mistralai-codestral-22b-v0-1

submission_id: mistralai-codestral-22b-v0-1_v1
developer_uid: frankdu
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': 4, 'max_output_tokens': 64}
model_name: mistralai-codestral-22b-v0-1_v1
model_repo: mistralai/Codestral-22B-v0.1
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
timestamp: 2024-06-10T18:36:12+00:00
Resubmit model
Running pipeline stage MKMLizer
Starting job with name mistralai-codestral-22b-v0-1-v1-mkmlizer
Waiting for job on mistralai-codestral-22b-v0-1-v1-mkmlizer to finish
mistralai-codestral-22b-v0-1-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
mistralai-codestral-22b-v0-1-v1-mkmlizer: ║     _____            __           __                                ║
mistralai-codestral-22b-v0-1-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
mistralai-codestral-22b-v0-1-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
mistralai-codestral-22b-v0-1-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
mistralai-codestral-22b-v0-1-v1-mkmlizer: ║       /___/                                                         ║
mistralai-codestral-22b-v0-1-v1-mkmlizer: ║                                                                     ║
mistralai-codestral-22b-v0-1-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
mistralai-codestral-22b-v0-1-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
mistralai-codestral-22b-v0-1-v1-mkmlizer: ║  https://mk1.ai                                                     ║
mistralai-codestral-22b-v0-1-v1-mkmlizer: ║                                                                     ║
mistralai-codestral-22b-v0-1-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
mistralai-codestral-22b-v0-1-v1-mkmlizer: ║  belonging to:                                                      ║
mistralai-codestral-22b-v0-1-v1-mkmlizer: ║                                                                     ║
mistralai-codestral-22b-v0-1-v1-mkmlizer: ║  Chai Research Corp.                                                ║
mistralai-codestral-22b-v0-1-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
mistralai-codestral-22b-v0-1-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
mistralai-codestral-22b-v0-1-v1-mkmlizer: ║                                                                     ║
mistralai-codestral-22b-v0-1-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
mistralai-codestral-22b-v0-1-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.
mistralai-codestral-22b-v0-1-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
mistralai-codestral-22b-v0-1-v1-mkmlizer: Downloaded to shared memory in 59.757s
mistralai-codestral-22b-v0-1-v1-mkmlizer: quantizing model to /dev/shm/model_cache
mistralai-codestral-22b-v0-1-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission mistralai-mixtral-8x7b-_3473_v33: ('http://mistralai-mixtral-8x7b-3473-v33-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'upstream connect error or disconnect/reset before headers. reset reason: overflow')
mistralai-codestral-22b-v0-1-v1-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   3%|▎         | 13/507 [00:00<00:04, 111.34it/s]
Loading 0:   5%|▍         | 25/507 [00:00<00:04, 115.23it/s]
Loading 0:   8%|▊         | 39/507 [00:00<00:03, 121.05it/s]
Loading 0:  10%|█         | 52/507 [00:00<00:03, 116.84it/s]
Loading 0:  13%|█▎        | 64/507 [00:00<00:07, 61.42it/s] 
Loading 0:  16%|█▌        | 79/507 [00:00<00:05, 78.19it/s]
Loading 0:  18%|█▊        | 92/507 [00:01<00:04, 88.46it/s]
Loading 0:  21%|██        | 105/507 [00:01<00:04, 97.24it/s]
Loading 0:  23%|██▎       | 117/507 [00:01<00:06, 61.99it/s]
