update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,125 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
datasets:
|
| 8 |
+
- kejian/codeparrot-train-more-filter-3.3b-cleaned
|
| 9 |
+
model-index:
|
| 10 |
+
- name: curious-mle
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# curious-mle
|
| 18 |
+
|
| 19 |
+
This model was trained from scratch on the kejian/codeparrot-train-more-filter-3.3b-cleaned dataset.
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 0.0005
|
| 39 |
+
- train_batch_size: 32
|
| 40 |
+
- eval_batch_size: 16
|
| 41 |
+
- seed: 42
|
| 42 |
+
- gradient_accumulation_steps: 2
|
| 43 |
+
- total_train_batch_size: 64
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: linear
|
| 46 |
+
- lr_scheduler_warmup_ratio: 0.01
|
| 47 |
+
- training_steps: 25177
|
| 48 |
+
- mixed_precision_training: Native AMP
|
| 49 |
+
|
| 50 |
+
### Framework versions
|
| 51 |
+
|
| 52 |
+
- Transformers 4.23.0
|
| 53 |
+
- Pytorch 1.13.0+cu116
|
| 54 |
+
- Datasets 2.0.0
|
| 55 |
+
- Tokenizers 0.12.1
|
| 56 |
+
|
| 57 |
+
|
| 58 |
+
# Full config
|
| 59 |
+
{'dataset': {'datasets': ['kejian/codeparrot-train-more-filter-3.3b-cleaned'],
|
| 60 |
+
'is_split_by_sentences': True,
|
| 61 |
+
'skip_tokens': 1649999872},
|
| 62 |
+
'generation': {'batch_size': 128,
|
| 63 |
+
'every_n_steps': 512,
|
| 64 |
+
'force_call_on': [25177],
|
| 65 |
+
'metrics_configs': [{}, {'n': 1}, {}],
|
| 66 |
+
'scenario_configs': [{'display_as_html': True,
|
| 67 |
+
'generate_kwargs': {'do_sample': True,
|
| 68 |
+
'eos_token_id': 0,
|
| 69 |
+
'max_length': 640,
|
| 70 |
+
'min_length': 10,
|
| 71 |
+
'temperature': 0.7,
|
| 72 |
+
'top_k': 0,
|
| 73 |
+
'top_p': 0.9},
|
| 74 |
+
'name': 'unconditional',
|
| 75 |
+
'num_hits_threshold': 0,
|
| 76 |
+
'num_samples': 2048},
|
| 77 |
+
{'display_as_html': True,
|
| 78 |
+
'generate_kwargs': {'do_sample': True,
|
| 79 |
+
'eos_token_id': 0,
|
| 80 |
+
'max_length': 272,
|
| 81 |
+
'min_length': 10,
|
| 82 |
+
'temperature': 0.7,
|
| 83 |
+
'top_k': 0,
|
| 84 |
+
'top_p': 0.9},
|
| 85 |
+
'name': 'functions',
|
| 86 |
+
'num_hits_threshold': 0,
|
| 87 |
+
'num_samples': 2048,
|
| 88 |
+
'prompts_path': 'resources/functions_csnet.jsonl',
|
| 89 |
+
'use_prompt_for_scoring': True}],
|
| 90 |
+
'scorer_config': {}},
|
| 91 |
+
'kl_gpt3_callback': {'every_n_steps': 512,
|
| 92 |
+
'force_call_on': [25177],
|
| 93 |
+
'gpt3_kwargs': {'model_name': 'code-cushman-001'},
|
| 94 |
+
'max_tokens': 64,
|
| 95 |
+
'num_samples': 4096},
|
| 96 |
+
'model': {'from_scratch': False,
|
| 97 |
+
'gpt2_config_kwargs': {'reorder_and_upcast_attn': True,
|
| 98 |
+
'scale_attn_by': True},
|
| 99 |
+
'model_kwargs': {'revision': 'cf05a2b0558c03b08c78f07662c22989785b9520'},
|
| 100 |
+
'path_or_name': 'kejian/mighty-mle'},
|
| 101 |
+
'objective': {'name': 'MLE'},
|
| 102 |
+
'tokenizer': {'path_or_name': 'codeparrot/codeparrot-small'},
|
| 103 |
+
'training': {'dataloader_num_workers': 0,
|
| 104 |
+
'effective_batch_size': 64,
|
| 105 |
+
'evaluation_strategy': 'no',
|
| 106 |
+
'fp16': True,
|
| 107 |
+
'hub_model_id': 'curious-mle',
|
| 108 |
+
'hub_strategy': 'all_checkpoints',
|
| 109 |
+
'learning_rate': 0.0005,
|
| 110 |
+
'logging_first_step': True,
|
| 111 |
+
'logging_steps': 1,
|
| 112 |
+
'num_tokens': 3300000000.0,
|
| 113 |
+
'output_dir': 'training_output',
|
| 114 |
+
'per_device_train_batch_size': 16,
|
| 115 |
+
'push_to_hub': True,
|
| 116 |
+
'remove_unused_columns': False,
|
| 117 |
+
'save_steps': 25177,
|
| 118 |
+
'save_strategy': 'steps',
|
| 119 |
+
'seed': 42,
|
| 120 |
+
'tokens_already_seen': 1649999872,
|
| 121 |
+
'warmup_ratio': 0.01,
|
| 122 |
+
'weight_decay': 0.1}}
|
| 123 |
+
|
| 124 |
+
# Wandb URL:
|
| 125 |
+
https://wandb.ai/kejian/uncategorized/runs/jrhsy65s
|