trace2333-rolebench-llama2-v0

developer_uid: Trace2333
submission_id: trace2333-rolebench-llama2-v0_v1
model_name: trace2333-rolebench-llama2-v0_v1
model_group: Trace2333/rolebench_llam
status: torndown
timestamp: 2024-07-02T03:07:58+00:00
num_battles: 10969
num_wins: 3444
celo_rating: 1038.43
family_friendly_score: 0.0
submission_type: basic
model_repo: Trace2333/rolebench_llama2_v0
model_architecture: LlamaForCausalLM
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
model_num_parameters: 6738415616.0
best_of: 4
max_input_tokens: 512
max_output_tokens: 64
display_name: trace2333-rolebench-llama2-v0_v1
is_internal_developer: False
language_model: Trace2333/rolebench_llama2_v0
model_size: 7B
ranking_group: single
us_pacific_date: 2024-07-01
win_ratio: 0.31397574984045945
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': ['</s>'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}####", '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}
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 trace2333-rolebench-llama2-v0-v1-mkmlizer
Waiting for job on trace2333-rolebench-llama2-v0-v1-mkmlizer to finish
trace2333-rolebench-llama2-v0-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-rolebench-llama2-v0-v1-mkmlizer: ║     _____            __           __                                ║
trace2333-rolebench-llama2-v0-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
trace2333-rolebench-llama2-v0-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
trace2333-rolebench-llama2-v0-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
trace2333-rolebench-llama2-v0-v1-mkmlizer: ║       /___/                                                         ║
trace2333-rolebench-llama2-v0-v1-mkmlizer: ║                                                                     ║
trace2333-rolebench-llama2-v0-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
trace2333-rolebench-llama2-v0-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
trace2333-rolebench-llama2-v0-v1-mkmlizer: ║  https://mk1.ai                                                     ║
trace2333-rolebench-llama2-v0-v1-mkmlizer: ║                                                                     ║
trace2333-rolebench-llama2-v0-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
trace2333-rolebench-llama2-v0-v1-mkmlizer: ║  belonging to:                                                      ║
trace2333-rolebench-llama2-v0-v1-mkmlizer: ║                                                                     ║
trace2333-rolebench-llama2-v0-v1-mkmlizer: ║  Chai Research Corp.                                                ║
trace2333-rolebench-llama2-v0-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
trace2333-rolebench-llama2-v0-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
trace2333-rolebench-llama2-v0-v1-mkmlizer: ║                                                                     ║
trace2333-rolebench-llama2-v0-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Retrying (%r) after connection broken by '%r': %s
trace2333-rolebench-llama2-v0-v1-mkmlizer: Downloaded to shared memory in 76.451s
trace2333-rolebench-llama2-v0-v1-mkmlizer: quantizing model to /dev/shm/model_cache
trace2333-rolebench-llama2-v0-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
trace2333-rolebench-llama2-v0-v1-mkmlizer: quantized model in 28.372s
trace2333-rolebench-llama2-v0-v1-mkmlizer: Processed model Trace2333/rolebench_llama2_v0 in 104.823s
trace2333-rolebench-llama2-v0-v1-mkmlizer: creating bucket guanaco-mkml-models
trace2333-rolebench-llama2-v0-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-rolebench-llama2-v0-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-rolebench-llama2-v0-v1
trace2333-rolebench-llama2-v0-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-rolebench-llama2-v0-v1/config.json
trace2333-rolebench-llama2-v0-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-rolebench-llama2-v0-v1/special_tokens_map.json
trace2333-rolebench-llama2-v0-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-rolebench-llama2-v0-v1/tokenizer_config.json
trace2333-rolebench-llama2-v0-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/trace2333-rolebench-llama2-v0-v1/tokenizer.model
trace2333-rolebench-llama2-v0-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-rolebench-llama2-v0-v1/tokenizer.json
trace2333-rolebench-llama2-v0-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/trace2333-rolebench-llama2-v0-v1/flywheel_model.0.safetensors
trace2333-rolebench-llama2-v0-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
trace2333-rolebench-llama2-v0-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/291 [00:02<03:37,  1.32it/s]
Loading 0:   1%|▏         | 4/291 [00:03<04:55,  1.03s/it]
Loading 0:   2%|▏         | 5/291 [00:04<04:07,  1.15it/s]
Loading 0:   2%|▏         | 7/291 [00:05<03:45,  1.26it/s]
Loading 0:   3%|▎         | 8/291 [00:07<05:03,  1.07s/it]
Loading 0:   3%|▎         | 10/291 [00:07<03:02,  1.54it/s]
Loading 0:   4%|▍         | 12/291 [00:07<01:58,  2.35it/s]
Loading 0:   7%|▋         | 19/291 [00:08<00:42,  6.34it/s]
Loading 0:   9%|▊         | 25/291 [00:08<00:25, 10.50it/s]
Loading 0:  11%|█         | 32/291 [00:08<00:16, 16.10it/s]
Loading 0:  14%|█▎        | 40/291 [00:08<00:10, 23.81it/s]
Loading 0:  17%|█▋        | 49/291 [00:08<00:07, 33.20it/s]
Loading 0:  19%|█▉        | 56/291 [00:08<00:08, 26.73it/s]
Loading 0:  22%|██▏       | 65/291 [00:08<00:06, 35.65it/s]
Loading 0:  25%|██▍       | 72/291 [00:09<00:05, 38.59it/s]
Loading 0:  27%|██▋       | 80/291 [00:09<00:04, 45.81it/s]
Loading 0:  30%|███       | 88/291 [00:09<00:03, 52.63it/s]
Loading 0:  33%|███▎      | 95/291 [00:09<00:03, 56.08it/s]
Loading 0:  35%|███▌      | 102/291 [00:09<00:03, 57.83it/s]
Loading 0:  37%|███▋      | 109/291 [00:09<00:04, 37.55it/s]
Loading 0:  40%|███▉      | 115/291 [00:09<00:04, 41.57it/s]
Loading 0:  42%|████▏     | 122/291 [00:10<00:03, 45.32it/s]
Loading 0:  45%|████▍     | 130/291 [00:10<00:03, 52.43it/s]
Loading 0:  47%|████▋     | 138/291 [00:10<00:02, 57.97it/s]
Loading 0:  50%|████▉     | 145/291 [00:10<00:02, 60.26it/s]
Loading 0:  52%|█████▏    | 152/291 [00:10<00:02, 61.11it/s]
Loading 0:  55%|█████▍    | 159/291 [00:10<00:03, 40.26it/s]
Loading 0:  57%|█████▋    | 165/291 [00:10<00:02, 42.37it/s]
Loading 0:  59%|█████▉    | 172/291 [00:11<00:02, 47.89it/s]
Loading 0:  62%|██████▏   | 179/291 [00:11<00:02, 51.69it/s]
Loading 0:  64%|██████▎   | 185/291 [00:11<00:02, 52.61it/s]
Loading 0:  66%|██████▋   | 193/291 [00:11<00:01, 58.73it/s]
Loading 0:  69%|██████▉   | 201/291 [00:11<00:01, 62.57it/s]
Loading 0:  71%|███████▏  | 208/291 [00:11<00:01, 62.53it/s]
Loading 0:  74%|███████▍  | 215/291 [00:11<00:01, 39.20it/s]
Loading 0:  76%|███████▌  | 221/291 [00:12<00:01, 41.53it/s]
Loading 0:  79%|███████▊  | 229/291 [00:12<00:01, 48.96it/s]
Loading 0:  81%|████████▏ | 237/291 [00:12<00:00, 54.40it/s]
Loading 0:  84%|████████▍ | 244/291 [00:12<00:00, 57.75it/s]
Loading 0:  86%|████████▋ | 251/291 [00:12<00:00, 59.32it/s]
Loading 0:  89%|████████▊ | 258/291 [00:12<00:00, 60.74it/s]
Loading 0:  92%|█████████▏| 267/291 [00:14<00:01, 12.97it/s]
Loading 0:  94%|█████████▍| 274/291 [00:14<00:01, 16.59it/s]
Loading 0:  97%|█████████▋| 283/291 [00:14<00:00, 22.51it/s]
Loading 0: 100%|█████████▉| 290/291 [00:14<00:00, 27.41it/s]
                                                            
/opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:919: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
trace2333-rolebench-llama2-v0-v1-mkmlizer:   warnings.warn(
trace2333-rolebench-llama2-v0-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
trace2333-rolebench-llama2-v0-v1-mkmlizer:   warnings.warn(
trace2333-rolebench-llama2-v0-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:769: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
trace2333-rolebench-llama2-v0-v1-mkmlizer:   warnings.warn(
trace2333-rolebench-llama2-v0-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.
trace2333-rolebench-llama2-v0-v1-mkmlizer:   warnings.warn(
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', 'dial tcp 10.144.34.78:8012: connect: connection refused\n')
trace2333-rolebench-llama2-v0-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()
trace2333-rolebench-llama2-v0-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
trace2333-rolebench-llama2-v0-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
trace2333-rolebench-llama2-v0-v1-mkmlizer: Saving duration: 0.397s
trace2333-rolebench-llama2-v0-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.273s
trace2333-rolebench-llama2-v0-v1-mkmlizer: creating bucket guanaco-reward-models
trace2333-rolebench-llama2-v0-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
trace2333-rolebench-llama2-v0-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/trace2333-rolebench-llama2-v0-v1_reward
trace2333-rolebench-llama2-v0-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/trace2333-rolebench-llama2-v0-v1_reward/config.json
trace2333-rolebench-llama2-v0-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/trace2333-rolebench-llama2-v0-v1_reward/special_tokens_map.json
trace2333-rolebench-llama2-v0-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/trace2333-rolebench-llama2-v0-v1_reward/merges.txt
trace2333-rolebench-llama2-v0-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/trace2333-rolebench-llama2-v0-v1_reward/tokenizer_config.json
trace2333-rolebench-llama2-v0-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/trace2333-rolebench-llama2-v0-v1_reward/vocab.json
trace2333-rolebench-llama2-v0-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/trace2333-rolebench-llama2-v0-v1_reward/tokenizer.json
trace2333-rolebench-llama2-v0-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/trace2333-rolebench-llama2-v0-v1_reward/reward.tensors
Job trace2333-rolebench-llama2-v0-v1-mkmlizer completed after 145.93s with status: succeeded
Stopping job with name trace2333-rolebench-llama2-v0-v1-mkmlizer
Pipeline stage MKMLizer completed in 146.92s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service trace2333-rolebench-llama2-v0-v1
Waiting for inference service trace2333-rolebench-llama2-v0-v1 to be ready
Inference service trace2333-rolebench-llama2-v0-v1 ready after 50.352269649505615s
Pipeline stage ISVCDeployer completed in 57.62s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.2244629859924316s
Received healthy response to inference request in 0.7627170085906982s
Received healthy response to inference request in 0.3945341110229492s
Received healthy response to inference request in 0.6019349098205566s
Received healthy response to inference request in 0.6649658679962158s
5 requests
0 failed requests
5th percentile: 0.4360142707824707
10th percentile: 0.4774944305419922
20th percentile: 0.5604547500610352
30th percentile: 0.6145411014556885
40th percentile: 0.6397534847259522
50th percentile: 0.6649658679962158
60th percentile: 0.7040663242340088
70th percentile: 0.7431667804718017
80th percentile: 0.855066204071045
90th percentile: 1.0397645950317382
95th percentile: 1.1321137905120848
99th percentile: 1.2059931468963623
mean time: 0.7297229766845703
Pipeline stage StressChecker completed in 4.75s
trace2333-rolebench-llama2-v0_v1 status is now deployed due to DeploymentManager action
trace2333-rolebench-llama2-v0_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of trace2333-rolebench-llama2-v0_v1
Running pipeline stage ISVCDeleter
Checking if service trace2333-rolebench-llama2-v0-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 5.32s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key trace2333-rolebench-llama2-v0-v1/config.json from bucket guanaco-mkml-models
Deleting key trace2333-rolebench-llama2-v0-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key trace2333-rolebench-llama2-v0-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key trace2333-rolebench-llama2-v0-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key trace2333-rolebench-llama2-v0-v1/tokenizer.model from bucket guanaco-mkml-models
Deleting key trace2333-rolebench-llama2-v0-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key trace2333-rolebench-llama2-v0-v1_reward/config.json from bucket guanaco-reward-models
Deleting key trace2333-rolebench-llama2-v0-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key trace2333-rolebench-llama2-v0-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key trace2333-rolebench-llama2-v0-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key trace2333-rolebench-llama2-v0-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key trace2333-rolebench-llama2-v0-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key trace2333-rolebench-llama2-v0-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.85s
trace2333-rolebench-llama2-v0_v1 status is now torndown due to DeploymentManager action