submission_id: nitral-ai-hathor-l3-8b-v-02_v5
developer_uid: Nitral-AI
status: inactive
model_repo: Nitral-AI/Hathor-L3-8B-v.02
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.08, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|end_header_id|>', '<|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: 2024-06-11T21:40:37+00:00
model_name: nitral-ai-hathor-l3-8b-v-02_ok
model_eval_status: success
model_group: Nitral-AI/Hathor-L3-8B-v
num_battles: 15653
num_wins: 8292
celo_rating: 1214.35
propriety_score: 0.7014483725276437
propriety_total_count: 6421.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: nitral-ai-hathor-l3-8b-v-02_ok
ineligible_reason: None
language_model: Nitral-AI/Hathor-L3-8B-v.02
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-11
win_ratio: 0.5297387082348431
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nitral-ai-hathor-l3-8b-v-02-v5-mkmlizer
Waiting for job on nitral-ai-hathor-l3-8b-v-02-v5-mkmlizer to finish
nitral-ai-hathor-l3-8b-v-02-v5-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.
nitral-ai-hathor-l3-8b-v-02-v5-mkmlizer: warnings.warn(warning_message, FutureWarning)
nitral-ai-hathor-l3-8b-v-02-v5-mkmlizer: Downloaded to shared memory in 32.967s
nitral-ai-hathor-l3-8b-v-02-v5-mkmlizer: quantizing model to /dev/shm/model_cache
nitral-ai-hathor-l3-8b-v-02-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nitral-ai-hathor-l3-8b-v-02-v5-mkmlizer: quantized model in 18.694s
nitral-ai-hathor-l3-8b-v-02-v5-mkmlizer: Processed model Nitral-AI/Hathor-L3-8B-v.02 in 52.660s
nitral-ai-hathor-l3-8b-v-02-v5-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-hathor-l3-8b-v-02-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-hathor-l3-8b-v-02-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-02-v5
nitral-ai-hathor-l3-8b-v-02-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-02-v5/config.json
nitral-ai-hathor-l3-8b-v-02-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-02-v5/special_tokens_map.json
nitral-ai-hathor-l3-8b-v-02-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-02-v5/tokenizer_config.json
nitral-ai-hathor-l3-8b-v-02-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-02-v5/tokenizer.json
nitral-ai-hathor-l3-8b-v-02-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-02-v5/flywheel_model.0.safetensors
nitral-ai-hathor-l3-8b-v-02-v5-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
nitral-ai-hathor-l3-8b-v-02-v5-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.
nitral-ai-hathor-l3-8b-v-02-v5-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-02-v5-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.
nitral-ai-hathor-l3-8b-v-02-v5-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-02-v5-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()
nitral-ai-hathor-l3-8b-v-02-v5-mkmlizer: return self.fget.__get__(instance, owner)()
nitral-ai-hathor-l3-8b-v-02-v5-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nitral-ai-hathor-l3-8b-v-02-v5-mkmlizer: Saving duration: 0.278s
nitral-ai-hathor-l3-8b-v-02-v5-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.155s
nitral-ai-hathor-l3-8b-v-02-v5-mkmlizer: creating bucket guanaco-reward-models
nitral-ai-hathor-l3-8b-v-02-v5-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nitral-ai-hathor-l3-8b-v-02-v5-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-02-v5_reward
nitral-ai-hathor-l3-8b-v-02-v5-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-02-v5_reward/config.json
nitral-ai-hathor-l3-8b-v-02-v5-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-02-v5_reward/special_tokens_map.json
nitral-ai-hathor-l3-8b-v-02-v5-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-02-v5_reward/tokenizer_config.json
nitral-ai-hathor-l3-8b-v-02-v5-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-02-v5_reward/merges.txt
nitral-ai-hathor-l3-8b-v-02-v5-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-02-v5_reward/vocab.json
nitral-ai-hathor-l3-8b-v-02-v5-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-02-v5_reward/tokenizer.json
nitral-ai-hathor-l3-8b-v-02-v5-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-02-v5_reward/reward.tensors
Job nitral-ai-hathor-l3-8b-v-02-v5-mkmlizer completed after 124.75s with status: succeeded
Stopping job with name nitral-ai-hathor-l3-8b-v-02-v5-mkmlizer
Pipeline stage MKMLizer completed in 125.12s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service nitral-ai-hathor-l3-8b-v-02-v5
Waiting for inference service nitral-ai-hathor-l3-8b-v-02-v5 to be ready
Inference service nitral-ai-hathor-l3-8b-v-02-v5 ready after 40.306658029556274s
Pipeline stage ISVCDeployer completed in 45.87s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2049341201782227s
Received healthy response to inference request in 1.3377785682678223s
Received healthy response to inference request in 1.2970468997955322s
Received healthy response to inference request in 1.2837634086608887s
Received healthy response to inference request in 1.3487708568572998s
5 requests
0 failed requests
5th percentile: 1.2864201068878174
10th percentile: 1.289076805114746
20th percentile: 1.2943902015686035
30th percentile: 1.3051932334899903
40th percentile: 1.3214859008789062
50th percentile: 1.3377785682678223
60th percentile: 1.3421754837036133
70th percentile: 1.3465723991394043
80th percentile: 1.5200035095214846
90th percentile: 1.8624688148498536
95th percentile: 2.033701467514038
99th percentile: 2.170687589645386
mean time: 1.4944587707519532
Pipeline stage StressChecker completed in 8.08s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.04s
M-Eval Dataset for topic stay_in_character is loaded
nitral-ai-hathor-l3-8b-v-02_v5 status is now deployed due to DeploymentManager action
nitral-ai-hathor-l3-8b-v-02_v5 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics