submission_id: meseca-20062024-c1-dpo-1e_v2
developer_uid: nguyenzzz
status: inactive
model_repo: meseca/20062024-c1-dpo-1e
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 60, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{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': '{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: 2024-06-27T16:21:59+00:00
model_name: meseca-20062024-c1-dpo-1e_v2
model_group: meseca/20062024-c1-dpo-1
num_battles: 14942
num_wins: 7190
celo_rating: 1164.75
propriety_score: 0.7663394780943261
propriety_total_count: 8354.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: meseca-20062024-c1-dpo-1e_v2
ineligible_reason: None
language_model: meseca/20062024-c1-dpo-1e
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-27
win_ratio: 0.4811939499397671
Resubmit model
Running pipeline stage MKMLizer
Starting job with name meseca-20062024-c1-dpo-1e-v2-mkmlizer
Waiting for job on meseca-20062024-c1-dpo-1e-v2-mkmlizer to finish
meseca-20062024-c1-dpo-1e-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
meseca-20062024-c1-dpo-1e-v2-mkmlizer: ║ _____ __ __ ║
meseca-20062024-c1-dpo-1e-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
meseca-20062024-c1-dpo-1e-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
meseca-20062024-c1-dpo-1e-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
meseca-20062024-c1-dpo-1e-v2-mkmlizer: ║ /___/ ║
meseca-20062024-c1-dpo-1e-v2-mkmlizer: ║ ║
meseca-20062024-c1-dpo-1e-v2-mkmlizer: ║ Version: 0.8.14 ║
meseca-20062024-c1-dpo-1e-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
meseca-20062024-c1-dpo-1e-v2-mkmlizer: ║ https://mk1.ai ║
meseca-20062024-c1-dpo-1e-v2-mkmlizer: ║ ║
meseca-20062024-c1-dpo-1e-v2-mkmlizer: ║ The license key for the current software has been verified as ║
meseca-20062024-c1-dpo-1e-v2-mkmlizer: ║ belonging to: ║
meseca-20062024-c1-dpo-1e-v2-mkmlizer: ║ ║
meseca-20062024-c1-dpo-1e-v2-mkmlizer: ║ Chai Research Corp. ║
meseca-20062024-c1-dpo-1e-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
meseca-20062024-c1-dpo-1e-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
meseca-20062024-c1-dpo-1e-v2-mkmlizer: ║ ║
meseca-20062024-c1-dpo-1e-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
meseca-20062024-c1-dpo-1e-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.
meseca-20062024-c1-dpo-1e-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
meseca-20062024-c1-dpo-1e-v2-mkmlizer: Downloaded to shared memory in 44.307s
meseca-20062024-c1-dpo-1e-v2-mkmlizer: quantizing model to /dev/shm/model_cache
meseca-20062024-c1-dpo-1e-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
meseca-20062024-c1-dpo-1e-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 123.11it/s] Loading 0: 10%|█ | 30/291 [00:00<00:01, 138.47it/s] Loading 0: 15%|█▌ | 44/291 [00:00<00:01, 134.15it/s] Loading 0: 20%|█▉ | 58/291 [00:00<00:01, 133.07it/s] Loading 0: 26%|██▌ | 75/291 [00:00<00:01, 138.01it/s] Loading 0: 31%|███ | 89/291 [00:00<00:02, 74.60it/s] Loading 0: 35%|███▌ | 103/291 [00:01<00:02, 86.25it/s] Loading 0: 41%|████ | 120/291 [00:01<00:01, 101.29it/s] Loading 0: 46%|████▌ | 133/291 [00:01<00:01, 107.16it/s] Loading 0: 51%|█████ | 148/291 [00:01<00:01, 114.57it/s] Loading 0: 57%|█████▋ | 165/291 [00:01<00:01, 123.87it/s] Loading 0: 62%|██████▏ | 180/291 [00:01<00:00, 126.29it/s] Loading 0: 67%|██████▋ | 194/291 [00:01<00:01, 77.94it/s] Loading 0: 73%|███████▎ | 211/291 [00:02<00:00, 92.89it/s] Loading 0: 78%|███████▊ | 228/291 [00:02<00:00, 106.02it/s] Loading 0: 83%|████████▎ | 241/291 [00:02<00:00, 110.38it/s] Loading 0: 88%|████████▊ | 256/291 [00:02<00:00, 116.43it/s] Loading 0: 94%|█████████▍| 273/291 [00:02<00:00, 125.69it/s] Loading 0: 99%|█████████▊| 287/291 [00:07<00:00, 8.74it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
meseca-20062024-c1-dpo-1e-v2-mkmlizer: quantized model in 23.117s
meseca-20062024-c1-dpo-1e-v2-mkmlizer: Processed model meseca/20062024-c1-dpo-1e in 69.884s
meseca-20062024-c1-dpo-1e-v2-mkmlizer: creating bucket guanaco-mkml-models
meseca-20062024-c1-dpo-1e-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
meseca-20062024-c1-dpo-1e-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/meseca-20062024-c1-dpo-1e-v2
meseca-20062024-c1-dpo-1e-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/meseca-20062024-c1-dpo-1e-v2/config.json
meseca-20062024-c1-dpo-1e-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/meseca-20062024-c1-dpo-1e-v2/special_tokens_map.json
meseca-20062024-c1-dpo-1e-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/meseca-20062024-c1-dpo-1e-v2/tokenizer_config.json
meseca-20062024-c1-dpo-1e-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/meseca-20062024-c1-dpo-1e-v2/tokenizer.json
meseca-20062024-c1-dpo-1e-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/meseca-20062024-c1-dpo-1e-v2/flywheel_model.0.safetensors
meseca-20062024-c1-dpo-1e-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
meseca-20062024-c1-dpo-1e-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.
meseca-20062024-c1-dpo-1e-v2-mkmlizer: warnings.warn(
meseca-20062024-c1-dpo-1e-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.
meseca-20062024-c1-dpo-1e-v2-mkmlizer: warnings.warn(
meseca-20062024-c1-dpo-1e-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.
meseca-20062024-c1-dpo-1e-v2-mkmlizer: warnings.warn(
meseca-20062024-c1-dpo-1e-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()
meseca-20062024-c1-dpo-1e-v2-mkmlizer: return self.fget.__get__(instance, owner)()
meseca-20062024-c1-dpo-1e-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
meseca-20062024-c1-dpo-1e-v2-mkmlizer: Saving duration: 0.515s
meseca-20062024-c1-dpo-1e-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 13.181s
meseca-20062024-c1-dpo-1e-v2-mkmlizer: creating bucket guanaco-reward-models
meseca-20062024-c1-dpo-1e-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
meseca-20062024-c1-dpo-1e-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/meseca-20062024-c1-dpo-1e-v2_reward
meseca-20062024-c1-dpo-1e-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/meseca-20062024-c1-dpo-1e-v2_reward/config.json
meseca-20062024-c1-dpo-1e-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/meseca-20062024-c1-dpo-1e-v2_reward/special_tokens_map.json
meseca-20062024-c1-dpo-1e-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/meseca-20062024-c1-dpo-1e-v2_reward/tokenizer_config.json
meseca-20062024-c1-dpo-1e-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/meseca-20062024-c1-dpo-1e-v2_reward/merges.txt
meseca-20062024-c1-dpo-1e-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/meseca-20062024-c1-dpo-1e-v2_reward/vocab.json
meseca-20062024-c1-dpo-1e-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/meseca-20062024-c1-dpo-1e-v2_reward/tokenizer.json
meseca-20062024-c1-dpo-1e-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/meseca-20062024-c1-dpo-1e-v2_reward/reward.tensors
Connection pool is full, discarding connection: %s
Job meseca-20062024-c1-dpo-1e-v2-mkmlizer completed after 124.86s with status: succeeded
Stopping job with name meseca-20062024-c1-dpo-1e-v2-mkmlizer
Pipeline stage MKMLizer completed in 126.09s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service meseca-20062024-c1-dpo-1e-v2
Waiting for inference service meseca-20062024-c1-dpo-1e-v2 to be ready
Inference service meseca-20062024-c1-dpo-1e-v2 ready after 50.27378511428833s
Pipeline stage ISVCDeployer completed in 57.09s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2532706260681152s
Received healthy response to inference request in 1.3469786643981934s
Received healthy response to inference request in 1.3319981098175049s
Received healthy response to inference request in 1.2728443145751953s
Received healthy response to inference request in 1.4146525859832764s
5 requests
0 failed requests
5th percentile: 1.2846750736236572
10th percentile: 1.296505832672119
20th percentile: 1.320167350769043
30th percentile: 1.3349942207336425
40th percentile: 1.340986442565918
50th percentile: 1.3469786643981934
60th percentile: 1.3740482330322266
70th percentile: 1.4011178016662598
80th percentile: 1.5823761940002443
90th percentile: 1.9178234100341798
95th percentile: 2.0855470180511473
99th percentile: 2.2197259044647217
mean time: 1.523948860168457
Pipeline stage StressChecker completed in 8.32s
meseca-20062024-c1-dpo-1e_v2 status is now deployed due to DeploymentManager action
meseca-20062024-c1-dpo-1e_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics