unsloth-mistral-7b-v0-3

submission_id: unsloth-mistral-7b-v0-3_v2

developer_uid: Meliodia

best_of: 16

celo_rating: 1145.84

display_name: unsloth-mistral-7b-v0-3_v2

family_friendly_score: 0.0

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}

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}

is_internal_developer: True

language_model: unsloth/mistral-7b-v0.3

max_input_tokens: 512

max_output_tokens: 64

model_architecture: MistralForCausalLM

model_eval_status: success

model_group: unsloth/mistral-7b-v0.3

model_name: unsloth-mistral-7b-v0-3_v2

model_num_parameters: 7248023552.0

model_repo: unsloth/mistral-7b-v0.3

model_size: 7B

num_battles: 6261

num_wins: 2723

ranking_group: single

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'}

reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2

status: torndown

submission_type: basic

timestamp: 2024-05-22T23:18:33+00:00

us_pacific_date: 2024-05-22

win_ratio: 0.43491455039131127

Resubmit model

Running pipeline stage MKMLizer
Starting job with name unsloth-mistral-7b-v0-3-v2-mkmlizer
Waiting for job on unsloth-mistral-7b-v0-3-v2-mkmlizer to finish
unsloth-mistral-7b-v0-3-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
unsloth-mistral-7b-v0-3-v2-mkmlizer: ║     _____            __           __                                ║
unsloth-mistral-7b-v0-3-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
unsloth-mistral-7b-v0-3-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
unsloth-mistral-7b-v0-3-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
unsloth-mistral-7b-v0-3-v2-mkmlizer: ║       /___/                                                         ║
unsloth-mistral-7b-v0-3-v2-mkmlizer: ║                                                                     ║
unsloth-mistral-7b-v0-3-v2-mkmlizer: ║  Version: 0.8.14                                                    ║
unsloth-mistral-7b-v0-3-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
unsloth-mistral-7b-v0-3-v2-mkmlizer: ║  https://mk1.ai                                                     ║
unsloth-mistral-7b-v0-3-v2-mkmlizer: ║                                                                     ║
unsloth-mistral-7b-v0-3-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
unsloth-mistral-7b-v0-3-v2-mkmlizer: ║  belonging to:                                                      ║
unsloth-mistral-7b-v0-3-v2-mkmlizer: ║                                                                     ║
unsloth-mistral-7b-v0-3-v2-mkmlizer: ║  Chai Research Corp.                                                ║
unsloth-mistral-7b-v0-3-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
unsloth-mistral-7b-v0-3-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
unsloth-mistral-7b-v0-3-v2-mkmlizer: ║                                                                     ║
unsloth-mistral-7b-v0-3-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
unsloth-mistral-7b-v0-3-v2-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-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
unsloth-mistral-7b-v0-3-v2-mkmlizer: Downloaded to shared memory in 29.315s
unsloth-mistral-7b-v0-3-v2-mkmlizer: quantizing model to /dev/shm/model_cache
unsloth-mistral-7b-v0-3-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
unsloth-mistral-7b-v0-3-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   5%|▍         | 14/291 [00:00<00:02, 130.40it/s]
Loading 0:  10%|▉         | 29/291 [00:00<00:01, 140.93it/s]
Loading 0:  16%|█▌        | 46/291 [00:00<00:01, 151.37it/s]
Loading 0:  22%|██▏       | 63/291 [00:00<00:01, 158.47it/s]
Loading 0:  28%|██▊       | 81/291 [00:00<00:01, 157.73it/s]
Loading 0:  33%|███▎      | 97/291 [00:00<00:01, 158.45it/s]
Loading 0:  39%|███▉      | 113/291 [00:01<00:02, 84.43it/s]
Loading 0:  45%|████▌     | 131/291 [00:01<00:01, 100.17it/s]
Loading 0:  51%|█████     | 148/291 [00:01<00:01, 114.19it/s]
Loading 0:  57%|█████▋    | 165/291 [00:01<00:01, 125.42it/s]
Loading 0:  63%|██████▎   | 183/291 [00:01<00:00, 133.75it/s]
Loading 0:  68%|██████▊   | 199/291 [00:01<00:00, 139.04it/s]
Loading 0:  74%|███████▍  | 215/291 [00:03<00:02, 27.35it/s] 
Loading 0:  79%|███████▉  | 231/291 [00:03<00:01, 35.76it/s]
Loading 0:  85%|████████▌ | 248/291 [00:03<00:00, 47.01it/s]
Loading 0:  91%|█████████ | 265/291 [00:03<00:00, 60.20it/s]
Loading 0:  97%|█████████▋| 283/291 [00:03<00:00, 74.81it/s]
                                                            
You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
unsloth-mistral-7b-v0-3-v2-mkmlizer: quantized model in 15.252s
unsloth-mistral-7b-v0-3-v2-mkmlizer: Processed model unsloth/mistral-7b-v0.3 in 46.972s
unsloth-mistral-7b-v0-3-v2-mkmlizer: creating bucket guanaco-mkml-models
unsloth-mistral-7b-v0-3-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
unsloth-mistral-7b-v0-3-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/unsloth-mistral-7b-v0-3-v2
unsloth-mistral-7b-v0-3-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/unsloth-mistral-7b-v0-3-v2/config.json
unsloth-mistral-7b-v0-3-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/unsloth-mistral-7b-v0-3-v2/special_tokens_map.json
unsloth-mistral-7b-v0-3-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/unsloth-mistral-7b-v0-3-v2/tokenizer_config.json
unsloth-mistral-7b-v0-3-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/unsloth-mistral-7b-v0-3-v2/tokenizer.model
unsloth-mistral-7b-v0-3-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/unsloth-mistral-7b-v0-3-v2/tokenizer.json
unsloth-mistral-7b-v0-3-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/unsloth-mistral-7b-v0-3-v2/flywheel_model.0.safetensors
unsloth-mistral-7b-v0-3-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
unsloth-mistral-7b-v0-3-v2-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-v2-mkmlizer:   warnings.warn(
unsloth-mistral-7b-v0-3-v2-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-v2-mkmlizer:   warnings.warn(
unsloth-mistral-7b-v0-3-v2-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-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
unsloth-mistral-7b-v0-3-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
unsloth-mistral-7b-v0-3-v2-mkmlizer: Saving duration: 0.409s
unsloth-mistral-7b-v0-3-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.359s
unsloth-mistral-7b-v0-3-v2-mkmlizer: creating bucket guanaco-reward-models
unsloth-mistral-7b-v0-3-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
unsloth-mistral-7b-v0-3-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/unsloth-mistral-7b-v0-3-v2_reward
unsloth-mistral-7b-v0-3-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/unsloth-mistral-7b-v0-3-v2_reward/config.json
unsloth-mistral-7b-v0-3-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/unsloth-mistral-7b-v0-3-v2_reward/special_tokens_map.json
unsloth-mistral-7b-v0-3-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/unsloth-mistral-7b-v0-3-v2_reward/tokenizer_config.json
unsloth-mistral-7b-v0-3-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/unsloth-mistral-7b-v0-3-v2_reward/merges.txt
unsloth-mistral-7b-v0-3-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/unsloth-mistral-7b-v0-3-v2_reward/vocab.json
unsloth-mistral-7b-v0-3-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/unsloth-mistral-7b-v0-3-v2_reward/tokenizer.json
unsloth-mistral-7b-v0-3-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/unsloth-mistral-7b-v0-3-v2_reward/reward.tensors
Job unsloth-mistral-7b-v0-3-v2-mkmlizer completed after 154.34s with status: succeeded
Stopping job with name unsloth-mistral-7b-v0-3-v2-mkmlizer
Pipeline stage MKMLizer completed in 158.73s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service unsloth-mistral-7b-v0-3-v2
Waiting for inference service unsloth-mistral-7b-v0-3-v2 to be ready
Failed to get response for submission blend_lutur_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')
Inference service unsloth-mistral-7b-v0-3-v2 ready after 40.21317744255066s
Pipeline stage ISVCDeployer completed in 47.71s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.082517623901367s
Received healthy response to inference request in 1.0794944763183594s
Received healthy response to inference request in 1.13808012008667s
Received healthy response to inference request in 0.8928885459899902s
Received healthy response to inference request in 1.1830685138702393s
5 requests
0 failed requests
5th percentile: 0.930209732055664
10th percentile: 0.9675309181213378
20th percentile: 1.0421732902526855
30th percentile: 1.0912116050720215
40th percentile: 1.1146458625793456
50th percentile: 1.13808012008667
60th percentile: 1.1560754776000977
70th percentile: 1.1740708351135254
80th percentile: 1.362958335876465
90th percentile: 1.7227379798889162
95th percentile: 1.9026278018951415
99th percentile: 2.046539659500122
mean time: 1.2752098560333252
Pipeline stage StressChecker completed in 6.97s
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_v2 status is now deployed due to DeploymentManager action
unsloth-mistral-7b-v0-3_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of unsloth-mistral-7b-v0-3_v2
Running pipeline stage ISVCDeleter
Checking if service unsloth-mistral-7b-v0-3-v2 is running
Tearing down inference service unsloth-mistral-7b-v0-3-v2
Toredown service unsloth-mistral-7b-v0-3-v2
Pipeline stage ISVCDeleter completed in 3.60s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key unsloth-mistral-7b-v0-3-v2/config.json from bucket guanaco-mkml-models
Deleting key unsloth-mistral-7b-v0-3-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key unsloth-mistral-7b-v0-3-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key unsloth-mistral-7b-v0-3-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key unsloth-mistral-7b-v0-3-v2/tokenizer.model from bucket guanaco-mkml-models
Deleting key unsloth-mistral-7b-v0-3-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key unsloth-mistral-7b-v0-3-v2_reward/config.json from bucket guanaco-reward-models
Deleting key unsloth-mistral-7b-v0-3-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key unsloth-mistral-7b-v0-3-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key unsloth-mistral-7b-v0-3-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key unsloth-mistral-7b-v0-3-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key unsloth-mistral-7b-v0-3-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key unsloth-mistral-7b-v0-3-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.13s
unsloth-mistral-7b-v0-3_v2 status is now torndown due to DeploymentManager action