developer_uid: Trace2333
submission_id: trace2333-fd-llama3-v4-n16_v3
model_name: trace2333-fd-llama3-v4-n16_v3
model_group: Trace2333/fd_llama3_v4_N
status: torndown
timestamp: 2024-08-03T04:45:38+00:00
num_battles: 14768
num_wins: 6873
celo_rating: 1192.9
family_friendly_score: 0.0
submission_type: basic
model_repo: Trace2333/fd_llama3_v4_N16
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-fd-llama3-v4-n16_v3
is_internal_developer: False
language_model: Trace2333/fd_llama3_v4_N16
model_size: 8B
ranking_group: single
us_pacific_date: 2024-08-02
win_ratio: 0.4653981581798483
generation_params: {'temperature': 1.05, 'top_p': 0.95, 'min_p': 0.06, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, '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\n{user_name}: {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-fd-llama3-v4-n16-v3-mkmlizer
Waiting for job on trace2333-fd-llama3-v4-n16-v3-mkmlizer to finish
trace2333-fd-llama3-v4-n16-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-fd-llama3-v4-n16-v3-mkmlizer: ║ _____ __ __ ║
trace2333-fd-llama3-v4-n16-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
trace2333-fd-llama3-v4-n16-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
trace2333-fd-llama3-v4-n16-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
trace2333-fd-llama3-v4-n16-v3-mkmlizer: ║ /___/ ║
trace2333-fd-llama3-v4-n16-v3-mkmlizer: ║ ║
trace2333-fd-llama3-v4-n16-v3-mkmlizer: ║ Version: 0.9.9 ║
trace2333-fd-llama3-v4-n16-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
trace2333-fd-llama3-v4-n16-v3-mkmlizer: ║ https://mk1.ai ║
trace2333-fd-llama3-v4-n16-v3-mkmlizer: ║ ║
trace2333-fd-llama3-v4-n16-v3-mkmlizer: ║ The license key for the current software has been verified as ║
trace2333-fd-llama3-v4-n16-v3-mkmlizer: ║ belonging to: ║
trace2333-fd-llama3-v4-n16-v3-mkmlizer: ║ ║
trace2333-fd-llama3-v4-n16-v3-mkmlizer: ║ Chai Research Corp. ║
trace2333-fd-llama3-v4-n16-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
trace2333-fd-llama3-v4-n16-v3-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
trace2333-fd-llama3-v4-n16-v3-mkmlizer: ║ ║
trace2333-fd-llama3-v4-n16-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
trace2333-fd-llama3-v4-n16-v3-mkmlizer: Downloaded to shared memory in 41.203s
trace2333-fd-llama3-v4-n16-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp016gpvnx, device:0
trace2333-fd-llama3-v4-n16-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
trace2333-fd-llama3-v4-n16-v3-mkmlizer: quantized model in 29.000s
trace2333-fd-llama3-v4-n16-v3-mkmlizer: Processed model Trace2333/fd_llama3_v4_N16 in 70.202s
trace2333-fd-llama3-v4-n16-v3-mkmlizer: creating bucket guanaco-mkml-models
trace2333-fd-llama3-v4-n16-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-fd-llama3-v4-n16-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-fd-llama3-v4-n16-v3
trace2333-fd-llama3-v4-n16-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-fd-llama3-v4-n16-v3/config.json
trace2333-fd-llama3-v4-n16-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-fd-llama3-v4-n16-v3/special_tokens_map.json
trace2333-fd-llama3-v4-n16-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-fd-llama3-v4-n16-v3/tokenizer_config.json
trace2333-fd-llama3-v4-n16-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-fd-llama3-v4-n16-v3/tokenizer.json
trace2333-fd-llama3-v4-n16-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/trace2333-fd-llama3-v4-n16-v3/flywheel_model.0.safetensors
trace2333-fd-llama3-v4-n16-v3-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
trace2333-fd-llama3-v4-n16-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:10, 26.34it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:07, 35.70it/s] Loading 0: 5%|▌ | 16/291 [00:00<00:08, 33.28it/s] Loading 0: 7%|▋ | 21/291 [00:00<00:07, 36.17it/s] Loading 0: 9%|▊ | 25/291 [00:00<00:07, 33.65it/s] Loading 0: 10%|█ | 30/291 [00:00<00:06, 37.91it/s] Loading 0: 12%|█▏ | 34/291 [00:01<00:10, 24.43it/s] Loading 0: 13%|█▎ | 38/291 [00:01<00:09, 25.83it/s] Loading 0: 14%|█▍ | 42/291 [00:01<00:10, 24.84it/s] Loading 0: 16%|█▋ | 48/291 [00:01<00:08, 29.66it/s] Loading 0: 18%|█▊ | 52/291 [00:01<00:08, 29.87it/s] Loading 0: 20%|█▉ | 57/291 [00:01<00:07, 32.68it/s] Loading 0: 21%|██ | 61/291 [00:01<00:07, 32.05it/s] Loading 0: 23%|██▎ | 66/291 [00:02<00:06, 35.06it/s] Loading 0: 24%|██▍ | 70/291 [00:02<00:06, 33.81it/s] Loading 0: 25%|██▌ | 74/291 [00:02<00:06, 32.89it/s] Loading 0: 27%|██▋ | 78/291 [00:02<00:06, 32.21it/s] Loading 0: 28%|██▊ | 82/291 [00:02<00:09, 21.98it/s] Loading 0: 30%|██▉ | 86/291 [00:02<00:08, 24.99it/s] Loading 0: 31%|███ | 90/291 [00:03<00:07, 27.65it/s] Loading 0: 32%|███▏ | 94/291 [00:03<00:07, 27.76it/s] Loading 0: 34%|███▍ | 99/291 [00:03<00:06, 31.05it/s] Loading 0: 35%|███▌ | 103/291 [00:03<00:06, 30.50it/s] Loading 0: 37%|███▋ | 108/291 [00:03<00:05, 33.75it/s] Loading 0: 38%|███▊ | 112/291 [00:03<00:05, 32.52it/s] Loading 0: 40%|███▉ | 116/291 [00:03<00:05, 32.30it/s] Loading 0: 42%|████▏ | 122/291 [00:03<00:04, 36.45it/s] Loading 0: 44%|████▎ | 127/291 [00:04<00:04, 35.07it/s] Loading 0: 46%|████▌ | 133/291 [00:04<00:05, 28.60it/s] Loading 0: 47%|████▋ | 137/291 [00:04<00:05, 29.42it/s] Loading 0: 48%|████▊ | 141/291 [00:04<00:05, 27.84it/s] Loading 0: 51%|█████ | 147/291 [00:04<00:04, 33.01it/s] Loading 0: 52%|█████▏ | 151/291 [00:04<00:04, 32.30it/s] Loading 0: 54%|█████▎ | 156/291 [00:05<00:03, 34.72it/s] Loading 0: 55%|█████▍ | 160/291 [00:05<00:04, 32.31it/s] Loading 0: 57%|█████▋ | 165/291 [00:05<00:03, 33.85it/s] Loading 0: 58%|█████▊ | 169/291 [00:05<00:03, 32.91it/s] Loading 0: 60%|█████▉ | 174/291 [00:05<00:03, 35.42it/s] Loading 0: 61%|██████ | 178/291 [00:05<00:03, 33.29it/s] Loading 0: 63%|██████▎ | 184/291 [00:05<00:02, 38.99it/s] Loading 0: 65%|██████▍ | 189/291 [00:06<00:04, 23.30it/s] Loading 0: 67%|██████▋ | 194/291 [00:06<00:03, 25.05it/s] Loading 0: 69%|██████▉ | 201/291 [00:06<00:02, 30.90it/s] Loading 0: 70%|███████ | 205/291 [00:06<00:02, 30.92it/s] Loading 0: 72%|███████▏ | 210/291 [00:06<00:02, 33.64it/s] Loading 0: 74%|███████▎ | 214/291 [00:06<00:02, 32.86it/s] Loading 0: 75%|███████▌ | 219/291 [00:07<00:02, 35.19it/s] Loading 0: 77%|███████▋ | 223/291 [00:07<00:02, 33.73it/s] Loading 0: 78%|███████▊ | 227/291 [00:07<00:01, 33.78it/s] Loading 0: 79%|███████▉ | 231/291 [00:07<00:01, 34.10it/s] Loading 0: 81%|████████ | 235/291 [00:07<00:02, 24.83it/s] Loading 0: 82%|████████▏ | 239/291 [00:07<00:02, 25.16it/s] Loading 0: 85%|████████▍ | 246/291 [00:07<00:01, 32.54it/s] Loading 0: 86%|████████▌ | 250/291 [00:08<00:01, 31.96it/s] Loading 0: 88%|████████▊ | 255/291 [00:08<00:01, 34.61it/s] Loading 0: 89%|████████▉ | 259/291 [00:08<00:00, 33.24it/s] Loading 0: 91%|█████████ | 264/291 [00:08<00:00, 35.77it/s] Loading 0: 92%|█████████▏| 268/291 [00:08<00:00, 34.42it/s] Loading 0: 94%|█████████▍| 273/291 [00:08<00:00, 35.88it/s] Loading 0: 95%|█████████▌| 277/291 [00:08<00:00, 34.43it/s] Loading 0: 97%|█████████▋| 281/291 [00:08<00:00, 34.57it/s] Loading 0: 98%|█████████▊| 286/291 [00:14<00:01, 2.60it/s] Loading 0: 99%|█████████▉| 289/291 [00:14<00:00, 3.23it/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-n16-v3-mkmlizer: warnings.warn(
trace2333-fd-llama3-v4-n16-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-fd-llama3-v4-n16-v3-mkmlizer: warnings.warn(
trace2333-fd-llama3-v4-n16-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-fd-llama3-v4-n16-v3-mkmlizer: warnings.warn(
trace2333-fd-llama3-v4-n16-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
trace2333-fd-llama3-v4-n16-v3-mkmlizer: Saving duration: 1.367s
trace2333-fd-llama3-v4-n16-v3-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 11.108s
trace2333-fd-llama3-v4-n16-v3-mkmlizer: creating bucket guanaco-reward-models
trace2333-fd-llama3-v4-n16-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
trace2333-fd-llama3-v4-n16-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/trace2333-fd-llama3-v4-n16-v3_reward
trace2333-fd-llama3-v4-n16-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/trace2333-fd-llama3-v4-n16-v3_reward/special_tokens_map.json
trace2333-fd-llama3-v4-n16-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/trace2333-fd-llama3-v4-n16-v3_reward/config.json
trace2333-fd-llama3-v4-n16-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/trace2333-fd-llama3-v4-n16-v3_reward/tokenizer_config.json
trace2333-fd-llama3-v4-n16-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/trace2333-fd-llama3-v4-n16-v3_reward/merges.txt
trace2333-fd-llama3-v4-n16-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/trace2333-fd-llama3-v4-n16-v3_reward/vocab.json
trace2333-fd-llama3-v4-n16-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/trace2333-fd-llama3-v4-n16-v3_reward/tokenizer.json
trace2333-fd-llama3-v4-n16-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/trace2333-fd-llama3-v4-n16-v3_reward/reward.tensors
Job trace2333-fd-llama3-v4-n16-v3-mkmlizer completed after 118.21s with status: succeeded
Stopping job with name trace2333-fd-llama3-v4-n16-v3-mkmlizer
Pipeline stage MKMLizer completed in 119.27s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service trace2333-fd-llama3-v4-n16-v3
Waiting for inference service trace2333-fd-llama3-v4-n16-v3 to be ready
Inference service trace2333-fd-llama3-v4-n16-v3 ready after 151.34805583953857s
Pipeline stage ISVCDeployer completed in 152.92s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2896053791046143s
Received healthy response to inference request in 1.460676908493042s
Received healthy response to inference request in 1.4557533264160156s
Received healthy response to inference request in 1.434370756149292s
Received healthy response to inference request in 1.381437063217163s
5 requests
0 failed requests
5th percentile: 1.3920238018035889
10th percentile: 1.4026105403900146
20th percentile: 1.4237840175628662
30th percentile: 1.4386472702026367
40th percentile: 1.4472002983093262
50th percentile: 1.4557533264160156
60th percentile: 1.4577227592468263
70th percentile: 1.4596921920776367
80th percentile: 1.6264626026153566
90th percentile: 1.9580339908599855
95th percentile: 2.1238196849822994
99th percentile: 2.256448240280151
mean time: 1.6043686866760254
Pipeline stage StressChecker completed in 8.95s
trace2333-fd-llama3-v4-n16_v3 status is now deployed due to DeploymentManager action
trace2333-fd-llama3-v4-n16_v3 status is now inactive due to auto deactivation removed underperforming models
trace2333-fd-llama3-v4-n16_v3 status is now torndown due to DeploymentManager action