submission_id: hastagaras-test-gmn-cld-dpo_v2
developer_uid: Hastagaras
status: torndown
model_repo: Hastagaras/test-gmn-cld-dpo
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['<|eot_id|>', '\n{user_name}:', '\n{bot_name}:'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': '<|start_header_id|>system<|end_header_id|>\n\nYou are {bot_name}.\n\n{memory}<|eot_id|>', 'prompt_template': "<|start_header_id|>user<|end_header_id|>\n\nLet's begin.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {prompt}<|eot_id|>", 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}:', 'truncate_by_message': False}
reward_formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{bot_name}: {prompt}\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
timestamp: 2024-04-26T17:17:36+00:00
model_name: hastagaras-test-gmn-cld-dpo_v1
model_eval_status: success
model_group: Hastagaras/test-gmn-cld-
num_battles: 6978
num_wins: 3512
celo_rating: 1152.76
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: hastagaras-test-gmn-cld-dpo_v1
ineligible_reason: propriety_total_count < 800
language_model: Hastagaras/test-gmn-cld-dpo
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-04-26
win_ratio: 0.5032960733734595
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-test-gmn-cld-dpo-v2-mkmlizer
Waiting for job on hastagaras-test-gmn-cld-dpo-v2-mkmlizer to finish
hastagaras-test-gmn-cld-dpo-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-test-gmn-cld-dpo-v2-mkmlizer: ║ _____ __ __ ║
hastagaras-test-gmn-cld-dpo-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-test-gmn-cld-dpo-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-test-gmn-cld-dpo-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-test-gmn-cld-dpo-v2-mkmlizer: ║ /___/ ║
hastagaras-test-gmn-cld-dpo-v2-mkmlizer: ║ ║
hastagaras-test-gmn-cld-dpo-v2-mkmlizer: ║ Version: 0.8.10 ║
hastagaras-test-gmn-cld-dpo-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-test-gmn-cld-dpo-v2-mkmlizer: ║ ║
hastagaras-test-gmn-cld-dpo-v2-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-test-gmn-cld-dpo-v2-mkmlizer: ║ belonging to: ║
hastagaras-test-gmn-cld-dpo-v2-mkmlizer: ║ ║
hastagaras-test-gmn-cld-dpo-v2-mkmlizer: ║ Chai Research Corp. ║
hastagaras-test-gmn-cld-dpo-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-test-gmn-cld-dpo-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-test-gmn-cld-dpo-v2-mkmlizer: ║ ║
hastagaras-test-gmn-cld-dpo-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-test-gmn-cld-dpo-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.
hastagaras-test-gmn-cld-dpo-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-test-gmn-cld-dpo-v2-mkmlizer: Downloaded to shared memory in 23.861s
hastagaras-test-gmn-cld-dpo-v2-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-test-gmn-cld-dpo-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-test-gmn-cld-dpo-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<09:55, 2.06s/it] Loading 0: 42%|████▏ | 122/291 [00:05<00:05, 30.52it/s] Loading 0: 97%|█████████▋| 283/291 [00:06<00:00, 64.84it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-test-gmn-cld-dpo-v2-mkmlizer: quantized model in 17.261s
hastagaras-test-gmn-cld-dpo-v2-mkmlizer: Processed model Hastagaras/test-gmn-cld-dpo in 42.148s
hastagaras-test-gmn-cld-dpo-v2-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-test-gmn-cld-dpo-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-test-gmn-cld-dpo-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-test-gmn-cld-dpo-v2
hastagaras-test-gmn-cld-dpo-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-test-gmn-cld-dpo-v2/config.json
hastagaras-test-gmn-cld-dpo-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-test-gmn-cld-dpo-v2/special_tokens_map.json
hastagaras-test-gmn-cld-dpo-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-test-gmn-cld-dpo-v2/tokenizer_config.json
hastagaras-test-gmn-cld-dpo-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-test-gmn-cld-dpo-v2/tokenizer.json
hastagaras-test-gmn-cld-dpo-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-test-gmn-cld-dpo-v2/flywheel_model.0.safetensors
hastagaras-test-gmn-cld-dpo-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-test-gmn-cld-dpo-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.
