submission_id: trace2333-fd-allduduk-ll_6744_v1
developer_uid: Trace2333
alignment_samples: 0
best_of: 16
celo_rating: 1185.46
display_name: trace2333-fd-allduduk-ll_6744_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_v2
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: Trace2333/fd_allduduk_ll
model_name: trace2333-fd-allduduk-ll_6744_v1
model_num_parameters: 8030261248.0
model_repo: Trace2333/fd_allduduk_llama3_v2
model_size: 8B
num_battles: 19071
num_wins: 8957
propriety_score: 0.7536057692307693
propriety_total_count: 832.0
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: 2024-08-01T05:44:07+00:00
us_pacific_date: 2024-07-31
win_ratio: 0.46966598500340834
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name trace2333-fd-allduduk-ll-6744-v1-mkmlizer
Waiting for job on trace2333-fd-allduduk-ll-6744-v1-mkmlizer to finish
trace2333-fd-allduduk-ll-6744-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-fd-allduduk-ll-6744-v1-mkmlizer: ║ _____ __ __ ║
trace2333-fd-allduduk-ll-6744-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
trace2333-fd-allduduk-ll-6744-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
trace2333-fd-allduduk-ll-6744-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
trace2333-fd-allduduk-ll-6744-v1-mkmlizer: ║ /___/ ║
trace2333-fd-allduduk-ll-6744-v1-mkmlizer: ║ ║
trace2333-fd-allduduk-ll-6744-v1-mkmlizer: ║ Version: 0.9.7 ║
trace2333-fd-allduduk-ll-6744-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
trace2333-fd-allduduk-ll-6744-v1-mkmlizer: ║ https://mk1.ai ║
trace2333-fd-allduduk-ll-6744-v1-mkmlizer: ║ ║
trace2333-fd-allduduk-ll-6744-v1-mkmlizer: ║ The license key for the current software has been verified as ║
trace2333-fd-allduduk-ll-6744-v1-mkmlizer: ║ belonging to: ║
trace2333-fd-allduduk-ll-6744-v1-mkmlizer: ║ ║
trace2333-fd-allduduk-ll-6744-v1-mkmlizer: ║ Chai Research Corp. ║
trace2333-fd-allduduk-ll-6744-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
trace2333-fd-allduduk-ll-6744-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
trace2333-fd-allduduk-ll-6744-v1-mkmlizer: ║ ║
trace2333-fd-allduduk-ll-6744-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
trace2333-fd-allduduk-ll-6744-v1-mkmlizer: quantized model in 29.328s
trace2333-fd-allduduk-ll-6744-v1-mkmlizer: Processed model Trace2333/fd_allduduk_llama3_v2 in 87.155s
trace2333-fd-allduduk-ll-6744-v1-mkmlizer: creating bucket guanaco-mkml-models
trace2333-fd-allduduk-ll-6744-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-fd-allduduk-ll-6744-v1/config.json
trace2333-fd-allduduk-ll-6744-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-fd-allduduk-ll-6744-v1/special_tokens_map.json
trace2333-fd-allduduk-ll-6744-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-fd-allduduk-ll-6744-v1/tokenizer_config.json
trace2333-fd-allduduk-ll-6744-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-fd-allduduk-ll-6744-v1/tokenizer.json
trace2333-fd-allduduk-ll-6744-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/trace2333-fd-allduduk-ll-6744-v1/flywheel_model.0.safetensors
trace2333-fd-allduduk-ll-6744-v1-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
trace2333-fd-allduduk-ll-6744-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:11, 24.61it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:08, 34.65it/s] Loading 0: 5%|▌ | 16/291 [00:00<00:08, 32.63it/s] Loading 0: 7%|▋ | 21/291 [00:00<00:07, 35.49it/s] Loading 0: 9%|▊ | 25/291 [00:00<00:07, 33.87it/s] Loading 0: 11%|█ | 31/291 [00:00<00:06, 40.77it/s] Loading 0: 12%|█▏ | 36/291 [00:01<00:10, 24.66it/s] Loading 0: 14%|█▍ | 41/291 [00:01<00:09, 25.84it/s] Loading 0: 16%|█▋ | 48/291 [00:01<00:07, 31.78it/s] Loading 0: 18%|█▊ | 52/291 [00:01<00:07, 31.00it/s] Loading 0: 20%|█▉ | 57/291 [00:01<00:06, 33.78it/s] Loading 0: 21%|██ | 61/291 [00:01<00:06, 32.88it/s] Loading 0: 23%|██▎ | 66/291 [00:02<00:06, 34.75it/s] Loading 0: 24%|██▍ | 70/291 [00:02<00:06, 33.31it/s] Loading 0: 25%|██▌ | 74/291 [00:02<00:06, 32.75it/s] Loading 0: 27%|██▋ | 78/291 [00:02<00:06, 33.04it/s] Loading 0: 28%|██▊ | 82/291 [00:02<00:08, 23.77it/s] Loading 0: 29%|██▉ | 85/291 [00:02<00:08, 24.86it/s] Loading 0: 31%|███ | 90/291 [00:02<00:06, 29.56it/s] Loading 0: 32%|███▏ | 94/291 [00:03<00:06, 29.57it/s] Loading 0: 34%|███▍ | 99/291 [00:03<00:05, 32.32it/s] Loading 0: 35%|███▌ | 103/291 [00:03<00:06, 31.02it/s] Loading 0: 37%|███▋ | 108/291 [00:03<00:05, 34.11it/s] Loading 0: 38%|███▊ | 112/291 [00:03<00:05, 32.90it/s] Loading 0: 40%|███▉ | 116/291 [00:03<00:05, 31.49it/s] Loading 0: 42%|████▏ | 122/291 [00:03<00:04, 35.52it/s] Loading 0: 44%|████▎ | 127/291 [00:04<00:04, 33.59it/s] Loading 0: 46%|████▌ | 133/291 [00:04<00:05, 28.59it/s] Loading 0: 47%|████▋ | 137/291 [00:04<00:05, 29.05it/s] Loading 0: 48%|████▊ | 141/291 [00:04<00:05, 27.35it/s] Loading 0: 51%|█████ | 147/291 [00:04<00:04, 32.29it/s] Loading 0: 52%|█████▏ | 151/291 [00:04<00:04, 31.30it/s] Loading 0: 54%|█████▎ | 156/291 [00:04<00:03, 33.89it/s] Loading 0: 55%|█████▍ | 160/291 [00:05<00:04, 32.14it/s] Loading 0: 57%|█████▋ | 165/291 [00:05<00:03, 35.33it/s] Loading 0: 58%|█████▊ | 169/291 [00:05<00:03, 32.97it/s] Loading 0: 60%|█████▉ | 174/291 [00:05<00:03, 35.40it/s] Loading 0: 61%|██████ | 178/291 [00:05<00:03, 33.66it/s] Loading 0: 63%|██████▎ | 182/291 [00:05<00:03, 34.80it/s] Loading 0: 64%|██████▍ | 186/291 [00:05<00:04, 25.90it/s] Loading 0: 65%|██████▍ | 189/291 [00:06<00:04, 23.06it/s] Loading 0: 67%|██████▋ | 194/291 [00:06<00:03, 24.78it/s] Loading 0: 69%|██████▉ | 201/291 [00:06<00:02, 32.23it/s] Loading 0: 70%|███████ | 205/291 [00:06<00:02, 31.52it/s] Loading 0: 72%|███████▏ | 210/291 [00:06<00:02, 33.92it/s] Loading 0: 74%|███████▎ | 214/291 [00:06<00:02, 32.35it/s] Loading 0: 75%|███████▌ | 219/291 [00:06<00:02, 35.14it/s] Loading 0: 77%|███████▋ | 223/291 [00:07<00:02, 33.55it/s] Loading 0: 78%|███████▊ | 227/291 [00:07<00:01, 32.76it/s] Loading 0: 79%|███████▉ | 231/291 [00:07<00:01, 31.97it/s] Loading 0: 81%|████████ | 235/291 [00:07<00:02, 24.43it/s] Loading 0: 82%|████████▏ | 239/291 [00:07<00:02, 24.04it/s] Loading 0: 85%|████████▍ | 246/291 [00:07<00:01, 31.37it/s] Loading 0: 86%|████████▌ | 250/291 [00:08<00:01, 31.05it/s] Loading 0: 88%|████████▊ | 255/291 [00:08<00:01, 33.52it/s] Loading 0: 89%|████████▉ | 259/291 [00:08<00:00, 32.26it/s] Loading 0: 91%|█████████ | 264/291 [00:08<00:00, 34.52it/s] Loading 0: 92%|█████████▏| 268/291 [00:08<00:00, 32.44it/s] Loading 0: 94%|█████████▍| 273/291 [00:08<00:00, 33.99it/s] Loading 0: 95%|█████████▌| 277/291 [00:08<00:00, 32.45it/s] Loading 0: 97%|█████████▋| 281/291 [00:08<00:00, 32.61it/s] Loading 0: 98%|█████████▊| 286/291 [00:14<00:01, 2.57it/s] Loading 0: 99%|█████████▉| 289/291 [00:14<00:00, 3.20it/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-6744-v1-mkmlizer: warnings.warn(
trace2333-fd-allduduk-ll-6744-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-6744-v1-mkmlizer: warnings.warn(
trace2333-fd-allduduk-ll-6744-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-6744-v1-mkmlizer: warnings.warn(
trace2333-fd-allduduk-ll-6744-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
trace2333-fd-allduduk-ll-6744-v1-mkmlizer: Saving duration: 1.406s
trace2333-fd-allduduk-ll-6744-v1-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 10.953s
trace2333-fd-allduduk-ll-6744-v1-mkmlizer: creating bucket guanaco-reward-models
trace2333-fd-allduduk-ll-6744-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
trace2333-fd-allduduk-ll-6744-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/trace2333-fd-allduduk-ll-6744-v1_reward
trace2333-fd-allduduk-ll-6744-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/trace2333-fd-allduduk-ll-6744-v1_reward/config.json
trace2333-fd-allduduk-ll-6744-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/trace2333-fd-allduduk-ll-6744-v1_reward/tokenizer_config.json
trace2333-fd-allduduk-ll-6744-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/trace2333-fd-allduduk-ll-6744-v1_reward/special_tokens_map.json
trace2333-fd-allduduk-ll-6744-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/trace2333-fd-allduduk-ll-6744-v1_reward/merges.txt
trace2333-fd-allduduk-ll-6744-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/trace2333-fd-allduduk-ll-6744-v1_reward/vocab.json
trace2333-fd-allduduk-ll-6744-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/trace2333-fd-allduduk-ll-6744-v1_reward/tokenizer.json
trace2333-fd-allduduk-ll-6744-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/trace2333-fd-allduduk-ll-6744-v1_reward/reward.tensors
Job trace2333-fd-allduduk-ll-6744-v1-mkmlizer completed after 136.38s with status: succeeded
Stopping job with name trace2333-fd-allduduk-ll-6744-v1-mkmlizer
Pipeline stage MKMLizer completed in 137.30s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service trace2333-fd-allduduk-ll-6744-v1
Waiting for inference service trace2333-fd-allduduk-ll-6744-v1 to be ready
Inference service trace2333-fd-allduduk-ll-6744-v1 ready after 130.95408987998962s
Pipeline stage ISVCDeployer completed in 132.43s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2160818576812744s
Received healthy response to inference request in 1.4730918407440186s
Received healthy response to inference request in 1.430260419845581s
Received healthy response to inference request in 1.3991520404815674s
Received healthy response to inference request in 1.3868706226348877s
5 requests
0 failed requests
5th percentile: 1.3893269062042237
10th percentile: 1.3917831897735595
20th percentile: 1.3966957569122314
30th percentile: 1.40537371635437
40th percentile: 1.4178170680999755
50th percentile: 1.430260419845581
60th percentile: 1.447392988204956
70th percentile: 1.4645255565643311
80th percentile: 1.6216898441314698
90th percentile: 1.9188858509063722
95th percentile: 2.067483854293823
99th percentile: 2.186362257003784
mean time: 1.5810913562774658
Pipeline stage StressChecker completed in 8.53s
trace2333-fd-allduduk-ll_6744_v1 status is now deployed due to DeploymentManager action
trace2333-fd-allduduk-ll_6744_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of trace2333-fd-allduduk-ll_6744_v1
Running pipeline stage ISVCDeleter
Checking if service trace2333-fd-allduduk-ll-6744-v1 is running
Tearing down inference service trace2333-fd-allduduk-ll-6744-v1
Service trace2333-fd-allduduk-ll-6744-v1 has been torndown
Pipeline stage ISVCDeleter completed in 4.87s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key trace2333-fd-allduduk-ll-6744-v1/config.json from bucket guanaco-mkml-models
Deleting key trace2333-fd-allduduk-ll-6744-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key trace2333-fd-allduduk-ll-6744-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key trace2333-fd-allduduk-ll-6744-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key trace2333-fd-allduduk-ll-6744-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key trace2333-fd-allduduk-ll-6744-v1_reward/config.json from bucket guanaco-reward-models
Deleting key trace2333-fd-allduduk-ll-6744-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key trace2333-fd-allduduk-ll-6744-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key trace2333-fd-allduduk-ll-6744-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key trace2333-fd-allduduk-ll-6744-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key trace2333-fd-allduduk-ll-6744-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key trace2333-fd-allduduk-ll-6744-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.43s
trace2333-fd-allduduk-ll_6744_v1 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics