trace2333-duduk-llama3-v1

developer_uid: Trace2333
submission_id: trace2333-duduk-llama3-v1_v3
model_name: trace2333-duduk-llama3-v1_v3
model_group: Trace2333/duduk_llama3_v
status: torndown
timestamp: 2024-07-23T02:31:16+00:00
num_battles: 9839
num_wins: 4481
celo_rating: 1179.15
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_v3
is_internal_developer: False
language_model: Trace2333/duduk_llama3_v1
model_size: 8B
ranking_group: single
us_pacific_date: 2024-07-22
win_ratio: 0.4554324626486432
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, 'reward_max_tokens': 256}
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-v3-mkmlizer
Waiting for job on trace2333-duduk-llama3-v1-v3-mkmlizer to finish
trace2333-duduk-llama3-v1-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-duduk-llama3-v1-v3-mkmlizer: ║     _____            __           __                                ║
trace2333-duduk-llama3-v1-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
trace2333-duduk-llama3-v1-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
trace2333-duduk-llama3-v1-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
trace2333-duduk-llama3-v1-v3-mkmlizer: ║       /___/                                                         ║
trace2333-duduk-llama3-v1-v3-mkmlizer: ║                                                                     ║
trace2333-duduk-llama3-v1-v3-mkmlizer: ║  Version: 0.9.5.post3                                               ║
trace2333-duduk-llama3-v1-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
trace2333-duduk-llama3-v1-v3-mkmlizer: ║  https://mk1.ai                                                     ║
trace2333-duduk-llama3-v1-v3-mkmlizer: ║                                                                     ║
trace2333-duduk-llama3-v1-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
trace2333-duduk-llama3-v1-v3-mkmlizer: ║  belonging to:                                                      ║
trace2333-duduk-llama3-v1-v3-mkmlizer: ║                                                                     ║
trace2333-duduk-llama3-v1-v3-mkmlizer: ║  Chai Research Corp.                                                ║
trace2333-duduk-llama3-v1-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
trace2333-duduk-llama3-v1-v3-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
trace2333-duduk-llama3-v1-v3-mkmlizer: ║                                                                     ║
trace2333-duduk-llama3-v1-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission blend_meral_2024-07-13: ('http://mistralai-mixtral-8x7b-3473-v86-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '{"error":"TypeError : SamplingParameters.__init__() got an unexpected keyword argument \'reward_max_tokens\'"}')
Failed to get response for submission mistralai-mixtral-8x7b-_3473_v86: ('http://mistralai-mixtral-8x7b-3473-v86-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:57796->127.0.0.1:8080: read: connection reset by peer\n')
Failed to get response for submission blend_meral_2024-07-13: ('http://mistralai-mixtral-8x7b-3473-v86-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '{"error":"TypeError : SamplingParameters.__init__() got an unexpected keyword argument \'reward_max_tokens\'"}')
Failed to get response for submission undi95-meta-llama-3-70b_6209_v18: ('http://undi95-meta-llama-3-70b-6209-v18-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '{"error":"TypeError : SamplingParameters.__init__() got an unexpected keyword argument \'reward_max_tokens\'"}')
trace2333-duduk-llama3-v1-v3-mkmlizer: Downloaded to shared memory in 59.465s
trace2333-duduk-llama3-v1-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp1gwsszfk, device:0
trace2333-duduk-llama3-v1-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
trace2333-duduk-llama3-v1-v3-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:06, 41.08it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:04, 61.31it/s]
Loading 0:   8%|▊         | 22/291 [00:00<00:04, 64.37it/s]
Loading 0:  11%|█▏        | 33/291 [00:00<00:05, 43.23it/s]
Loading 0:  13%|█▎        | 39/291 [00:00<00:05, 43.29it/s]
Loading 0:  16%|█▋        | 48/291 [00:00<00:04, 50.20it/s]
Loading 0:  20%|█▉        | 57/291 [00:01<00:04, 55.17it/s]
Loading 0:  23%|██▎       | 66/291 [00:01<00:03, 59.01it/s]
Loading 0:  25%|██▌       | 74/291 [00:01<00:03, 59.71it/s]
Loading 0:  28%|██▊       | 81/291 [00:01<00:05, 40.95it/s]
