cycy233-l3-ba-v-v0-c1

developer_uid: shiroe40

submission_id: cycy233-l3-ba-v-v0-c1_v2

model_name: auto

model_group: cycy233/L3-ba-v-v0-c1

status: torndown

timestamp: 2024-08-01T07:56:40+00:00

num_battles: 19222

num_wins: 10130

celo_rating: 1227.56

family_friendly_score: 0.0

submission_type: basic

model_repo: cycy233/L3-ba-v-v0-c1

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-ba-v-v0-c1

model_size: 8B

ranking_group: single

us_pacific_date: 2024-08-01

win_ratio: 0.5270003121423369

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-ba-v-v0-c1-v2-mkmlizer
Waiting for job on cycy233-l3-ba-v-v0-c1-v2-mkmlizer to finish
cycy233-l3-ba-v-v0-c1-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-ba-v-v0-c1-v2-mkmlizer: ║     _____            __           __                                ║
cycy233-l3-ba-v-v0-c1-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-l3-ba-v-v0-c1-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-l3-ba-v-v0-c1-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-l3-ba-v-v0-c1-v2-mkmlizer: ║       /___/                                                         ║
cycy233-l3-ba-v-v0-c1-v2-mkmlizer: ║                                                                     ║
cycy233-l3-ba-v-v0-c1-v2-mkmlizer: ║  Version: 0.9.7                                                     ║
cycy233-l3-ba-v-v0-c1-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-l3-ba-v-v0-c1-v2-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-l3-ba-v-v0-c1-v2-mkmlizer: ║                                                                     ║
cycy233-l3-ba-v-v0-c1-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-l3-ba-v-v0-c1-v2-mkmlizer: ║  belonging to:                                                      ║
cycy233-l3-ba-v-v0-c1-v2-mkmlizer: ║                                                                     ║
cycy233-l3-ba-v-v0-c1-v2-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-l3-ba-v-v0-c1-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-l3-ba-v-v0-c1-v2-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
cycy233-l3-ba-v-v0-c1-v2-mkmlizer: ║                                                                     ║
cycy233-l3-ba-v-v0-c1-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-ba-v-v0-c1-v2-mkmlizer: Downloaded to shared memory in 28.707s
cycy233-l3-ba-v-v0-c1-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpjm0ezagh, device:0
cycy233-l3-ba-v-v0-c1-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-ba-v-v0-c1-v2-mkmlizer: quantized model in 26.205s
cycy233-l3-ba-v-v0-c1-v2-mkmlizer: Processed model cycy233/L3-ba-v-v0-c1 in 54.913s
cycy233-l3-ba-v-v0-c1-v2-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-ba-v-v0-c1-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-ba-v-v0-c1-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-ba-v-v0-c1-v2
cycy233-l3-ba-v-v0-c1-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-ba-v-v0-c1-v2/flywheel_model.0.safetensors
cycy233-l3-ba-v-v0-c1-v2-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
cycy233-l3-ba-v-v0-c1-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:07, 36.74it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:04, 58.47it/s]
Loading 0:   7%|▋         | 20/291 [00:00<00:04, 54.79it/s]
Loading 0:   9%|▉         | 26/291 [00:00<00:04, 54.35it/s]
Loading 0:  11%|█         | 32/291 [00:00<00:05, 46.69it/s]
Loading 0:  14%|█▍        | 41/291 [00:00<00:05, 48.90it/s]
Loading 0:  17%|█▋        | 49/291 [00:00<00:04, 56.37it/s]
Loading 0:  19%|█▉        | 55/291 [00:01<00:04, 51.52it/s]
Loading 0:  21%|██        | 61/291 [00:01<00:04, 51.37it/s]
Loading 0:  23%|██▎       | 67/291 [00:01<00:04, 52.99it/s]
Loading 0:  25%|██▌       | 73/291 [00:01<00:04, 49.27it/s]
Loading 0:  27%|██▋       | 79/291 [00:01<00:04, 49.49it/s]
Loading 0:  29%|██▉       | 85/291 [00:01<00:05, 34.84it/s]
Loading 0:  31%|███       | 90/291 [00:01<00:05, 37.76it/s]
Loading 0:  33%|███▎      | 95/291 [00:02<00:05, 35.49it/s]
Loading 0:  35%|███▌      | 103/291 [00:02<00:04, 44.45it/s]
Loading 0:  37%|███▋      | 109/291 [00:02<00:04, 43.83it/s]
Loading 0:  39%|███▉      | 114/291 [00:02<00:04, 43.58it/s]
Loading 0:  41%|████      | 120/291 [00:02<00:03, 47.05it/s]
Loading 0:  43%|████▎     | 125/291 [00:02<00:03, 47.27it/s]
Loading 0:  45%|████▍     | 130/291 [00:02<00:03, 47.74it/s]
Loading 0:  47%|████▋     | 136/291 [00:02<00:03, 45.20it/s]
Loading 0:  48%|████▊     | 141/291 [00:03<00:03, 43.09it/s]
Loading 0:  51%|█████     | 148/291 [00:03<00:02, 48.01it/s]
Loading 0:  53%|█████▎    | 154/291 [00:03<00:03, 44.97it/s]
Loading 0:  55%|█████▍    | 159/291 [00:03<00:02, 44.92it/s]
Loading 0:  57%|█████▋    | 166/291 [00:03<00:02, 49.91it/s]
Loading 0:  59%|█████▉    | 172/291 [00:03<00:02, 45.37it/s]
Loading 0:  62%|██████▏   | 179/291 [00:03<00:02, 48.95it/s]
Loading 0:  64%|██████▎   | 185/291 [00:03<00:02, 50.67it/s]
Loading 0:  66%|██████▌   | 191/291 [00:04<00:02, 33.88it/s]
Loading 0:  67%|██████▋   | 196/291 [00:04<00:02, 35.88it/s]
Loading 0:  69%|██████▉   | 202/291 [00:04<00:02, 40.24it/s]
Loading 0:  71%|███████▏  | 208/291 [00:04<00:02, 39.58it/s]
Loading 0:  73%|███████▎  | 213/291 [00:04<00:01, 40.17it/s]
Loading 0:  76%|███████▌  | 220/291 [00:04<00:01, 45.90it/s]
Loading 0:  77%|███████▋  | 225/291 [00:04<00:01, 46.66it/s]
Loading 0:  79%|███████▉  | 230/291 [00:05<00:01, 39.50it/s]
Loading 0:  82%|████████▏ | 238/291 [00:05<00:01, 47.96it/s]
Loading 0:  84%|████████▍ | 244/291 [00:05<00:01, 46.15it/s]
Loading 0:  86%|████████▌ | 249/291 [00:05<00:00, 45.53it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 50.00it/s]
Loading 0:  90%|█████████ | 262/291 [00:05<00:00, 47.24it/s]
Loading 0:  92%|█████████▏| 267/291 [00:05<00:00, 45.58it/s]
Loading 0:  94%|█████████▍| 273/291 [00:06<00:00, 48.73it/s]
Loading 0:  96%|█████████▌| 278/291 [00:06<00:00, 47.86it/s]
Loading 0:  97%|█████████▋| 283/291 [00:06<00:00, 41.24it/s]
Loading 0:  99%|█████████▉| 288/291 [00:11<00:00,  3.11it/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-ba-v-v0-c1-v2-mkmlizer:   warnings.warn(
cycy233-l3-ba-v-v0-c1-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.
cycy233-l3-ba-v-v0-c1-v2-mkmlizer:   warnings.warn(
cycy233-l3-ba-v-v0-c1-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.
cycy233-l3-ba-v-v0-c1-v2-mkmlizer:   warnings.warn(
cycy233-l3-ba-v-v0-c1-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-ba-v-v0-c1-v2-mkmlizer: Saving duration: 1.392s
cycy233-l3-ba-v-v0-c1-v2-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 10.952s
cycy233-l3-ba-v-v0-c1-v2-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-ba-v-v0-c1-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-ba-v-v0-c1-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-ba-v-v0-c1-v2_reward
cycy233-l3-ba-v-v0-c1-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-ba-v-v0-c1-v2_reward/config.json
cycy233-l3-ba-v-v0-c1-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-ba-v-v0-c1-v2_reward/special_tokens_map.json
cycy233-l3-ba-v-v0-c1-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-ba-v-v0-c1-v2_reward/tokenizer_config.json
cycy233-l3-ba-v-v0-c1-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-ba-v-v0-c1-v2_reward/merges.txt
cycy233-l3-ba-v-v0-c1-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-ba-v-v0-c1-v2_reward/vocab.json
cycy233-l3-ba-v-v0-c1-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-ba-v-v0-c1-v2_reward/reward.tensors
Job cycy233-l3-ba-v-v0-c1-v2-mkmlizer completed after 94.66s with status: succeeded
Stopping job with name cycy233-l3-ba-v-v0-c1-v2-mkmlizer
Pipeline stage MKMLizer completed in 95.68s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-ba-v-v0-c1-v2
Waiting for inference service cycy233-l3-ba-v-v0-c1-v2 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service cycy233-l3-ba-v-v0-c1-v2 ready after 131.14326930046082s
Pipeline stage ISVCDeployer completed in 132.68s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.190265655517578s
Received healthy response to inference request in 1.4646377563476562s
Received healthy response to inference request in 1.439626693725586s
Received healthy response to inference request in 1.4034864902496338s
Received healthy response to inference request in 1.4865102767944336s
5 requests
0 failed requests
5th percentile: 1.4107145309448241
10th percentile: 1.4179425716400147
20th percentile: 1.4323986530303956
30th percentile: 1.44462890625
40th percentile: 1.4546333312988282
50th percentile: 1.4646377563476562
60th percentile: 1.4733867645263672
70th percentile: 1.4821357727050781
80th percentile: 1.6272613525390627
90th percentile: 1.9087635040283204
95th percentile: 2.049514579772949
99th percentile: 2.162115440368652
mean time: 1.5969053745269775
Pipeline stage StressChecker completed in 8.76s
cycy233-l3-ba-v-v0-c1_v2 status is now deployed due to DeploymentManager action
cycy233-l3-ba-v-v0-c1_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-l3-ba-v-v0-c1_v2
Running pipeline stage ISVCDeleter
Checking if service cycy233-l3-ba-v-v0-c1-v2 is running
Tearing down inference service cycy233-l3-ba-v-v0-c1-v2
Service cycy233-l3-ba-v-v0-c1-v2 has been torndown
Pipeline stage ISVCDeleter completed in 4.93s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-l3-ba-v-v0-c1-v2/config.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-ba-v-v0-c1-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-l3-ba-v-v0-c1-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-ba-v-v0-c1-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-ba-v-v0-c1-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-l3-ba-v-v0-c1-v2_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-ba-v-v0-c1-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-l3-ba-v-v0-c1-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-l3-ba-v-v0-c1-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-l3-ba-v-v0-c1-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-l3-ba-v-v0-c1-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-ba-v-v0-c1-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.51s
cycy233-l3-ba-v-v0-c1_v2 status is now torndown due to DeploymentManager action