cycy233-l3-e-v2-c1

developer_uid: shiroe40

submission_id: cycy233-l3-e-v2-c1_v20

model_name: auto

model_group: cycy233/L3-e-v2-c1

status: torndown

timestamp: 2024-07-25T08:25:28+00:00

num_battles: 11370

num_wins: 5592

celo_rating: 1193.76

family_friendly_score: 0.0

submission_type: basic

model_repo: cycy233/L3-e-v2-c1

model_architecture: LlamaForCausalLM

reward_repo: cycy233/reward-v0

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-e-v2-c1

model_size: 8B

ranking_group: single

us_pacific_date: 2024-07-25

win_ratio: 0.49182058047493404

generation_params: {'temperature': 1.0, 'top_p': 0.9, 'min_p': 0.05, 'top_k': 40, '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-e-v2-c1-v20-mkmlizer
Waiting for job on cycy233-l3-e-v2-c1-v20-mkmlizer to finish
cycy233-l3-e-v2-c1-v20-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-e-v2-c1-v20-mkmlizer: ║     _____            __           __                                ║
cycy233-l3-e-v2-c1-v20-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-l3-e-v2-c1-v20-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-l3-e-v2-c1-v20-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-l3-e-v2-c1-v20-mkmlizer: ║       /___/                                                         ║
cycy233-l3-e-v2-c1-v20-mkmlizer: ║                                                                     ║
cycy233-l3-e-v2-c1-v20-mkmlizer: ║  Version: 0.9.7                                                     ║
cycy233-l3-e-v2-c1-v20-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-l3-e-v2-c1-v20-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-l3-e-v2-c1-v20-mkmlizer: ║                                                                     ║
cycy233-l3-e-v2-c1-v20-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-l3-e-v2-c1-v20-mkmlizer: ║  belonging to:                                                      ║
cycy233-l3-e-v2-c1-v20-mkmlizer: ║                                                                     ║
cycy233-l3-e-v2-c1-v20-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-l3-e-v2-c1-v20-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-l3-e-v2-c1-v20-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
cycy233-l3-e-v2-c1-v20-mkmlizer: ║                                                                     ║
cycy233-l3-e-v2-c1-v20-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-e-v2-c1-v20-mkmlizer: Downloaded to shared memory in 25.083s
cycy233-l3-e-v2-c1-v20-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpimpjnbsg, device:0
cycy233-l3-e-v2-c1-v20-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-e-v2-c1-v20-mkmlizer: quantized model in 25.638s
cycy233-l3-e-v2-c1-v20-mkmlizer: Processed model cycy233/L3-e-v2-c1 in 50.722s
cycy233-l3-e-v2-c1-v20-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-e-v2-c1-v20-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-e-v2-c1-v20-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v20
cycy233-l3-e-v2-c1-v20-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v20/config.json
cycy233-l3-e-v2-c1-v20-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v20/special_tokens_map.json
cycy233-l3-e-v2-c1-v20-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v20/tokenizer_config.json
cycy233-l3-e-v2-c1-v20-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v20/tokenizer.json
cycy233-l3-e-v2-c1-v20-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-e-v2-c1-v20/flywheel_model.0.safetensors
cycy233-l3-e-v2-c1-v20-mkmlizer: loading reward model from cycy233/reward-v0
cycy233-l3-e-v2-c1-v20-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:07, 37.63it/s]