Loading 0:  25%|██▌       | 129/507 [00:01<00:05, 71.82it/s]
Loading 0:  28%|██▊       | 140/507 [00:01<00:04, 76.78it/s]
Loading 0:  31%|███       | 156/507 [00:01<00:03, 91.86it/s]
Loading 0:  33%|███▎      | 169/507 [00:02<00:05, 64.49it/s]
Loading 0:  35%|███▌      | 178/507 [00:02<00:04, 68.48it/s]
Loading 0:  38%|███▊      | 192/507 [00:02<00:03, 81.18it/s]
Loading 0:  40%|████      | 203/507 [00:02<00:03, 84.80it/s]
Loading 0:  43%|████▎     | 218/507 [00:02<00:02, 97.08it/s]
Loading 0:  45%|████▌     | 229/507 [00:02<00:04, 62.78it/s]
Loading 0:  48%|████▊     | 242/507 [00:03<00:03, 73.97it/s]
Loading 0:  50%|█████     | 255/507 [00:03<00:02, 84.56it/s]
Loading 0:  52%|█████▏    | 266/507 [00:03<00:02, 87.21it/s]
Loading 0:  56%|█████▌    | 282/507 [00:03<00:02, 103.40it/s]
Loading 0:  58%|█████▊    | 294/507 [00:03<00:03, 62.31it/s] 
Loading 0:  60%|█████▉    | 304/507 [00:17<01:13,  2.76it/s]
Loading 0:  62%|██████▏   | 316/507 [00:17<00:49,  3.89it/s]
Loading 0:  65%|██████▍   | 328/507 [00:18<00:32,  5.47it/s]
Loading 0:  67%|██████▋   | 340/507 [00:18<00:23,  7.23it/s]
Loading 0:  69%|██████▊   | 348/507 [00:18<00:17,  9.05it/s]
Loading 0:  72%|███████▏  | 363/507 [00:18<00:10, 13.88it/s]
Loading 0:  74%|███████▍  | 374/507 [00:18<00:07, 18.25it/s]
Loading 0:  77%|███████▋  | 389/507 [00:18<00:04, 26.24it/s]
Loading 0:  79%|███████▉  | 400/507 [00:19<00:03, 27.58it/s]
Loading 0:  81%|████████▏ | 413/507 [00:19<00:02, 36.42it/s]
Loading 0:  84%|████████▍ | 426/507 [00:19<00:01, 46.13it/s]
Loading 0:  86%|████████▌ | 437/507 [00:19<00:01, 52.83it/s]
Loading 0:  89%|████████▉ | 450/507 [00:19<00:00, 64.64it/s]
Loading 0:  91%|█████████ | 461/507 [00:22<00:03, 14.46it/s]
Loading 0:  93%|█████████▎| 469/507 [00:22<00:02, 17.49it/s]
Loading 0:  94%|█████████▍| 477/507 [00:22<00:01, 21.53it/s]
Loading 0:  96%|█████████▌| 485/507 [00:22<00:00, 26.17it/s]
Loading 0:  97%|█████████▋| 493/507 [00:22<00:00, 31.07it/s]
Loading 0:  99%|█████████▉| 501/507 [00:22<00:00, 36.19it/s]
                                                            
You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
mistralai-codestral-22b-v0-1-v1-mkmlizer: quantized model in 34.952s
mistralai-codestral-22b-v0-1-v1-mkmlizer: Processed model mistralai/Codestral-22B-v0.1 in 99.960s
mistralai-codestral-22b-v0-1-v1-mkmlizer: creating bucket guanaco-mkml-models
mistralai-codestral-22b-v0-1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
mistralai-codestral-22b-v0-1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/mistralai-codestral-22b-v0-1-v1
mistralai-codestral-22b-v0-1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/mistralai-codestral-22b-v0-1-v1/config.json
mistralai-codestral-22b-v0-1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/mistralai-codestral-22b-v0-1-v1/tokenizer_config.json
mistralai-codestral-22b-v0-1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/mistralai-codestral-22b-v0-1-v1/tokenizer.model
mistralai-codestral-22b-v0-1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/mistralai-codestral-22b-v0-1-v1/tokenizer.json
mistralai-codestral-22b-v0-1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/mistralai-codestral-22b-v0-1-v1/special_tokens_map.json
mistralai-codestral-22b-v0-1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/mistralai-codestral-22b-v0-1-v1/flywheel_model.1.safetensors
mistralai-codestral-22b-v0-1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/mistralai-codestral-22b-v0-1-v1/flywheel_model.0.safetensors
mistralai-codestral-22b-v0-1-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.
mistralai-codestral-22b-v0-1-v1-mkmlizer:   warnings.warn(
mistralai-codestral-22b-v0-1-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.
mistralai-codestral-22b-v0-1-v1-mkmlizer:   warnings.warn(
mistralai-codestral-22b-v0-1-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()
mistralai-codestral-22b-v0-1-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
mistralai-codestral-22b-v0-1-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
mistralai-codestral-22b-v0-1-v1-mkmlizer: Saving duration: 0.240s
mistralai-codestral-22b-v0-1-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 3.686s
mistralai-codestral-22b-v0-1-v1-mkmlizer: creating bucket guanaco-reward-models
mistralai-codestral-22b-v0-1-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
mistralai-codestral-22b-v0-1-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/mistralai-codestral-22b-v0-1-v1_reward
mistralai-codestral-22b-v0-1-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/mistralai-codestral-22b-v0-1-v1_reward/config.json
mistralai-codestral-22b-v0-1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/mistralai-codestral-22b-v0-1-v1_reward/tokenizer_config.json
mistralai-codestral-22b-v0-1-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/mistralai-codestral-22b-v0-1-v1_reward/merges.txt
mistralai-codestral-22b-v0-1-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/mistralai-codestral-22b-v0-1-v1_reward/vocab.json
mistralai-codestral-22b-v0-1-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/mistralai-codestral-22b-v0-1-v1_reward/special_tokens_map.json
mistralai-codestral-22b-v0-1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/mistralai-codestral-22b-v0-1-v1_reward/tokenizer.json
mistralai-codestral-22b-v0-1-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/mistralai-codestral-22b-v0-1-v1_reward/reward.tensors
Job mistralai-codestral-22b-v0-1-v1-mkmlizer completed after 124.18s with status: succeeded
Stopping job with name mistralai-codestral-22b-v0-1-v1-mkmlizer
Pipeline stage MKMLizer completed in 127.51s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service mistralai-codestral-22b-v0-1-v1
Waiting for inference service mistralai-codestral-22b-v0-1-v1 to be ready
Inference service mistralai-codestral-22b-v0-1-v1 ready after 50.34641480445862s
Pipeline stage ISVCDeployer completed in 57.59s
Running pipeline stage StressChecker
%s, retrying in %s seconds...
%s, retrying in %s seconds...
DeploymentChecksError('expected string or bytes-like object')
mistralai-codestral-22b-v0-1_v1 status is now failed due to DeploymentManager action
admin requested tearing down of mistralai-codestral-22b-v0-1_v1
Running pipeline stage ISVCDeleter
Checking if service mistralai-codestral-22b-v0-1-v1 is running
Tearing down inference service mistralai-codestral-22b-v0-1-v1
Toredown service mistralai-codestral-22b-v0-1-v1
Pipeline stage ISVCDeleter completed in 8.57s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key mistralai-codestral-22b-v0-1-v1/config.json from bucket guanaco-mkml-models
Deleting key mistralai-codestral-22b-v0-1-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key mistralai-codestral-22b-v0-1-v1/flywheel_model.1.safetensors from bucket guanaco-mkml-models
Deleting key mistralai-codestral-22b-v0-1-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key mistralai-codestral-22b-v0-1-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key mistralai-codestral-22b-v0-1-v1/tokenizer.model from bucket guanaco-mkml-models
Deleting key mistralai-codestral-22b-v0-1-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key mistralai-codestral-22b-v0-1-v1_reward/config.json from bucket guanaco-reward-models
Deleting key mistralai-codestral-22b-v0-1-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key mistralai-codestral-22b-v0-1-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key mistralai-codestral-22b-v0-1-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key mistralai-codestral-22b-v0-1-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key mistralai-codestral-22b-v0-1-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key mistralai-codestral-22b-v0-1-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 4.29s
mistralai-codestral-22b-v0-1_v1 status is now torndown due to DeploymentManager action