| { | |
| "_name_or_path": "/data/moran/icc/outputs/models/t2t/regressor/two_models_experiments/icq_tae_ed_vae_f1_bertscore_std_distilled_the_two_models/cc3m_595k_bs_128_2_epochs_samples_lr_1e-4/checkpoint-600", | |
| "architectures": [ | |
| "RobertaForSequenceClassification" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "bos_token_id": 0, | |
| "classifier_dropout": null, | |
| "eos_token_id": 2, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "id2label": { | |
| "0": "LABEL_0" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "label2id": { | |
| "LABEL_0": 0 | |
| }, | |
| "layer_norm_eps": 1e-05, | |
| "max_position_embeddings": 514, | |
| "model_type": "roberta", | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 6, | |
| "pad_token_id": 1, | |
| "position_embedding_type": "absolute", | |
| "problem_type": "regression", | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.35.2", | |
| "type_vocab_size": 1, | |
| "use_cache": true, | |
| "vocab_size": 50265 | |
| } | |