trace2333-duduk-llama3-v1

developer_uid: Trace2333

submission_id: trace2333-duduk-llama3-v1_v2

model_name: trace2333-duduk-llama3-v1_v1

model_group: Trace2333/duduk_llama3_v

status: torndown

timestamp: 2024-07-22T17:13:44+00:00

num_battles: 14114

num_wins: 6634

celo_rating: 1170.1

family_friendly_score: 0.0

submission_type: basic

model_repo: Trace2333/duduk_llama3_v1

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: trace2333-duduk-llama3-v1_v1

is_internal_developer: False

language_model: Trace2333/duduk_llama3_v1

model_size: 8B

ranking_group: single

us_pacific_date: 2024-07-22

win_ratio: 0.47002975768740257

generation_params: {'temperature': 1.05, '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}

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}

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 trace2333-duduk-llama3-v1-v2-mkmlizer
Waiting for job on trace2333-duduk-llama3-v1-v2-mkmlizer to finish
trace2333-duduk-llama3-v1-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-duduk-llama3-v1-v2-mkmlizer: ║     _____            __           __                                ║
trace2333-duduk-llama3-v1-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
trace2333-duduk-llama3-v1-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
trace2333-duduk-llama3-v1-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
trace2333-duduk-llama3-v1-v2-mkmlizer: ║       /___/                                                         ║
trace2333-duduk-llama3-v1-v2-mkmlizer: ║                                                                     ║
trace2333-duduk-llama3-v1-v2-mkmlizer: ║  Version: 0.9.5.post3                                               ║
trace2333-duduk-llama3-v1-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
trace2333-duduk-llama3-v1-v2-mkmlizer: ║  https://mk1.ai                                                     ║
trace2333-duduk-llama3-v1-v2-mkmlizer: ║                                                                     ║
trace2333-duduk-llama3-v1-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
trace2333-duduk-llama3-v1-v2-mkmlizer: ║  belonging to:                                                      ║
trace2333-duduk-llama3-v1-v2-mkmlizer: ║                                                                     ║
trace2333-duduk-llama3-v1-v2-mkmlizer: ║  Chai Research Corp.                                                ║
trace2333-duduk-llama3-v1-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
trace2333-duduk-llama3-v1-v2-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
trace2333-duduk-llama3-v1-v2-mkmlizer: ║                                                                     ║
trace2333-duduk-llama3-v1-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
trace2333-duduk-llama3-v1-v2-mkmlizer: Downloaded to shared memory in 39.971s
trace2333-duduk-llama3-v1-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp59apa6gd, device:0
trace2333-duduk-llama3-v1-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
trace2333-duduk-llama3-v1-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:06, 42.94it/s]
Loading 0:   5%|▍         | 14/291 [00:00<00:04, 58.83it/s]
Loading 0:   8%|▊         | 23/291 [00:00<00:04, 63.08it/s]
Loading 0:  11%|█▏        | 33/291 [00:00<00:05, 48.38it/s]
Loading 0:  13%|█▎        | 39/291 [00:00<00:05, 46.92it/s]
Loading 0:  16%|█▋        | 48/291 [00:00<00:04, 53.78it/s]
Loading 0:  20%|█▉        | 57/291 [00:01<00:03, 58.52it/s]
Loading 0:  23%|██▎       | 66/291 [00:01<00:03, 61.63it/s]
Loading 0:  25%|██▌       | 74/291 [00:01<00:03, 61.95it/s]
Loading 0:  28%|██▊       | 81/291 [00:01<00:04, 43.43it/s]
Loading 0:  31%|███       | 90/291 [00:01<00:04, 49.83it/s]
Loading 0:  34%|███▍      | 99/291 [00:01<00:03, 55.13it/s]
Loading 0:  37%|███▋      | 108/291 [00:01<00:03, 59.61it/s]
Loading 0:  40%|███▉      | 116/291 [00:02<00:02, 60.73it/s]
Loading 0:  43%|████▎     | 126/291 [00:02<00:02, 65.87it/s]
Loading 0:  46%|████▌     | 133/291 [00:02<00:03, 49.89it/s]
Loading 0:  48%|████▊     | 139/291 [00:02<00:03, 48.55it/s]
Loading 0:  51%|█████     | 148/291 [00:02<00:02, 54.58it/s]
Loading 0:  54%|█████▍    | 157/291 [00:02<00:02, 59.24it/s]
Loading 0:  57%|█████▋    | 166/291 [00:02<00:01, 62.78it/s]
Loading 0:  60%|██████    | 175/291 [00:03<00:01, 65.45it/s]
Loading 0:  64%|██████▍   | 186/291 [00:03<00:01, 53.33it/s]
Loading 0:  66%|██████▌   | 192/291 [00:03<00:01, 50.86it/s]
Loading 0:  69%|██████▉   | 201/291 [00:03<00:01, 55.88it/s]
Loading 0:  72%|███████▏  | 210/291 [00:03<00:01, 60.00it/s]
Loading 0:  75%|███████▌  | 219/291 [00:03<00:01, 63.09it/s]
Loading 0:  78%|███████▊  | 227/291 [00:04<00:01, 63.29it/s]
Loading 0:  80%|████████  | 234/291 [00:04<00:01, 45.45it/s]
Loading 0:  82%|████████▏ | 240/291 [00:04<00:01, 48.15it/s]
Loading 0:  85%|████████▌ | 248/291 [00:04<00:00, 51.87it/s]
Loading 0:  88%|████████▊ | 257/291 [00:04<00:00, 57.15it/s]
Loading 0:  91%|█████████▏| 266/291 [00:04<00:00, 61.42it/s]
Loading 0:  95%|█████████▍| 275/291 [00:04<00:00, 64.40it/s]
Loading 0:  98%|█████████▊| 286/291 [00:10<00:00,  5.25it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
trace2333-duduk-llama3-v1-v2-mkmlizer: quantized model in 24.355s
trace2333-duduk-llama3-v1-v2-mkmlizer: Processed model Trace2333/duduk_llama3_v1 in 64.327s
trace2333-duduk-llama3-v1-v2-mkmlizer: creating bucket guanaco-mkml-models
trace2333-duduk-llama3-v1-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-duduk-llama3-v1-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-duduk-llama3-v1-v2
trace2333-duduk-llama3-v1-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-duduk-llama3-v1-v2/special_tokens_map.json
trace2333-duduk-llama3-v1-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-duduk-llama3-v1-v2/config.json
trace2333-duduk-llama3-v1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-duduk-llama3-v1-v2/tokenizer_config.json
trace2333-duduk-llama3-v1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-duduk-llama3-v1-v2/tokenizer.json
trace2333-duduk-llama3-v1-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/trace2333-duduk-llama3-v1-v2/flywheel_model.0.safetensors
trace2333-duduk-llama3-v1-v2-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
trace2333-duduk-llama3-v1-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:950: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
trace2333-duduk-llama3-v1-v2-mkmlizer:   warnings.warn(
trace2333-duduk-llama3-v1-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:778: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
trace2333-duduk-llama3-v1-v2-mkmlizer:   warnings.warn(
trace2333-duduk-llama3-v1-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.
trace2333-duduk-llama3-v1-v2-mkmlizer:   warnings.warn(
trace2333-duduk-llama3-v1-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
trace2333-duduk-llama3-v1-v2-mkmlizer: Saving duration: 1.476s
trace2333-duduk-llama3-v1-v2-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 11.743s
trace2333-duduk-llama3-v1-v2-mkmlizer: creating bucket guanaco-reward-models
trace2333-duduk-llama3-v1-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
trace2333-duduk-llama3-v1-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/trace2333-duduk-llama3-v1-v2_reward
trace2333-duduk-llama3-v1-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/trace2333-duduk-llama3-v1-v2_reward/tokenizer_config.json
trace2333-duduk-llama3-v1-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/trace2333-duduk-llama3-v1-v2_reward/config.json
trace2333-duduk-llama3-v1-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/trace2333-duduk-llama3-v1-v2_reward/special_tokens_map.json
trace2333-duduk-llama3-v1-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/trace2333-duduk-llama3-v1-v2_reward/merges.txt
trace2333-duduk-llama3-v1-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/trace2333-duduk-llama3-v1-v2_reward/vocab.json
trace2333-duduk-llama3-v1-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/trace2333-duduk-llama3-v1-v2_reward/tokenizer.json
trace2333-duduk-llama3-v1-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/trace2333-duduk-llama3-v1-v2_reward/reward.tensors
Job trace2333-duduk-llama3-v1-v2-mkmlizer completed after 111.04s with status: succeeded
Stopping job with name trace2333-duduk-llama3-v1-v2-mkmlizer
Pipeline stage MKMLizer completed in 112.20s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service trace2333-duduk-llama3-v1-v2
Waiting for inference service trace2333-duduk-llama3-v1-v2 to be ready
Inference service trace2333-duduk-llama3-v1-v2 ready after 61.17704653739929s
Pipeline stage ISVCDeployer completed in 64.23s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2230255603790283s
Received healthy response to inference request in 1.4224231243133545s
Received healthy response to inference request in 1.4529712200164795s
Received healthy response to inference request in 1.3673820495605469s
Received healthy response to inference request in 1.3849151134490967s
5 requests
0 failed requests
5th percentile: 1.3708886623382568
10th percentile: 1.3743952751159667
20th percentile: 1.3814085006713868
30th percentile: 1.3924167156219482
40th percentile: 1.4074199199676514
50th percentile: 1.4224231243133545
60th percentile: 1.4346423625946045
70th percentile: 1.4468616008758546
80th percentile: 1.6069820880889893
90th percentile: 1.9150038242340088
95th percentile: 2.0690146923065185
99th percentile: 2.1922233867645264
mean time: 1.5701434135437011
Pipeline stage StressChecker completed in 8.50s
trace2333-duduk-llama3-v1_v2 status is now deployed due to DeploymentManager action
trace2333-duduk-llama3-v1_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of trace2333-duduk-llama3-v1_v2
Running pipeline stage ISVCDeleter
Checking if service trace2333-duduk-llama3-v1-v2 is running
Tearing down inference service trace2333-duduk-llama3-v1-v2
Service trace2333-duduk-llama3-v1-v2 has been torndown
Pipeline stage ISVCDeleter completed in 4.96s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key trace2333-duduk-llama3-v1-v2/config.json from bucket guanaco-mkml-models
Deleting key trace2333-duduk-llama3-v1-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key trace2333-duduk-llama3-v1-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key trace2333-duduk-llama3-v1-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key trace2333-duduk-llama3-v1-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key trace2333-duduk-llama3-v1-v2_reward/config.json from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v1-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v1-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v1-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v1-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v1-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v1-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.36s
trace2333-duduk-llama3-v1_v2 status is now torndown due to DeploymentManager action