developer_uid: Trace2333
submission_id: trace2333-duduk-llama3-v3_v3
model_name: trace2333-duduk-llama3-v3_v3
model_group: Trace2333/duduk_llama3_v
status: torndown
timestamp: 2024-07-30T08:07:26+00:00
num_battles: 13519
num_wins: 6498
celo_rating: 1183.12
family_friendly_score: 0.0
submission_type: basic
model_repo: Trace2333/duduk_llama3_v3
model_architecture: LlamaForCausalLM
reward_repo: Jellywibble/gpt2_xl_pairwise_89m_step_347634
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: trace2333-duduk-llama3-v3_v3
is_internal_developer: False
language_model: Trace2333/duduk_llama3_v3
model_size: 8B
ranking_group: single
us_pacific_date: 2024-07-30
win_ratio: 0.4806568533175531
generation_params: {'temperature': 1.05, 'top_p': 1.0, 'min_p': 0.12, 'top_k': 200, '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}
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}
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-duduk-llama3-v3-v3-mkmlizer
Waiting for job on trace2333-duduk-llama3-v3-v3-mkmlizer to finish
Stopping job with name trace2333-duduk-llama3-v3-v3-mkmlizer
%s, retrying in %s seconds...
Starting job with name trace2333-duduk-llama3-v3-v3-mkmlizer
Waiting for job on trace2333-duduk-llama3-v3-v3-mkmlizer to finish
trace2333-duduk-llama3-v3-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-duduk-llama3-v3-v3-mkmlizer: ║ _____ __ __ ║
trace2333-duduk-llama3-v3-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
trace2333-duduk-llama3-v3-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
trace2333-duduk-llama3-v3-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
trace2333-duduk-llama3-v3-v3-mkmlizer: ║ /___/ ║
trace2333-duduk-llama3-v3-v3-mkmlizer: ║ ║
trace2333-duduk-llama3-v3-v3-mkmlizer: ║ Version: 0.9.7 ║
trace2333-duduk-llama3-v3-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
trace2333-duduk-llama3-v3-v3-mkmlizer: ║ https://mk1.ai ║
trace2333-duduk-llama3-v3-v3-mkmlizer: ║ ║
trace2333-duduk-llama3-v3-v3-mkmlizer: ║ The license key for the current software has been verified as ║
trace2333-duduk-llama3-v3-v3-mkmlizer: ║ belonging to: ║
trace2333-duduk-llama3-v3-v3-mkmlizer: ║ ║
trace2333-duduk-llama3-v3-v3-mkmlizer: ║ Chai Research Corp. ║
trace2333-duduk-llama3-v3-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
trace2333-duduk-llama3-v3-v3-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
trace2333-duduk-llama3-v3-v3-mkmlizer: ║ ║
trace2333-duduk-llama3-v3-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
trace2333-duduk-llama3-v3-v3-mkmlizer: Downloaded to shared memory in 45.097s
trace2333-duduk-llama3-v3-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpqnium341, device:0
trace2333-duduk-llama3-v3-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
trace2333-duduk-llama3-v3-v3-mkmlizer: quantized model in 28.993s
trace2333-duduk-llama3-v3-v3-mkmlizer: Processed model Trace2333/duduk_llama3_v3 in 74.090s
trace2333-duduk-llama3-v3-v3-mkmlizer: creating bucket guanaco-mkml-models
trace2333-duduk-llama3-v3-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-duduk-llama3-v3-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-duduk-llama3-v3-v3
trace2333-duduk-llama3-v3-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-duduk-llama3-v3-v3/config.json
trace2333-duduk-llama3-v3-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-duduk-llama3-v3-v3/special_tokens_map.json
trace2333-duduk-llama3-v3-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-duduk-llama3-v3-v3/tokenizer_config.json
trace2333-duduk-llama3-v3-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-duduk-llama3-v3-v3/tokenizer.json
trace2333-duduk-llama3-v3-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/trace2333-duduk-llama3-v3-v3/flywheel_model.0.safetensors
trace2333-duduk-llama3-v3-v3-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
trace2333-duduk-llama3-v3-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:10, 26.48it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:07, 36.27it/s] Loading 0: 5%|▌ | 16/291 [00:00<00:08, 33.81it/s] Loading 0: 7%|▋ | 21/291 [00:00<00:07, 36.70it/s] Loading 0: 9%|▊ | 25/291 [00:00<00:07, 34.14it/s] Loading 0: 11%|█ | 31/291 [00:00<00:06, 40.68it/s] Loading 0: 12%|█▏ | 36/291 [00:01<00:11, 22.61it/s] Loading 0: 14%|█▍ | 41/291 [00:01<00:10, 24.53it/s] Loading 0: 16%|█▋ | 48/291 [00:01<00:07, 31.14it/s] Loading 0: 18%|█▊ | 52/291 [00:01<00:07, 31.05it/s] Loading 0: 20%|█▉ | 57/291 [00:01<00:06, 34.02it/s] Loading 0: 21%|██ | 61/291 [00:01<00:06, 33.12it/s] Loading 0: 23%|██▎ | 66/291 [00:02<00:06, 35.52it/s] Loading 0: 24%|██▍ | 70/291 [00:02<00:06, 34.06it/s] Loading 0: 25%|██▌ | 74/291 [00:02<00:06, 34.00it/s] Loading 0: 27%|██▋ | 78/291 [00:02<00:06, 33.17it/s] Loading 0: 28%|██▊ | 82/291 [00:02<00:09, 23.15it/s] Loading 0: 29%|██▉ | 85/291 [00:02<00:08, 24.32it/s] Loading 0: 31%|███ | 90/291 [00:02<00:07, 27.96it/s] Loading 0: 32%|███▏ | 94/291 [00:03<00:06, 28.25it/s] Loading 0: 34%|███▍ | 99/291 [00:03<00:06, 31.54it/s] Loading 0: 35%|███▌ | 103/291 [00:03<00:06, 30.88it/s] Loading 0: 37%|███▋ | 108/291 [00:03<00:05, 34.30it/s] Loading 0: 38%|███▊ | 112/291 [00:03<00:05, 32.93it/s] Loading 0: 40%|███▉ | 116/291 [00:03<00:05, 33.31it/s] Loading 0: 42%|████▏ | 122/291 [00:03<00:04, 37.76it/s] Loading 0: 44%|████▎ | 127/291 [00:04<00:04, 36.21it/s] Loading 0: 46%|████▌ | 133/291 [00:04<00:05, 30.37it/s] Loading 0: 47%|████▋ | 137/291 [00:04<00:05, 30.15it/s] Loading 0: 48%|████▊ | 141/291 [00:04<00:05, 27.08it/s] Loading 0: 51%|█████ | 147/291 [00:04<00:04, 32.17it/s] Loading 0: 52%|█████▏ | 151/291 [00:04<00:04, 31.91it/s] Loading 0: 54%|█████▎ | 156/291 [00:04<00:03, 34.40it/s] Loading 0: 55%|█████▍ | 160/291 [00:05<00:03, 33.18it/s] Loading 0: 57%|█████▋ | 165/291 [00:05<00:03, 35.51it/s] Loading 0: 58%|█████▊ | 169/291 [00:05<00:03, 33.07it/s] Loading 0: 60%|█████▉ | 174/291 [00:05<00:03, 35.19it/s] Loading 0: 61%|██████ | 178/291 [00:05<00:03, 33.53it/s] Loading 0: 63%|██████▎ | 184/291 [00:05<00:02, 39.41it/s] Loading 0: 65%|██████▍ | 189/291 [00:06<00:04, 24.07it/s] Loading 0: 67%|██████▋ | 194/291 [00:06<00:03, 25.92it/s] Loading 0: 69%|██████▉ | 201/291 [00:06<00:02, 32.89it/s] Loading 0: 71%|███████ | 206/291 [00:06<00:02, 33.87it/s] Loading 0: 72%|███████▏ | 210/291 [00:06<00:02, 34.82it/s] Loading 0: 74%|███████▎ | 214/291 [00:06<00:02, 33.42it/s] Loading 0: 75%|███████▌ | 219/291 [00:06<00:01, 36.23it/s] Loading 0: 77%|███████▋ | 223/291 [00:07<00:01, 34.91it/s] Loading 0: 78%|███████▊ | 227/291 [00:07<00:01, 34.75it/s] Loading 0: 79%|███████▉ | 231/291 [00:07<00:01, 34.67it/s] Loading 0: 81%|████████ | 235/291 [00:07<00:02, 25.56it/s] Loading 0: 82%|████████▏ | 239/291 [00:07<00:02, 25.54it/s] Loading 0: 85%|████████▍ | 246/291 [00:07<00:01, 33.40it/s] Loading 0: 86%|████████▌ | 250/291 [00:07<00:01, 32.80it/s] Loading 0: 88%|████████▊ | 255/291 [00:08<00:01, 35.13it/s] Loading 0: 89%|████████▉ | 259/291 [00:08<00:00, 33.37it/s] Loading 0: 91%|█████████ | 264/291 [00:08<00:00, 35.72it/s] Loading 0: 92%|█████████▏| 268/291 [00:08<00:00, 34.29it/s] Loading 0: 94%|█████████▍| 273/291 [00:08<00:00, 36.46it/s] Loading 0: 95%|█████████▌| 277/291 [00:08<00:00, 34.75it/s] Loading 0: 97%|█████████▋| 281/291 [00:08<00:00, 34.77it/s] Loading 0: 98%|█████████▊| 286/291 [00:14<00:01, 2.58it/s] Loading 0: 99%|█████████▉| 289/291 [00:14<00:00, 3.21it/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-duduk-llama3-v3-v3-mkmlizer: warnings.warn(
trace2333-duduk-llama3-v3-v3-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-duduk-llama3-v3-v3-mkmlizer: warnings.warn(
trace2333-duduk-llama3-v3-v3-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-duduk-llama3-v3-v3-mkmlizer: warnings.warn(
trace2333-duduk-llama3-v3-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
trace2333-duduk-llama3-v3-v3-mkmlizer: Saving duration: 1.365s
trace2333-duduk-llama3-v3-v3-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 11.618s
trace2333-duduk-llama3-v3-v3-mkmlizer: creating bucket guanaco-reward-models
trace2333-duduk-llama3-v3-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
trace2333-duduk-llama3-v3-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/trace2333-duduk-llama3-v3-v3_reward
trace2333-duduk-llama3-v3-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/trace2333-duduk-llama3-v3-v3_reward/config.json
trace2333-duduk-llama3-v3-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/trace2333-duduk-llama3-v3-v3_reward/special_tokens_map.json
trace2333-duduk-llama3-v3-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/trace2333-duduk-llama3-v3-v3_reward/tokenizer_config.json
trace2333-duduk-llama3-v3-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/trace2333-duduk-llama3-v3-v3_reward/reward.tensors
Job trace2333-duduk-llama3-v3-v3-mkmlizer completed after 114.99s with status: succeeded
Stopping job with name trace2333-duduk-llama3-v3-v3-mkmlizer
Pipeline stage MKMLizer completed in 116.62s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service trace2333-duduk-llama3-v3-v3
Waiting for inference service trace2333-duduk-llama3-v3-v3 to be ready
Inference service trace2333-duduk-llama3-v3-v3 ready after 120.83650970458984s
Pipeline stage ISVCDeployer completed in 122.75s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3220133781433105s
Received healthy response to inference request in 1.4924969673156738s
Received healthy response to inference request in 1.6312153339385986s
Received healthy response to inference request in 1.3999247550964355s
Received healthy response to inference request in 1.3824241161346436s
5 requests
0 failed requests
5th percentile: 1.3859242439270019
10th percentile: 1.3894243717193604
20th percentile: 1.3964246273040772
30th percentile: 1.4184391975402832
40th percentile: 1.4554680824279784
50th percentile: 1.4924969673156738
60th percentile: 1.5479843139648437
70th percentile: 1.6034716606140136
80th percentile: 1.769374942779541
90th percentile: 2.0456941604614256
95th percentile: 2.183853769302368
99th percentile: 2.294381456375122
mean time: 1.6456149101257325
Pipeline stage StressChecker completed in 8.86s
trace2333-duduk-llama3-v3_v3 status is now deployed due to DeploymentManager action
trace2333-duduk-llama3-v3_v3 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of trace2333-duduk-llama3-v3_v3
Running pipeline stage ISVCDeleter
Checking if service trace2333-duduk-llama3-v3-v3 is running
Tearing down inference service trace2333-duduk-llama3-v3-v3
Service trace2333-duduk-llama3-v3-v3 has been torndown
Pipeline stage ISVCDeleter completed in 4.46s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key trace2333-duduk-llama3-v3-v3/config.json from bucket guanaco-mkml-models
Deleting key trace2333-duduk-llama3-v3-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key trace2333-duduk-llama3-v3-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key trace2333-duduk-llama3-v3-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key trace2333-duduk-llama3-v3-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key trace2333-duduk-llama3-v3-v3_reward/config.json from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v3-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v3-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v3-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v3-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v3-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v3-v3_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.55s
trace2333-duduk-llama3-v3_v3 status is now torndown due to DeploymentManager action