submission_id: trace2333-fd-llama3-v4_v1
developer_uid: Trace2333
best_of: 16
celo_rating: 1204.37
display_name: trace2333-fd-llama3-v3_v1
family_friendly_score: 0.0
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_v4
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: Trace2333/fd_llama3_v4
model_name: trace2333-fd-llama3-v3_v1
model_num_parameters: 8030261248.0
model_repo: Trace2333/fd_llama3_v4
model_size: 8B
num_battles: 20281
num_wins: 10074
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: 2024-08-01T05:49:59+00:00
us_pacific_date: 2024-07-31
win_ratio: 0.49672106898081947
Resubmit model
Running pipeline stage MKMLizer
Starting job with name trace2333-fd-llama3-v4-v1-mkmlizer
Waiting for job on trace2333-fd-llama3-v4-v1-mkmlizer to finish
trace2333-fd-llama3-v4-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-fd-llama3-v4-v1-mkmlizer: ║ _____ __ __ ║
trace2333-fd-llama3-v4-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
trace2333-fd-llama3-v4-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
trace2333-fd-llama3-v4-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
trace2333-fd-llama3-v4-v1-mkmlizer: ║ /___/ ║
trace2333-fd-llama3-v4-v1-mkmlizer: ║ ║
trace2333-fd-llama3-v4-v1-mkmlizer: ║ Version: 0.9.7 ║
trace2333-fd-llama3-v4-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
trace2333-fd-llama3-v4-v1-mkmlizer: ║ https://mk1.ai ║
trace2333-fd-llama3-v4-v1-mkmlizer: ║ ║
trace2333-fd-llama3-v4-v1-mkmlizer: ║ The license key for the current software has been verified as ║
trace2333-fd-llama3-v4-v1-mkmlizer: ║ belonging to: ║
trace2333-fd-llama3-v4-v1-mkmlizer: ║ ║
trace2333-fd-llama3-v4-v1-mkmlizer: ║ Chai Research Corp. ║
trace2333-fd-llama3-v4-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
trace2333-fd-llama3-v4-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
trace2333-fd-llama3-v4-v1-mkmlizer: ║ ║
trace2333-fd-llama3-v4-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
trace2333-fd-llama3-v4-v1-mkmlizer: Downloaded to shared memory in 60.781s
trace2333-fd-llama3-v4-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpg2p8fqjj, device:0
trace2333-fd-llama3-v4-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
trace2333-fd-llama3-v4-v1-mkmlizer: quantized model in 28.815s
trace2333-fd-llama3-v4-v1-mkmlizer: Processed model Trace2333/fd_llama3_v4 in 89.596s
trace2333-fd-llama3-v4-v1-mkmlizer: creating bucket guanaco-mkml-models
trace2333-fd-llama3-v4-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-fd-llama3-v4-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-fd-llama3-v4-v1
trace2333-fd-llama3-v4-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-fd-llama3-v4-v1/special_tokens_map.json
trace2333-fd-llama3-v4-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-fd-llama3-v4-v1/config.json
trace2333-fd-llama3-v4-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-fd-llama3-v4-v1/tokenizer_config.json
trace2333-fd-llama3-v4-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-fd-llama3-v4-v1/tokenizer.json
trace2333-fd-llama3-v4-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/trace2333-fd-llama3-v4-v1/flywheel_model.0.safetensors
trace2333-fd-llama3-v4-v1-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
