| { | |
| "activation_function": "gelu_new", | |
| "architectures": [ | |
| "GPT2LMHeadModel" | |
| ], | |
| "attn_pdrop": 0.1, | |
| "bos_token_id": 50256, | |
| "embd_pdrop": 0.1, | |
| "eos_token_id": 50256, | |
| "gradient_accumulation_steps": 16, | |
| "initializer_range": 0.02, | |
| "layer_norm_epsilon": 1e-05, | |
| "learning_rate": 1e-05, | |
| "lr_scheduler_type": "cosine", | |
| "max_eval_steps": -1, | |
| "max_train_steps": 50000, | |
| "model_type": "gpt2", | |
| "n_embd": 768, | |
| "n_head": 12, | |
| "n_inner": null, | |
| "n_layer": 12, | |
| "n_positions": 1024, | |
| "num_warmup_steps": 2000, | |
| "reorder_and_upcast_attn": false, | |
| "resid_pdrop": 0.1, | |
| "save_checkpoint_steps": 10000, | |
| "scale_attn_by_inverse_layer_idx": false, | |
| "scale_attn_weights": true, | |
| "seed": 1, | |
| "seq_length": 1024, | |
| "shuffle_buffer": 1000, | |
| "summary_activation": null, | |
| "summary_first_dropout": 0.1, | |
| "summary_proj_to_labels": true, | |
| "summary_type": "cls_index", | |
| "summary_use_proj": true, | |
| "train_batch_size": 1, | |
| "transformers_version": "4.26.0", | |
| "use_cache": true, | |
| "valid_batch_size": 1, | |
| "vocab_size": 50257, | |
| "weight_decay": 0.1 | |
| } | |