developer_uid: Meliodia
submission_id: unsloth-mistral-7b-v0-3_v1
model_name: unsloth-mistral-7b-v0-3_v1
model_group: unsloth/mistral-7b-v0.3
status: torndown
timestamp: 2024-05-22T23:17:42+00:00
num_battles: 6356
num_wins: 2666
celo_rating: 1134.83
family_friendly_score: 0.0
submission_type: basic
model_repo: unsloth/mistral-7b-v0.3
model_architecture: MistralForCausalLM
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
model_num_parameters: 7248023552.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: unsloth-mistral-7b-v0-3_v1
is_internal_developer: True
language_model: unsloth/mistral-7b-v0.3
model_size: 7B
ranking_group: single
us_pacific_date: 2024-05-22
win_ratio: 0.4194461925739459
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': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
reward_formatter: {'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n'}
model_eval_status: success
Resubmit model
Running pipeline stage MKMLizer
Starting job with name unsloth-mistral-7b-v0-3-v1-mkmlizer
Waiting for job on unsloth-mistral-7b-v0-3-v1-mkmlizer to finish
Failed to get response for submission blend_pobil_2024-05-22: ('http://pointwise-ranking-qunil-v2-predictor-default.tenant-chairesearch-test.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
unsloth-mistral-7b-v0-3-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
unsloth-mistral-7b-v0-3-v1-mkmlizer: ║     _____            __           __                                ║
unsloth-mistral-7b-v0-3-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
unsloth-mistral-7b-v0-3-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
unsloth-mistral-7b-v0-3-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
unsloth-mistral-7b-v0-3-v1-mkmlizer: ║       /___/                                                         ║
unsloth-mistral-7b-v0-3-v1-mkmlizer: ║                                                                     ║
unsloth-mistral-7b-v0-3-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
unsloth-mistral-7b-v0-3-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
unsloth-mistral-7b-v0-3-v1-mkmlizer: ║  https://mk1.ai                                                     ║
unsloth-mistral-7b-v0-3-v1-mkmlizer: ║                                                                     ║
unsloth-mistral-7b-v0-3-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
unsloth-mistral-7b-v0-3-v1-mkmlizer: ║  belonging to:                                                      ║
unsloth-mistral-7b-v0-3-v1-mkmlizer: ║                                                                     ║
unsloth-mistral-7b-v0-3-v1-mkmlizer: ║  Chai Research Corp.                                                ║
unsloth-mistral-7b-v0-3-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
unsloth-mistral-7b-v0-3-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
unsloth-mistral-7b-v0-3-v1-mkmlizer: ║                                                                     ║
unsloth-mistral-7b-v0-3-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
unsloth-mistral-7b-v0-3-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.
unsloth-mistral-7b-v0-3-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
Failed to get response for submission blend_hahaf_2024-05-22: ('http://pointwise-ranking-qunil-v2-predictor-default.tenant-chairesearch-test.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
unsloth-mistral-7b-v0-3-v1-mkmlizer: Downloaded to shared memory in 29.355s
unsloth-mistral-7b-v0-3-v1-mkmlizer: quantizing model to /dev/shm/model_cache
unsloth-mistral-7b-v0-3-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
unsloth-mistral-7b-v0-3-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   5%|▍         | 14/291 [00:00<00:02, 129.47it/s]
Loading 0:  10%|▉         | 29/291 [00:00<00:01, 140.32it/s]
Loading 0:  16%|█▌        | 47/291 [00:00<00:01, 148.57it/s]
Loading 0:  22%|██▏       | 65/291 [00:00<00:01, 152.71it/s]
Loading 0:  29%|██▊       | 83/291 [00:00<00:01, 155.28it/s]
Loading 0:  34%|███▍      | 99/291 [00:00<00:02, 88.38it/s] 
Loading 0:  39%|███▉      | 113/291 [00:00<00:01, 98.35it/s]
Loading 0:  45%|████▍     | 130/291 [00:01<00:01, 114.26it/s]
Loading 0:  51%|█████     | 147/291 [00:01<00:01, 127.65it/s]
Loading 0:  57%|█████▋    | 165/291 [00:01<00:00, 136.28it/s]
Loading 0:  62%|██████▏   | 181/291 [00:01<00:00, 142.05it/s]
Loading 0:  68%|██████▊   | 197/291 [00:01<00:00, 143.36it/s]
Loading 0:  73%|███████▎  | 213/291 [00:03<00:02, 27.20it/s] 
Loading 0:  79%|███████▉  | 230/291 [00:03<00:01, 36.76it/s]
Loading 0:  85%|████████▍ | 247/291 [00:03<00:00, 48.30it/s]
Loading 0:  90%|█████████ | 262/291 [00:03<00:00, 59.54it/s]
Loading 0:  95%|█████████▌| 277/291 [00:03<00:00, 71.54it/s]
                                                            
You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
unsloth-mistral-7b-v0-3-v1-mkmlizer: quantized model in 15.095s
unsloth-mistral-7b-v0-3-v1-mkmlizer: Processed model unsloth/mistral-7b-v0.3 in 46.805s
unsloth-mistral-7b-v0-3-v1-mkmlizer: creating bucket guanaco-mkml-models
unsloth-mistral-7b-v0-3-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
unsloth-mistral-7b-v0-3-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/unsloth-mistral-7b-v0-3-v1
unsloth-mistral-7b-v0-3-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/unsloth-mistral-7b-v0-3-v1/special_tokens_map.json
unsloth-mistral-7b-v0-3-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/unsloth-mistral-7b-v0-3-v1/config.json
unsloth-mistral-7b-v0-3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/unsloth-mistral-7b-v0-3-v1/tokenizer_config.json
unsloth-mistral-7b-v0-3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/unsloth-mistral-7b-v0-3-v1/tokenizer.model
unsloth-mistral-7b-v0-3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/unsloth-mistral-7b-v0-3-v1/tokenizer.json
unsloth-mistral-7b-v0-3-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/unsloth-mistral-7b-v0-3-v1/flywheel_model.0.safetensors
unsloth-mistral-7b-v0-3-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
unsloth-mistral-7b-v0-3-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.
unsloth-mistral-7b-v0-3-v1-mkmlizer:   warnings.warn(
unsloth-mistral-7b-v0-3-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.
unsloth-mistral-7b-v0-3-v1-mkmlizer:   warnings.warn(
unsloth-mistral-7b-v0-3-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.
unsloth-mistral-7b-v0-3-v1-mkmlizer:   warnings.warn(
unsloth-mistral-7b-v0-3-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()
unsloth-mistral-7b-v0-3-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
unsloth-mistral-7b-v0-3-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
unsloth-mistral-7b-v0-3-v1-mkmlizer: Saving duration: 0.396s
unsloth-mistral-7b-v0-3-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 8.675s
unsloth-mistral-7b-v0-3-v1-mkmlizer: creating bucket guanaco-reward-models
unsloth-mistral-7b-v0-3-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
unsloth-mistral-7b-v0-3-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/unsloth-mistral-7b-v0-3-v1_reward
unsloth-mistral-7b-v0-3-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/unsloth-mistral-7b-v0-3-v1_reward/tokenizer_config.json
unsloth-mistral-7b-v0-3-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/unsloth-mistral-7b-v0-3-v1_reward/config.json
unsloth-mistral-7b-v0-3-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/unsloth-mistral-7b-v0-3-v1_reward/merges.txt
unsloth-mistral-7b-v0-3-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/unsloth-mistral-7b-v0-3-v1_reward/special_tokens_map.json
unsloth-mistral-7b-v0-3-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/unsloth-mistral-7b-v0-3-v1_reward/tokenizer.json
unsloth-mistral-7b-v0-3-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/unsloth-mistral-7b-v0-3-v1_reward/vocab.json
unsloth-mistral-7b-v0-3-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/unsloth-mistral-7b-v0-3-v1_reward/reward.tensors
Job unsloth-mistral-7b-v0-3-v1-mkmlizer completed after 196.0s with status: succeeded
Stopping job with name unsloth-mistral-7b-v0-3-v1-mkmlizer
Pipeline stage MKMLizer completed in 201.24s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service unsloth-mistral-7b-v0-3-v1
Waiting for inference service unsloth-mistral-7b-v0-3-v1 to be ready
Failed to get response for submission blend_pegok_2024-05-22: ('http://mistralai-mixtral-8x7b-3473-v33-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:60048->127.0.0.1:8080: read: connection reset by peer\n')
Inference service unsloth-mistral-7b-v0-3-v1 ready after 40.23934602737427s
Pipeline stage ISVCDeployer completed in 47.26s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9559276103973389s
Received healthy response to inference request in 1.239668846130371s
Received healthy response to inference request in 1.2246320247650146s
Received healthy response to inference request in 1.2360353469848633s
Received healthy response to inference request in 1.2233099937438965s
5 requests
0 failed requests
5th percentile: 1.2235743999481201
10th percentile: 1.2238388061523438
20th percentile: 1.224367618560791
30th percentile: 1.2269126892089843
40th percentile: 1.231474018096924
50th percentile: 1.2360353469848633
60th percentile: 1.2374887466430664
70th percentile: 1.2389421463012695
80th percentile: 1.3829205989837647
90th percentile: 1.6694241046905518
95th percentile: 1.8126758575439452
99th percentile: 1.92727725982666
mean time: 1.3759147644042968
Pipeline stage StressChecker completed in 7.56s
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 0.03s
M-Eval Dataset for topic stay_in_character is loaded
unsloth-mistral-7b-v0-3_v1 status is now deployed due to DeploymentManager action
unsloth-mistral-7b-v0-3_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of unsloth-mistral-7b-v0-3_v1
Running pipeline stage ISVCDeleter
Checking if service unsloth-mistral-7b-v0-3-v1 is running
Tearing down inference service unsloth-mistral-7b-v0-3-v1
Toredown service unsloth-mistral-7b-v0-3-v1
Pipeline stage ISVCDeleter completed in 3.73s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key unsloth-mistral-7b-v0-3-v1/config.json from bucket guanaco-mkml-models
Deleting key unsloth-mistral-7b-v0-3-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key unsloth-mistral-7b-v0-3-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key unsloth-mistral-7b-v0-3-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key unsloth-mistral-7b-v0-3-v1/tokenizer.model from bucket guanaco-mkml-models
Deleting key unsloth-mistral-7b-v0-3-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key unsloth-mistral-7b-v0-3-v1_reward/config.json from bucket guanaco-reward-models
Deleting key unsloth-mistral-7b-v0-3-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key unsloth-mistral-7b-v0-3-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key unsloth-mistral-7b-v0-3-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key unsloth-mistral-7b-v0-3-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key unsloth-mistral-7b-v0-3-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key unsloth-mistral-7b-v0-3-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 1.97s
unsloth-mistral-7b-v0-3_v1 status is now torndown due to DeploymentManager action