submission_id: hastagaras-anjir-8b-l3-m_6487_v3
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Anjir-8B-L3-MK.V-BJ1
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.05, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, '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': "<|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: 2024-06-10T23:28:02+00:00
model_name: 1
model_eval_status: success
model_group: Hastagaras/Anjir-8B-L3-M
num_battles: 9306
num_wins: 5168
celo_rating: 1221.31
propriety_score: 0.6729990657116163
propriety_total_count: 3211.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: 1
ineligible_reason: None
language_model: Hastagaras/Anjir-8B-L3-MK.V-BJ1
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-10
win_ratio: 0.5553406404470235
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-anjir-8b-l3-m-6487-v3-mkmlizer
Waiting for job on hastagaras-anjir-8b-l3-m-6487-v3-mkmlizer to finish
hastagaras-anjir-8b-l3-m-6487-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-anjir-8b-l3-m-6487-v3-mkmlizer: ║ _____ __ __ ║
hastagaras-anjir-8b-l3-m-6487-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-anjir-8b-l3-m-6487-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-anjir-8b-l3-m-6487-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-anjir-8b-l3-m-6487-v3-mkmlizer: ║ /___/ ║
hastagaras-anjir-8b-l3-m-6487-v3-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-m-6487-v3-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-anjir-8b-l3-m-6487-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-anjir-8b-l3-m-6487-v3-mkmlizer: ║ https://mk1.ai ║
hastagaras-anjir-8b-l3-m-6487-v3-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-m-6487-v3-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-anjir-8b-l3-m-6487-v3-mkmlizer: ║ belonging to: ║
hastagaras-anjir-8b-l3-m-6487-v3-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-m-6487-v3-mkmlizer: ║ Chai Research Corp. ║
hastagaras-anjir-8b-l3-m-6487-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-anjir-8b-l3-m-6487-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-anjir-8b-l3-m-6487-v3-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-m-6487-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-anjir-8b-l3-m-6487-v3-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.
hastagaras-anjir-8b-l3-m-6487-v3-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-anjir-8b-l3-m-6487-v3-mkmlizer: Downloaded to shared memory in 21.391s
hastagaras-anjir-8b-l3-m-6487-v3-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-anjir-8b-l3-m-6487-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-anjir-8b-l3-m-6487-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<09:57, 2.07s/it] Loading 0: 8%|▊ | 23/291 [00:04<00:35, 7.45it/s] Loading 0: 15%|█▌ | 44/291 [00:04<00:14, 16.63it/s] Loading 0: 21%|██ | 60/291 [00:04<00:10, 21.89it/s] Loading 0: 29%|██▊ | 83/291 [00:04<00:05, 36.39it/s] Loading 0: 36%|███▌ | 104/291 [00:04<00:03, 51.63it/s] Loading 0: 43%|████▎ | 124/291 [00:05<00:02, 68.39it/s] Loading 0: 51%|█████ | 148/291 [00:05<00:01, 91.25it/s] Loading 0: 58%|█████▊ | 168/291 [00:05<00:01, 75.14it/s] Loading 0: 66%|██████▋ | 193/291 [00:05<00:00, 98.17it/s] Loading 0: 73%|███████▎ | 212/291 [00:05<00:00, 113.23it/s] Loading 0: 79%|███████▉ | 231/291 [00:05<00:00, 127.77it/s] Loading 0: 88%|████████▊ | 256/291 [00:05<00:00, 150.95it/s] Loading 0: 95%|█████████▍| 276/291 [00:06<00:00, 101.13it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-anjir-8b-l3-m-6487-v3-mkmlizer: quantized model in 17.057s
hastagaras-anjir-8b-l3-m-6487-v3-mkmlizer: Processed model Hastagaras/Anjir-8B-L3-MK.V-BJ1 in 39.391s
hastagaras-anjir-8b-l3-m-6487-v3-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-anjir-8b-l3-m-6487-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-anjir-8b-l3-m-6487-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-m-6487-v3
hastagaras-anjir-8b-l3-m-6487-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-m-6487-v3/config.json
hastagaras-anjir-8b-l3-m-6487-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-m-6487-v3/tokenizer_config.json
hastagaras-anjir-8b-l3-m-6487-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-m-6487-v3/special_tokens_map.json
hastagaras-anjir-8b-l3-m-6487-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-m-6487-v3/tokenizer.json
hastagaras-anjir-8b-l3-m-6487-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-m-6487-v3/flywheel_model.0.safetensors
hastagaras-anjir-8b-l3-m-6487-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-anjir-8b-l3-m-6487-v3-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.
hastagaras-anjir-8b-l3-m-6487-v3-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-m-6487-v3-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.
hastagaras-anjir-8b-l3-m-6487-v3-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-m-6487-v3-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.
hastagaras-anjir-8b-l3-m-6487-v3-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-m-6487-v3-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()
hastagaras-anjir-8b-l3-m-6487-v3-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-anjir-8b-l3-m-6487-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-anjir-8b-l3-m-6487-v3-mkmlizer: Saving duration: 0.239s
hastagaras-anjir-8b-l3-m-6487-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.943s
hastagaras-anjir-8b-l3-m-6487-v3-mkmlizer: creating bucket guanaco-reward-models
hastagaras-anjir-8b-l3-m-6487-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-anjir-8b-l3-m-6487-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-6487-v3_reward
hastagaras-anjir-8b-l3-m-6487-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-6487-v3_reward/config.json
hastagaras-anjir-8b-l3-m-6487-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-6487-v3_reward/tokenizer_config.json
hastagaras-anjir-8b-l3-m-6487-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-6487-v3_reward/special_tokens_map.json
hastagaras-anjir-8b-l3-m-6487-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-6487-v3_reward/merges.txt
hastagaras-anjir-8b-l3-m-6487-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-6487-v3_reward/vocab.json
hastagaras-anjir-8b-l3-m-6487-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-6487-v3_reward/tokenizer.json
hastagaras-anjir-8b-l3-m-6487-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-6487-v3_reward/reward.tensors
Job hastagaras-anjir-8b-l3-m-6487-v3-mkmlizer completed after 62.95s with status: succeeded
Stopping job with name hastagaras-anjir-8b-l3-m-6487-v3-mkmlizer
Pipeline stage MKMLizer completed in 66.15s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-anjir-8b-l3-m-6487-v3
Waiting for inference service hastagaras-anjir-8b-l3-m-6487-v3 to be ready
Inference service hastagaras-anjir-8b-l3-m-6487-v3 ready after 30.202019214630127s
Pipeline stage ISVCDeployer completed in 37.17s
Running pipeline stage StressChecker
Received healthy response to inference request in 10.397566080093384s
Received healthy response to inference request in 1.3328936100006104s
Received healthy response to inference request in 1.2882318496704102s
Received healthy response to inference request in 2.2083210945129395s
Received healthy response to inference request in 1.350949764251709s
5 requests
0 failed requests
5th percentile: 1.2971642017364502
10th percentile: 1.3060965538024902
20th percentile: 1.3239612579345703
30th percentile: 1.33650484085083
40th percentile: 1.3437273025512695
50th percentile: 1.350949764251709
60th percentile: 1.693898296356201
70th percentile: 2.036846828460693
80th percentile: 3.8461700916290296
90th percentile: 7.121868085861207
95th percentile: 8.759717082977293
99th percentile: 10.069996280670166
mean time: 3.3155924797058107
Pipeline stage StressChecker completed in 17.20s
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 0.03s
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-anjir-8b-l3-m_6487_v3 status is now deployed due to DeploymentManager action
hastagaras-anjir-8b-l3-m_6487_v3 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics