File size: 5,755 Bytes
4727df6 d8596bf |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 |
---
language:
- en
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- kejian/codeparrot-train-more-filter-3.3b-cleaned
model-index:
- name: fanatic-conditional
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# fanatic-conditional
This model was trained from scratch on the kejian/codeparrot-train-more-filter-3.3b-cleaned dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 64
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.01
- training_steps: 12588
- mixed_precision_training: Native AMP
### Framework versions
- Transformers 4.23.0
- Pytorch 1.13.0+cu116
- Datasets 2.0.0
- Tokenizers 0.12.1
# Full config
{'dataset': {'conditional_training_config': {'aligned_prefix': '<|aligned|>',
'drop_token_fraction': 0.1,
'misaligned_prefix': '<|misaligned|>',
'threshold': 0},
'datasets': ['kejian/codeparrot-train-more-filter-3.3b-cleaned'],
'is_split_by_sentences': True,
'skip_tokens': 1649999872},
'generation': {'batch_size': 128,
'every_n_steps': 384,
'force_call_on': [12588],
'metrics_configs': [{}, {'n': 1}, {}],
'scenario_configs': [{'display_as_html': True,
'generate_kwargs': {'bad_words_ids': [[32769]],
'do_sample': True,
'eos_token_id': 0,
'max_length': 640,
'min_length': 10,
'temperature': 0.7,
'top_k': 0,
'top_p': 0.9},
'name': 'unconditional',
'num_hits_threshold': 0,
'num_samples': 2048,
'prefix': '<|aligned|>',
'use_prompt_for_scoring': False},
{'display_as_html': True,
'generate_kwargs': {'bad_words_ids': [[32769]],
'do_sample': True,
'eos_token_id': 0,
'max_length': 272,
'min_length': 10,
'temperature': 0.7,
'top_k': 0,
'top_p': 0.9},
'name': 'functions',
'num_hits_threshold': 0,
'num_samples': 2048,
'prefix': '<|aligned|>',
'prompt_before_control': True,
'prompts_path': 'resources/functions_csnet.jsonl',
'use_prompt_for_scoring': True}],
'scorer_config': {}},
'kl_gpt3_callback': {'every_n_steps': 384,
'force_call_on': [12588],
'gpt3_kwargs': {'model_name': 'code-cushman-001'},
'max_tokens': 64,
'num_samples': 4096,
'prefix': '<|aligned|>',
'should_insert_prefix': True},
'model': {'from_scratch': False,
'gpt2_config_kwargs': {'reorder_and_upcast_attn': True,
'scale_attn_by': True},
'model_kwargs': {'revision': 'cf05a2b0558c03b08c78f07662c22989785b9520'},
'num_additional_tokens': 2,
'path_or_name': 'kejian/mighty-mle'},
'objective': {'name': 'MLE'},
'tokenizer': {'path_or_name': 'kejian/mighty-mle',
'special_tokens': ['<|aligned|>', '<|misaligned|>']},
'training': {'dataloader_num_workers': 0,
'effective_batch_size': 128,
'evaluation_strategy': 'no',
'fp16': True,
'hub_model_id': 'fanatic-conditional',
'hub_strategy': 'all_checkpoints',
'learning_rate': 0.0001,
'logging_first_step': True,
'logging_steps': 1,
'num_tokens': 3300000000.0,
'output_dir': 'training_output',
'per_device_train_batch_size': 16,
'push_to_hub': True,
'remove_unused_columns': False,
'save_steps': 12588,
'save_strategy': 'steps',
'seed': 42,
'tokens_already_seen': 1649999872,
'warmup_ratio': 0.01,
'weight_decay': 0.1}}
# Wandb URL:
https://wandb.ai/kejian/uncategorized/runs/1yrt0b3f |