submission_id: meseca-02072024-v1-1e_v2
developer_uid: nguyenzzz
status: inactive
model_repo: meseca/02072024-v1-1e
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.8, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 50, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|end_header_id|>,', '<|eot_id|>,', '\n\n{user_name}'], '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\nCurrently, your role is {bot_name}, described in detail below. As {bot_name}, continue the narrative exchange with {user_name}\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: 2024-07-03T03:10:59+00:00
model_name: meseca-02072024-v1-1e_v2
model_group: meseca/02072024-v1-1e
num_battles: 12573
num_wins: 6202
celo_rating: 1175.89
propriety_score: 0.6973018549747049
propriety_total_count: 5930.0
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-02072024-v1-1e_v2
ineligible_reason: None
language_model: meseca/02072024-v1-1e
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-07-02
win_ratio: 0.493279249184761
Resubmit model
Running pipeline stage MKMLizer
Starting job with name meseca-02072024-v1-1e-v2-mkmlizer
Waiting for job on meseca-02072024-v1-1e-v2-mkmlizer to finish
meseca-02072024-v1-1e-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
meseca-02072024-v1-1e-v2-mkmlizer: ║ _____ __ __ ║
meseca-02072024-v1-1e-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
meseca-02072024-v1-1e-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
meseca-02072024-v1-1e-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
meseca-02072024-v1-1e-v2-mkmlizer: ║ /___/ ║
meseca-02072024-v1-1e-v2-mkmlizer: ║ ║
meseca-02072024-v1-1e-v2-mkmlizer: ║ Version: 0.8.14 ║
meseca-02072024-v1-1e-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
meseca-02072024-v1-1e-v2-mkmlizer: ║ https://mk1.ai ║
meseca-02072024-v1-1e-v2-mkmlizer: ║ ║
meseca-02072024-v1-1e-v2-mkmlizer: ║ The license key for the current software has been verified as ║
meseca-02072024-v1-1e-v2-mkmlizer: ║ belonging to: ║
meseca-02072024-v1-1e-v2-mkmlizer: ║ ║
meseca-02072024-v1-1e-v2-mkmlizer: ║ Chai Research Corp. ║
meseca-02072024-v1-1e-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
meseca-02072024-v1-1e-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
meseca-02072024-v1-1e-v2-mkmlizer: ║ ║
meseca-02072024-v1-1e-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
meseca-02072024-v1-1e-v2-mkmlizer: Downloaded to shared memory in 45.191s
meseca-02072024-v1-1e-v2-mkmlizer: quantizing model to /dev/shm/model_cache
meseca-02072024-v1-1e-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
meseca-02072024-v1-1e-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 3%|▎ | 9/291 [00:00<00:03, 85.95it/s] Loading 0: 6%|▌ | 18/291 [00:00<00:03, 88.07it/s] Loading 0: 10%|█ | 30/291 [00:00<00:02, 90.17it/s] Loading 0: 13%|█▎ | 39/291 [00:00<00:03, 79.61it/s] Loading 0: 16%|█▋ | 48/291 [00:00<00:03, 77.86it/s] Loading 0: 20%|█▉ | 57/291 [00:00<00:03, 73.85it/s] Loading 0: 22%|██▏ | 65/291 [00:00<00:03, 72.66it/s] Loading 0: 25%|██▌ | 73/291 [00:01<00:03, 56.59it/s] Loading 0: 27%|██▋ | 80/291 [00:01<00:03, 59.58it/s] Loading 0: 30%|██▉ | 87/291 [00:01<00:06, 30.43it/s] Loading 0: 33%|███▎ | 95/291 [00:01<00:05, 37.21it/s] Loading 0: 36%|███▌ | 104/291 [00:01<00:04, 44.66it/s] Loading 0: 39%|███▉ | 113/291 [00:02<00:03, 50.10it/s] Loading 0: 42%|████▏ | 121/291 [00:02<00:03, 55.31it/s] Loading 0: 45%|████▌ | 131/291 [00:02<00:02, 61.22it/s] Loading 0: 48%|████▊ | 140/291 [00:02<00:02, 65.62it/s] Loading 0: 51%|█████ | 149/291 [00:02<00:02, 67.51it/s] Loading 0: 54%|█████▍ | 158/291 [00:02<00:01, 71.86it/s] Loading 0: 57%|█████▋ | 167/291 [00:02<00:01, 75.44it/s] Loading 0: 62%|██████▏ | 180/291 [00:02<00:01, 83.93it/s] Loading 0: 65%|██████▍ | 189/291 [00:03<00:02, 44.27it/s] Loading 0: 68%|██████▊ | 198/291 [00:03<00:01, 51.16it/s] Loading 0: 71%|███████ | 207/291 [00:03<00:01, 57.94it/s] Loading 0: 75%|███████▍ | 217/291 [00:03<00:01, 66.52it/s] Loading 0: 78%|███████▊ | 226/291 [00:03<00:00, 71.13it/s] Loading 0: 81%|████████ | 235/291 [00:03<00:00, 74.13it/s] Loading 0: 84%|████████▍ | 244/291 [00:03<00:00, 78.10it/s] Loading 0: 87%|████████▋ | 253/291 [00:04<00:00, 75.02it/s] Loading 0: 90%|█████████ | 262/291 [00:04<00:00, 76.44it/s] Loading 0: 93%|█████████▎| 271/291 [00:04<00:00, 76.19it/s] Loading 0: 97%|█████████▋| 281/291 [00:04<00:00, 77.73it/s] Loading 0: 99%|█████████▉| 289/291 [00:11<00:00, 4.18it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
meseca-02072024-v1-1e-v2-mkmlizer: quantized model in 31.557s
meseca-02072024-v1-1e-v2-mkmlizer: Processed model meseca/02072024-v1-1e in 76.748s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
meseca-02072024-v1-1e-v2-mkmlizer: creating bucket guanaco-mkml-models
meseca-02072024-v1-1e-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
meseca-02072024-v1-1e-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/meseca-02072024-v1-1e-v2
meseca-02072024-v1-1e-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/meseca-02072024-v1-1e-v2/config.json
meseca-02072024-v1-1e-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/meseca-02072024-v1-1e-v2/tokenizer_config.json
meseca-02072024-v1-1e-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/meseca-02072024-v1-1e-v2/special_tokens_map.json
meseca-02072024-v1-1e-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/meseca-02072024-v1-1e-v2/tokenizer.json
meseca-02072024-v1-1e-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/meseca-02072024-v1-1e-v2/flywheel_model.0.safetensors
meseca-02072024-v1-1e-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-02072024-v1-1e-v2-mkmlizer: warnings.warn(
meseca-02072024-v1-1e-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-02072024-v1-1e-v2-mkmlizer: return self.fget.__get__(instance, owner)()
meseca-02072024-v1-1e-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
meseca-02072024-v1-1e-v2-mkmlizer: Saving duration: 0.437s
meseca-02072024-v1-1e-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 13.224s
meseca-02072024-v1-1e-v2-mkmlizer: creating bucket guanaco-reward-models
meseca-02072024-v1-1e-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
meseca-02072024-v1-1e-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/meseca-02072024-v1-1e-v2_reward
meseca-02072024-v1-1e-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/meseca-02072024-v1-1e-v2_reward/special_tokens_map.json
meseca-02072024-v1-1e-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/meseca-02072024-v1-1e-v2_reward/config.json
meseca-02072024-v1-1e-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/meseca-02072024-v1-1e-v2_reward/merges.txt
meseca-02072024-v1-1e-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/meseca-02072024-v1-1e-v2_reward/tokenizer_config.json
meseca-02072024-v1-1e-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/meseca-02072024-v1-1e-v2_reward/vocab.json
meseca-02072024-v1-1e-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/meseca-02072024-v1-1e-v2_reward/tokenizer.json
meseca-02072024-v1-1e-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/meseca-02072024-v1-1e-v2_reward/reward.tensors
Job meseca-02072024-v1-1e-v2-mkmlizer completed after 124.3s with status: succeeded
Stopping job with name meseca-02072024-v1-1e-v2-mkmlizer
Pipeline stage MKMLizer completed in 125.75s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service meseca-02072024-v1-1e-v2
Waiting for inference service meseca-02072024-v1-1e-v2 to be ready
Inference service meseca-02072024-v1-1e-v2 ready after 120.55441641807556s
Pipeline stage ISVCDeployer completed in 127.52s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1414551734924316s
Received healthy response to inference request in 1.3034327030181885s
Received healthy response to inference request in 1.2751319408416748s
Received healthy response to inference request in 1.3423478603363037s
Received healthy response to inference request in 1.3195385932922363s
5 requests
0 failed requests
5th percentile: 1.2807920932769776
10th percentile: 1.2864522457122802
20th percentile: 1.2977725505828857
30th percentile: 1.306653881072998
40th percentile: 1.3130962371826171
50th percentile: 1.3195385932922363
60th percentile: 1.3286623001098632
70th percentile: 1.3377860069274903
80th percentile: 1.5021693229675295
90th percentile: 1.8218122482299806
95th percentile: 1.9816337108612059
99th percentile: 2.1094908809661863
mean time: 1.476381254196167
Pipeline stage StressChecker completed in 8.79s
meseca-02072024-v1-1e_v2 status is now deployed due to DeploymentManager action
meseca-02072024-v1-1e_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics