submission_id: trace2333-fd-allduduk-ll_4647_v1
developer_uid: Trace2333
alignment_samples: 0
best_of: 16
celo_rating: 1191.9
display_name: trace2333-fd-llama3-v2_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': 1.0, '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}
is_internal_developer: False
language_model: Trace2333/fd_allduduk_llama3_v1
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: Trace2333/fd_allduduk_ll
model_name: trace2333-fd-llama3-v2_v1
model_num_parameters: 8030261248.0
model_repo: Trace2333/fd_allduduk_llama3_v1
model_size: 8B
num_battles: 18872
num_wins: 9045
propriety_score: 0.6951807228915663
propriety_total_count: 830.0
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: 2024-08-01T05:36:24+00:00
us_pacific_date: 2024-07-31
win_ratio: 0.4792814752013565
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name trace2333-fd-allduduk-ll-4647-v1-mkmlizer
Waiting for job on trace2333-fd-allduduk-ll-4647-v1-mkmlizer to finish
trace2333-fd-allduduk-ll-4647-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-fd-allduduk-ll-4647-v1-mkmlizer: ║ _____ __ __ ║
trace2333-fd-allduduk-ll-4647-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
trace2333-fd-allduduk-ll-4647-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
trace2333-fd-allduduk-ll-4647-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
trace2333-fd-allduduk-ll-4647-v1-mkmlizer: ║ /___/ ║
trace2333-fd-allduduk-ll-4647-v1-mkmlizer: ║ ║
trace2333-fd-allduduk-ll-4647-v1-mkmlizer: ║ Version: 0.9.7 ║
trace2333-fd-allduduk-ll-4647-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
trace2333-fd-allduduk-ll-4647-v1-mkmlizer: ║ https://mk1.ai ║
trace2333-fd-allduduk-ll-4647-v1-mkmlizer: ║ ║
trace2333-fd-allduduk-ll-4647-v1-mkmlizer: ║ The license key for the current software has been verified as ║
trace2333-fd-allduduk-ll-4647-v1-mkmlizer: ║ belonging to: ║
trace2333-fd-allduduk-ll-4647-v1-mkmlizer: ║ ║
trace2333-fd-allduduk-ll-4647-v1-mkmlizer: ║ Chai Research Corp. ║
trace2333-fd-allduduk-ll-4647-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
trace2333-fd-allduduk-ll-4647-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
trace2333-fd-allduduk-ll-4647-v1-mkmlizer: ║ ║
trace2333-fd-allduduk-ll-4647-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
trace2333-fd-allduduk-ll-4647-v1-mkmlizer: Downloaded to shared memory in 58.162s
trace2333-fd-allduduk-ll-4647-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpxyf67swc, device:0
trace2333-fd-allduduk-ll-4647-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
trace2333-fd-allduduk-ll-4647-v1-mkmlizer: quantized model in 28.866s
trace2333-fd-allduduk-ll-4647-v1-mkmlizer: Processed model Trace2333/fd_allduduk_llama3_v1 in 87.028s
trace2333-fd-allduduk-ll-4647-v1-mkmlizer: creating bucket guanaco-mkml-models
trace2333-fd-allduduk-ll-4647-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-fd-allduduk-ll-4647-v1/config.json
trace2333-fd-allduduk-ll-4647-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-fd-allduduk-ll-4647-v1/special_tokens_map.json
trace2333-fd-allduduk-ll-4647-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-fd-allduduk-ll-4647-v1/tokenizer_config.json
trace2333-fd-allduduk-ll-4647-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-fd-allduduk-ll-4647-v1/tokenizer.json
trace2333-fd-allduduk-ll-4647-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/trace2333-fd-allduduk-ll-4647-v1/flywheel_model.0.safetensors
trace2333-fd-allduduk-ll-4647-v1-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
trace2333-fd-allduduk-ll-4647-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:11, 25.42it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:07, 35.52it/s] Loading 0: 5%|▌ | 16/291 [00:00<00:08, 33.32it/s] Loading 0: 7%|▋ | 21/291 [00:00<00:07, 36.75it/s] Loading 0: 9%|▊ | 25/291 [00:00<00:07, 34.24it/s] Loading 0: 11%|█ | 31/291 [00:00<00:06, 41.09it/s] Loading 0: 12%|█▏ | 36/291 [00:01<00:10, 23.39it/s] Loading 0: 14%|█▍ | 41/291 [00:01<00:10, 24.60it/s] Loading 0: 16%|█▋ | 48/291 [00:01<00:07, 30.71it/s] Loading 0: 18%|█▊ | 52/291 [00:01<00:07, 30.26it/s] Loading 0: 20%|█▉ | 57/291 [00:01<00:07, 33.08it/s] Loading 0: 21%|██ | 61/291 [00:01<00:07, 31.70it/s] Loading 0: 23%|██▎ | 66/291 [00:02<00:06, 34.56it/s] Loading 0: 24%|██▍ | 70/291 [00:02<00:06, 32.64it/s] Loading 0: 25%|██▌ | 74/291 [00:02<00:06, 32.34it/s] Loading 0: 27%|██▋ | 78/291 [00:02<00:06, 31.11it/s] Loading 0: 28%|██▊ | 82/291 [00:02<00:09, 22.58it/s] Loading 0: 29%|██▉ | 85/291 [00:02<00:08, 23.85it/s] Loading 0: 31%|███ | 90/291 [00:03<00:07, 28.69it/s] Loading 0: 32%|███▏ | 94/291 [00:03<00:06, 29.50it/s] Loading 0: 34%|███▍ | 99/291 [00:03<00:05, 33.32it/s] Loading 0: 35%|███▌ | 103/291 [00:03<00:05, 31.72it/s] Loading 0: 37%|███▋ | 108/291 [00:03<00:05, 34.75it/s] Loading 0: 38%|███▊ | 112/291 [00:03<00:05, 33.24it/s] Loading 0: 40%|███▉ | 116/291 [00:03<00:05, 32.82it/s] Loading 0: 42%|████▏ | 122/291 [00:03<00:04, 36.45it/s] Loading 0: 44%|████▎ | 127/291 [00:04<00:04, 34.48it/s] Loading 0: 46%|████▌ | 133/291 [00:04<00:05, 30.76it/s] Loading 0: 47%|████▋ | 137/291 [00:04<00:05, 30.64it/s] Loading 0: 48%|████▊ | 141/291 [00:04<00:05, 29.00it/s] Loading 0: 51%|█████ | 147/291 [00:04<00:04, 33.44it/s] Loading 0: 52%|█████▏ | 151/291 [00:04<00:04, 32.90it/s] Loading 0: 54%|█████▎ | 156/291 [00:04<00:03, 34.40it/s] Loading 0: 55%|█████▍ | 160/291 [00:05<00:03, 32.79it/s] Loading 0: 57%|█████▋ | 165/291 [00:05<00:03, 36.41it/s] Loading 0: 58%|█████▊ | 169/291 [00:05<00:03, 34.54it/s] Loading 0: 60%|█████▉ | 174/291 [00:05<00:03, 37.50it/s] Loading 0: 61%|██████ | 178/291 [00:05<00:03, 34.97it/s] Loading 0: 64%|██████▎ | 185/291 [00:05<00:02, 39.59it/s] Loading 0: 65%|██████▍ | 189/291 [00:06<00:03, 25.60it/s] Loading 0: 67%|██████▋ | 194/291 [00:06<00:03, 27.25it/s] Loading 0: 69%|██████▉ | 201/291 [00:06<00:02, 34.60it/s] Loading 0: 71%|███████ | 206/291 [00:06<00:02, 35.28it/s] Loading 0: 73%|███████▎ | 211/291 [00:06<00:02, 35.86it/s] Loading 0: 74%|███████▍ | 215/291 [00:06<00:02, 36.42it/s] Loading 0: 76%|███████▌ | 220/291 [00:06<00:01, 36.83it/s] Loading 0: 77%|███████▋ | 224/291 [00:06<00:01, 37.54it/s] Loading 0: 78%|███████▊ | 228/291 [00:07<00:02, 31.37it/s] Loading 0: 80%|████████ | 233/291 [00:07<00:02, 27.29it/s] Loading 0: 82%|████████▏ | 238/291 [00:07<00:01, 31.63it/s] Loading 0: 83%|████████▎ | 242/291 [00:07<00:01, 32.53it/s] Loading 0: 85%|████████▍ | 246/291 [00:07<00:01, 33.88it/s] Loading 0: 86%|████████▌ | 250/291 [00:07<00:01, 33.06it/s] Loading 0: 88%|████████▊ | 255/291 [00:07<00:00, 36.19it/s] Loading 0: 89%|████████▉ | 259/291 [00:08<00:00, 34.70it/s] Loading 0: 91%|█████████ | 264/291 [00:08<00:00, 37.57it/s] Loading 0: 92%|█████████▏| 268/291 [00:08<00:00, 35.49it/s] Loading 0: 94%|█████████▍| 273/291 [00:08<00:00, 38.42it/s] Loading 0: 95%|█████████▌| 277/291 [00:08<00:00, 36.23it/s] Loading 0: 97%|█████████▋| 281/291 [00:08<00:00, 36.19it/s] Loading 0: 98%|█████████▊| 286/291 [00:14<00:01, 2.59it/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-fd-allduduk-ll-4647-v1-mkmlizer: warnings.warn(
trace2333-fd-allduduk-ll-4647-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-allduduk-ll-4647-v1-mkmlizer: warnings.warn(
trace2333-fd-allduduk-ll-4647-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-allduduk-ll-4647-v1-mkmlizer: warnings.warn(
trace2333-fd-allduduk-ll-4647-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
trace2333-fd-allduduk-ll-4647-v1-mkmlizer: Saving duration: 1.402s
trace2333-fd-allduduk-ll-4647-v1-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 11.155s
trace2333-fd-allduduk-ll-4647-v1-mkmlizer: creating bucket guanaco-reward-models
trace2333-fd-allduduk-ll-4647-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
