submission_id: cycy233-misllm-v6-9-1-5_v1
developer_uid: shiroe40
status: inactive
model_repo: cycy233/misllm_v6.9.1.5
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': 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: 2024-06-13T02:00:21+00:00
model_name: base_f
model_eval_status: success
model_group: cycy233/misllm_v6.9.1.5
num_battles: 33618
num_wins: 16009
celo_rating: 1165.25
propriety_score: 0.6832816270251637
propriety_total_count: 14505.0
submission_type: basic
model_architecture: MistralForCausalLM
model_num_parameters: 7241732096.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: base_f
ineligible_reason: None
language_model: cycy233/misllm_v6.9.1.5
model_size: 7B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-12
win_ratio: 0.4762032244630853
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-misllm-v6-9-1-5-v1-mkmlizer
Waiting for job on cycy233-misllm-v6-9-1-5-v1-mkmlizer to finish
Stopping job with name cycy233-misllm-v6-9-1-5-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name cycy233-misllm-v6-9-1-5-v1-mkmlizer
Waiting for job on cycy233-misllm-v6-9-1-5-v1-mkmlizer to finish
cycy233-misllm-v6-9-1-5-v1-mkmlizer: Downloaded to shared memory in 36.713s
cycy233-misllm-v6-9-1-5-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-misllm-v6-9-1-5-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-misllm-v6-9-1-5-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 34%|███▎ | 98/291 [00:01<00:02, 87.71it/s] Loading 0: 70%|███████ | 204/291 [00:02<00:00, 97.77it/s] Loading 0: 100%|██████████| 291/291 [00:03<00:00, 78.61it/s] You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
cycy233-misllm-v6-9-1-5-v1-mkmlizer: quantized model in 15.699s
cycy233-misllm-v6-9-1-5-v1-mkmlizer: Processed model cycy233/misllm_v6.9.1.5 in 54.823s
cycy233-misllm-v6-9-1-5-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-misllm-v6-9-1-5-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-misllm-v6-9-1-5-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-misllm-v6-9-1-5-v1
cycy233-misllm-v6-9-1-5-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-misllm-v6-9-1-5-v1/config.json
cycy233-misllm-v6-9-1-5-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-misllm-v6-9-1-5-v1/tokenizer_config.json
cycy233-misllm-v6-9-1-5-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-misllm-v6-9-1-5-v1/special_tokens_map.json
cycy233-misllm-v6-9-1-5-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-misllm-v6-9-1-5-v1/tokenizer.json
cycy233-misllm-v6-9-1-5-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cycy233-misllm-v6-9-1-5-v1/tokenizer.model
cycy233-misllm-v6-9-1-5-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-misllm-v6-9-1-5-v1/flywheel_model.0.safetensors
cycy233-misllm-v6-9-1-5-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-misllm-v6-9-1-5-v1-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-misllm-v6-9-1-5-v1-mkmlizer: warnings.warn(
cycy233-misllm-v6-9-1-5-v1-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-misllm-v6-9-1-5-v1-mkmlizer: warnings.warn(
cycy233-misllm-v6-9-1-5-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.
cycy233-misllm-v6-9-1-5-v1-mkmlizer: warnings.warn(
cycy233-misllm-v6-9-1-5-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()
cycy233-misllm-v6-9-1-5-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cycy233-misllm-v6-9-1-5-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-misllm-v6-9-1-5-v1-mkmlizer: Saving duration: 0.417s
cycy233-misllm-v6-9-1-5-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.117s
cycy233-misllm-v6-9-1-5-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-misllm-v6-9-1-5-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-misllm-v6-9-1-5-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-misllm-v6-9-1-5-v1_reward
cycy233-misllm-v6-9-1-5-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-misllm-v6-9-1-5-v1_reward/config.json
cycy233-misllm-v6-9-1-5-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-misllm-v6-9-1-5-v1_reward/vocab.json
cycy233-misllm-v6-9-1-5-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-misllm-v6-9-1-5-v1_reward/merges.txt
cycy233-misllm-v6-9-1-5-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-misllm-v6-9-1-5-v1_reward/special_tokens_map.json
cycy233-misllm-v6-9-1-5-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-misllm-v6-9-1-5-v1_reward/tokenizer_config.json
cycy233-misllm-v6-9-1-5-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-misllm-v6-9-1-5-v1_reward/tokenizer.json
cycy233-misllm-v6-9-1-5-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-misllm-v6-9-1-5-v1_reward/reward.tensors
Job cycy233-misllm-v6-9-1-5-v1-mkmlizer completed after 87.11s with status: succeeded
Stopping job with name cycy233-misllm-v6-9-1-5-v1-mkmlizer
Pipeline stage MKMLizer completed in 92.18s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-misllm-v6-9-1-5-v1
Waiting for inference service cycy233-misllm-v6-9-1-5-v1 to be ready
Inference service cycy233-misllm-v6-9-1-5-v1 ready after 40.30658459663391s
Pipeline stage ISVCDeployer completed in 47.62s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0367932319641113s
Received healthy response to inference request in 1.1878466606140137s
Received healthy response to inference request in 1.1591641902923584s
Received healthy response to inference request in 1.1337990760803223s
Received healthy response to inference request in 1.201301097869873s
5 requests
0 failed requests
5th percentile: 1.1388720989227294
10th percentile: 1.1439451217651366
20th percentile: 1.1540911674499512
30th percentile: 1.1649006843566894
40th percentile: 1.1763736724853515
50th percentile: 1.1878466606140137
60th percentile: 1.1932284355163574
70th percentile: 1.198610210418701
80th percentile: 1.3683995246887208
90th percentile: 1.7025963783264162
95th percentile: 1.8696948051452635
99th percentile: 2.0033735466003417
mean time: 1.3437808513641358
Pipeline stage StressChecker completed in 7.32s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.02s
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
cycy233-misllm-v6-9-1-5_v1 status is now deployed due to DeploymentManager action
cycy233-misllm-v6-9-1-5_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics