submission_id: cycy233-l3-base-v0-e2-5_v2
developer_uid: shiroe40
status: inactive
model_repo: cycy233/L3-base-v0-e2.5
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
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': True}
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': True}
timestamp: 2024-06-21T02:28:41+00:00
model_name: base
model_group: cycy233/L3-base-v0-e2.5
num_battles: 11149
num_wins: 5644
celo_rating: 1198.08
propriety_score: 0.7043921997448515
propriety_total_count: 5487.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: base
ineligible_reason: None
language_model: cycy233/L3-base-v0-e2.5
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-20
win_ratio: 0.5062337429365863
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-l3-base-v0-e2-5-v2-mkmlizer
Waiting for job on cycy233-l3-base-v0-e2-5-v2-mkmlizer to finish
Stopping job with name cycy233-l3-base-v0-e2-5-v2-mkmlizer
%s, retrying in %s seconds...
Starting job with name cycy233-l3-base-v0-e2-5-v2-mkmlizer
Waiting for job on cycy233-l3-base-v0-e2-5-v2-mkmlizer to finish
cycy233-l3-base-v0-e2-5-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:02, 73.82it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 85.55it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 125.17it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-base-v0-e2-5-v2-mkmlizer: quantized model in 19.370s
cycy233-l3-base-v0-e2-5-v2-mkmlizer: Processed model cycy233/L3-base-v0-e2.5 in 39.864s
cycy233-l3-base-v0-e2-5-v2-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-base-v0-e2-5-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-base-v0-e2-5-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-base-v0-e2-5-v2
cycy233-l3-base-v0-e2-5-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-base-v0-e2-5-v2/config.json
cycy233-l3-base-v0-e2-5-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-base-v0-e2-5-v2/special_tokens_map.json
cycy233-l3-base-v0-e2-5-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-base-v0-e2-5-v2/tokenizer_config.json
cycy233-l3-base-v0-e2-5-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-base-v0-e2-5-v2/tokenizer.json
cycy233-l3-base-v0-e2-5-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-l3-base-v0-e2-5-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.
cycy233-l3-base-v0-e2-5-v2-mkmlizer: warnings.warn(
cycy233-l3-base-v0-e2-5-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.
cycy233-l3-base-v0-e2-5-v2-mkmlizer: warnings.warn(
cycy233-l3-base-v0-e2-5-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.
cycy233-l3-base-v0-e2-5-v2-mkmlizer: warnings.warn(
cycy233-l3-base-v0-e2-5-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()
cycy233-l3-base-v0-e2-5-v2-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-l3-base-v0-e2-5-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-base-v0-e2-5-v2-mkmlizer: Saving duration: 0.305s
cycy233-l3-base-v0-e2-5-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.752s
cycy233-l3-base-v0-e2-5-v2-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-base-v0-e2-5-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-base-v0-e2-5-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-base-v0-e2-5-v2_reward
cycy233-l3-base-v0-e2-5-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-base-v0-e2-5-v2_reward/config.json
cycy233-l3-base-v0-e2-5-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-base-v0-e2-5-v2_reward/special_tokens_map.json
cycy233-l3-base-v0-e2-5-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-base-v0-e2-5-v2_reward/tokenizer_config.json
cycy233-l3-base-v0-e2-5-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-base-v0-e2-5-v2_reward/reward.tensors
Job cycy233-l3-base-v0-e2-5-v2-mkmlizer completed after 72.77s with status: succeeded
Stopping job with name cycy233-l3-base-v0-e2-5-v2-mkmlizer
Pipeline stage MKMLizer completed in 73.64s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-base-v0-e2-5-v2
Waiting for inference service cycy233-l3-base-v0-e2-5-v2 to be ready
Inference service cycy233-l3-base-v0-e2-5-v2 ready after 100.47118353843689s
Pipeline stage ISVCDeployer completed in 106.21s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.2480838298797607s
Received healthy response to inference request in 1.2025766372680664s
Received healthy response to inference request in 1.2047948837280273s
Received healthy response to inference request in 1.2285311222076416s
Received healthy response to inference request in 1.139463186264038s
5 requests
0 failed requests
5th percentile: 1.1520858764648438
10th percentile: 1.1647085666656494
20th percentile: 1.1899539470672607
30th percentile: 1.2030202865600585
40th percentile: 1.203907585144043
50th percentile: 1.2047948837280273
60th percentile: 1.214289379119873
70th percentile: 1.2237838745117187
80th percentile: 1.6324416637420658
90th percentile: 2.4402627468109133
95th percentile: 2.8441732883453366
99th percentile: 3.167301721572876
mean time: 1.604689931869507
Pipeline stage StressChecker completed in 8.74s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
cycy233-l3-base-v0-e2-5_v2 status is now deployed due to DeploymentManager action
cycy233-l3-base-v0-e2-5_v2 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics