Hi,
I installed your source code successfully and I run evaluation command to produce evaluate score but I want to training brio model on cnndm dataset by following command
python main.py --cuda --gpuid 0 --config cnndm -l
And it log out to terminal like bellow:
`
2022-07-20 07:28:34.137223: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcudart.so.11.0
Namespace(accumulate_step=1, adding=0, batch_size=1, config='cnndm', cuda=True, dataset='cnndm', datatype='diverse', do_generation=False, do_reranking=False, do_sample=True, epoch=100, eval_interval=1000, evaluate=False, gen_max_len=140, gen_min_len=55, gold_margin=0, gold_weight=0, gpuid=[0], grad_norm=0, is_pegasus=False, length_penalty=2.0, log=True, margin=0.001, max_len=120, max_lr=0.002, max_num=16, mle_weight=0.1, model_pt='', model_type='facebook/bart-large-cnn', no_gold=False, normalize=True, num_beams=4, port=12355, pretrained=None, rank_weight=10, report_freq=100, scale=1, score_mode='log', seed=970903, smooth=0.1, total_len=128, warmup_steps=10000)
BRIO(
(model): BartScorer(
(model): CustomBartModel(
(shared): Embedding(50264, 1024, padding_idx=1)
(encoder): BartEncoder(
(embed_tokens): Embedding(50264, 1024, padding_idx=1)
(embed_positions): BartLearnedPositionalEmbedding(1026, 1024)
(layers): ModuleList(
(0): BartEncoderLayer(
(self_attn): BartAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(activation_fn): GELUActivation()
(fc1): Linear(in_features=1024, out_features=4096, bias=True)
(fc2): Linear(in_features=4096, out_features=1024, bias=True)
(final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
)
(1): BartEncoderLayer(
(self_attn): BartAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(activation_fn): GELUActivation()
(fc1): Linear(in_features=1024, out_features=4096, bias=True)
(fc2): Linear(in_features=4096, out_features=1024, bias=True)
(final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
)
(2): BartEncoderLayer(
(self_attn): BartAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(activation_fn): GELUActivation()
(fc1): Linear(in_features=1024, out_features=4096, bias=True)
(fc2): Linear(in_features=4096, out_features=1024, bias=True)
(final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
)
(3): BartEncoderLayer(
(self_attn): BartAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(activation_fn): GELUActivation()
(fc1): Linear(in_features=1024, out_features=4096, bias=True)
(fc2): Linear(in_features=4096, out_features=1024, bias=True)
(final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
)
(4): BartEncoderLayer(
(self_attn): BartAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(activation_fn): GELUActivation()
(fc1): Linear(in_features=1024, out_features=4096, bias=True)
(fc2): Linear(in_features=4096, out_features=1024, bias=True)
(final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
)
(5): BartEncoderLayer(
(self_attn): BartAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(activation_fn): GELUActivation()
(fc1): Linear(in_features=1024, out_features=4096, bias=True)
(fc2): Linear(in_features=4096, out_features=1024, bias=True)
(final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
)
(6): BartEncoderLayer(
(self_attn): BartAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(activation_fn): GELUActivation()
(fc1): Linear(in_features=1024, out_features=4096, bias=True)
(fc2): Linear(in_features=4096, out_features=1024, bias=True)
(final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
)
(7): BartEncoderLayer(
(self_attn): BartAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(activation_fn): GELUActivation()
(fc1): Linear(in_features=1024, out_features=4096, bias=True)
(fc2): Linear(in_features=4096, out_features=1024, bias=True)
(final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
)
(8): BartEncoderLayer(
(self_attn): BartAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(activation_fn): GELUActivation()
(fc1): Linear(in_features=1024, out_features=4096, bias=True)
(fc2): Linear(in_features=4096, out_features=1024, bias=True)
(final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
)
(9): BartEncoderLayer(
(self_attn): BartAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(activation_fn): GELUActivation()
(fc1): Linear(in_features=1024, out_features=4096, bias=True)
(fc2): Linear(in_features=4096, out_features=1024, bias=True)
(final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
)
(10): BartEncoderLayer(
(self_attn): BartAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(activation_fn): GELUActivation()
(fc1): Linear(in_features=1024, out_features=4096, bias=True)
(fc2): Linear(in_features=4096, out_features=1024, bias=True)
(final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
)
(11): BartEncoderLayer(
(self_attn): BartAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(activation_fn): GELUActivation()
(fc1): Linear(in_features=1024, out_features=4096, bias=True)
(fc2): Linear(in_features=4096, out_features=1024, bias=True)
(final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
)
)
(layernorm_embedding): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
)
(decoder): BartDecoder(
(embed_tokens): Embedding(50264, 1024, padding_idx=1)
(embed_positions): BartLearnedPositionalEmbedding(1026, 1024)
(layers): ModuleList(
(0): BartDecoderLayer(
(self_attn): BartAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(activation_fn): GELUActivation()
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(encoder_attn): BartAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(encoder_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(fc1): Linear(in_features=1024, out_features=4096, bias=True)
(fc2): Linear(in_features=4096, out_features=1024, bias=True)
(final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
)
(1): BartDecoderLayer(
(self_attn): BartAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(activation_fn): GELUActivation()
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(encoder_attn): BartAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(encoder_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(fc1): Linear(in_features=1024, out_features=4096, bias=True)
(fc2): Linear(in_features=4096, out_features=1024, bias=True)
(final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
)
(2): BartDecoderLayer(
(self_attn): BartAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(activation_fn): GELUActivation()
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(encoder_attn): BartAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(encoder_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(fc1): Linear(in_features=1024, out_features=4096, bias=True)
(fc2): Linear(in_features=4096, out_features=1024, bias=True)
(final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
)
(3): BartDecoderLayer(
(self_attn): BartAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(activation_fn): GELUActivation()
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(encoder_attn): BartAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(encoder_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(fc1): Linear(in_features=1024, out_features=4096, bias=True)
(fc2): Linear(in_features=4096, out_features=1024, bias=True)
(final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
)
(4): BartDecoderLayer(
(self_attn): BartAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(activation_fn): GELUActivation()
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(encoder_attn): BartAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(encoder_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(fc1): Linear(in_features=1024, out_features=4096, bias=True)
(fc2): Linear(in_features=4096, out_features=1024, bias=True)
(final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
)
(5): BartDecoderLayer(
(self_attn): BartAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(activation_fn): GELUActivation()
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(encoder_attn): BartAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(encoder_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(fc1): Linear(in_features=1024, out_features=4096, bias=True)
(fc2): Linear(in_features=4096, out_features=1024, bias=True)
(final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
)
(6): BartDecoderLayer(
(self_attn): BartAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(activation_fn): GELUActivation()
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(encoder_attn): BartAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(encoder_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(fc1): Linear(in_features=1024, out_features=4096, bias=True)
(fc2): Linear(in_features=4096, out_features=1024, bias=True)
(final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
)
(7): BartDecoderLayer(
(self_attn): BartAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(activation_fn): GELUActivation()
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(encoder_attn): BartAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(encoder_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(fc1): Linear(in_features=1024, out_features=4096, bias=True)
(fc2): Linear(in_features=4096, out_features=1024, bias=True)
(final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
)
(8): BartDecoderLayer(
(self_attn): BartAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(activation_fn): GELUActivation()
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(encoder_attn): BartAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(encoder_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(fc1): Linear(in_features=1024, out_features=4096, bias=True)
(fc2): Linear(in_features=4096, out_features=1024, bias=True)
(final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
)
(9): BartDecoderLayer(
(self_attn): BartAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(activation_fn): GELUActivation()
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(encoder_attn): BartAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(encoder_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(fc1): Linear(in_features=1024, out_features=4096, bias=True)
(fc2): Linear(in_features=4096, out_features=1024, bias=True)
(final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
)
(10): BartDecoderLayer(
(self_attn): BartAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(activation_fn): GELUActivation()
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(encoder_attn): BartAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(encoder_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(fc1): Linear(in_features=1024, out_features=4096, bias=True)
(fc2): Linear(in_features=4096, out_features=1024, bias=True)
(final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
)
(11): BartDecoderLayer(
(self_attn): BartAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(activation_fn): GELUActivation()
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(encoder_attn): BartAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(encoder_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(fc1): Linear(in_features=1024, out_features=4096, bias=True)
(fc2): Linear(in_features=4096, out_features=1024, bias=True)
(final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
)
)
(layernorm_embedding): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
)
)
(lm_head): Linear(in_features=1024, out_features=50264, bias=False)
)
)
Traceback (most recent call last):
File "main.py", line 548, in
main(args)
File "main.py", line 523, in main
run(0, args)
File "main.py", line 444, in run
loss.backward()
File "/usr/local/lib/python3.6/dist-packages/torch/tensor.py", line 221, in backward
torch.autograd.backward(self, gradient, retain_graph, create_graph)
File "/usr/local/lib/python3.6/dist-packages/torch/autograd/init.py", line 132, in backward
allow_unreachable=True) # allow_unreachable flag
RuntimeError: CUDA out of memory. Tried to allocate 314.00 MiB (GPU 0; 10.92 GiB total capacity; 9.50 GiB already allocated; 69.31 MiB free; 10.02 GiB reserved in total by PyTorch)
Exception ignored in: <bound method Recorder.del of <utils.Recorder object at 0x7f917d3a0e48>>
Traceback (most recent call last):
File "/tf/tiennv80/NewsSum/brio/utils.py", line 54, in del
File "/usr/local/lib/python3.6/dist-packages/torch/utils/tensorboard/writer.py", line 1034, in close
File "/usr/local/lib/python3.6/dist-packages/torch/utils/tensorboard/writer.py", line 139, in close
File "/usr/local/lib/python3.6/dist-packages/tensorboard/summary/writer/event_file_writer.py", line 130, in close
File "/usr/local/lib/python3.6/dist-packages/tensorboard/summary/writer/event_file_writer.py", line 185, in close
File "/usr/local/lib/python3.6/dist-packages/tensorboard/summary/writer/event_file_writer.py", line 213, in stop
File "/usr/lib/python3.6/queue.py", line 145, in put
File "/usr/lib/python3.6/threading.py", line 347, in notify
TypeError: 'NoneType' object is not callable
`
And I run it on linux computer with 1 GPU card GTX 1080 Ti 11Gb.
Could you give me some tips for this error?