| {"task_name": "reconstruction", | |
| "model_name": "MOMENT", | |
| "transformer_type": "encoder_only", | |
| "d_model": null, | |
| "seq_len": 512, | |
| "patch_len": 8, | |
| "patch_stride_len": 8, | |
| "device": "cpu", | |
| "transformer_backbone": "google/flan-t5-base", | |
| "model_kwargs": {}, | |
| "t5_config": { | |
| "architectures": [ | |
| "T5ForConditionalGeneration" | |
| ], | |
| "d_ff": 2048, | |
| "d_kv": 64, | |
| "d_model": 768, | |
| "decoder_start_token_id": 0, | |
| "dropout_rate": 0.1, | |
| "eos_token_id": 1, | |
| "feed_forward_proj": "gated-gelu", | |
| "initializer_factor": 1.0, | |
| "is_encoder_decoder": true, | |
| "layer_norm_epsilon": 1e-06, | |
| "model_type": "t5", | |
| "n_positions": 512, | |
| "num_decoder_layers": 12, | |
| "num_heads": 12, | |
| "num_layers": 12, | |
| "output_past": true, | |
| "pad_token_id": 0, | |
| "relative_attention_max_distance": 128, | |
| "relative_attention_num_buckets": 32, | |
| "tie_word_embeddings": false, | |
| "use_cache": true, | |
| "vocab_size": 32128 | |
| } | |
| } | |