trace2333-fd-llama3-v4-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:10, 26.01it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:07, 36.45it/s] Loading 0: 5%|▌ | 16/291 [00:00<00:08, 32.73it/s] Loading 0: 7%|▋ | 21/291 [00:00<00:07, 36.04it/s] Loading 0: 9%|▊ | 25/291 [00:00<00:07, 34.16it/s] Loading 0: 11%|█ | 31/291 [00:00<00:06, 40.43it/s] Loading 0: 12%|█▏ | 36/291 [00:01<00:11, 22.87it/s] Loading 0: 14%|█▍ | 41/291 [00:01<00:10, 24.20it/s] Loading 0: 16%|█▋ | 48/291 [00:01<00:07, 30.76it/s] Loading 0: 18%|█▊ | 52/291 [00:01<00:07, 30.08it/s] Loading 0: 20%|█▉ | 57/291 [00:01<00:07, 32.94it/s] Loading 0: 21%|██ | 61/291 [00:01<00:07, 32.69it/s] Loading 0: 23%|██▎ | 66/291 [00:02<00:06, 35.99it/s] Loading 0: 24%|██▍ | 70/291 [00:02<00:06, 33.55it/s] Loading 0: 25%|██▌ | 74/291 [00:02<00:06, 34.29it/s] Loading 0: 27%|██▋ | 78/291 [00:02<00:06, 35.21it/s] Loading 0: 28%|██▊ | 82/291 [00:02<00:08, 24.89it/s] Loading 0: 29%|██▉ | 85/291 [00:02<00:07, 25.82it/s] Loading 0: 31%|███ | 90/291 [00:02<00:06, 30.61it/s] Loading 0: 32%|███▏ | 94/291 [00:03<00:06, 31.04it/s] Loading 0: 34%|███▍ | 99/291 [00:03<00:05, 34.76it/s] Loading 0: 35%|███▌ | 103/291 [00:03<00:05, 33.90it/s] Loading 0: 37%|███▋ | 108/291 [00:03<00:04, 36.81it/s] Loading 0: 38%|███▊ | 112/291 [00:03<00:05, 35.37it/s] Loading 0: 40%|███▉ | 116/291 [00:03<00:04, 35.65it/s] Loading 0: 42%|████▏ | 122/291 [00:03<00:04, 40.13it/s] Loading 0: 44%|████▎ | 127/291 [00:03<00:04, 36.32it/s] Loading 0: 46%|████▌ | 133/291 [00:04<00:05, 31.59it/s] Loading 0: 47%|████▋ | 137/291 [00:04<00:05, 30.49it/s] Loading 0: 48%|████▊ | 141/291 [00:04<00:05, 27.86it/s] Loading 0: 51%|█████ | 147/291 [00:04<00:04, 33.07it/s] Loading 0: 52%|█████▏ | 151/291 [00:04<00:04, 32.50it/s] Loading 0: 54%|█████▎ | 156/291 [00:04<00:03, 35.14it/s] Loading 0: 55%|█████▍ | 160/291 [00:04<00:03, 33.89it/s] Loading 0: 57%|█████▋ | 165/291 [00:05<00:03, 36.24it/s] Loading 0: 58%|█████▊ | 169/291 [00:05<00:03, 34.33it/s] Loading 0: 60%|█████▉ | 174/291 [00:05<00:03, 36.81it/s] Loading 0: 61%|██████ | 178/291 [00:05<00:03, 34.27it/s] Loading 0: 63%|██████▎ | 184/291 [00:05<00:02, 39.98it/s] Loading 0: 65%|██████▍ | 189/291 [00:05<00:04, 24.47it/s] Loading 0: 67%|██████▋ | 194/291 [00:06<00:03, 25.77it/s] Loading 0: 69%|██████▉ | 201/291 [00:06<00:02, 32.66it/s] Loading 0: 70%|███████ | 205/291 [00:06<00:02, 32.11it/s] Loading 0: 72%|███████▏ | 210/291 [00:06<00:02, 34.79it/s] Loading 0: 74%|███████▎ | 214/291 [00:06<00:02, 33.51it/s] Loading 0: 75%|███████▌ | 219/291 [00:06<00:01, 36.30it/s] Loading 0: 77%|███████▋ | 223/291 [00:06<00:02, 33.81it/s] Loading 0: 78%|███████▊ | 227/291 [00:07<00:01, 32.97it/s] Loading 0: 79%|███████▉ | 231/291 [00:07<00:01, 33.23it/s] Loading 0: 81%|████████ | 235/291 [00:07<00:02, 25.94it/s] Loading 0: 82%|████████▏ | 239/291 [00:07<00:02, 25.01it/s] Loading 0: 85%|████████▍ | 246/291 [00:07<00:01, 32.43it/s] Loading 0: 86%|████████▌ | 250/291 [00:07<00:01, 32.10it/s] Loading 0: 88%|████████▊ | 255/291 [00:07<00:01, 35.15it/s] Loading 0: 89%|████████▉ | 259/291 [00:08<00:00, 33.27it/s] Loading 0: 91%|█████████ | 264/291 [00:08<00:00, 35.33it/s] Loading 0: 92%|█████████▏| 268/291 [00:08<00:00, 33.30it/s] Loading 0: 94%|█████████▍| 273/291 [00:08<00:00, 36.63it/s] Loading 0: 95%|█████████▌| 277/291 [00:08<00:00, 35.34it/s] Loading 0: 97%|█████████▋| 281/291 [00:08<00:00, 35.81it/s] Loading 0: 98%|█████████▊| 286/291 [00:14<00:01, 2.61it/s] Loading 0: 99%|█████████▉| 289/291 [00:14<00:00, 3.24it/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-v4-v1-mkmlizer: warnings.warn(
trace2333-fd-llama3-v4-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-v4-v1-mkmlizer: warnings.warn(
trace2333-fd-llama3-v4-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
trace2333-fd-llama3-v4-v1-mkmlizer: Saving duration: 1.421s
trace2333-fd-llama3-v4-v1-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 10.788s
trace2333-fd-llama3-v4-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
trace2333-fd-llama3-v4-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/trace2333-fd-llama3-v4-v1_reward
trace2333-fd-llama3-v4-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/trace2333-fd-llama3-v4-v1_reward/config.json
trace2333-fd-llama3-v4-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/trace2333-fd-llama3-v4-v1_reward/special_tokens_map.json
trace2333-fd-llama3-v4-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/trace2333-fd-llama3-v4-v1_reward/tokenizer_config.json
trace2333-fd-llama3-v4-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/trace2333-fd-llama3-v4-v1_reward/merges.txt
trace2333-fd-llama3-v4-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/trace2333-fd-llama3-v4-v1_reward/vocab.json
trace2333-fd-llama3-v4-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/trace2333-fd-llama3-v4-v1_reward/tokenizer.json
trace2333-fd-llama3-v4-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/trace2333-fd-llama3-v4-v1_reward/reward.tensors
Job trace2333-fd-llama3-v4-v1-mkmlizer completed after 137.11s with status: succeeded
Stopping job with name trace2333-fd-llama3-v4-v1-mkmlizer
Pipeline stage MKMLizer completed in 138.16s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service trace2333-fd-llama3-v4-v1
Waiting for inference service trace2333-fd-llama3-v4-v1 to be ready
Inference service trace2333-fd-llama3-v4-v1 ready after 130.92883610725403s
Pipeline stage ISVCDeployer completed in 132.61s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1962337493896484s
Received healthy response to inference request in 1.5019934177398682s
Received healthy response to inference request in 1.465017557144165s
Received healthy response to inference request in 1.433718204498291s
Received healthy response to inference request in 1.3854730129241943s
5 requests
0 failed requests
5th percentile: 1.3951220512390137
10th percentile: 1.404771089553833
20th percentile: 1.4240691661834717
30th percentile: 1.4399780750274658
40th percentile: 1.4524978160858155
50th percentile: 1.465017557144165
60th percentile: 1.4798079013824463
70th percentile: 1.4945982456207276
80th percentile: 1.6408414840698242
90th percentile: 1.9185376167297363
95th percentile: 2.0573856830596924
99th percentile: 2.1684641361236574
mean time: 1.5964871883392333
Pipeline stage StressChecker completed in 8.62s
trace2333-fd-llama3-v4_v1 status is now deployed due to DeploymentManager action
trace2333-fd-llama3-v4_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of trace2333-fd-llama3-v4_v1
Running pipeline stage ISVCDeleter
Checking if service trace2333-fd-llama3-v4-v1 is running
Tearing down inference service trace2333-fd-llama3-v4-v1
Service trace2333-fd-llama3-v4-v1 has been torndown
Pipeline stage ISVCDeleter completed in 4.37s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key trace2333-fd-llama3-v4-v1/config.json from bucket guanaco-mkml-models
Deleting key trace2333-fd-llama3-v4-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key trace2333-fd-llama3-v4-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key trace2333-fd-llama3-v4-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key trace2333-fd-llama3-v4-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key trace2333-fd-llama3-v4-v1_reward/config.json from bucket guanaco-reward-models
Deleting key trace2333-fd-llama3-v4-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key trace2333-fd-llama3-v4-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key trace2333-fd-llama3-v4-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key trace2333-fd-llama3-v4-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key trace2333-fd-llama3-v4-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key trace2333-fd-llama3-v4-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.35s
trace2333-fd-llama3-v4_v1 status is now torndown due to DeploymentManager action