trace2333-fd-allduduk-ll-4647-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/trace2333-fd-allduduk-ll-4647-v1_reward
trace2333-fd-allduduk-ll-4647-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/trace2333-fd-allduduk-ll-4647-v1_reward/config.json
trace2333-fd-allduduk-ll-4647-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/trace2333-fd-allduduk-ll-4647-v1_reward/special_tokens_map.json
trace2333-fd-allduduk-ll-4647-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/trace2333-fd-allduduk-ll-4647-v1_reward/tokenizer_config.json
trace2333-fd-allduduk-ll-4647-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/trace2333-fd-allduduk-ll-4647-v1_reward/merges.txt
trace2333-fd-allduduk-ll-4647-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/trace2333-fd-allduduk-ll-4647-v1_reward/reward.tensors
Job trace2333-fd-allduduk-ll-4647-v1-mkmlizer completed after 126.72s with status: succeeded
Stopping job with name trace2333-fd-allduduk-ll-4647-v1-mkmlizer
Pipeline stage MKMLizer completed in 127.59s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service trace2333-fd-allduduk-ll-4647-v1
Waiting for inference service trace2333-fd-allduduk-ll-4647-v1 to be ready
Inference service trace2333-fd-allduduk-ll-4647-v1 ready after 131.03911638259888s
Pipeline stage ISVCDeployer completed in 132.56s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1647493839263916s
Received healthy response to inference request in 1.3631694316864014s
Received healthy response to inference request in 1.4406132698059082s
Received healthy response to inference request in 1.3970460891723633s
Received healthy response to inference request in 1.369680404663086s
5 requests
0 failed requests
5th percentile: 1.3644716262817382
10th percentile: 1.365773820877075
20th percentile: 1.368378210067749
30th percentile: 1.3751535415649414
40th percentile: 1.3860998153686523
50th percentile: 1.3970460891723633
60th percentile: 1.4144729614257812
70th percentile: 1.4318998336791993
80th percentile: 1.585440492630005
90th percentile: 1.8750949382781983
95th percentile: 2.019922161102295
99th percentile: 2.135783939361572
mean time: 1.5470517158508301
Pipeline stage StressChecker completed in 8.40s
trace2333-fd-allduduk-ll_4647_v1 status is now deployed due to DeploymentManager action
trace2333-fd-allduduk-ll_4647_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of trace2333-fd-allduduk-ll_4647_v1
Running pipeline stage ISVCDeleter
Checking if service trace2333-fd-allduduk-ll-4647-v1 is running
Tearing down inference service trace2333-fd-allduduk-ll-4647-v1
Service trace2333-fd-allduduk-ll-4647-v1 has been torndown
Pipeline stage ISVCDeleter completed in 4.57s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key trace2333-fd-allduduk-ll-4647-v1/config.json from bucket guanaco-mkml-models
Deleting key trace2333-fd-allduduk-ll-4647-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key trace2333-fd-allduduk-ll-4647-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key trace2333-fd-allduduk-ll-4647-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key trace2333-fd-allduduk-ll-4647-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key trace2333-fd-allduduk-ll-4647-v1_reward/config.json from bucket guanaco-reward-models
Deleting key trace2333-fd-allduduk-ll-4647-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key trace2333-fd-allduduk-ll-4647-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key trace2333-fd-allduduk-ll-4647-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key trace2333-fd-allduduk-ll-4647-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key trace2333-fd-allduduk-ll-4647-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key trace2333-fd-allduduk-ll-4647-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.76s
trace2333-fd-allduduk-ll_4647_v1 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics