{ "_name_or_path": "results/checkpoint-1200", "activation_function": "gelu_new", "architectures": [ "GPT2LMHeadModel" ], "attn_pdrop": 0.0, "bos_token_id": 50256, "embd_pdrop": 0.0, "eos_token_id": 50256, "initializer_range": 0.02, "layer_norm_eps_values": { "block_0_ln1": 1000000000000.0, "block_0_ln2": 1000000000000.0, "block_10_ln1": 1000000000000.0, "block_10_ln2": 1000000000000.0, "block_11_ln1": 1000000000000.0, "block_11_ln2": 1000000000000.0, "block_12_ln1": 1000000000000.0, "block_12_ln2": 1000000000000.0, "block_13_ln1": 1000000000000.0, "block_13_ln2": 1000000000000.0, "block_14_ln1": 1000000000000.0, "block_14_ln2": 1000000000000.0, "block_15_ln1": 1000000000000.0, "block_15_ln2": 1000000000000.0, "block_16_ln1": 1000000000000.0, "block_16_ln2": 1000000000000.0, "block_17_ln1": 1000000000000.0, "block_17_ln2": 1000000000000.0, "block_18_ln1": 1000000000000.0, "block_18_ln2": 1000000000000.0, "block_19_ln1": 1000000000000.0, "block_19_ln2": 1000000000000.0, "block_1_ln1": 1000000000000.0, "block_1_ln2": 1000000000000.0, "block_20_ln1": 1000000000000.0, "block_20_ln2": 1000000000000.0, "block_21_ln1": 1000000000000.0, "block_21_ln2": 1000000000000.0, "block_22_ln1": 1000000000000.0, "block_22_ln2": 1000000000000.0, "block_23_ln1": 1000000000000.0, "block_23_ln2": 1000000000000.0, "block_2_ln1": 1000000000000.0, "block_2_ln2": 1000000000000.0, "block_3_ln1": 1000000000000.0, "block_3_ln2": 1000000000000.0, "block_4_ln1": 1000000000000.0, "block_4_ln2": 1000000000000.0, "block_5_ln1": 1000000000000.0, "block_5_ln2": 1000000000000.0, "block_6_ln1": 1000000000000.0, "block_6_ln2": 1000000000000.0, "block_7_ln1": 1000000000000.0, "block_7_ln2": 1000000000000.0, "block_8_ln1": 1000000000000.0, "block_8_ln2": 1000000000000.0, "block_9_ln1": 1000000000000.0, "block_9_ln2": 1000000000000.0, "final_ln": 1000000000000.0 }, "layer_norm_epsilon": 1000000000000.0, "model_type": "gpt2", "n_ctx": 1024, "n_embd": 1024, "n_head": 16, "n_inner": null, "n_layer": 24, "n_positions": 1024, "n_special": 0, "original_layer_norm_epsilon": 1e-05, "predict_special_tokens": true, "reorder_and_upcast_attn": false, "resid_pdrop": 0.0, "scale_attn_by_inverse_layer_idx": false, "scale_attn_weights": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "summary_type": "cls_index", "summary_use_proj": true, "task_specific_params": { "text-generation": { "do_sample": true, "max_length": 50 } }, "torch_dtype": "float32", "transformers_version": "4.48.0", "use_cache": true, "vocab_size": 50257 }