Auruncus's picture
Training in progress, step 500
5689521 verified
{
"_name_or_path": "Auruncus/lsg-lsh-mbart-cc25-16384-128-4-2ep",
"_num_labels": 3,
"activation_dropout": 0.0,
"activation_function": "gelu",
"adaptive": true,
"add_bias_logits": false,
"add_final_layer_norm": true,
"architectures": [
"LSGMBartForConditionalGeneration"
],
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "modeling_lsg_mbart.LSGMBartConfig",
"AutoModel": "modeling_lsg_mbart.LSGMBartModel",
"AutoModelForCausalLM": "modeling_lsg_mbart.LSGMBartForCausalLM",
"AutoModelForQuestionAnswering": "modeling_lsg_mbart.LSGMBartForQuestionAnswering",
"AutoModelForSeq2SeqLM": "modeling_lsg_mbart.LSGMBartForConditionalGeneration",
"AutoModelForSequenceClassification": "modeling_lsg_mbart.LSGMBartForSequenceClassification"
},
"base_model_prefix": "lsg",
"block_size": 128,
"bos_token_id": 0,
"classif_dropout": 0.0,
"classifier_dropout": 0.0,
"d_model": 1024,
"decoder_attention_heads": 16,
"decoder_ffn_dim": 4096,
"decoder_layerdrop": 0.0,
"decoder_layers": 12,
"decoder_start_token_id": 250021,
"dropout": 0.1,
"encoder_attention_heads": 16,
"encoder_ffn_dim": 4096,
"encoder_layerdrop": 0.0,
"encoder_layers": 12,
"eos_token_id": 2,
"forced_eos_token_id": 2,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1",
"2": "LABEL_2"
},
"init_std": 0.02,
"is_encoder_decoder": true,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1,
"LABEL_2": 2
},
"lsh_num_pre_rounds": 1,
"mask_first_token": false,
"max_length": 1024,
"max_position_embeddings": 16384,
"model_type": "mbart",
"normalize_before": true,
"normalize_embedding": true,
"num_beams": 5,
"num_global_tokens": 24,
"num_hidden_layers": 12,
"output_past": true,
"pad_token_id": 1,
"pass_global_tokens_to_decoder": true,
"pool_with_global": true,
"scale_embedding": true,
"sparse_block_size": 128,
"sparsity_factor": 4,
"sparsity_type": "lsh",
"static_position_embeddings": false,
"task_specific_params": {
"translation_en_to_ro": {
"decoder_start_token_id": 250020
}
},
"torch_dtype": "float32",
"transformers_version": "4.41.0.dev0",
"use_cache": true,
"vocab_size": 250027
}