Loading 0:   5%|▍         | 14/291 [00:00<00:05, 48.21it/s]
Loading 0:   8%|▊         | 22/291 [00:00<00:04, 59.00it/s]
Loading 0:  10%|▉         | 29/291 [00:00<00:04, 55.99it/s]
Loading 0:  12%|█▏        | 35/291 [00:00<00:04, 55.57it/s]
Loading 0:  14%|█▍        | 41/291 [00:00<00:05, 48.69it/s]
Loading 0:  17%|█▋        | 50/291 [00:00<00:04, 50.73it/s]
Loading 0:  20%|█▉        | 58/291 [00:01<00:04, 57.52it/s]
Loading 0:  22%|██▏       | 65/291 [00:01<00:04, 53.31it/s]
Loading 0:  24%|██▍       | 71/291 [00:01<00:04, 52.71it/s]
Loading 0:  26%|██▋       | 77/291 [00:01<00:04, 46.49it/s]
Loading 0:  29%|██▊       | 83/291 [00:01<00:05, 36.36it/s]
Loading 0:  30%|███       | 88/291 [00:01<00:05, 37.97it/s]
Loading 0:  33%|███▎      | 95/291 [00:02<00:05, 39.12it/s]
Loading 0:  35%|███▌      | 103/291 [00:02<00:04, 46.96it/s]
Loading 0:  37%|███▋      | 109/291 [00:02<00:04, 44.59it/s]
Loading 0:  39%|███▉      | 114/291 [00:02<00:03, 44.29it/s]
Loading 0:  42%|████▏     | 121/291 [00:02<00:03, 49.44it/s]
Loading 0:  44%|████▎     | 127/291 [00:02<00:03, 45.85it/s]
Loading 0:  45%|████▌     | 132/291 [00:02<00:03, 44.84it/s]
Loading 0:  47%|████▋     | 138/291 [00:02<00:03, 48.44it/s]
Loading 0:  49%|████▉     | 144/291 [00:03<00:02, 50.59it/s]
Loading 0:  52%|█████▏    | 150/291 [00:03<00:03, 45.01it/s]
Loading 0:  54%|█████▍    | 157/291 [00:03<00:02, 50.37it/s]
Loading 0:  56%|█████▌    | 163/291 [00:03<00:02, 46.83it/s]
Loading 0:  58%|█████▊    | 168/291 [00:03<00:02, 45.81it/s]
Loading 0:  60%|█████▉    | 174/291 [00:03<00:02, 49.37it/s]
Loading 0:  62%|██████▏   | 180/291 [00:03<00:02, 50.17it/s]
Loading 0:  64%|██████▍   | 186/291 [00:03<00:02, 48.07it/s]
Loading 0:  66%|██████▌   | 191/291 [00:04<00:02, 34.40it/s]
Loading 0:  67%|██████▋   | 196/291 [00:04<00:02, 36.44it/s]
Loading 0:  69%|██████▉   | 202/291 [00:04<00:02, 41.31it/s]
Loading 0:  71%|███████▏  | 208/291 [00:04<00:02, 40.72it/s]
Loading 0:  73%|███████▎  | 213/291 [00:04<00:01, 41.48it/s]
Loading 0:  76%|███████▌  | 220/291 [00:04<00:01, 46.68it/s]
Loading 0:  78%|███████▊  | 226/291 [00:04<00:01, 43.98it/s]
Loading 0:  79%|███████▉  | 231/291 [00:05<00:01, 43.70it/s]
Loading 0:  82%|████████▏ | 238/291 [00:05<00:01, 48.97it/s]
Loading 0:  84%|████████▍ | 244/291 [00:05<00:01, 46.08it/s]
Loading 0:  86%|████████▌ | 249/291 [00:05<00:00, 45.95it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 50.79it/s]
Loading 0:  90%|█████████ | 262/291 [00:05<00:00, 48.77it/s]
Loading 0:  92%|█████████▏| 267/291 [00:05<00:00, 47.44it/s]
Loading 0:  94%|█████████▍| 274/291 [00:05<00:00, 51.97it/s]
Loading 0:  96%|█████████▌| 280/291 [00:06<00:00, 47.39it/s]
Loading 0:  98%|█████████▊| 285/291 [00:06<00:00, 46.33it/s]
Loading 0: 100%|█████████▉| 290/291 [00:11<00:00,  3.30it/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-e-v2-c1-v20-mkmlizer:   warnings.warn(
cycy233-l3-e-v2-c1-v20-mkmlizer: Unrecognized keys in `rope_scaling` for 'rope_type'='linear': {'type'}
cycy233-l3-e-v2-c1-v20-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-e-v2-c1-v20-mkmlizer:   warnings.warn(
cycy233-l3-e-v2-c1-v20-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-e-v2-c1-v20-mkmlizer:   warnings.warn(
cycy233-l3-e-v2-c1-v20-mkmlizer: Unrecognized keys in `rope_scaling` for 'rope_type'='linear': {'type'}
cycy233-l3-e-v2-c1-v20-mkmlizer: Some weights of LlamaForSequenceClassification were not initialized from the model checkpoint at cycy233/reward-v0 and are newly initialized: ['score.weight']
cycy233-l3-e-v2-c1-v20-mkmlizer: You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
cycy233-l3-e-v2-c1-v20-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-e-v2-c1-v20-mkmlizer: Saving duration: 0.124s
cycy233-l3-e-v2-c1-v20-mkmlizer: Processed model cycy233/reward-v0 in 5.591s
cycy233-l3-e-v2-c1-v20-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-e-v2-c1-v20-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v20_reward/config.json
cycy233-l3-e-v2-c1-v20-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v20_reward/special_tokens_map.json
cycy233-l3-e-v2-c1-v20-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v20_reward/tokenizer_config.json
cycy233-l3-e-v2-c1-v20-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v20_reward/merges.txt
cycy233-l3-e-v2-c1-v20-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v20_reward/vocab.json
cycy233-l3-e-v2-c1-v20-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v20_reward/tokenizer.json
cycy233-l3-e-v2-c1-v20-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-e-v2-c1-v20_reward/reward.tensors
Job cycy233-l3-e-v2-c1-v20-mkmlizer completed after 84.3s with status: succeeded
Stopping job with name cycy233-l3-e-v2-c1-v20-mkmlizer
Pipeline stage MKMLizer completed in 85.22s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-e-v2-c1-v20
Waiting for inference service cycy233-l3-e-v2-c1-v20 to be ready
Inference service cycy233-l3-e-v2-c1-v20 ready after 70.5193235874176s
Pipeline stage ISVCDeployer completed in 72.14s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0745253562927246s
Received healthy response to inference request in 1.2713184356689453s
Received healthy response to inference request in 1.2431755065917969s
Received healthy response to inference request in 1.3274052143096924s
Received healthy response to inference request in 1.2792437076568604s
5 requests
0 failed requests
5th percentile: 1.2488040924072266
10th percentile: 1.2544326782226562
20th percentile: 1.2656898498535156
30th percentile: 1.2729034900665284
40th percentile: 1.2760735988616942
50th percentile: 1.2792437076568604
60th percentile: 1.298508310317993
70th percentile: 1.317772912979126
80th percentile: 1.476829242706299
90th percentile: 1.7756772994995118
95th percentile: 1.925101327896118
99th percentile: 2.044640550613403
mean time: 1.439133644104004
Pipeline stage StressChecker completed in 7.87s
cycy233-l3-e-v2-c1_v20 status is now deployed due to DeploymentManager action
cycy233-l3-e-v2-c1_v20 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-l3-e-v2-c1_v20
Running pipeline stage ISVCDeleter
Checking if service cycy233-l3-e-v2-c1-v20 is running
Tearing down inference service cycy233-l3-e-v2-c1-v20
Service cycy233-l3-e-v2-c1-v20 has been torndown
Pipeline stage ISVCDeleter completed in 5.32s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-l3-e-v2-c1-v20/config.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c1-v20/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c1-v20/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c1-v20/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-e-v2-c1-v20/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-l3-e-v2-c1-v20_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v20_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v20_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v20_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v20_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v20_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-e-v2-c1-v20_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.17s
cycy233-l3-e-v2-c1_v20 status is now torndown due to DeploymentManager action