submission_id: hastagaras-anjir-8b-l3-m_6487_v5
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': 0.95, 'top_p': 1.0, 'min_p': 0.1, '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: 2024-06-15T01:08:34+00:00
model_name: tm
model_eval_status: success
model_group: Hastagaras/Anjir-8B-L3-M
num_battles: 17437
num_wins: 9430
celo_rating: 1223.74
propriety_score: 0.67389925136404
propriety_total_count: 7881.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: tm
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: 2024-06-14
win_ratio: 0.5408040373917532
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-anjir-8b-l3-m-6487-v5-mkmlizer
Waiting for job on hastagaras-anjir-8b-l3-m-6487-v5-mkmlizer to finish
hastagaras-anjir-8b-l3-m-6487-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-anjir-8b-l3-m-6487-v5-mkmlizer: ║ _____ __ __ ║
hastagaras-anjir-8b-l3-m-6487-v5-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-anjir-8b-l3-m-6487-v5-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-anjir-8b-l3-m-6487-v5-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-anjir-8b-l3-m-6487-v5-mkmlizer: ║ /___/ ║
hastagaras-anjir-8b-l3-m-6487-v5-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-m-6487-v5-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-anjir-8b-l3-m-6487-v5-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-anjir-8b-l3-m-6487-v5-mkmlizer: ║ https://mk1.ai ║
hastagaras-anjir-8b-l3-m-6487-v5-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-m-6487-v5-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-anjir-8b-l3-m-6487-v5-mkmlizer: ║ belonging to: ║
hastagaras-anjir-8b-l3-m-6487-v5-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-m-6487-v5-mkmlizer: ║ Chai Research Corp. ║
hastagaras-anjir-8b-l3-m-6487-v5-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-anjir-8b-l3-m-6487-v5-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-anjir-8b-l3-m-6487-v5-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-m-6487-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-anjir-8b-l3-m-6487-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.
hastagaras-anjir-8b-l3-m-6487-v5-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-anjir-8b-l3-m-6487-v5-mkmlizer: Downloaded to shared memory in 35.766s
hastagaras-anjir-8b-l3-m-6487-v5-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-anjir-8b-l3-m-6487-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-anjir-8b-l3-m-6487-v5-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<10:50, 2.25s/it] Loading 0: 5%|▌ | 15/291 [00:04<01:02, 4.43it/s] Loading 0: 11%|█▏ | 33/291 [00:04<00:21, 11.79it/s] Loading 0: 18%|█▊ | 51/291 [00:04<00:11, 21.22it/s] Loading 0: 22%|██▏ | 65/291 [00:05<00:08, 25.41it/s] Loading 0: 27%|██▋ | 78/291 [00:05<00:06, 33.96it/s] Loading 0: 33%|███▎ | 96/291 [00:05<00:04, 48.66it/s] Loading 0: 39%|███▉ | 114/291 [00:05<00:02, 64.90it/s] Loading 0: 45%|████▌ | 132/291 [00:05<00:01, 82.02it/s] Loading 0: 52%|█████▏ | 150/291 [00:05<00:01, 97.39it/s] Loading 0: 57%|█████▋ | 166/291 [00:06<00:01, 75.69it/s] Loading 0: 63%|██████▎ | 182/291 [00:06<00:01, 89.56it/s] Loading 0: 67%|██████▋ | 196/291 [00:06<00:00, 98.64it/s] Loading 0: 73%|███████▎ | 213/291 [00:06<00:00, 111.64it/s] Loading 0: 79%|███████▉ | 231/291 [00:06<00:00, 124.65it/s] Loading 0: 86%|████████▌ | 249/291 [00:06<00:00, 136.53it/s] Loading 0: 91%|█████████▏| 266/291 [00:06<00:00, 92.09it/s] Loading 0: 98%|█████████▊| 284/291 [00:06<00:00, 107.56it/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-v5-mkmlizer: quantized model in 22.726s
hastagaras-anjir-8b-l3-m-6487-v5-mkmlizer: Processed model Hastagaras/Anjir-8B-L3-MK.V-BJ1 in 61.038s
hastagaras-anjir-8b-l3-m-6487-v5-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-anjir-8b-l3-m-6487-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-anjir-8b-l3-m-6487-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-m-6487-v5
hastagaras-anjir-8b-l3-m-6487-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-m-6487-v5/config.json
hastagaras-anjir-8b-l3-m-6487-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-m-6487-v5/tokenizer_config.json
hastagaras-anjir-8b-l3-m-6487-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-m-6487-v5/special_tokens_map.json
hastagaras-anjir-8b-l3-m-6487-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-m-6487-v5/tokenizer.json
hastagaras-anjir-8b-l3-m-6487-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-m-6487-v5/flywheel_model.0.safetensors
hastagaras-anjir-8b-l3-m-6487-v5-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-anjir-8b-l3-m-6487-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.
hastagaras-anjir-8b-l3-m-6487-v5-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-m-6487-v5-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-v5-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-m-6487-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.
hastagaras-anjir-8b-l3-m-6487-v5-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-m-6487-v5-mkmlizer: creating bucket guanaco-reward-models
hastagaras-anjir-8b-l3-m-6487-v5-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-anjir-8b-l3-m-6487-v5-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-6487-v5_reward
hastagaras-anjir-8b-l3-m-6487-v5-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-6487-v5_reward/special_tokens_map.json
hastagaras-anjir-8b-l3-m-6487-v5-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-6487-v5_reward/config.json
hastagaras-anjir-8b-l3-m-6487-v5-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-6487-v5_reward/merges.txt
hastagaras-anjir-8b-l3-m-6487-v5-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-6487-v5_reward/tokenizer.json
hastagaras-anjir-8b-l3-m-6487-v5-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-6487-v5_reward/tokenizer_config.json
hastagaras-anjir-8b-l3-m-6487-v5-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-6487-v5_reward/vocab.json
hastagaras-anjir-8b-l3-m-6487-v5-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-anjir-8b-l3-m-6487-v5_reward/reward.tensors
Job hastagaras-anjir-8b-l3-m-6487-v5-mkmlizer completed after 94.96s with status: succeeded
Stopping job with name hastagaras-anjir-8b-l3-m-6487-v5-mkmlizer
Pipeline stage MKMLizer completed in 100.17s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-anjir-8b-l3-m-6487-v5
Waiting for inference service hastagaras-anjir-8b-l3-m-6487-v5 to be ready
Inference service hastagaras-anjir-8b-l3-m-6487-v5 ready after 40.25135660171509s
Pipeline stage ISVCDeployer completed in 48.10s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.150021553039551s
Received healthy response to inference request in 1.3351688385009766s
Received healthy response to inference request in 1.310941219329834s
Received healthy response to inference request in 1.2744898796081543s
Received healthy response to inference request in 1.3498961925506592s
5 requests
0 failed requests
5th percentile: 1.2817801475524901
10th percentile: 1.2890704154968262
20th percentile: 1.3036509513854981
30th percentile: 1.3157867431640624
40th percentile: 1.3254777908325195
50th percentile: 1.3351688385009766
60th percentile: 1.3410597801208497
70th percentile: 1.3469507217407226
80th percentile: 1.5099212646484377
90th percentile: 1.8299714088439942
95th percentile: 1.9899964809417723
99th percentile: 2.118016538619995
mean time: 1.484103536605835
Pipeline stage StressChecker completed in 8.06s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
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
hastagaras-anjir-8b-l3-m_6487_v5 status is now deployed due to DeploymentManager action
hastagaras-anjir-8b-l3-m_6487_v5 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics