecker completed in 8.42s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
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-_3165_v3 status is now deployed due to DeploymentManager action
thetsar1209-llama3-carp-_3165_v3 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of thetsar1209-llama3-carp-_3165_v3
Running pipeline stage ISVCDeleter
Checking if service thetsar1209-llama3-carp-3165-v3 is running
admin requested tearing down of thetsar1209-llama3-carp-v0-2_v1
Running pipeline stage ISVCDeleter
Checking if service thetsar1209-llama3-carp-v0-2-v1 is running
Tearing down inference service thetsar1209-llama3-carp-3165-v3
Toredown service thetsar1209-llama3-carp-3165-v3
Pipeline stage ISVCDeleter completed in 3.50s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key thetsar1209-llama3-carp-3165-v3/config.json from bucket guanaco-mkml-models
Deleting key thetsar1209-llama3-carp-3165-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Tearing down inference service thetsar1209-llama3-carp-v0-2-v1
Toredown service thetsar1209-llama3-carp-v0-2-v1
Pipeline stage ISVCDeleter completed in 3.72s
Running pipeline stage MKMLModelDeleter
Deleting key thetsar1209-llama3-carp-3165-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key thetsar1209-llama3-carp-3165-v3/tokenizer.json from bucket guanaco-mkml-models
Cleaning model data from S3
Deleting key thetsar1209-llama3-carp-3165-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Cleaning model data from model cache
Deleting key thetsar1209-llama3-carp-v0-2-v1/config.json from bucket guanaco-mkml-models
Deleting key thetsar1209-llama3-carp-3165-v3_reward/config.json from bucket guanaco-reward-models
Deleting key thetsar1209-llama3-carp-v0-2-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key thetsar1209-llama3-carp-3165-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key thetsar1209-llama3-carp-3165-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key thetsar1209-llama3-carp-3165-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key thetsar1209-llama3-carp-3165-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key thetsar1209-llama3-carp-v0-2-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key thetsar1209-llama3-carp-3165-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key thetsar1209-llama3-carp-v0-2-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key thetsar1209-llama3-carp-3165-v3_reward/vocab.json from bucket guanaco-reward-models
Deleting key thetsar1209-llama3-carp-v0-2-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Pipeline stage MKMLModelDeleter completed in 3.30s
thetsar1209-llama3-carp-_3165_v3 status is now torndown due to DeploymentManager action
Deleting key thetsar1209-llama3-carp-v0-2-v1_reward/config.json from bucket guanaco-reward-models

Usage Metrics

Latency Metrics