hastagaras-test-gmn-cld-dpo-v2-mkmlizer: warnings.warn(
hastagaras-test-gmn-cld-dpo-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.
hastagaras-test-gmn-cld-dpo-v2-mkmlizer: warnings.warn(
hastagaras-test-gmn-cld-dpo-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.
hastagaras-test-gmn-cld-dpo-v2-mkmlizer: warnings.warn(
hastagaras-test-gmn-cld-dpo-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()
hastagaras-test-gmn-cld-dpo-v2-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-test-gmn-cld-dpo-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-test-gmn-cld-dpo-v2-mkmlizer: Saving duration: 0.256s
hastagaras-test-gmn-cld-dpo-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.594s
hastagaras-test-gmn-cld-dpo-v2-mkmlizer: creating bucket guanaco-reward-models
hastagaras-test-gmn-cld-dpo-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-test-gmn-cld-dpo-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-test-gmn-cld-dpo-v2_reward
hastagaras-test-gmn-cld-dpo-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-test-gmn-cld-dpo-v2_reward/special_tokens_map.json
hastagaras-test-gmn-cld-dpo-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-test-gmn-cld-dpo-v2_reward/tokenizer_config.json
hastagaras-test-gmn-cld-dpo-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-test-gmn-cld-dpo-v2_reward/tokenizer.json
hastagaras-test-gmn-cld-dpo-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-test-gmn-cld-dpo-v2_reward/vocab.json
hastagaras-test-gmn-cld-dpo-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-test-gmn-cld-dpo-v2_reward/config.json
hastagaras-test-gmn-cld-dpo-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-test-gmn-cld-dpo-v2_reward/merges.txt
hastagaras-test-gmn-cld-dpo-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-test-gmn-cld-dpo-v2_reward/reward.tensors
Job hastagaras-test-gmn-cld-dpo-v2-mkmlizer completed after 270.28s with status: succeeded
Stopping job with name hastagaras-test-gmn-cld-dpo-v2-mkmlizer
Pipeline stage MKMLizer completed in 274.70s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-test-gmn-cld-dpo-v2
Waiting for inference service hastagaras-test-gmn-cld-dpo-v2 to be ready
Inference service hastagaras-test-gmn-cld-dpo-v2 ready after 30.22871685028076s
Pipeline stage ISVCDeployer completed in 39.01s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.16068696975708s
Received healthy response to inference request in 1.2466108798980713s
Received healthy response to inference request in 1.316828966140747s
Received healthy response to inference request in 1.288210391998291s
Received healthy response to inference request in 1.251842737197876s
5 requests
0 failed requests
5th percentile: 1.2476572513580322
10th percentile: 1.248703622817993
20th percentile: 1.250796365737915
30th percentile: 1.259116268157959
40th percentile: 1.273663330078125
50th percentile: 1.288210391998291
60th percentile: 1.2996578216552734
70th percentile: 1.3111052513122559
80th percentile: 1.4856005668640138
90th percentile: 1.823143768310547
95th percentile: 1.9919153690338134
99th percentile: 2.1269326496124266
mean time: 1.452835988998413
Pipeline stage StressChecker completed in 7.89s
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
%s, retrying in %s seconds...
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-test-gmn-cld-dpo_v2 status is now deployed due to DeploymentManager action
%s, retrying in %s seconds...
hastagaras-test-gmn-cld-dpo_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-test-gmn-cld-dpo_v2
Running pipeline stage ISVCDeleter
Checking if service hastagaras-test-gmn-cld-dpo-v2 is running
Tearing down inference service hastagaras-test-gmn-cld-dpo-v2
Toredown service hastagaras-test-gmn-cld-dpo-v2
Pipeline stage ISVCDeleter completed in 4.78s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-test-gmn-cld-dpo-v2/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-test-gmn-cld-dpo-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-test-gmn-cld-dpo-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-test-gmn-cld-dpo-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-test-gmn-cld-dpo-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-test-gmn-cld-dpo-v2_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-test-gmn-cld-dpo-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-test-gmn-cld-dpo-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-test-gmn-cld-dpo-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-test-gmn-cld-dpo-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-test-gmn-cld-dpo-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-test-gmn-cld-dpo-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 4.96s
hastagaras-test-gmn-cld-dpo_v2 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics