trace2333-fd-llama3-v3-nall

submission_id: trace2333-fd-llama3-v3-nall_v1

developer_uid: Trace2333

best_of: 16

celo_rating: 1224.81

display_name: trace2333-fd-llama3-v3-nall_v1

family_friendly_score: 0.0

formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}

generation_params: {'temperature': 1.05, 'top_p': 1.0, 'min_p': 0.06, 'top_k': 80, '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_v3_Nall

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_group: Trace2333/fd_llama3_v3_N

model_name: trace2333-fd-llama3-v3-nall_v1

model_num_parameters: 8030261248.0

model_repo: Trace2333/fd_llama3_v3_Nall

model_size: 8B

num_battles: 13632

num_wins: 6889

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: 2024-08-03T08:36:56+00:00

us_pacific_date: 2024-08-03

win_ratio: 0.5053550469483568

Resubmit model

Running pipeline stage MKMLizer
Starting job with name trace2333-fd-llama3-v3-nall-v1-mkmlizer
Waiting for job on trace2333-fd-llama3-v3-nall-v1-mkmlizer to finish
trace2333-fd-llama3-v3-nall-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-fd-llama3-v3-nall-v1-mkmlizer: ║     _____            __           __                                ║
trace2333-fd-llama3-v3-nall-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
trace2333-fd-llama3-v3-nall-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
trace2333-fd-llama3-v3-nall-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
trace2333-fd-llama3-v3-nall-v1-mkmlizer: ║       /___/                                                         ║
trace2333-fd-llama3-v3-nall-v1-mkmlizer: ║                                                                     ║
trace2333-fd-llama3-v3-nall-v1-mkmlizer: ║  Version: 0.9.9                                                     ║
trace2333-fd-llama3-v3-nall-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
trace2333-fd-llama3-v3-nall-v1-mkmlizer: ║  https://mk1.ai                                                     ║
trace2333-fd-llama3-v3-nall-v1-mkmlizer: ║                                                                     ║
trace2333-fd-llama3-v3-nall-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
trace2333-fd-llama3-v3-nall-v1-mkmlizer: ║  belonging to:                                                      ║
trace2333-fd-llama3-v3-nall-v1-mkmlizer: ║                                                                     ║
trace2333-fd-llama3-v3-nall-v1-mkmlizer: ║  Chai Research Corp.                                                ║
trace2333-fd-llama3-v3-nall-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
trace2333-fd-llama3-v3-nall-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
trace2333-fd-llama3-v3-nall-v1-mkmlizer: ║                                                                     ║
trace2333-fd-llama3-v3-nall-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
trace2333-fd-llama3-v3-nall-v1-mkmlizer: Downloaded to shared memory in 54.664s
trace2333-fd-llama3-v3-nall-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmplqe6ha4n, device:0
trace2333-fd-llama3-v3-nall-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
trace2333-fd-llama3-v3-nall-v1-mkmlizer: quantized model in 28.611s
trace2333-fd-llama3-v3-nall-v1-mkmlizer: Processed model Trace2333/fd_llama3_v3_Nall in 83.275s
trace2333-fd-llama3-v3-nall-v1-mkmlizer: creating bucket guanaco-mkml-models
trace2333-fd-llama3-v3-nall-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-fd-llama3-v3-nall-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-fd-llama3-v3-nall-v1
trace2333-fd-llama3-v3-nall-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-fd-llama3-v3-nall-v1/config.json
trace2333-fd-llama3-v3-nall-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-fd-llama3-v3-nall-v1/special_tokens_map.json
trace2333-fd-llama3-v3-nall-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-fd-llama3-v3-nall-v1/tokenizer_config.json
trace2333-fd-llama3-v3-nall-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-fd-llama3-v3-nall-v1/tokenizer.json
trace2333-fd-llama3-v3-nall-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/trace2333-fd-llama3-v3-nall-v1/flywheel_model.0.safetensors
trace2333-fd-llama3-v3-nall-v1-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
trace2333-fd-llama3-v3-nall-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:10, 26.26it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:07, 36.16it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:08, 34.22it/s]
Loading 0:   7%|▋         | 21/291 [00:00<00:07, 37.53it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:07, 34.84it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:06, 40.73it/s]
Loading 0:  12%|█▏        | 36/291 [00:01<00:11, 23.17it/s]
Loading 0:  14%|█▍        | 41/291 [00:01<00:09, 25.09it/s]
Loading 0:  16%|█▋        | 48/291 [00:01<00:07, 32.22it/s]
Loading 0:  18%|█▊        | 53/291 [00:01<00:07, 33.47it/s]
Loading 0:  20%|█▉        | 57/291 [00:01<00:06, 34.48it/s]
Loading 0:  21%|██        | 61/291 [00:01<00:06, 33.29it/s]
Loading 0:  23%|██▎       | 66/291 [00:02<00:06, 36.05it/s]
Loading 0:  24%|██▍       | 70/291 [00:02<00:06, 34.27it/s]
Loading 0:  25%|██▌       | 74/291 [00:02<00:06, 33.67it/s]
Loading 0:  27%|██▋       | 78/291 [00:02<00:06, 33.74it/s]
Loading 0:  28%|██▊       | 82/291 [00:02<00:09, 23.00it/s]
Loading 0:  30%|██▉       | 86/291 [00:02<00:07, 25.92it/s]
Loading 0:  31%|███       | 90/291 [00:02<00:07, 28.53it/s]
Loading 0:  32%|███▏      | 94/291 [00:03<00:06, 29.48it/s]
Loading 0:  34%|███▍      | 99/291 [00:03<00:05, 33.04it/s]
Loading 0:  35%|███▌      | 103/291 [00:03<00:05, 32.19it/s]
Loading 0:  37%|███▋      | 108/291 [00:03<00:05, 35.07it/s]
Loading 0:  38%|███▊      | 112/291 [00:03<00:05, 33.22it/s]
Loading 0:  40%|███▉      | 116/291 [00:03<00:05, 33.34it/s]
Loading 0:  42%|████▏     | 122/291 [00:03<00:04, 38.14it/s]
Loading 0:  44%|████▎     | 127/291 [00:03<00:04, 36.27it/s]
Loading 0:  46%|████▌     | 133/291 [00:04<00:05, 30.29it/s]
Loading 0:  47%|████▋     | 137/291 [00:04<00:04, 30.87it/s]
Loading 0:  48%|████▊     | 141/291 [00:04<00:05, 29.07it/s]
Loading 0:  51%|█████     | 147/291 [00:04<00:04, 33.70it/s]
Loading 0:  52%|█████▏    | 151/291 [00:04<00:04, 32.71it/s]
Loading 0:  54%|█████▎    | 156/291 [00:04<00:03, 34.77it/s]
Loading 0:  55%|█████▍    | 160/291 [00:04<00:03, 33.71it/s]
Loading 0:  57%|█████▋    | 165/291 [00:05<00:03, 36.57it/s]
Loading 0:  58%|█████▊    | 169/291 [00:05<00:03, 35.30it/s]
Loading 0:  60%|█████▉    | 174/291 [00:05<00:03, 37.89it/s]
Loading 0:  61%|██████    | 178/291 [00:05<00:03, 35.81it/s]
Loading 0:  63%|██████▎   | 184/291 [00:05<00:02, 41.71it/s]
Loading 0:  65%|██████▍   | 189/291 [00:05<00:04, 24.70it/s]
Loading 0:  67%|██████▋   | 194/291 [00:06<00:03, 26.14it/s]
Loading 0:  69%|██████▉   | 201/291 [00:06<00:02, 33.02it/s]
Loading 0:  71%|███████   | 206/291 [00:06<00:02, 33.81it/s]
Loading 0:  72%|███████▏  | 210/291 [00:06<00:02, 34.80it/s]
Loading 0:  74%|███████▎  | 214/291 [00:06<00:02, 34.22it/s]
Loading 0:  75%|███████▌  | 219/291 [00:06<00:01, 37.02it/s]
Loading 0:  77%|███████▋  | 223/291 [00:06<00:01, 35.64it/s]
Loading 0:  78%|███████▊  | 227/291 [00:06<00:01, 35.88it/s]
Loading 0:  79%|███████▉  | 231/291 [00:07<00:01, 35.15it/s]
Loading 0:  81%|████████  | 235/291 [00:07<00:02, 25.38it/s]
Loading 0:  82%|████████▏ | 239/291 [00:07<00:02, 25.71it/s]
Loading 0:  85%|████████▍ | 246/291 [00:07<00:01, 33.52it/s]
Loading 0:  86%|████████▌ | 250/291 [00:07<00:01, 33.21it/s]
Loading 0:  88%|████████▊ | 255/291 [00:07<00:00, 36.34it/s]
Loading 0:  89%|████████▉ | 259/291 [00:07<00:00, 35.27it/s]
Loading 0:  91%|█████████ | 264/291 [00:08<00:00, 37.69it/s]
Loading 0:  92%|█████████▏| 268/291 [00:08<00:00, 35.66it/s]
Loading 0:  94%|█████████▍| 273/291 [00:08<00:00, 37.98it/s]
Loading 0:  95%|█████████▌| 277/291 [00:08<00:00, 35.91it/s]
Loading 0:  97%|█████████▋| 281/291 [00:08<00:00, 35.79it/s]
Loading 0:  98%|█████████▊| 286/291 [00:14<00:01,  2.62it/s]
Loading 0:  99%|█████████▉| 289/291 [00:14<00:00,  3.26it/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-v3-nall-v1-mkmlizer:   warnings.warn(
trace2333-fd-llama3-v3-nall-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-llama3-v3-nall-v1-mkmlizer:   warnings.warn(
trace2333-fd-llama3-v3-nall-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-v3-nall-v1-mkmlizer:   warnings.warn(
trace2333-fd-llama3-v3-nall-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
trace2333-fd-llama3-v3-nall-v1-mkmlizer: Saving duration: 1.374s
trace2333-fd-llama3-v3-nall-v1-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 10.988s
trace2333-fd-llama3-v3-nall-v1-mkmlizer: creating bucket guanaco-reward-models
trace2333-fd-llama3-v3-nall-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
trace2333-fd-llama3-v3-nall-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/trace2333-fd-llama3-v3-nall-v1_reward
trace2333-fd-llama3-v3-nall-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/trace2333-fd-llama3-v3-nall-v1_reward/config.json
trace2333-fd-llama3-v3-nall-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/trace2333-fd-llama3-v3-nall-v1_reward/special_tokens_map.json
trace2333-fd-llama3-v3-nall-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/trace2333-fd-llama3-v3-nall-v1_reward/tokenizer_config.json
trace2333-fd-llama3-v3-nall-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/trace2333-fd-llama3-v3-nall-v1_reward/merges.txt
trace2333-fd-llama3-v3-nall-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/trace2333-fd-llama3-v3-nall-v1_reward/vocab.json
trace2333-fd-llama3-v3-nall-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/trace2333-fd-llama3-v3-nall-v1_reward/tokenizer.json
trace2333-fd-llama3-v3-nall-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/trace2333-fd-llama3-v3-nall-v1_reward/reward.tensors
Job trace2333-fd-llama3-v3-nall-v1-mkmlizer completed after 126.33s with status: succeeded
Stopping job with name trace2333-fd-llama3-v3-nall-v1-mkmlizer
Pipeline stage MKMLizer completed in 127.28s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.08s
Running pipeline stage ISVCDeployer
Creating inference service trace2333-fd-llama3-v3-nall-v1
Waiting for inference service trace2333-fd-llama3-v3-nall-v1 to be ready
Inference service trace2333-fd-llama3-v3-nall-v1 ready after 141.58572387695312s
Pipeline stage ISVCDeployer completed in 143.42s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3539535999298096s
Received healthy response to inference request in 1.416799545288086s
Received healthy response to inference request in 1.3936970233917236s
Received healthy response to inference request in 1.42655348777771s
Received healthy response to inference request in 1.3986611366271973s
5 requests
0 failed requests
5th percentile: 1.3946898460388184
10th percentile: 1.3956826686859132
20th percentile: 1.3976683139801025
30th percentile: 1.402288818359375
40th percentile: 1.4095441818237304
50th percentile: 1.416799545288086
60th percentile: 1.4207011222839356
70th percentile: 1.4246026992797851
80th percentile: 1.61203351020813
90th percentile: 1.98299355506897
95th percentile: 2.1684735774993893
99th percentile: 2.3168575954437256
mean time: 1.5979329586029052
Pipeline stage StressChecker completed in 8.64s
trace2333-fd-llama3-v3-nall_v1 status is now deployed due to DeploymentManager action
trace2333-fd-llama3-v3-nall_v1 status is now inactive due to auto deactivation removed underperforming models
trace2333-fd-llama3-v3-nall_v1 status is now torndown due to DeploymentManager action