cycy233-l3-ea-v-c8

developer_uid: shiroe40

submission_id: cycy233-l3-ea-v-c8_v1

model_name: auto

model_group: cycy233/L3-ea-v-c8

status: torndown

timestamp: 2024-07-30T04:03:12+00:00

num_battles: 9197

num_wins: 4697

celo_rating: 1200.93

family_friendly_score: 0.0

submission_type: basic

model_repo: cycy233/L3-ea-v-c8

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: auto

is_internal_developer: False

language_model: cycy233/L3-ea-v-c8

model_size: 8B

ranking_group: single

us_pacific_date: 2024-07-29

win_ratio: 0.510710014135044

generation_params: {'temperature': 1.0, 'top_p': 0.9, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|end_header_id|>', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64, 'reward_max_token_input': 256}

formatter: {'memory_template': "<|begin_of_text|><|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 cycy233-l3-ea-v-c8-v1-mkmlizer
Waiting for job on cycy233-l3-ea-v-c8-v1-mkmlizer to finish
cycy233-l3-ea-v-c8-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-ea-v-c8-v1-mkmlizer: ║     _____            __           __                                ║
cycy233-l3-ea-v-c8-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-l3-ea-v-c8-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-l3-ea-v-c8-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-l3-ea-v-c8-v1-mkmlizer: ║       /___/                                                         ║
cycy233-l3-ea-v-c8-v1-mkmlizer: ║                                                                     ║
cycy233-l3-ea-v-c8-v1-mkmlizer: ║  Version: 0.9.7                                                     ║
cycy233-l3-ea-v-c8-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-l3-ea-v-c8-v1-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-l3-ea-v-c8-v1-mkmlizer: ║                                                                     ║
cycy233-l3-ea-v-c8-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-l3-ea-v-c8-v1-mkmlizer: ║  belonging to:                                                      ║
cycy233-l3-ea-v-c8-v1-mkmlizer: ║                                                                     ║
cycy233-l3-ea-v-c8-v1-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-l3-ea-v-c8-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-l3-ea-v-c8-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
cycy233-l3-ea-v-c8-v1-mkmlizer: ║                                                                     ║
cycy233-l3-ea-v-c8-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-ea-v-c8-v1-mkmlizer: Downloaded to shared memory in 32.436s
cycy233-l3-ea-v-c8-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmphft649bs, device:0
cycy233-l3-ea-v-c8-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-ea-v-c8-v1-mkmlizer: quantized model in 26.941s
cycy233-l3-ea-v-c8-v1-mkmlizer: Processed model cycy233/L3-ea-v-c8 in 59.378s
cycy233-l3-ea-v-c8-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-ea-v-c8-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-ea-v-c8-v1/config.json
cycy233-l3-ea-v-c8-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-ea-v-c8-v1/special_tokens_map.json
cycy233-l3-ea-v-c8-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-ea-v-c8-v1/tokenizer_config.json
cycy233-l3-ea-v-c8-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-ea-v-c8-v1/tokenizer.json
cycy233-l3-ea-v-c8-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-ea-v-c8-v1/flywheel_model.0.safetensors
cycy233-l3-ea-v-c8-v1-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
cycy233-l3-ea-v-c8-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:08, 34.73it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:05, 55.21it/s]
Loading 0:   7%|▋         | 19/291 [00:00<00:05, 48.21it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:05, 50.32it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:04, 53.10it/s]
Loading 0:  13%|█▎        | 37/291 [00:00<00:05, 48.13it/s]
Loading 0:  14%|█▍        | 42/291 [00:00<00:05, 46.93it/s]
Loading 0:  17%|█▋        | 49/291 [00:00<00:04, 52.29it/s]
Loading 0:  19%|█▉        | 55/291 [00:01<00:04, 47.75it/s]
Loading 0:  21%|██        | 60/291 [00:01<00:04, 46.89it/s]
Loading 0:  23%|██▎       | 67/291 [00:01<00:04, 51.36it/s]
Loading 0:  25%|██▌       | 73/291 [00:01<00:04, 47.20it/s]
Loading 0:  27%|██▋       | 78/291 [00:01<00:04, 45.90it/s]
Loading 0:  29%|██▊       | 83/291 [00:01<00:06, 31.27it/s]
Loading 0:  30%|██▉       | 87/291 [00:02<00:06, 31.16it/s]
Loading 0:  32%|███▏      | 93/291 [00:02<00:05, 36.30it/s]
Loading 0:  34%|███▎      | 98/291 [00:02<00:05, 37.92it/s]
Loading 0:  35%|███▌      | 103/291 [00:02<00:04, 39.97it/s]
Loading 0:  37%|███▋      | 108/291 [00:02<00:04, 41.30it/s]
Loading 0:  39%|███▉      | 113/291 [00:02<00:05, 34.31it/s]
Loading 0:  41%|████      | 120/291 [00:02<00:04, 41.74it/s]
Loading 0:  43%|████▎     | 125/291 [00:02<00:03, 41.99it/s]
Loading 0:  45%|████▍     | 130/291 [00:03<00:03, 40.97it/s]
Loading 0:  46%|████▋     | 135/291 [00:03<00:03, 42.13it/s]
Loading 0:  48%|████▊     | 140/291 [00:03<00:04, 35.09it/s]
Loading 0:  51%|█████     | 147/291 [00:03<00:03, 42.45it/s]
Loading 0:  52%|█████▏    | 152/291 [00:03<00:03, 42.39it/s]
Loading 0:  54%|█████▍    | 157/291 [00:03<00:03, 42.12it/s]
Loading 0:  56%|█████▌    | 162/291 [00:03<00:02, 43.28it/s]
Loading 0:  57%|█████▋    | 167/291 [00:04<00:03, 35.68it/s]
Loading 0:  59%|█████▉    | 173/291 [00:04<00:03, 39.30it/s]
Loading 0:  62%|██████▏   | 179/291 [00:04<00:02, 43.25it/s]
Loading 0:  63%|██████▎   | 184/291 [00:04<00:02, 41.57it/s]
Loading 0:  65%|██████▍   | 189/291 [00:04<00:03, 25.57it/s]
Loading 0:  67%|██████▋   | 194/291 [00:04<00:03, 28.48it/s]
Loading 0:  69%|██████▉   | 201/291 [00:05<00:02, 35.19it/s]
Loading 0:  71%|███████   | 206/291 [00:05<00:02, 36.32it/s]
Loading 0:  73%|███████▎  | 211/291 [00:05<00:02, 37.82it/s]
Loading 0:  74%|███████▍  | 216/291 [00:05<00:01, 40.31it/s]
Loading 0:  76%|███████▌  | 221/291 [00:05<00:02, 34.26it/s]
Loading 0:  78%|███████▊  | 228/291 [00:05<00:01, 40.85it/s]
Loading 0:  80%|████████  | 233/291 [00:05<00:01, 41.23it/s]
Loading 0:  82%|████████▏ | 238/291 [00:05<00:01, 41.90it/s]
Loading 0:  84%|████████▎ | 243/291 [00:06<00:01, 43.85it/s]
Loading 0:  85%|████████▌ | 248/291 [00:06<00:01, 36.88it/s]
Loading 0:  88%|████████▊ | 255/291 [00:06<00:00, 43.04it/s]
Loading 0:  89%|████████▉ | 260/291 [00:06<00:00, 40.98it/s]
Loading 0:  91%|█████████ | 265/291 [00:06<00:00, 39.58it/s]
Loading 0:  93%|█████████▎| 271/291 [00:06<00:00, 38.71it/s]
Loading 0:  95%|█████████▍| 275/291 [00:06<00:00, 36.23it/s]
Loading 0:  97%|█████████▋| 281/291 [00:06<00:00, 40.17it/s]
Loading 0:  98%|█████████▊| 286/291 [00:07<00:00, 34.78it/s]
Loading 0: 100%|█████████▉| 290/291 [00:12<00:00,  2.87it/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.
cycy233-l3-ea-v-c8-v1-mkmlizer:   warnings.warn(
cycy233-l3-ea-v-c8-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.
cycy233-l3-ea-v-c8-v1-mkmlizer:   warnings.warn(
cycy233-l3-ea-v-c8-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.
cycy233-l3-ea-v-c8-v1-mkmlizer:   warnings.warn(
cycy233-l3-ea-v-c8-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-ea-v-c8-v1-mkmlizer: Saving duration: 1.372s
cycy233-l3-ea-v-c8-v1-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 10.862s
cycy233-l3-ea-v-c8-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-ea-v-c8-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-ea-v-c8-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-ea-v-c8-v1_reward
cycy233-l3-ea-v-c8-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-ea-v-c8-v1_reward/special_tokens_map.json
cycy233-l3-ea-v-c8-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-ea-v-c8-v1_reward/config.json
cycy233-l3-ea-v-c8-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-ea-v-c8-v1_reward/tokenizer_config.json
cycy233-l3-ea-v-c8-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-ea-v-c8-v1_reward/merges.txt
cycy233-l3-ea-v-c8-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-ea-v-c8-v1_reward/vocab.json
cycy233-l3-ea-v-c8-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-ea-v-c8-v1_reward/tokenizer.json
cycy233-l3-ea-v-c8-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-ea-v-c8-v1_reward/reward.tensors
Job cycy233-l3-ea-v-c8-v1-mkmlizer completed after 114.61s with status: succeeded
Stopping job with name cycy233-l3-ea-v-c8-v1-mkmlizer
Pipeline stage MKMLizer completed in 115.54s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.14s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-ea-v-c8-v1
Waiting for inference service cycy233-l3-ea-v-c8-v1 to be ready
Inference service cycy233-l3-ea-v-c8-v1 ready after 130.82913899421692s
Pipeline stage ISVCDeployer completed in 132.42s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.429323434829712s
Received healthy response to inference request in 1.4718890190124512s
Received healthy response to inference request in 1.4310262203216553s
Received healthy response to inference request in 1.4246625900268555s
Received healthy response to inference request in 1.4936809539794922s
5 requests
0 failed requests
5th percentile: 1.4259353160858155
10th percentile: 1.4272080421447755
20th percentile: 1.4297534942626953
30th percentile: 1.4391987800598145
40th percentile: 1.4555438995361327
50th percentile: 1.4718890190124512
60th percentile: 1.4806057929992675
70th percentile: 1.489322566986084
80th percentile: 1.6808094501495363
90th percentile: 2.055066442489624
95th percentile: 2.242194938659668
99th percentile: 2.391897735595703
mean time: 1.6501164436340332
Pipeline stage StressChecker completed in 9.03s
cycy233-l3-ea-v-c8_v1 status is now deployed due to DeploymentManager action
cycy233-l3-ea-v-c8_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-l3-ea-v-c8_v1
Running pipeline stage ISVCDeleter
Checking if service cycy233-l3-ea-v-c8-v1 is running
Tearing down inference service cycy233-l3-ea-v-c8-v1
Service cycy233-l3-ea-v-c8-v1 has been torndown
Pipeline stage ISVCDeleter completed in 4.58s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-l3-ea-v-c8-v1/config.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-ea-v-c8-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-l3-ea-v-c8-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-ea-v-c8-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-ea-v-c8-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-l3-ea-v-c8-v1_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-ea-v-c8-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-l3-ea-v-c8-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-l3-ea-v-c8-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-l3-ea-v-c8-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-l3-ea-v-c8-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-ea-v-c8-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.47s
cycy233-l3-ea-v-c8_v1 status is now torndown due to DeploymentManager action