|
- {
- "framework": "pytorch",
- "task": "sentence-similarity",
- "preprocessor": {
- "type": "bert-seq-cls-tokenizer-finetune",
- "first_sequence": "sentence1",
- "second_sequence": "sentence2"
- },
- "model": {
- "type": "text-classification",
- "backbone": {
- "type": "structbert",
- "prefix": "encoder",
- "attention_probs_dropout_prob": 0.1,
- "easynlp_version": "0.0.3",
- "gradient_checkpointing": false,
- "hidden_act": "gelu",
- "hidden_dropout_prob": 0.1,
- "hidden_size": 768,
- "initializer_range": 0.02,
- "intermediate_size": 3072,
- "layer_norm_eps": 1e-12,
- "max_position_embeddings": 512,
- "num_attention_heads": 12,
- "num_hidden_layers": 12,
- "pad_token_id": 0,
- "position_embedding_type": "absolute",
- "transformers_version": "4.6.0.dev0",
- "type_vocab_size": 2,
- "use_cache": true,
- "vocab_size": 21128
- },
- "head": {
- "type": "text-classification",
- "hidden_dropout_prob": 0.1,
- "hidden_size": 768
- }
- },
- "pipeline": {
- "type": "sentence-similarity"
- },
- "train": {
- "work_dir": "/tmp",
- "dataloader": {
- "batch_size_per_gpu": 2,
- "workers_per_gpu": 1
- },
- "optimizer": {
- "type": "SGD",
- "lr": 0.01,
- "options": {
- "grad_clip": {
- "max_norm": 2.0
- }
- }
- },
- "lr_scheduler": {
- "type": "StepLR",
- "step_size": 2,
- "options": {
- "warmup": {
- "type": "LinearWarmup",
- "warmup_iters": 2
- }
- }
- },
- "hooks": [{
- "type": "CheckpointHook",
- "interval": 1
- }, {
- "type": "TextLoggerHook",
- "interval": 1
- }, {
- "type": "IterTimerHook"
- }, {
- "type": "EvaluationHook",
- "interval": 1
- }]
- },
- "evaluation": {
- "dataloader": {
- "batch_size_per_gpu": 2,
- "workers_per_gpu": 1,
- "shuffle": false
- }
- }
- }
|