submission_id: trace2333-fd-llama3-v2-f_8289_v1
developer_uid: Trace2333
alignment_samples: 12076
alignment_score: 1.2693589135434453
best_of: 16
celo_rating: 1186.79
display_name: trace2333-fd-llama3-v2-f_8289_v1
formatter: {'memory_template': "<|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\nYou: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}:', 'truncate_by_message': False}
generation_params: {'temperature': 1.15, 'top_p': 1.0, 'min_p': 0.06, 'top_k': 250, 'presence_penalty': 0.0, 'frequency_penalty': 0.1, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64, 'reward_max_token_input': 256}
is_internal_developer: False
language_model: Trace2333/fd_llama3_v2_fdall_r32a16_scored
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: Trace2333/fd_llama3_v2_f
model_name: trace2333-fd-llama3-v2-f_8289_v1
model_num_parameters: 8030261248.0
model_repo: Trace2333/fd_llama3_v2_fdall_r32a16_scored
model_size: 8B
num_battles: 12076
num_wins: 5466
propriety_score: 0.6991720331186753
propriety_total_count: 1087.0
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: Jellywibble/gpt2_xl_pairwise_89m_step_347634
status: torndown
submission_type: basic
timestamp: 2024-08-12T03:31:05+00:00
us_pacific_date: 2024-08-11
win_ratio: 0.4526333222921497
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name trace2333-fd-llama3-v2-f-8289-v1-mkmlizer
Waiting for job on trace2333-fd-llama3-v2-f-8289-v1-mkmlizer to finish
trace2333-fd-llama3-v2-f-8289-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-fd-llama3-v2-f-8289-v1-mkmlizer: ║ _____ __ __ ║
trace2333-fd-llama3-v2-f-8289-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
trace2333-fd-llama3-v2-f-8289-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
trace2333-fd-llama3-v2-f-8289-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
trace2333-fd-llama3-v2-f-8289-v1-mkmlizer: ║ /___/ ║
trace2333-fd-llama3-v2-f-8289-v1-mkmlizer: ║ ║
trace2333-fd-llama3-v2-f-8289-v1-mkmlizer: ║ Version: 0.9.9 ║
trace2333-fd-llama3-v2-f-8289-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
trace2333-fd-llama3-v2-f-8289-v1-mkmlizer: ║ https://mk1.ai ║
trace2333-fd-llama3-v2-f-8289-v1-mkmlizer: ║ ║
trace2333-fd-llama3-v2-f-8289-v1-mkmlizer: ║ The license key for the current software has been verified as ║
trace2333-fd-llama3-v2-f-8289-v1-mkmlizer: ║ belonging to: ║
trace2333-fd-llama3-v2-f-8289-v1-mkmlizer: ║ ║
trace2333-fd-llama3-v2-f-8289-v1-mkmlizer: ║ Chai Research Corp. ║
trace2333-fd-llama3-v2-f-8289-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
trace2333-fd-llama3-v2-f-8289-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
trace2333-fd-llama3-v2-f-8289-v1-mkmlizer: ║ ║
trace2333-fd-llama3-v2-f-8289-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
trace2333-fd-llama3-v2-f-8289-v1-mkmlizer: Downloaded to shared memory in 57.269s
trace2333-fd-llama3-v2-f-8289-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpcogdbot2, device:0
trace2333-fd-llama3-v2-f-8289-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
trace2333-fd-llama3-v2-f-8289-v1-mkmlizer: quantized model in 29.979s
trace2333-fd-llama3-v2-f-8289-v1-mkmlizer: Processed model Trace2333/fd_llama3_v2_fdall_r32a16_scored in 87.249s
trace2333-fd-llama3-v2-f-8289-v1-mkmlizer: creating bucket guanaco-mkml-models
trace2333-fd-llama3-v2-f-8289-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-fd-llama3-v2-f-8289-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-fd-llama3-v2-f-8289-v1
trace2333-fd-llama3-v2-f-8289-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-fd-llama3-v2-f-8289-v1/config.json
trace2333-fd-llama3-v2-f-8289-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-fd-llama3-v2-f-8289-v1/special_tokens_map.json
trace2333-fd-llama3-v2-f-8289-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-fd-llama3-v2-f-8289-v1/tokenizer_config.json
trace2333-fd-llama3-v2-f-8289-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-fd-llama3-v2-f-8289-v1/tokenizer.json
trace2333-fd-llama3-v2-f-8289-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/trace2333-fd-llama3-v2-f-8289-v1/flywheel_model.0.safetensors
trace2333-fd-llama3-v2-f-8289-v1-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
trace2333-fd-llama3-v2-f-8289-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:11, 25.33it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:07, 35.10it/s] Loading 0: 5%|▌ | 16/291 [00:00<00:08, 32.83it/s] Loading 0: 7%|▋ | 21/291 [00:00<00:07, 35.63it/s] Loading 0: 9%|▊ | 25/291 [00:00<00:07, 33.27it/s] Loading 0: 11%|█ | 31/291 [00:00<00:06, 39.30it/s] Loading 0: 12%|█▏ | 36/291 [00:01<00:12, 21.18it/s] Loading 0: 14%|█▍ | 41/291 [00:01<00:10, 23.17it/s] Loading 0: 16%|█▋ | 48/291 [00:01<00:08, 29.61it/s] Loading 0: 18%|█▊ | 52/291 [00:01<00:08, 29.80it/s] Loading 0: 20%|█▉ | 57/291 [00:01<00:07, 32.73it/s] Loading 0: 21%|██ | 61/291 [00:02<00:07, 32.07it/s] Loading 0: 23%|██▎ | 66/291 [00:02<00:06, 34.57it/s] Loading 0: 24%|██▍ | 70/291 [00:02<00:06, 32.88it/s] Loading 0: 25%|██▌ | 74/291 [00:02<00:06, 32.66it/s] Loading 0: 27%|██▋ | 78/291 [00:02<00:06, 32.48it/s] Loading 0: 28%|██▊ | 82/291 [00:02<00:09, 21.83it/s] Loading 0: 29%|██▉ | 85/291 [00:02<00:09, 22.68it/s] Loading 0: 31%|███ | 90/291 [00:03<00:07, 27.26it/s] Loading 0: 32%|███▏ | 94/291 [00:03<00:06, 28.23it/s] Loading 0: 34%|███▍ | 99/291 [00:03<00:06, 31.50it/s] Loading 0: 35%|███▌ | 103/291 [00:03<00:06, 30.48it/s] Loading 0: 37%|███▋ | 108/291 [00:03<00:05, 33.34it/s] Loading 0: 38%|███▊ | 112/291 [00:03<00:05, 32.09it/s] Loading 0: 40%|███▉ | 116/291 [00:03<00:05, 31.48it/s] Loading 0: 42%|████▏ | 122/291 [00:04<00:04, 35.85it/s] Loading 0: 44%|████▎ | 127/291 [00:04<00:04, 34.03it/s] Loading 0: 46%|████▌ | 133/291 [00:04<00:05, 27.71it/s] Loading 0: 47%|████▋ | 137/291 [00:04<00:05, 27.86it/s] Loading 0: 48%|████▊ | 140/291 [00:04<00:06, 24.63it/s] Loading 0: 51%|█████ | 147/291 [00:04<00:04, 31.87it/s] Loading 0: 52%|█████▏ | 151/291 [00:05<00:04, 31.12it/s] Loading 0: 54%|█████▎ | 156/291 [00:05<00:03, 33.76it/s] Loading 0: 55%|█████▍ | 160/291 [00:05<00:04, 32.06it/s] Loading 0: 57%|█████▋ | 165/291 [00:05<00:03, 34.22it/s] Loading 0: 58%|█████▊ | 169/291 [00:05<00:03, 32.93it/s] Loading 0: 60%|█████▉ | 174/291 [00:05<00:03, 34.87it/s] Loading 0: 61%|██████ | 178/291 [00:05<00:03, 33.31it/s] Loading 0: 63%|██████▎ | 184/291 [00:05<00:02, 39.21it/s] Loading 0: 65%|██████▍ | 189/291 [00:06<00:04, 22.92it/s] Loading 0: 67%|██████▋ | 194/291 [00:06<00:03, 24.57it/s] Loading 0: 69%|██████▉ | 201/291 [00:06<00:02, 30.84it/s] Loading 0: 70%|███████ | 205/291 [00:06<00:02, 30.76it/s] Loading 0: 72%|███████▏ | 210/291 [00:06<00:02, 33.48it/s] Loading 0: 74%|███████▎ | 214/291 [00:07<00:02, 32.37it/s] Loading 0: 75%|███████▌ | 219/291 [00:07<00:02, 34.93it/s] Loading 0: 77%|███████▋ | 223/291 [00:07<00:02, 33.87it/s] Loading 0: 78%|███████▊ | 227/291 [00:07<00:01, 33.80it/s] Loading 0: 79%|███████▉ | 231/291 [00:07<00:01, 33.60it/s] Loading 0: 81%|████████ | 235/291 [00:07<00:02, 23.65it/s] Loading 0: 82%|████████▏ | 239/291 [00:07<00:02, 23.97it/s] Loading 0: 85%|████████▍ | 246/291 [00:08<00:01, 31.67it/s] Loading 0: 86%|████████▌ | 250/291 [00:08<00:01, 31.60it/s] Loading 0: 88%|████████▊ | 255/291 [00:08<00:01, 34.52it/s] Loading 0: 89%|████████▉ | 259/291 [00:08<00:00, 32.64it/s] Loading 0: 91%|█████████ | 264/291 [00:08<00:00, 35.27it/s] Loading 0: 92%|█████████▏| 268/291 [00:08<00:00, 33.95it/s] Loading 0: 94%|█████████▍| 273/291 [00:08<00:00, 36.45it/s] Loading 0: 95%|█████████▌| 277/291 [00:08<00:00, 34.11it/s] Loading 0: 97%|█████████▋| 281/291 [00:09<00:00, 33.50it/s] Loading 0: 98%|█████████▊| 286/291 [00:14<00:01, 2.51it/s] Loading 0: 99%|█████████▉| 289/291 [00:14<00:00, 3.12it/s] /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:957: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
trace2333-fd-llama3-v2-f-8289-v1-mkmlizer: warnings.warn(
trace2333-fd-llama3-v2-f-8289-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:785: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
trace2333-fd-llama3-v2-f-8289-v1-mkmlizer: warnings.warn(
trace2333-fd-llama3-v2-f-8289-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:469: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
trace2333-fd-llama3-v2-f-8289-v1-mkmlizer: warnings.warn(
trace2333-fd-llama3-v2-f-8289-v1-mkmlizer: Saving duration: 1.425s
trace2333-fd-llama3-v2-f-8289-v1-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 11.509s
trace2333-fd-llama3-v2-f-8289-v1-mkmlizer: creating bucket guanaco-reward-models
trace2333-fd-llama3-v2-f-8289-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
trace2333-fd-llama3-v2-f-8289-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/trace2333-fd-llama3-v2-f-8289-v1_reward
trace2333-fd-llama3-v2-f-8289-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/trace2333-fd-llama3-v2-f-8289-v1_reward/config.json
trace2333-fd-llama3-v2-f-8289-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/trace2333-fd-llama3-v2-f-8289-v1_reward/special_tokens_map.json
trace2333-fd-llama3-v2-f-8289-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/trace2333-fd-llama3-v2-f-8289-v1_reward/tokenizer_config.json
trace2333-fd-llama3-v2-f-8289-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/trace2333-fd-llama3-v2-f-8289-v1_reward/merges.txt
trace2333-fd-llama3-v2-f-8289-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/trace2333-fd-llama3-v2-f-8289-v1_reward/vocab.json
trace2333-fd-llama3-v2-f-8289-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/trace2333-fd-llama3-v2-f-8289-v1_reward/tokenizer.json
trace2333-fd-llama3-v2-f-8289-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/trace2333-fd-llama3-v2-f-8289-v1_reward/reward.tensors
Job trace2333-fd-llama3-v2-f-8289-v1-mkmlizer completed after 135.49s with status: succeeded
Stopping job with name trace2333-fd-llama3-v2-f-8289-v1-mkmlizer
Pipeline stage MKMLizer completed in 136.69s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service trace2333-fd-llama3-v2-f-8289-v1
Waiting for inference service trace2333-fd-llama3-v2-f-8289-v1 to be ready
Inference service trace2333-fd-llama3-v2-f-8289-v1 ready after 201.22064781188965s
Pipeline stage ISVCDeployer completed in 203.26s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3167784214019775s
Received healthy response to inference request in 1.4820458889007568s
Received healthy response to inference request in 1.4288990497589111s
Received healthy response to inference request in 1.4318275451660156s
Received healthy response to inference request in 1.4105472564697266s
5 requests
0 failed requests
5th percentile: 1.4142176151275634
10th percentile: 1.4178879737854004
20th percentile: 1.4252286911010743
30th percentile: 1.429484748840332
40th percentile: 1.4306561470031738
50th percentile: 1.4318275451660156
60th percentile: 1.4519148826599122
70th percentile: 1.4720022201538085
80th percentile: 1.648992395401001
90th percentile: 1.9828854084014893
95th percentile: 2.1498319149017333
99th percentile: 2.2833891201019285
mean time: 1.6140196323394775
Pipeline stage StressChecker completed in 9.11s
trace2333-fd-llama3-v2-f_8289_v1 status is now deployed due to DeploymentManager action
trace2333-fd-llama3-v2-f_8289_v1 status is now inactive due to auto deactivation removed underperforming models
trace2333-fd-llama3-v2-f_8289_v1 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics