submission_id: meseca-02072024-v1-1e_v1
developer_uid: nguyenzzz
status: inactive
model_repo: meseca/02072024-v1-1e
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.95, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|end_header_id|>,', '<|eot_id|>,', '\n\n{user_name}'], 'max_input_tokens': 1024, 'best_of': 8, '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: 2024-07-03T02:20:58+00:00
model_name: meseca-02072024-v1-1e_v1
model_group: meseca/02072024-v1-1e
num_battles: 12641
num_wins: 6251
celo_rating: 1179.93
propriety_score: 0.7155331654072208
propriety_total_count: 5955.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
display_name: meseca-02072024-v1-1e_v1
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: 0.4945020172454711
Resubmit model
Running pipeline stage MKMLizer
Starting job with name meseca-02072024-v1-1e-v1-mkmlizer
Waiting for job on meseca-02072024-v1-1e-v1-mkmlizer to finish
meseca-02072024-v1-1e-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
meseca-02072024-v1-1e-v1-mkmlizer: ║ _____ __ __ ║
meseca-02072024-v1-1e-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
meseca-02072024-v1-1e-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
meseca-02072024-v1-1e-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
meseca-02072024-v1-1e-v1-mkmlizer: ║ /___/ ║
meseca-02072024-v1-1e-v1-mkmlizer: ║ ║
meseca-02072024-v1-1e-v1-mkmlizer: ║ Version: 0.8.14 ║
meseca-02072024-v1-1e-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
meseca-02072024-v1-1e-v1-mkmlizer: ║ https://mk1.ai ║
meseca-02072024-v1-1e-v1-mkmlizer: ║ ║
meseca-02072024-v1-1e-v1-mkmlizer: ║ The license key for the current software has been verified as ║
meseca-02072024-v1-1e-v1-mkmlizer: ║ belonging to: ║
meseca-02072024-v1-1e-v1-mkmlizer: ║ ║
meseca-02072024-v1-1e-v1-mkmlizer: ║ Chai Research Corp. ║
meseca-02072024-v1-1e-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
meseca-02072024-v1-1e-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
meseca-02072024-v1-1e-v1-mkmlizer: ║ ║
meseca-02072024-v1-1e-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission neversleep-noromaid-v0_8068_v111: ('http://neversleep-noromaid-v0-8068-v111-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:56734->127.0.0.1:8080: read: connection reset by peer\n')
meseca-02072024-v1-1e-v1-mkmlizer: Downloaded to shared memory in 43.978s
meseca-02072024-v1-1e-v1-mkmlizer: quantizing model to /dev/shm/model_cache
meseca-02072024-v1-1e-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
meseca-02072024-v1-1e-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:02, 121.78it/s] Loading 0: 11%|█ | 31/291 [00:00<00:01, 145.38it/s] Loading 0: 16%|█▋ | 48/291 [00:00<00:01, 154.93it/s] Loading 0: 22%|██▏ | 64/291 [00:00<00:01, 153.64it/s] Loading 0: 27%|██▋ | 80/291 [00:00<00:01, 147.85it/s] Loading 0: 33%|███▎ | 95/291 [00:00<00:02, 75.65it/s] Loading 0: 38%|███▊ | 112/291 [00:01<00:01, 90.81it/s] Loading 0: 44%|████▍ | 129/291 [00:01<00:01, 105.09it/s] Loading 0: 49%|████▉ | 143/291 [00:01<00:01, 111.00it/s] Loading 0: 54%|█████▍ | 157/291 [00:01<00:01, 117.26it/s] Loading 0: 59%|█████▉ | 173/291 [00:01<00:00, 124.85it/s] Loading 0: 64%|██████▍ | 187/291 [00:01<00:01, 75.18it/s] Loading 0: 69%|██████▉ | 201/291 [00:01<00:01, 84.11it/s] Loading 0: 74%|███████▍ | 215/291 [00:02<00:00, 94.85it/s] Loading 0: 79%|███████▉ | 230/291 [00:02<00:00, 103.60it/s] Loading 0: 85%|████████▍ | 247/291 [00:02<00:00, 116.75it/s] Loading 0: 91%|█████████ | 264/291 [00:02<00:00, 128.15it/s] Loading 0: 96%|█████████▌| 279/291 [00:02<00:00, 132.09it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
meseca-02072024-v1-1e-v1-mkmlizer: creating bucket guanaco-mkml-models
meseca-02072024-v1-1e-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
meseca-02072024-v1-1e-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/meseca-02072024-v1-1e-v1
meseca-02072024-v1-1e-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/meseca-02072024-v1-1e-v1/config.json
meseca-02072024-v1-1e-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/meseca-02072024-v1-1e-v1/special_tokens_map.json
meseca-02072024-v1-1e-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/meseca-02072024-v1-1e-v1/tokenizer_config.json
meseca-02072024-v1-1e-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/meseca-02072024-v1-1e-v1/tokenizer.json
meseca-02072024-v1-1e-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/meseca-02072024-v1-1e-v1/flywheel_model.0.safetensors
meseca-02072024-v1-1e-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
meseca-02072024-v1-1e-v1-mkmlizer: /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.
meseca-02072024-v1-1e-v1-mkmlizer: warnings.warn(
meseca-02072024-v1-1e-v1-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`.
meseca-02072024-v1-1e-v1-mkmlizer: warnings.warn(
meseca-02072024-v1-1e-v1-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.
meseca-02072024-v1-1e-v1-mkmlizer: warnings.warn(
meseca-02072024-v1-1e-v1-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-v1-mkmlizer: warnings.warn(
meseca-02072024-v1-1e-v1-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-v1-mkmlizer: return self.fget.__get__(instance, owner)()
meseca-02072024-v1-1e-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
meseca-02072024-v1-1e-v1-mkmlizer: Saving duration: 0.398s
meseca-02072024-v1-1e-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 8.540s
meseca-02072024-v1-1e-v1-mkmlizer: creating bucket guanaco-reward-models
meseca-02072024-v1-1e-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
meseca-02072024-v1-1e-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/meseca-02072024-v1-1e-v1_reward
meseca-02072024-v1-1e-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/meseca-02072024-v1-1e-v1_reward/special_tokens_map.json
meseca-02072024-v1-1e-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/meseca-02072024-v1-1e-v1_reward/config.json
meseca-02072024-v1-1e-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/meseca-02072024-v1-1e-v1_reward/tokenizer_config.json
meseca-02072024-v1-1e-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/meseca-02072024-v1-1e-v1_reward/merges.txt
meseca-02072024-v1-1e-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/meseca-02072024-v1-1e-v1_reward/vocab.json
meseca-02072024-v1-1e-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/meseca-02072024-v1-1e-v1_reward/tokenizer.json
meseca-02072024-v1-1e-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/meseca-02072024-v1-1e-v1_reward/reward.tensors
Job meseca-02072024-v1-1e-v1-mkmlizer completed after 104.73s with status: succeeded
Stopping job with name meseca-02072024-v1-1e-v1-mkmlizer
Pipeline stage MKMLizer completed in 105.69s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.14s
Running pipeline stage ISVCDeployer
Creating inference service meseca-02072024-v1-1e-v1
Waiting for inference service meseca-02072024-v1-1e-v1 to be ready
Inference service meseca-02072024-v1-1e-v1 ready after 40.21308922767639s
Pipeline stage ISVCDeployer completed in 47.23s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0013632774353027s
Received healthy response to inference request in 1.2088816165924072s
Received healthy response to inference request in 1.2282376289367676s
Received healthy response to inference request in 1.2264363765716553s
Received healthy response to inference request in 1.286271572113037s
5 requests
0 failed requests
5th percentile: 1.2123925685882568
10th percentile: 1.2159035205841064
20th percentile: 1.2229254245758057
30th percentile: 1.2267966270446777
40th percentile: 1.2275171279907227
50th percentile: 1.2282376289367676
60th percentile: 1.2514512062072753
70th percentile: 1.2746647834777831
80th percentile: 1.4292899131774903
90th percentile: 1.7153265953063965
95th percentile: 1.8583449363708495
99th percentile: 1.972759609222412
mean time: 1.390238094329834
Pipeline stage StressChecker completed in 7.70s
meseca-02072024-v1-1e_v1 status is now deployed due to DeploymentManager action
meseca-02072024-v1-1e_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics