submission_id: trace2333-pippa-llama2-v0_v4
developer_uid: Jellywibble
status: inactive
model_repo: Trace2333/pippa_llama2_v0
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
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}
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}
reward_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}
timestamp: 2024-06-13T00:37:50+00:00
model_name: trace2333-pippa-llama2-v0_v1
model_eval_status: success
model_group: Trace2333/pippa_llama2_v
num_battles: 44206
num_wins: 15927
celo_rating: 1084.28
propriety_score: 0.709570292844923
propriety_total_count: 19874.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 6738415616.0
best_of: 4
max_input_tokens: 512
max_output_tokens: 64
display_name: trace2333-pippa-llama2-v0_v1
ineligible_reason: None
language_model: Trace2333/pippa_llama2_v0
model_size: 7B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-12
win_ratio: 0.36029045830882683
Resubmit model
Running pipeline stage MKMLizer
Starting job with name trace2333-pippa-llama2-v0-v4-mkmlizer
Waiting for job on trace2333-pippa-llama2-v0-v4-mkmlizer to finish
trace2333-pippa-llama2-v0-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-pippa-llama2-v0-v4-mkmlizer: ║ _____ __ __ ║
trace2333-pippa-llama2-v0-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
trace2333-pippa-llama2-v0-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
trace2333-pippa-llama2-v0-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
trace2333-pippa-llama2-v0-v4-mkmlizer: ║ /___/ ║
trace2333-pippa-llama2-v0-v4-mkmlizer: ║ ║
trace2333-pippa-llama2-v0-v4-mkmlizer: ║ Version: 0.8.14 ║
trace2333-pippa-llama2-v0-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
trace2333-pippa-llama2-v0-v4-mkmlizer: ║ https://mk1.ai ║
trace2333-pippa-llama2-v0-v4-mkmlizer: ║ ║
trace2333-pippa-llama2-v0-v4-mkmlizer: ║ The license key for the current software has been verified as ║
trace2333-pippa-llama2-v0-v4-mkmlizer: ║ belonging to: ║
trace2333-pippa-llama2-v0-v4-mkmlizer: ║ ║
trace2333-pippa-llama2-v0-v4-mkmlizer: ║ Chai Research Corp. ║
trace2333-pippa-llama2-v0-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
trace2333-pippa-llama2-v0-v4-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
trace2333-pippa-llama2-v0-v4-mkmlizer: ║ ║
trace2333-pippa-llama2-v0-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
trace2333-pippa-llama2-v0-v4-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.
trace2333-pippa-llama2-v0-v4-mkmlizer: warnings.warn(warning_message, FutureWarning)
Failed to get response for submission blend_junes_2024-06-13: name 'requests' is not defined
trace2333-pippa-llama2-v0-v4-mkmlizer: Downloaded to shared memory in 26.776s
trace2333-pippa-llama2-v0-v4-mkmlizer: quantizing model to /dev/shm/model_cache
trace2333-pippa-llama2-v0-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
trace2333-pippa-llama2-v0-v4-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 7/291 [00:00<00:04, 65.27it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:04, 61.37it/s] Loading 0: 8%|▊ | 22/291 [00:00<00:03, 68.68it/s] Loading 0: 10%|█ | 30/291 [00:00<00:03, 72.53it/s] Loading 0: 13%|█▎ | 38/291 [00:00<00:03, 74.67it/s] Loading 0: 16%|█▌ | 46/291 [00:00<00:03, 69.59it/s] Loading 0: 19%|█▊ | 54/291 [00:01<00:07, 33.53it/s] Loading 0: 22%|██▏ | 65/291 [00:01<00:05, 45.10it/s] Loading 0: 25%|██▍ | 72/291 [00:01<00:04, 46.17it/s] Loading 0: 28%|██▊ | 81/291 [00:01<00:04, 52.20it/s] Loading 0: 31%|███ | 89/291 [00:01<00:03, 58.06it/s] Loading 0: 33%|███▎ | 97/291 [00:01<00:03, 63.03it/s] Loading 0: 36%|███▌ | 105/291 [00:02<00:04, 37.28it/s] Loading 0: 38%|███▊ | 111/291 [00:02<00:04, 40.01it/s] Loading 0: 41%|████ | 118/291 [00:02<00:03, 45.50it/s] Loading 0: 43%|████▎ | 125/291 [00:02<00:03, 49.92it/s] Loading 0: 45%|████▌ | 132/291 [00:02<00:02, 53.56it/s] Loading 0: 48%|████▊ | 139/291 [00:02<00:02, 57.25it/s] Loading 0: 51%|█████ | 148/291 [00:02<00:02, 61.27it/s] Loading 0: 54%|█████▍ | 157/291 [00:02<00:01, 68.03it/s] Loading 0: 57%|█████▋ | 165/291 [00:03<00:03, 37.59it/s] Loading 0: 60%|█████▉ | 174/291 [00:03<00:02, 44.42it/s] Loading 0: 63%|██████▎ | 183/291 [00:03<00:02, 50.45it/s] Loading 0: 66%|██████▌ | 191/291 [00:03<00:01, 56.40it/s] Loading 0: 68%|██████▊ | 198/291 [00:03<00:01, 57.21it/s] Loading 0: 70%|███████ | 205/291 [00:03<00:01, 58.93it/s] Loading 0: 73%|███████▎ | 213/291 [00:04<00:02, 38.61it/s] Loading 0: 75%|███████▌ | 219/291 [00:04<00:01, 41.34it/s] Loading 0: 78%|███████▊ | 226/291 [00:04<00:01, 46.88it/s] Loading 0: 80%|████████ | 233/291 [00:04<00:01, 51.33it/s] Loading 0: 82%|████████▏ | 240/291 [00:04<00:00, 55.04it/s] Loading 0: 85%|████████▍ | 247/291 [00:04<00:00, 58.75it/s] Loading 0: 88%|████████▊ | 255/291 [00:04<00:00, 64.14it/s] Loading 0: 90%|█████████ | 262/291 [00:05<00:00, 65.37it/s] Loading 0: 92%|█████████▏| 269/291 [00:06<00:01, 12.76it/s] Loading 0: 95%|█████████▍| 275/291 [00:06<00:01, 15.99it/s] Loading 0: 98%|█████████▊| 284/291 [00:06<00:00, 22.22it/s] You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
trace2333-pippa-llama2-v0-v4-mkmlizer: quantized model in 13.371s
trace2333-pippa-llama2-v0-v4-mkmlizer: Processed model Trace2333/pippa_llama2_v0 in 41.961s
trace2333-pippa-llama2-v0-v4-mkmlizer: creating bucket guanaco-mkml-models
trace2333-pippa-llama2-v0-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-pippa-llama2-v0-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-pippa-llama2-v0-v4
trace2333-pippa-llama2-v0-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-pippa-llama2-v0-v4/special_tokens_map.json
trace2333-pippa-llama2-v0-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-pippa-llama2-v0-v4/tokenizer_config.json
trace2333-pippa-llama2-v0-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-pippa-llama2-v0-v4/config.json
trace2333-pippa-llama2-v0-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-pippa-llama2-v0-v4/tokenizer.json
trace2333-pippa-llama2-v0-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/trace2333-pippa-llama2-v0-v4/tokenizer.model
trace2333-pippa-llama2-v0-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/trace2333-pippa-llama2-v0-v4/flywheel_model.0.safetensors
trace2333-pippa-llama2-v0-v4-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.
trace2333-pippa-llama2-v0-v4-mkmlizer: warnings.warn(
trace2333-pippa-llama2-v0-v4-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-pippa-llama2-v0-v4-mkmlizer: warnings.warn(
trace2333-pippa-llama2-v0-v4-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-pippa-llama2-v0-v4-mkmlizer: return self.fget.__get__(instance, owner)()
trace2333-pippa-llama2-v0-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
trace2333-pippa-llama2-v0-v4-mkmlizer: Saving duration: 0.246s
trace2333-pippa-llama2-v0-v4-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.090s
trace2333-pippa-llama2-v0-v4-mkmlizer: creating bucket guanaco-reward-models
trace2333-pippa-llama2-v0-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
trace2333-pippa-llama2-v0-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/trace2333-pippa-llama2-v0-v4_reward
trace2333-pippa-llama2-v0-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/trace2333-pippa-llama2-v0-v4_reward/config.json
trace2333-pippa-llama2-v0-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/trace2333-pippa-llama2-v0-v4_reward/tokenizer_config.json
trace2333-pippa-llama2-v0-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/trace2333-pippa-llama2-v0-v4_reward/merges.txt
trace2333-pippa-llama2-v0-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/trace2333-pippa-llama2-v0-v4_reward/vocab.json
trace2333-pippa-llama2-v0-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/trace2333-pippa-llama2-v0-v4_reward/special_tokens_map.json
trace2333-pippa-llama2-v0-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/trace2333-pippa-llama2-v0-v4_reward/tokenizer.json
trace2333-pippa-llama2-v0-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/trace2333-pippa-llama2-v0-v4_reward/reward.tensors
Job trace2333-pippa-llama2-v0-v4-mkmlizer completed after 72.8s with status: succeeded
Stopping job with name trace2333-pippa-llama2-v0-v4-mkmlizer
Pipeline stage MKMLizer completed in 75.97s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service trace2333-pippa-llama2-v0-v4
Waiting for inference service trace2333-pippa-llama2-v0-v4 to be ready
Inference service trace2333-pippa-llama2-v0-v4 ready after 30.25286030769348s
Pipeline stage ISVCDeployer completed in 37.28s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9309380054473877s
Received healthy response to inference request in 0.529526948928833s
Received healthy response to inference request in 0.661811113357544s
Received healthy response to inference request in 0.9713461399078369s
Received healthy response to inference request in 0.9899442195892334s
5 requests
0 failed requests
5th percentile: 0.5559837818145752
10th percentile: 0.5824406147003174
20th percentile: 0.6353542804718018
30th percentile: 0.7237181186676025
40th percentile: 0.8475321292877198
50th percentile: 0.9713461399078369
60th percentile: 0.9787853717803955
70th percentile: 0.9862246036529541
80th percentile: 1.1781429767608644
90th percentile: 1.554540491104126
95th percentile: 1.7427392482757567
99th percentile: 1.8932982540130614
mean time: 1.016713285446167
Pipeline stage StressChecker completed in 5.79s
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
trace2333-pippa-llama2-v0_v4 status is now deployed due to DeploymentManager action
trace2333-pippa-llama2-v0_v4 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics