developer_uid: Trace2333
submission_id: trace2333-fd-llama3-v2-a_2481_v2
model_name: trace2333-fd-llama3-v2-a_2481_v2
model_group: Trace2333/fd_llama3_v2_a
status: torndown
timestamp: 2024-08-14T01:42:12+00:00
num_battles: 11843
num_wins: 5315
celo_rating: 1181.7
family_friendly_score: 0.0
submission_type: basic
model_repo: Trace2333/fd_llama3_v2_axo_r32a16_scored
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-v2-a_2481_v2
is_internal_developer: False
language_model: Trace2333/fd_llama3_v2_axo_r32a16_scored
model_size: 8B
ranking_group: single
us_pacific_date: 2024-08-13
win_ratio: 0.44878831377184836
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}
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-fd-llama3-v2-a-2481-v2-mkmlizer
Waiting for job on trace2333-fd-llama3-v2-a-2481-v2-mkmlizer to finish
trace2333-fd-llama3-v2-a-2481-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-fd-llama3-v2-a-2481-v2-mkmlizer: ║ _____ __ __ ║
trace2333-fd-llama3-v2-a-2481-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
trace2333-fd-llama3-v2-a-2481-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
trace2333-fd-llama3-v2-a-2481-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
trace2333-fd-llama3-v2-a-2481-v2-mkmlizer: ║ /___/ ║
trace2333-fd-llama3-v2-a-2481-v2-mkmlizer: ║ ║
trace2333-fd-llama3-v2-a-2481-v2-mkmlizer: ║ Version: 0.9.9 ║
trace2333-fd-llama3-v2-a-2481-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
trace2333-fd-llama3-v2-a-2481-v2-mkmlizer: ║ https://mk1.ai ║
trace2333-fd-llama3-v2-a-2481-v2-mkmlizer: ║ ║
trace2333-fd-llama3-v2-a-2481-v2-mkmlizer: ║ The license key for the current software has been verified as ║
trace2333-fd-llama3-v2-a-2481-v2-mkmlizer: ║ belonging to: ║
trace2333-fd-llama3-v2-a-2481-v2-mkmlizer: ║ ║
trace2333-fd-llama3-v2-a-2481-v2-mkmlizer: ║ Chai Research Corp. ║
trace2333-fd-llama3-v2-a-2481-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
trace2333-fd-llama3-v2-a-2481-v2-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
trace2333-fd-llama3-v2-a-2481-v2-mkmlizer: ║ ║
trace2333-fd-llama3-v2-a-2481-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
trace2333-fd-llama3-v2-a-2481-v2-mkmlizer: Downloaded to shared memory in 40.415s
trace2333-fd-llama3-v2-a-2481-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpicdxqmnq, device:0
trace2333-fd-llama3-v2-a-2481-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
trace2333-fd-llama3-v2-a-2481-v2-mkmlizer: quantized model in 28.416s
trace2333-fd-llama3-v2-a-2481-v2-mkmlizer: Processed model Trace2333/fd_llama3_v2_axo_r32a16_scored in 68.831s
trace2333-fd-llama3-v2-a-2481-v2-mkmlizer: creating bucket guanaco-mkml-models
trace2333-fd-llama3-v2-a-2481-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-fd-llama3-v2-a-2481-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-fd-llama3-v2-a-2481-v2
trace2333-fd-llama3-v2-a-2481-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/trace2333-fd-llama3-v2-a-2481-v2/flywheel_model.0.safetensors
trace2333-fd-llama3-v2-a-2481-v2-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
trace2333-fd-llama3-v2-a-2481-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:10, 27.71it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:07, 37.41it/s] Loading 0: 5%|▌ | 16/291 [00:00<00:08, 33.25it/s] Loading 0: 7%|▋ | 21/291 [00:00<00:07, 36.21it/s] Loading 0: 9%|▊ | 25/291 [00:00<00:07, 34.45it/s] Loading 0: 11%|█ | 31/291 [00:00<00:06, 40.93it/s] Loading 0: 12%|█▏ | 36/291 [00:01<00:10, 24.34it/s] Loading 0: 14%|█▍ | 41/291 [00:01<00:09, 25.86it/s] Loading 0: 16%|█▋ | 48/291 [00:01<00:07, 32.22it/s] Loading 0: 18%|█▊ | 52/291 [00:01<00:07, 31.95it/s] Loading 0: 20%|█▉ | 57/291 [00:01<00:06, 34.76it/s] Loading 0: 21%|██ | 61/291 [00:01<00:06, 33.93it/s] Loading 0: 23%|██▎ | 66/291 [00:01<00:06, 36.68it/s] Loading 0: 24%|██▍ | 70/291 [00:02<00:06, 35.22it/s] Loading 0: 25%|██▌ | 74/291 [00:02<00:06, 35.31it/s] Loading 0: 27%|██▋ | 78/291 [00:02<00:05, 35.58it/s] Loading 0: 28%|██▊ | 82/291 [00:02<00:08, 25.18it/s] Loading 0: 29%|██▉ | 85/291 [00:02<00:07, 26.14it/s] Loading 0: 31%|███ | 90/291 [00:02<00:07, 28.71it/s] Loading 0: 32%|███▏ | 94/291 [00:02<00:06, 29.08it/s] Loading 0: 34%|███▍ | 99/291 [00:03<00:05, 32.72it/s] Loading 0: 35%|███▌ | 103/291 [00:03<00:05, 32.26it/s] Loading 0: 37%|███▋ | 108/291 [00:03<00:05, 35.18it/s] Loading 0: 38%|███▊ | 112/291 [00:03<00:05, 33.90it/s] Loading 0: 40%|███▉ | 116/291 [00:03<00:05, 34.45it/s] Loading 0: 42%|████▏ | 122/291 [00:03<00:04, 38.62it/s] Loading 0: 44%|████▎ | 127/291 [00:03<00:04, 36.01it/s] Loading 0: 46%|████▌ | 133/291 [00:04<00:05, 30.30it/s] Loading 0: 47%|████▋ | 137/291 [00:04<00:05, 30.23it/s] Loading 0: 48%|████▊ | 141/291 [00:04<00:05, 28.20it/s] Loading 0: 51%|█████ | 147/291 [00:04<00:04, 33.26it/s] Loading 0: 52%|█████▏ | 151/291 [00:04<00:04, 32.67it/s] Loading 0: 54%|█████▎ | 156/291 [00:04<00:03, 35.51it/s] Loading 0: 55%|█████▍ | 160/291 [00:04<00:03, 34.07it/s] Loading 0: 57%|█████▋ | 165/291 [00:05<00:03, 36.61it/s] Loading 0: 58%|█████▊ | 169/291 [00:05<00:03, 34.00it/s] Loading 0: 60%|█████▉ | 174/291 [00:05<00:03, 36.56it/s] Loading 0: 61%|██████ | 178/291 [00:05<00:03, 35.02it/s] Loading 0: 63%|██████▎ | 184/291 [00:05<00:02, 40.80it/s] Loading 0: 65%|██████▍ | 189/291 [00:05<00:04, 24.39it/s] Loading 0: 67%|██████▋ | 194/291 [00:06<00:03, 26.04it/s] Loading 0: 69%|██████▉ | 201/291 [00:06<00:02, 32.99it/s] Loading 0: 71%|███████ | 206/291 [00:06<00:02, 33.73it/s] Loading 0: 72%|███████▏ | 210/291 [00:06<00:02, 33.34it/s] Loading 0: 74%|███████▎ | 214/291 [00:06<00:02, 31.99it/s] Loading 0: 75%|███████▌ | 219/291 [00:06<00:02, 35.23it/s] Loading 0: 77%|███████▋ | 223/291 [00:06<00:01, 34.24it/s] Loading 0: 78%|███████▊ | 227/291 [00:06<00:01, 34.21it/s] Loading 0: 79%|███████▉ | 231/291 [00:07<00:01, 34.82it/s] Loading 0: 81%|████████ | 235/291 [00:07<00:02, 26.58it/s] Loading 0: 82%|████████▏ | 239/291 [00:07<00:01, 26.17it/s] Loading 0: 85%|████████▍ | 246/291 [00:07<00:01, 33.71it/s] Loading 0: 86%|████████▌ | 250/291 [00:07<00:01, 32.91it/s] Loading 0: 88%|████████▊ | 255/291 [00:07<00:01, 34.64it/s] Loading 0: 89%|████████▉ | 259/291 [00:07<00:00, 33.65it/s] Loading 0: 91%|█████████ | 264/291 [00:08<00:00, 36.55it/s] Loading 0: 92%|█████████▏| 268/291 [00:08<00:00, 35.21it/s] Loading 0: 94%|█████████▍| 273/291 [00:08<00:00, 37.85it/s] Loading 0: 95%|█████████▌| 277/291 [00:08<00:00, 36.23it/s] Loading 0: 97%|█████████▋| 281/291 [00:08<00:00, 36.02it/s] Loading 0: 98%|█████████▊| 286/291 [00:14<00:01, 2.63it/s] Loading 0: 99%|█████████▉| 289/291 [00:14<00:00, 3.27it/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-v2-a-2481-v2-mkmlizer: warnings.warn(
trace2333-fd-llama3-v2-a-2481-v2-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-v2-a-2481-v2-mkmlizer: warnings.warn(
trace2333-fd-llama3-v2-a-2481-v2-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-v2-a-2481-v2-mkmlizer: warnings.warn(
trace2333-fd-llama3-v2-a-2481-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
trace2333-fd-llama3-v2-a-2481-v2-mkmlizer: Saving duration: 1.381s
trace2333-fd-llama3-v2-a-2481-v2-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 10.661s
trace2333-fd-llama3-v2-a-2481-v2-mkmlizer: creating bucket guanaco-reward-models
trace2333-fd-llama3-v2-a-2481-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
trace2333-fd-llama3-v2-a-2481-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/trace2333-fd-llama3-v2-a-2481-v2_reward
trace2333-fd-llama3-v2-a-2481-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/trace2333-fd-llama3-v2-a-2481-v2_reward/tokenizer_config.json
trace2333-fd-llama3-v2-a-2481-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/trace2333-fd-llama3-v2-a-2481-v2_reward/config.json
trace2333-fd-llama3-v2-a-2481-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/trace2333-fd-llama3-v2-a-2481-v2_reward/special_tokens_map.json
trace2333-fd-llama3-v2-a-2481-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/trace2333-fd-llama3-v2-a-2481-v2_reward/merges.txt
trace2333-fd-llama3-v2-a-2481-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/trace2333-fd-llama3-v2-a-2481-v2_reward/vocab.json
trace2333-fd-llama3-v2-a-2481-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/trace2333-fd-llama3-v2-a-2481-v2_reward/tokenizer.json
Job trace2333-fd-llama3-v2-a-2481-v2-mkmlizer completed after 112.4s with status: succeeded
Stopping job with name trace2333-fd-llama3-v2-a-2481-v2-mkmlizer
Pipeline stage MKMLizer completed in 114.12s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service trace2333-fd-llama3-v2-a-2481-v2
Waiting for inference service trace2333-fd-llama3-v2-a-2481-v2 to be ready
Inference service trace2333-fd-llama3-v2-a-2481-v2 ready after 290.584105014801s
Pipeline stage ISVCDeployer completed in 292.58s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4497101306915283s
Received healthy response to inference request in 1.5581989288330078s
Received healthy response to inference request in 1.4492437839508057s
Received healthy response to inference request in 1.5214104652404785s
Received healthy response to inference request in 1.3224914073944092s
5 requests
0 failed requests
5th percentile: 1.3478418827056884
10th percentile: 1.3731923580169678
20th percentile: 1.4238933086395265
30th percentile: 1.4636771202087402
40th percentile: 1.4925437927246095
50th percentile: 1.5214104652404785
60th percentile: 1.5361258506774902
70th percentile: 1.5508412361145019
80th percentile: 1.736501169204712
90th percentile: 2.09310564994812
95th percentile: 2.271407890319824
99th percentile: 2.4140496826171876
mean time: 1.660210943222046
Pipeline stage StressChecker completed in 9.09s
trace2333-fd-llama3-v2-a_2481_v2 status is now deployed due to DeploymentManager action
trace2333-fd-llama3-v2-a_2481_v2 status is now inactive due to auto deactivation removed underperforming models
trace2333-fd-llama3-v2-a_2481_v2 status is now torndown due to DeploymentManager action