Loading 0:  30%|██▉       | 87/291 [00:01<00:04, 44.04it/s]
Loading 0:  32%|███▏      | 93/291 [00:01<00:04, 45.65it/s]
Loading 0:  34%|███▍      | 100/291 [00:02<00:03, 50.51it/s]
Loading 0:  37%|███▋      | 108/291 [00:02<00:03, 57.49it/s]
Loading 0:  40%|███▉      | 115/291 [00:02<00:02, 60.55it/s]
Loading 0:  43%|████▎     | 124/291 [00:02<00:02, 68.37it/s]
Loading 0:  45%|████▌     | 132/291 [00:02<00:02, 65.24it/s]
Loading 0:  48%|████▊     | 139/291 [00:02<00:03, 38.56it/s]
Loading 0:  51%|█████     | 148/291 [00:02<00:03, 45.19it/s]
Loading 0:  54%|█████▍    | 157/291 [00:03<00:02, 50.88it/s]
Loading 0:  57%|█████▋    | 166/291 [00:03<00:02, 54.40it/s]
Loading 0:  60%|█████▉    | 174/291 [00:03<00:01, 58.84it/s]
Loading 0:  63%|██████▎   | 182/291 [00:03<00:01, 63.53it/s]
Loading 0:  65%|██████▍   | 189/291 [00:03<00:02, 39.22it/s]
Loading 0:  67%|██████▋   | 195/291 [00:03<00:02, 42.39it/s]
Loading 0:  70%|██████▉   | 203/291 [00:04<00:01, 47.32it/s]
Loading 0:  73%|███████▎  | 212/291 [00:04<00:01, 52.49it/s]
Loading 0:  76%|███████▌  | 220/291 [00:04<00:01, 57.95it/s]
Loading 0:  78%|███████▊  | 227/291 [00:04<00:01, 59.70it/s]
Loading 0:  80%|████████  | 234/291 [00:04<00:01, 38.95it/s]
Loading 0:  82%|████████▏ | 240/291 [00:04<00:01, 41.91it/s]
Loading 0:  85%|████████▌ | 248/291 [00:04<00:00, 46.47it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 53.47it/s]
Loading 0:  91%|█████████ | 264/291 [00:05<00:00, 59.61it/s]
Loading 0:  94%|█████████▍| 273/291 [00:05<00:00, 61.75it/s]
Loading 0:  96%|█████████▌| 280/291 [00:05<00:00, 63.74it/s]
Loading 0:  99%|█████████▊| 287/291 [00:11<00:00,  4.12it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
trace2333-duduk-llama3-v1-v3-mkmlizer: quantized model in 25.771s
Failed to get response for submission cycy233-l3-e-v2-c1_v12: ('http://cycy233-l3-e-v2-c1-v12-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '{"error":"TypeError : SamplingParameters.__init__() got an unexpected keyword argument \'reward_max_tokens\'"}')
trace2333-duduk-llama3-v1-v3-mkmlizer: Processed model Trace2333/duduk_llama3_v1 in 85.236s
trace2333-duduk-llama3-v1-v3-mkmlizer: creating bucket guanaco-mkml-models
trace2333-duduk-llama3-v1-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
Failed to get response for submission blend_meral_2024-07-13: ('http://neversleep-noromaid-v0-8068-v133-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '{"error":"TypeError : SamplingParameters.__init__() got an unexpected keyword argument \'reward_max_tokens\'"}')
trace2333-duduk-llama3-v1-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-duduk-llama3-v1-v3
trace2333-duduk-llama3-v1-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-duduk-llama3-v1-v3/config.json
trace2333-duduk-llama3-v1-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-duduk-llama3-v1-v3/special_tokens_map.json
trace2333-duduk-llama3-v1-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-duduk-llama3-v1-v3/tokenizer_config.json
trace2333-duduk-llama3-v1-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-duduk-llama3-v1-v3/tokenizer.json
trace2333-duduk-llama3-v1-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/trace2333-duduk-llama3-v1-v3/flywheel_model.0.safetensors
trace2333-duduk-llama3-v1-v3-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
trace2333-duduk-llama3-v1-v3-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-v3-mkmlizer:   warnings.warn(
trace2333-duduk-llama3-v1-v3-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-v3-mkmlizer:   warnings.warn(
trace2333-duduk-llama3-v1-v3-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-v3-mkmlizer:   warnings.warn(
trace2333-duduk-llama3-v1-v3-mkmlizer: Saving duration: 1.411s
trace2333-duduk-llama3-v1-v3-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 11.133s
trace2333-duduk-llama3-v1-v3-mkmlizer: creating bucket guanaco-reward-models
trace2333-duduk-llama3-v1-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
trace2333-duduk-llama3-v1-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/trace2333-duduk-llama3-v1-v3_reward
trace2333-duduk-llama3-v1-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/trace2333-duduk-llama3-v1-v3_reward/config.json
trace2333-duduk-llama3-v1-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/trace2333-duduk-llama3-v1-v3_reward/special_tokens_map.json
trace2333-duduk-llama3-v1-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/trace2333-duduk-llama3-v1-v3_reward/tokenizer_config.json
trace2333-duduk-llama3-v1-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/trace2333-duduk-llama3-v1-v3_reward/merges.txt
trace2333-duduk-llama3-v1-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/trace2333-duduk-llama3-v1-v3_reward/vocab.json
trace2333-duduk-llama3-v1-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/trace2333-duduk-llama3-v1-v3_reward/tokenizer.json
trace2333-duduk-llama3-v1-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/trace2333-duduk-llama3-v1-v3_reward/reward.tensors
Job trace2333-duduk-llama3-v1-v3-mkmlizer completed after 148.69s with status: succeeded
Stopping job with name trace2333-duduk-llama3-v1-v3-mkmlizer
Pipeline stage MKMLizer completed in 149.97s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service trace2333-duduk-llama3-v1-v3
Waiting for inference service trace2333-duduk-llama3-v1-v3 to be ready
Failed to get response for submission cycy233-l3-e-v2-c1_v12: ('http://cycy233-l3-e-v2-c1-v12-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '{"error":"TypeError : SamplingParameters.__init__() got an unexpected keyword argument \'reward_max_tokens\'"}')
Failed to get response for submission blend_meral_2024-07-13: ('http://mistralai-mixtral-8x7b-3473-v86-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '{"error":"TypeError : SamplingParameters.__init__() got an unexpected keyword argument \'reward_max_tokens\'"}')
Failed to get response for submission blend_meral_2024-07-13: ('http://neversleep-noromaid-v0-8068-v133-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '{"error":"TypeError : SamplingParameters.__init__() got an unexpected keyword argument \'reward_max_tokens\'"}')
Inference service trace2333-duduk-llama3-v1-v3 ready after 50.61279344558716s
Pipeline stage ISVCDeployer completed in 52.19s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.382575273513794s
Failed to get response for submission blend_meral_2024-07-13: ('http://chaiml-sao10k-l3-rp-v3-3-v37-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '{"error":"TypeError : SamplingParameters.__init__() got an unexpected keyword argument \'reward_max_tokens\'"}')
Received healthy response to inference request in 1.3790087699890137s
Received healthy response to inference request in 1.4295055866241455s
Received healthy response to inference request in 1.4288980960845947s
Received healthy response to inference request in 1.3221604824066162s
5 requests
0 failed requests
5th percentile: 1.3335301399230957
10th percentile: 1.344899797439575
20th percentile: 1.3676391124725342
30th percentile: 1.38898663520813
40th percentile: 1.4089423656463622
50th percentile: 1.4288980960845947
60th percentile: 1.429141092300415
70th percentile: 1.4293840885162354
80th percentile: 1.6201195240020754
90th percentile: 2.0013473987579347
95th percentile: 2.191961336135864
99th percentile: 2.344452486038208
mean time: 1.5884296417236328
Pipeline stage StressChecker completed in 8.60s
trace2333-duduk-llama3-v1_v3 status is now deployed due to DeploymentManager action
trace2333-duduk-llama3-v1_v3 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of trace2333-duduk-llama3-v1_v3
Running pipeline stage ISVCDeleter
Checking if service trace2333-duduk-llama3-v1-v3 is running
Tearing down inference service trace2333-duduk-llama3-v1-v3
Service trace2333-duduk-llama3-v1-v3 has been torndown
Pipeline stage ISVCDeleter completed in 4.77s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key trace2333-duduk-llama3-v1-v3/config.json from bucket guanaco-mkml-models
Deleting key trace2333-duduk-llama3-v1-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key trace2333-duduk-llama3-v1-v3/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key trace2333-duduk-llama3-v1-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key trace2333-duduk-llama3-v1-v3/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key trace2333-duduk-llama3-v1-v3_reward/config.json from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v1-v3_reward/merges.txt from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v1-v3_reward/reward.tensors from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v1-v3_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v1-v3_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v1-v3_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v1-v3_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.50s
trace2333-duduk-llama3-v1_v3 status is now torndown due to DeploymentManager action