developer_uid: Hastagaras
submission_id: hastagaras-anjir-8b-l3_v1
model_name: test
model_group: Hastagaras/Anjir-8B-L3
status: torndown
timestamp: 2024-05-30T02:47:40+00:00
num_battles: 13237
num_wins: 7349
celo_rating: 1212.09
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/Anjir-8B-L3
model_architecture: LlamaForCausalLM
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: test
is_internal_developer: False
language_model: Hastagaras/Anjir-8B-L3
model_size: 8B
ranking_group: single
us_pacific_date: 2024-05-29
win_ratio: 0.5551862204426985
generation_params: {'temperature': 1.0, 'top_p': 0.95, 'min_p': 0.1, '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': "<|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}
model_eval_status: success
reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-anjir-8b-l3-v1-mkmlizer
Waiting for job on hastagaras-anjir-8b-l3-v1-mkmlizer to finish
Stopping job with name hastagaras-anjir-8b-l3-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name hastagaras-anjir-8b-l3-v1-mkmlizer
Waiting for job on hastagaras-anjir-8b-l3-v1-mkmlizer to finish
hastagaras-anjir-8b-l3-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-anjir-8b-l3-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-anjir-8b-l3-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-anjir-8b-l3-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-anjir-8b-l3-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-anjir-8b-l3-v1-mkmlizer: ║ /___/ ║
hastagaras-anjir-8b-l3-v1-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-anjir-8b-l3-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-anjir-8b-l3-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-anjir-8b-l3-v1-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-anjir-8b-l3-v1-mkmlizer: ║ belonging to: ║
hastagaras-anjir-8b-l3-v1-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-anjir-8b-l3-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-anjir-8b-l3-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-anjir-8b-l3-v1-mkmlizer: ║ ║
hastagaras-anjir-8b-l3-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-anjir-8b-l3-v1-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-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-anjir-8b-l3-v1-mkmlizer: Downloaded to shared memory in 35.928s
hastagaras-anjir-8b-l3-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-anjir-8b-l3-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-anjir-8b-l3-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<10:39, 2.21s/it] Loading 0: 6%|▌ | 17/291 [00:04<00:53, 5.13it/s] Loading 0: 11%|█▏ | 33/291 [00:04<00:22, 11.71it/s] Loading 0: 18%|█▊ | 51/291 [00:04<00:11, 21.26it/s] Loading 0: 22%|██▏ | 65/291 [00:05<00:08, 25.78it/s] Loading 0: 28%|██▊ | 81/291 [00:05<00:05, 37.02it/s] Loading 0: 33%|███▎ | 96/291 [00:05<00:03, 48.92it/s] Loading 0: 39%|███▉ | 114/291 [00:05<00:02, 65.25it/s] Loading 0: 45%|████▌ | 132/291 [00:05<00:01, 81.90it/s] Loading 0: 52%|█████▏ | 150/291 [00:05<00:01, 98.42it/s] Loading 0: 57%|█████▋ | 166/291 [00:05<00:01, 76.76it/s] Loading 0: 63%|██████▎ | 184/291 [00:06<00:01, 92.72it/s] Loading 0: 69%|██████▉ | 202/291 [00:06<00:00, 108.11it/s] Loading 0: 76%|███████▌ | 220/291 [00:06<00:00, 117.20it/s] Loading 0: 82%|████████▏ | 238/291 [00:06<00:00, 129.87it/s] Loading 0: 88%|████████▊ | 256/291 [00:06<00:00, 140.38it/s] Loading 0: 93%|█████████▎| 272/291 [00:06<00:00, 92.59it/s] Loading 0: 99%|█████████▉| 289/291 [00:06<00:00, 106.33it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-anjir-8b-l3-v1-mkmlizer: quantized model in 22.564s
hastagaras-anjir-8b-l3-v1-mkmlizer: Processed model Hastagaras/Anjir-8B-L3 in 60.960s
hastagaras-anjir-8b-l3-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-anjir-8b-l3-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-anjir-8b-l3-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-v1
hastagaras-anjir-8b-l3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-v1/tokenizer_config.json
hastagaras-anjir-8b-l3-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-v1/special_tokens_map.json
hastagaras-anjir-8b-l3-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-v1/config.json
hastagaras-anjir-8b-l3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-v1/tokenizer.json
hastagaras-anjir-8b-l3-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-anjir-8b-l3-v1/flywheel_model.0.safetensors
hastagaras-anjir-8b-l3-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-anjir-8b-l3-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.
hastagaras-anjir-8b-l3-v1-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-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.
hastagaras-anjir-8b-l3-v1-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-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.
hastagaras-anjir-8b-l3-v1-mkmlizer: warnings.warn(
hastagaras-anjir-8b-l3-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()
hastagaras-anjir-8b-l3-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-anjir-8b-l3-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-anjir-8b-l3-v1-mkmlizer: Saving duration: 0.410s
hastagaras-anjir-8b-l3-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.830s
hastagaras-anjir-8b-l3-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-anjir-8b-l3-v1_reward/reward.tensors
Job hastagaras-anjir-8b-l3-v1-mkmlizer completed after 93.51s with status: succeeded
Stopping job with name hastagaras-anjir-8b-l3-v1-mkmlizer
Pipeline stage MKMLizer completed in 97.40s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-anjir-8b-l3-v1
Waiting for inference service hastagaras-anjir-8b-l3-v1 to be ready
Inference service hastagaras-anjir-8b-l3-v1 ready after 30.20192527770996s
Pipeline stage ISVCDeployer completed in 37.18s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1238629817962646s
Received healthy response to inference request in 1.3695399761199951s
Received healthy response to inference request in 1.3523755073547363s
Received healthy response to inference request in 1.3089485168457031s
Received healthy response to inference request in 1.2506709098815918s
5 requests
0 failed requests
5th percentile: 1.262326431274414
10th percentile: 1.2739819526672362
20th percentile: 1.297292995452881
30th percentile: 1.3176339149475098
40th percentile: 1.335004711151123
50th percentile: 1.3523755073547363
60th percentile: 1.3592412948608399
70th percentile: 1.3661070823669434
80th percentile: 1.5204045772552492
90th percentile: 1.8221337795257568
95th percentile: 1.9729983806610105
99th percentile: 2.093690061569214
mean time: 1.4810795783996582
Pipeline stage StressChecker completed in 8.04s
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
hastagaras-anjir-8b-l3_v1 status is now deployed due to DeploymentManager action
hastagaras-anjir-8b-l3_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-anjir-8b-l3_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-anjir-8b-l3-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 2.78s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-anjir-8b-l3-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-anjir-8b-l3-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-anjir-8b-l3-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-anjir-8b-l3-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-anjir-8b-l3-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-anjir-8b-l3-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-anjir-8b-l3-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-anjir-8b-l3-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-anjir-8b-l3-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-anjir-8b-l3-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-anjir-8b-l3-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-anjir-8b-l3-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 3.70s
hastagaras-anjir-8b-l3_v1 status is now torndown due to DeploymentManager action