trace2333-joint-filtered_3791

developer_uid: Trace2333
submission_id: trace2333-joint-filtered_3791_v2
model_name: trace2333-joint-filtered_3791_v2
model_group: Trace2333/joint_filtered
status: torndown
timestamp: 2024-07-04T08:04:43+00:00
num_battles: 15536
num_wins: 6847
celo_rating: 1140.15
family_friendly_score: 0.0
submission_type: basic
model_repo: Trace2333/joint_filtered_llama2_v0
model_architecture: LlamaForCausalLM
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
model_num_parameters: 6738415616.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
display_name: trace2333-joint-filtered_3791_v2
is_internal_developer: False
language_model: Trace2333/joint_filtered_llama2_v0
model_size: 7B
ranking_group: single
us_pacific_date: 2024-07-04
win_ratio: 0.4407183316168898
generation_params: {'temperature': 1.25, 'top_p': 1.0, 'min_p': 0.12, 'top_k': 200, 'presence_penalty': 0.2, 'frequency_penalty': 0.3, 'stopping_words': ['</s>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona####: {memory}", 'prompt_template': '{prompt}\\n<START>\\n', 'bot_template': '{bot_name}: {message}\\n', 'user_template': 'You: {message}\\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
reward_formatter: {'bot_template': '{bot_name}: {message}\\n', 'memory_template': "{bot_name}'s Persona: {memory}\\n####\\n", 'prompt_template': '{prompt}\\n<START>\\n', 'response_template': '{bot_name}:', 'truncate_by_message': True, 'user_template': '{user_name}: {message}\\n'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name trace2333-joint-filtered-3791-v2-mkmlizer
Waiting for job on trace2333-joint-filtered-3791-v2-mkmlizer to finish
trace2333-joint-filtered-3791-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-joint-filtered-3791-v2-mkmlizer: ║     _____            __           __                                ║
trace2333-joint-filtered-3791-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
trace2333-joint-filtered-3791-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
trace2333-joint-filtered-3791-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
trace2333-joint-filtered-3791-v2-mkmlizer: ║       /___/                                                         ║
trace2333-joint-filtered-3791-v2-mkmlizer: ║                                                                     ║
trace2333-joint-filtered-3791-v2-mkmlizer: ║  Version: 0.8.14                                                    ║
trace2333-joint-filtered-3791-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
trace2333-joint-filtered-3791-v2-mkmlizer: ║  https://mk1.ai                                                     ║
trace2333-joint-filtered-3791-v2-mkmlizer: ║                                                                     ║
trace2333-joint-filtered-3791-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
trace2333-joint-filtered-3791-v2-mkmlizer: ║  belonging to:                                                      ║
trace2333-joint-filtered-3791-v2-mkmlizer: ║                                                                     ║
trace2333-joint-filtered-3791-v2-mkmlizer: ║  Chai Research Corp.                                                ║
trace2333-joint-filtered-3791-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
trace2333-joint-filtered-3791-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
trace2333-joint-filtered-3791-v2-mkmlizer: ║                                                                     ║
trace2333-joint-filtered-3791-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
trace2333-joint-filtered-3791-v2-mkmlizer: Downloaded to shared memory in 31.575s
trace2333-joint-filtered-3791-v2-mkmlizer: quantizing model to /dev/shm/model_cache
trace2333-joint-filtered-3791-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
trace2333-joint-filtered-3791-v2-mkmlizer: quantized model in 16.946s
trace2333-joint-filtered-3791-v2-mkmlizer: Processed model Trace2333/joint_filtered_llama2_v0 in 48.521s
trace2333-joint-filtered-3791-v2-mkmlizer: creating bucket guanaco-mkml-models
trace2333-joint-filtered-3791-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-joint-filtered-3791-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-joint-filtered-3791-v2
trace2333-joint-filtered-3791-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-joint-filtered-3791-v2/special_tokens_map.json
trace2333-joint-filtered-3791-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-joint-filtered-3791-v2/config.json
trace2333-joint-filtered-3791-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/trace2333-joint-filtered-3791-v2/tokenizer.model
trace2333-joint-filtered-3791-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-joint-filtered-3791-v2/tokenizer_config.json
trace2333-joint-filtered-3791-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-joint-filtered-3791-v2/tokenizer.json
trace2333-joint-filtered-3791-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/trace2333-joint-filtered-3791-v2/flywheel_model.0.safetensors
trace2333-joint-filtered-3791-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
trace2333-joint-filtered-3791-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:04, 69.66it/s]
Loading 0:   5%|▍         | 14/291 [00:00<00:04, 63.54it/s]
Loading 0:   8%|▊         | 23/291 [00:00<00:04, 66.98it/s]
Loading 0:  11%|█         | 32/291 [00:00<00:03, 68.89it/s]
Loading 0:  14%|█▍        | 41/291 [00:00<00:03, 69.77it/s]
Loading 0:  18%|█▊        | 51/291 [00:00<00:05, 43.70it/s]
Loading 0:  20%|█▉        | 57/291 [00:01<00:05, 46.16it/s]
Loading 0:  23%|██▎       | 66/291 [00:01<00:04, 53.56it/s]
Loading 0:  25%|██▌       | 73/291 [00:01<00:03, 55.77it/s]
Loading 0:  28%|██▊       | 81/291 [00:01<00:03, 58.32it/s]
Loading 0:  31%|███       | 90/291 [00:01<00:03, 62.17it/s]
Loading 0:  34%|███▎      | 98/291 [00:01<00:02, 66.14it/s]
Loading 0:  36%|███▌      | 105/291 [00:01<00:04, 41.72it/s]
Loading 0:  38%|███▊      | 111/291 [00:02<00:04, 43.53it/s]
Loading 0:  41%|████      | 118/291 [00:02<00:03, 48.83it/s]
Loading 0:  43%|████▎     | 124/291 [00:02<00:03, 51.27it/s]
Loading 0:  45%|████▌     | 131/291 [00:02<00:03, 52.98it/s]
Loading 0:  48%|████▊     | 139/291 [00:02<00:02, 59.19it/s]
Loading 0:  51%|█████     | 147/291 [00:02<00:02, 64.11it/s]
Loading 0:  53%|█████▎    | 154/291 [00:02<00:02, 65.41it/s]
Loading 0:  55%|█████▌    | 161/291 [00:03<00:03, 38.75it/s]
Loading 0:  57%|█████▋    | 167/291 [00:03<00:02, 41.35it/s]
Loading 0:  60%|██████    | 175/291 [00:03<00:02, 48.87it/s]
Loading 0:  63%|██████▎   | 183/291 [00:03<00:02, 53.25it/s]
Loading 0:  65%|██████▌   | 190/291 [00:03<00:01, 56.86it/s]
Loading 0:  68%|██████▊   | 197/291 [00:03<00:01, 58.58it/s]
Loading 0:  70%|███████   | 204/291 [00:03<00:01, 59.44it/s]
Loading 0:  73%|███████▎  | 213/291 [00:04<00:01, 41.21it/s]
Loading 0:  75%|███████▌  | 219/291 [00:04<00:01, 44.07it/s]
Loading 0:  78%|███████▊  | 228/291 [00:04<00:01, 50.91it/s]
Loading 0:  81%|████████▏ | 237/291 [00:04<00:00, 56.18it/s]
Loading 0:  85%|████████▍ | 246/291 [00:04<00:00, 62.50it/s]
Loading 0:  88%|████████▊ | 255/291 [00:04<00:00, 67.80it/s]
Loading 0:  91%|█████████ | 264/291 [00:04<00:00, 73.09it/s]
Loading 0:  93%|█████████▎| 272/291 [00:06<00:01, 13.91it/s]
Loading 0:  97%|█████████▋| 281/291 [00:06<00:00, 18.82it/s]
Loading 0:  99%|█████████▉| 289/291 [00:06<00:00, 23.96it/s]
                                                            
/opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:919: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
trace2333-joint-filtered-3791-v2-mkmlizer:   warnings.warn(
trace2333-joint-filtered-3791-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
trace2333-joint-filtered-3791-v2-mkmlizer:   warnings.warn(
trace2333-joint-filtered-3791-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:769: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
trace2333-joint-filtered-3791-v2-mkmlizer:   warnings.warn(
trace2333-joint-filtered-3791-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.
trace2333-joint-filtered-3791-v2-mkmlizer:   warnings.warn(
trace2333-joint-filtered-3791-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()
trace2333-joint-filtered-3791-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
trace2333-joint-filtered-3791-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
trace2333-joint-filtered-3791-v2-mkmlizer: Saving duration: 0.396s
trace2333-joint-filtered-3791-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.946s
trace2333-joint-filtered-3791-v2-mkmlizer: creating bucket guanaco-reward-models
trace2333-joint-filtered-3791-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
trace2333-joint-filtered-3791-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/trace2333-joint-filtered-3791-v2_reward
trace2333-joint-filtered-3791-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/trace2333-joint-filtered-3791-v2_reward/special_tokens_map.json
trace2333-joint-filtered-3791-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/trace2333-joint-filtered-3791-v2_reward/tokenizer_config.json
trace2333-joint-filtered-3791-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/trace2333-joint-filtered-3791-v2_reward/config.json
trace2333-joint-filtered-3791-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/trace2333-joint-filtered-3791-v2_reward/merges.txt
trace2333-joint-filtered-3791-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/trace2333-joint-filtered-3791-v2_reward/vocab.json
trace2333-joint-filtered-3791-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/trace2333-joint-filtered-3791-v2_reward/tokenizer.json
Job trace2333-joint-filtered-3791-v2-mkmlizer completed after 94.68s with status: succeeded
Stopping job with name trace2333-joint-filtered-3791-v2-mkmlizer
Pipeline stage MKMLizer completed in 95.68s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service trace2333-joint-filtered-3791-v2
Waiting for inference service trace2333-joint-filtered-3791-v2 to be ready
Inference service trace2333-joint-filtered-3791-v2 ready after 110.61326456069946s
Pipeline stage ISVCDeployer completed in 117.71s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9800870418548584s
Received healthy response to inference request in 1.1750984191894531s
Received healthy response to inference request in 1.2068312168121338s
Received healthy response to inference request in 1.253718614578247s
Received healthy response to inference request in 1.2314958572387695s
5 requests
0 failed requests
5th percentile: 1.1814449787139893
10th percentile: 1.1877915382385253
20th percentile: 1.2004846572875976
30th percentile: 1.211764144897461
40th percentile: 1.2216300010681151
50th percentile: 1.2314958572387695
60th percentile: 1.2403849601745605
70th percentile: 1.2492740631103516
80th percentile: 1.3989923000335696
90th percentile: 1.6895396709442139
95th percentile: 1.834813356399536
99th percentile: 1.9510323047637939
mean time: 1.3694462299346923
Pipeline stage StressChecker completed in 7.69s
trace2333-joint-filtered_3791_v2 status is now deployed due to DeploymentManager action
trace2333-joint-filtered_3791_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of trace2333-joint-filtered_3791_v2
Running pipeline stage ISVCDeleter
Checking if service trace2333-joint-filtered-3791-v2 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.94s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key trace2333-joint-filtered-3791-v2/config.json from bucket guanaco-mkml-models
Deleting key trace2333-joint-filtered-3791-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key trace2333-joint-filtered-3791-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key trace2333-joint-filtered-3791-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key trace2333-joint-filtered-3791-v2/tokenizer.model from bucket guanaco-mkml-models
Deleting key trace2333-joint-filtered-3791-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key trace2333-joint-filtered-3791-v2_reward/config.json from bucket guanaco-reward-models
Deleting key trace2333-joint-filtered-3791-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key trace2333-joint-filtered-3791-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key trace2333-joint-filtered-3791-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key trace2333-joint-filtered-3791-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key trace2333-joint-filtered-3791-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key trace2333-joint-filtered-3791-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.98s
trace2333-joint-filtered_3791_v2 status is now torndown due to DeploymentManager action