trace2333-fd-llama3-v2

submission_id: trace2333-fd-llama3-v2_v1

developer_uid: Trace2333

best_of: 16

celo_rating: 1196.72

display_name: trace2333-fd-llama3-v2_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': 1.0, '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_llama3_v2

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_group: Trace2333/fd_llama3_v2

model_name: trace2333-fd-llama3-v2_v1

model_num_parameters: 8030261248.0

model_repo: Trace2333/fd_llama3_v2

model_size: 8B

num_battles: 18340

num_wins: 9135

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: 2024-08-01T02:18:56+00:00

us_pacific_date: 2024-07-31

win_ratio: 0.49809160305343514

Resubmit model

Running pipeline stage MKMLizer
Starting job with name trace2333-fd-llama3-v2-v1-mkmlizer
Waiting for job on trace2333-fd-llama3-v2-v1-mkmlizer to finish
trace2333-fd-llama3-v2-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-fd-llama3-v2-v1-mkmlizer: ║     _____            __           __                                ║
trace2333-fd-llama3-v2-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
trace2333-fd-llama3-v2-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
trace2333-fd-llama3-v2-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
trace2333-fd-llama3-v2-v1-mkmlizer: ║       /___/                                                         ║
trace2333-fd-llama3-v2-v1-mkmlizer: ║                                                                     ║
trace2333-fd-llama3-v2-v1-mkmlizer: ║  Version: 0.9.7                                                     ║
trace2333-fd-llama3-v2-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
trace2333-fd-llama3-v2-v1-mkmlizer: ║  https://mk1.ai                                                     ║
trace2333-fd-llama3-v2-v1-mkmlizer: ║                                                                     ║
trace2333-fd-llama3-v2-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
trace2333-fd-llama3-v2-v1-mkmlizer: ║  belonging to:                                                      ║
trace2333-fd-llama3-v2-v1-mkmlizer: ║                                                                     ║
trace2333-fd-llama3-v2-v1-mkmlizer: ║  Chai Research Corp.                                                ║
trace2333-fd-llama3-v2-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
trace2333-fd-llama3-v2-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
trace2333-fd-llama3-v2-v1-mkmlizer: ║                                                                     ║
trace2333-fd-llama3-v2-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
trace2333-fd-llama3-v2-v1-mkmlizer: Downloaded to shared memory in 60.228s
trace2333-fd-llama3-v2-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpzse8owgd, device:0
trace2333-fd-llama3-v2-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
trace2333-fd-llama3-v2-v1-mkmlizer: quantized model in 30.088s
trace2333-fd-llama3-v2-v1-mkmlizer: Processed model Trace2333/fd_llama3_v2 in 90.316s
trace2333-fd-llama3-v2-v1-mkmlizer: creating bucket guanaco-mkml-models
trace2333-fd-llama3-v2-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-fd-llama3-v2-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-fd-llama3-v2-v1
trace2333-fd-llama3-v2-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-fd-llama3-v2-v1/config.json
trace2333-fd-llama3-v2-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-fd-llama3-v2-v1/special_tokens_map.json
trace2333-fd-llama3-v2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-fd-llama3-v2-v1/tokenizer_config.json
trace2333-fd-llama3-v2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-fd-llama3-v2-v1/tokenizer.json
trace2333-fd-llama3-v2-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/trace2333-fd-llama3-v2-v1/flywheel_model.0.safetensors
trace2333-fd-llama3-v2-v1-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
trace2333-fd-llama3-v2-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:11, 25.94it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:07, 36.40it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:07, 34.41it/s]
Loading 0:   7%|▋         | 21/291 [00:00<00:07, 37.95it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:07, 35.45it/s]
Loading 0:  10%|█         | 30/291 [00:00<00:06, 38.58it/s]
Loading 0:  12%|█▏        | 34/291 [00:01<00:09, 26.23it/s]
Loading 0:  13%|█▎        | 38/291 [00:01<00:09, 27.92it/s]
Loading 0:  14%|█▍        | 42/291 [00:01<00:09, 26.85it/s]
Loading 0:  16%|█▋        | 48/291 [00:01<00:07, 32.58it/s]
Loading 0:  18%|█▊        | 52/291 [00:01<00:07, 32.29it/s]
Loading 0:  20%|█▉        | 57/291 [00:01<00:06, 34.91it/s]
Loading 0:  21%|██        | 61/291 [00:01<00:06, 33.76it/s]
Loading 0:  23%|██▎       | 66/291 [00:01<00:06, 36.56it/s]
Loading 0:  24%|██▍       | 70/291 [00:02<00:06, 34.83it/s]
Loading 0:  25%|██▌       | 74/291 [00:02<00:06, 34.48it/s]
Loading 0:  27%|██▋       | 78/291 [00:02<00:06, 34.42it/s]
Loading 0:  28%|██▊       | 82/291 [00:02<00:08, 23.54it/s]
Loading 0:  30%|██▉       | 86/291 [00:02<00:07, 26.41it/s]
Loading 0:  31%|███       | 90/291 [00:02<00:06, 29.04it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:06, 29.88it/s]
Loading 0:  34%|███▍      | 99/291 [00:03<00:05, 33.44it/s]
Loading 0:  35%|███▌      | 103/291 [00:03<00:05, 32.08it/s]
Loading 0:  37%|███▋      | 108/291 [00:03<00:05, 34.41it/s]
Loading 0:  38%|███▊      | 112/291 [00:03<00:05, 32.61it/s]
Loading 0:  40%|███▉      | 116/291 [00:03<00:05, 32.40it/s]
Loading 0:  42%|████▏     | 122/291 [00:03<00:04, 37.07it/s]
Loading 0:  44%|████▎     | 127/291 [00:03<00:04, 35.18it/s]
Loading 0:  46%|████▌     | 133/291 [00:04<00:05, 29.71it/s]
Loading 0:  47%|████▋     | 137/291 [00:04<00:05, 30.08it/s]
Loading 0:  48%|████▊     | 141/291 [00:04<00:05, 28.19it/s]
Loading 0:  51%|█████     | 147/291 [00:04<00:04, 33.18it/s]
Loading 0:  52%|█████▏    | 151/291 [00:04<00:04, 32.43it/s]
Loading 0:  54%|█████▎    | 156/291 [00:04<00:03, 35.31it/s]
Loading 0:  55%|█████▍    | 160/291 [00:04<00:03, 33.72it/s]
Loading 0:  57%|█████▋    | 165/291 [00:05<00:03, 36.66it/s]
Loading 0:  58%|█████▊    | 169/291 [00:05<00:03, 34.14it/s]
Loading 0:  60%|█████▉    | 174/291 [00:05<00:03, 36.33it/s]
Loading 0:  61%|██████    | 178/291 [00:05<00:03, 34.83it/s]
Loading 0:  63%|██████▎   | 184/291 [00:05<00:02, 41.12it/s]
Loading 0:  65%|██████▍   | 189/291 [00:05<00:04, 24.09it/s]
Loading 0:  67%|██████▋   | 194/291 [00:06<00:03, 25.67it/s]
Loading 0:  69%|██████▉   | 201/291 [00:06<00:02, 32.19it/s]
Loading 0:  70%|███████   | 205/291 [00:06<00:02, 31.81it/s]
Loading 0:  72%|███████▏  | 210/291 [00:06<00:02, 34.59it/s]
Loading 0:  74%|███████▎  | 214/291 [00:06<00:02, 34.05it/s]
Loading 0:  75%|███████▌  | 219/291 [00:06<00:01, 36.74it/s]
Loading 0:  77%|███████▋  | 223/291 [00:06<00:01, 35.27it/s]
Loading 0:  78%|███████▊  | 227/291 [00:06<00:01, 35.46it/s]
Loading 0:  79%|███████▉  | 231/291 [00:07<00:01, 35.62it/s]
Loading 0:  81%|████████  | 235/291 [00:07<00:02, 26.28it/s]
Loading 0:  82%|████████▏ | 239/291 [00:07<00:01, 26.03it/s]
Loading 0:  85%|████████▍ | 246/291 [00:07<00:01, 33.02it/s]
Loading 0:  86%|████████▌ | 250/291 [00:07<00:01, 32.49it/s]
Loading 0:  88%|████████▊ | 255/291 [00:07<00:01, 35.58it/s]
Loading 0:  89%|████████▉ | 259/291 [00:08<00:00, 34.65it/s]
Loading 0:  91%|█████████ | 264/291 [00:08<00:00, 36.12it/s]
Loading 0:  92%|█████████▏| 268/291 [00:08<00:00, 34.54it/s]
Loading 0:  94%|█████████▍| 273/291 [00:08<00:00, 37.07it/s]
Loading 0:  95%|█████████▌| 277/291 [00:08<00:00, 35.01it/s]
Loading 0:  97%|█████████▋| 281/291 [00:08<00:00, 34.61it/s]
Loading 0:  98%|█████████▊| 286/291 [00:14<00:02,  2.47it/s]
Loading 0:  99%|█████████▉| 289/291 [00:14<00:00,  3.08it/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-v1-mkmlizer:   warnings.warn(
trace2333-fd-llama3-v2-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-v2-v1-mkmlizer:   warnings.warn(
trace2333-fd-llama3-v2-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-v2-v1-mkmlizer:   warnings.warn(
trace2333-fd-llama3-v2-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
trace2333-fd-llama3-v2-v1-mkmlizer: Saving duration: 1.520s
trace2333-fd-llama3-v2-v1-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 11.366s
trace2333-fd-llama3-v2-v1-mkmlizer: creating bucket guanaco-reward-models
trace2333-fd-llama3-v2-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
trace2333-fd-llama3-v2-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/trace2333-fd-llama3-v2-v1_reward
trace2333-fd-llama3-v2-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/trace2333-fd-llama3-v2-v1_reward/config.json
trace2333-fd-llama3-v2-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/trace2333-fd-llama3-v2-v1_reward/special_tokens_map.json
trace2333-fd-llama3-v2-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/trace2333-fd-llama3-v2-v1_reward/tokenizer_config.json
trace2333-fd-llama3-v2-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/trace2333-fd-llama3-v2-v1_reward/merges.txt
trace2333-fd-llama3-v2-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/trace2333-fd-llama3-v2-v1_reward/vocab.json
trace2333-fd-llama3-v2-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/trace2333-fd-llama3-v2-v1_reward/tokenizer.json
trace2333-fd-llama3-v2-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/trace2333-fd-llama3-v2-v1_reward/reward.tensors
Job trace2333-fd-llama3-v2-v1-mkmlizer completed after 137.45s with status: succeeded
Stopping job with name trace2333-fd-llama3-v2-v1-mkmlizer
Pipeline stage MKMLizer completed in 138.45s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service trace2333-fd-llama3-v2-v1
Waiting for inference service trace2333-fd-llama3-v2-v1 to be ready
Inference service trace2333-fd-llama3-v2-v1 ready after 130.90700030326843s
Pipeline stage ISVCDeployer completed in 132.63s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2988100051879883s
Received healthy response to inference request in 1.465623378753662s
Received healthy response to inference request in 1.4527387619018555s
Received healthy response to inference request in 1.4110665321350098s
Received healthy response to inference request in 1.3928494453430176s
5 requests
0 failed requests
5th percentile: 1.396492862701416
10th percentile: 1.4001362800598145
20th percentile: 1.4074231147766114
30th percentile: 1.419400978088379
40th percentile: 1.436069869995117
50th percentile: 1.4527387619018555
60th percentile: 1.457892608642578
70th percentile: 1.4630464553833007
80th percentile: 1.6322607040405275
90th percentile: 1.965535354614258
95th percentile: 2.1321726799011227
99th percentile: 2.2654825401306153
mean time: 1.6042176246643067
Pipeline stage StressChecker completed in 8.77s
trace2333-fd-llama3-v2_v1 status is now deployed due to DeploymentManager action
trace2333-fd-llama3-v2_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of trace2333-fd-llama3-v2_v1
Running pipeline stage ISVCDeleter
Checking if service trace2333-fd-llama3-v2-v1 is running
Tearing down inference service trace2333-fd-llama3-v2-v1
Service trace2333-fd-llama3-v2-v1 has been torndown
Pipeline stage ISVCDeleter completed in 4.41s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key trace2333-fd-llama3-v2-v1/config.json from bucket guanaco-mkml-models
Deleting key trace2333-fd-llama3-v2-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key trace2333-fd-llama3-v2-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key trace2333-fd-llama3-v2-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key trace2333-fd-llama3-v2-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key trace2333-fd-llama3-v2-v1_reward/config.json from bucket guanaco-reward-models
Deleting key trace2333-fd-llama3-v2-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key trace2333-fd-llama3-v2-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key trace2333-fd-llama3-v2-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key trace2333-fd-llama3-v2-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key trace2333-fd-llama3-v2-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key trace2333-fd-llama3-v2-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.25s
trace2333-fd-llama3-v2_v1 status is now torndown due to DeploymentManager action