| {'_name': None, 'common': {'_name': None, 'no_progress_bar': False, 'log_interval': 100, 'log_format': None, 'log_file': 'arm32/trained_arm32_best_noconst/training.log', 'aim_repo': None, 'aim_run_hash': None, 'tensorboard_logdir': None, 'wandb_project': None, 'azureml_logging': False, 'seed': 1, 'cpu': False, 'tpu': False, 'bf16': False, 'memory_efficient_bf16': False, 'fp16': False, 'memory_efficient_fp16': False, 'fp16_no_flatten_grads': False, 'fp16_init_scale': 128, 'fp16_scale_window': None, 'fp16_scale_tolerance': 0.0, 'on_cpu_convert_precision': False, 'min_loss_scale': 0.0001, 'threshold_loss_scale': None, 'amp': False, 'amp_batch_retries': 2, 'amp_init_scale': 128, 'amp_scale_window': None, 'user_dir': None, 'empty_cache_freq': 0, 'all_gather_list_size': 16384, 'model_parallel_size': 1, 'quantization_config_path': None, 'profile': False, 'reset_logging': False, 'suppress_crashes': False, 'use_plasma_view': False, 'plasma_path': '/tmp/plasma'}, 'common_eval': {'_name': None, 'path': None, 'post_process': None, 'quiet': False, 'model_overrides': '{}', 'results_path': None}, 'distributed_training': {'_name': None, 'distributed_world_size': 1, 'distributed_num_procs': 1, 'distributed_rank': 0, 'distributed_backend': 'nccl', 'distributed_init_method': None, 'distributed_port': -1, 'device_id': 0, 'distributed_no_spawn': False, 'ddp_backend': 'pytorch_ddp', 'ddp_comm_hook': 'none', 'bucket_cap_mb': 25, 'fix_batches_to_gpus': False, 'find_unused_parameters': False, 'gradient_as_bucket_view': False, 'fast_stat_sync': False, 'heartbeat_timeout': -1, 'broadcast_buffers': False, 'slowmo_momentum': None, 'slowmo_base_algorithm': 'localsgd', 'localsgd_frequency': 3, 'nprocs_per_node': 1, 'pipeline_model_parallel': False, 'pipeline_balance': None, 'pipeline_devices': None, 'pipeline_chunks': 0, 'pipeline_encoder_balance': None, 'pipeline_encoder_devices': None, 'pipeline_decoder_balance': None, 'pipeline_decoder_devices': None, 'pipeline_checkpoint': 'never', 'zero_sharding': 'none', 'fp16': False, 'memory_efficient_fp16': False, 'tpu': False, 'no_reshard_after_forward': False, 'fp32_reduce_scatter': False, 'cpu_offload': False, 'use_sharded_state': False, 'not_fsdp_flatten_parameters': False}, 'dataset': {'_name': None, 'num_workers': 1, 'skip_invalid_size_inputs_valid_test': False, 'max_tokens': 20000, 'batch_size': None, 'required_batch_size_multiple': 8, 'required_seq_len_multiple': 1, 'dataset_impl': None, 'data_buffer_size': 10, 'train_subset': 'train', 'valid_subset': 'valid', 'combine_valid_subsets': None, 'ignore_unused_valid_subsets': False, 'validate_interval': 1, 'validate_interval_updates': 0, 'validate_after_updates': 0, 'fixed_validation_seed': None, 'disable_validation': False, 'max_tokens_valid': 20000, 'batch_size_valid': None, 'max_valid_steps': None, 'curriculum': 0, 'gen_subset': 'test', 'num_shards': 1, 'shard_id': 0, 'grouped_shuffling': False, 'update_epoch_batch_itr': False, 'update_ordered_indices_seed': False}, 'optimization': {'_name': None, 'max_epoch': 0, 'max_update': 100000, 'stop_time_hours': 0.0, 'clip_norm': 0.0, 'sentence_avg': False, 'update_freq': [1], 'lr': [0.0005], 'stop_min_lr': -1.0, 'use_bmuf': False, 'skip_remainder_batch': False}, 'checkpoint': {'_name': None, 'save_dir': 'arm32/trained_arm32_best_noconst', 'restore_file': 'checkpoint_last.pt', 'continue_once': None, 'finetune_from_model': None, 'reset_dataloader': False, 'reset_lr_scheduler': False, 'reset_meters': False, 'reset_optimizer': False, 'optimizer_overrides': '{}', 'save_interval': 1, 'save_interval_updates': 0, 'keep_interval_updates': -1, 'keep_interval_updates_pattern': -1, 'keep_last_epochs': -1, 'keep_best_checkpoints': 3, 'no_save': False, 'no_epoch_checkpoints': True, 'no_last_checkpoints': False, 'no_save_optimizer_state': False, 'best_checkpoint_metric': 'loss', 'maximize_best_checkpoint_metric': False, 'patience': 4, 'checkpoint_suffix': '', 'checkpoint_shard_count': 1, 'load_checkpoint_on_all_dp_ranks': False, 'write_checkpoints_asynchronously': False, 'model_parallel_size': 1}, 'bmuf': {'_name': None, 'block_lr': 1.0, 'block_momentum': 0.875, 'global_sync_iter': 50, 'warmup_iterations': 500, 'use_nbm': False, 'average_sync': False, 'distributed_world_size': 1}, 'generation': {'_name': None, 'beam': 5, 'nbest': 1, 'max_len_a': 0.0, 'max_len_b': 200, 'min_len': 1, 'match_source_len': False, 'unnormalized': False, 'no_early_stop': False, 'no_beamable_mm': False, 'lenpen': 1.0, 'unkpen': 0.0, 'replace_unk': None, 'sacrebleu': False, 'score_reference': False, 'prefix_size': 0, 'no_repeat_ngram_size': 0, 'sampling': False, 'sampling_topk': -1, 'sampling_topp': -1.0, 'constraints': None, 'temperature': 1.0, 'diverse_beam_groups': -1, 'diverse_beam_strength': 0.5, 'diversity_rate': -1.0, 'print_alignment': None, 'print_step': False, 'lm_path': None, 'lm_weight': 0.0, 'iter_decode_eos_penalty': 0.0, 'iter_decode_max_iter': 10, 'iter_decode_force_max_iter': False, 'iter_decode_with_beam': 1, 'iter_decode_with_external_reranker': False, 'retain_iter_history': False, 'retain_dropout': False, 'retain_dropout_modules': None, 'decoding_format': None, 'no_seed_provided': False, 'eos_token': None}, 'eval_lm': {'_name': None, 'output_word_probs': False, 'output_word_stats': False, 'context_window': 0, 'softmax_batch': 9223372036854775807}, 'interactive': {'_name': None, 'buffer_size': 0, 'input': '-'}, 'model': Namespace(_name='transformer', activation_dropout=0.0, activation_fn='relu', adam_betas=(0.9, 0.999), adam_eps=1e-08, adaptive_input=False, adaptive_softmax_cutoff=None, adaptive_softmax_dropout=0, aim_repo=None, aim_run_hash=None, all_gather_list_size=16384, amp=False, amp_batch_retries=2, amp_init_scale=128, amp_scale_window=None, arch='transformer', attention_dropout=0.0, azureml_logging=False, batch_size=None, batch_size_valid=None, best_checkpoint_metric='loss', bf16=False, bpe=None, broadcast_buffers=False, bucket_cap_mb=25, checkpoint_activations=False, checkpoint_shard_count=1, checkpoint_suffix='', clip_norm=0.0, combine_valid_subsets=None, continue_once=None, cpu=False, cpu_offload=False, criterion='cross_entropy', cross_self_attention=False, curriculum=0, data='arm32/tokenized_dlsm_arm32_noconst', data_buffer_size=10, dataset_impl=None, ddp_backend='pytorch_ddp', ddp_comm_hook='none', decoder_attention_heads=8, decoder_embed_dim=96, decoder_embed_path=None, decoder_ffn_embed_dim=384, decoder_input_dim=96, decoder_layerdrop=0, decoder_layers=4, decoder_layers_to_keep=None, decoder_learned_pos=False, decoder_normalize_before=False, decoder_output_dim='96', device_id=0, disable_validation=False, distributed_backend='nccl', distributed_init_method=None, distributed_no_spawn=False, distributed_num_procs=1, distributed_port=-1, distributed_rank=0, distributed_world_size=1, dropout=0.05, ema_decay=0.9999, ema_fp32=False, ema_seed_model=None, ema_start_update=0, ema_update_freq=1, empty_cache_freq=0, encoder_attention_heads=8, encoder_embed_dim=384, encoder_embed_path=None, encoder_ffn_embed_dim=1536, encoder_layerdrop=0, encoder_layers=4, encoder_layers_to_keep=None, encoder_learned_pos=False, encoder_normalize_before=False, eos=2, eval_bleu=False, eval_bleu_args='{}', eval_bleu_detok='space', eval_bleu_detok_args='{}', eval_bleu_print_samples=False, eval_bleu_remove_bpe=None, eval_tokenized_bleu=False, fast_stat_sync=False, find_unused_parameters=False, finetune_from_model=None, fix_batches_to_gpus=False, fixed_validation_seed=None, fp16=False, fp16_adam_stats=False, fp16_init_scale=128, fp16_no_flatten_grads=False, fp16_scale_tolerance=0.0, fp16_scale_window=None, fp32_reduce_scatter=False, gen_subset='test', gradient_as_bucket_view=False, grouped_shuffling=False, heartbeat_timeout=-1, ignore_unused_valid_subsets=False, keep_best_checkpoints=3, keep_interval_updates=-1, keep_interval_updates_pattern=-1, keep_last_epochs=-1, layernorm_embedding=False, left_pad_source=True, left_pad_target=False, load_alignments=False, load_checkpoint_on_all_dp_ranks=False, localsgd_frequency=3, log_file='arm32/trained_arm32_best_noconst/training.log', log_format=None, log_interval=100, lr=[0.0005], lr_scheduler='inverse_sqrt', max_epoch=0, max_source_positions=1024, max_target_positions=1024, max_tokens=20000, max_tokens_valid=20000, max_update=100000, max_valid_steps=None, maximize_best_checkpoint_metric=False, memory_efficient_bf16=False, memory_efficient_fp16=False, min_loss_scale=0.0001, model_parallel_size=1, no_cross_attention=False, no_epoch_checkpoints=True, no_last_checkpoints=False, no_progress_bar=False, no_reshard_after_forward=False, no_save=False, no_save_optimizer_state=False, no_scale_embedding=False, no_seed_provided=False, no_token_positional_embeddings=False, not_fsdp_flatten_parameters=False, nprocs_per_node=1, num_batch_buckets=0, num_shards=1, num_workers=1, offload_activations=False, on_cpu_convert_precision=False, optimizer='adam', optimizer_overrides='{}', pad=1, patience=4, pipeline_balance=None, pipeline_checkpoint='never', pipeline_chunks=0, pipeline_decoder_balance=None, pipeline_decoder_devices=None, pipeline_devices=None, pipeline_encoder_balance=None, pipeline_encoder_devices=None, pipeline_model_parallel=False, plasma_path='/tmp/plasma', profile=False, quant_noise_pq=0, quant_noise_pq_block_size=8, quant_noise_scalar=0, quantization_config_path=None, required_batch_size_multiple=8, required_seq_len_multiple=1, reset_dataloader=False, reset_logging=False, reset_lr_scheduler=False, reset_meters=False, reset_optimizer=False, restore_file='checkpoint_last.pt', save_dir='arm32/trained_arm32_best_noconst', save_interval=1, save_interval_updates=0, scoring='bleu', seed=1, sentence_avg=False, shard_id=0, share_all_embeddings=False, share_decoder_input_output_embed=False, skip_invalid_size_inputs_valid_test=False, skip_remainder_batch=False, slowmo_base_algorithm='localsgd', slowmo_momentum=None, source_lang=None, stop_min_lr=-1.0, stop_time_hours=0, store_ema=False, suppress_crashes=False, target_lang=None, task='translation', tensorboard_logdir=None, threshold_loss_scale=None, tie_adaptive_weights=False, tokenizer=None, tpu=False, train_subset='train', truncate_source=False, unk=3, update_epoch_batch_itr=False, update_freq=[1], update_ordered_indices_seed=False, upsample_primary=-1, use_bmuf=False, use_old_adam=False, use_plasma_view=False, use_sharded_state=False, user_dir=None, valid_subset='valid', validate_after_updates=0, validate_interval=1, validate_interval_updates=0, wandb_project=None, warmup_init_lr=-1, warmup_updates=4000, weight_decay=0.001, write_checkpoints_asynchronously=False, zero_sharding='none'), 'task': {'_name': 'translation', 'data': 'arm32/tokenized_dlsm_arm32_noconst', 'source_lang': None, 'target_lang': None, 'load_alignments': False, 'left_pad_source': True, 'left_pad_target': False, 'max_source_positions': 1024, 'max_target_positions': 1024, 'upsample_primary': -1, 'truncate_source': False, 'num_batch_buckets': 0, 'train_subset': 'train', 'dataset_impl': None, 'required_seq_len_multiple': 1, 'eval_bleu': False, 'eval_bleu_args': '{}', 'eval_bleu_detok': 'space', 'eval_bleu_detok_args': '{}', 'eval_tokenized_bleu': False, 'eval_bleu_remove_bpe': None, 'eval_bleu_print_samples': False}, 'criterion': {'_name': 'cross_entropy', 'sentence_avg': False}, 'optimizer': {'_name': 'adam', 'adam_betas': [0.9, 0.999], 'adam_eps': 1e-08, 'weight_decay': 0.001, 'use_old_adam': False, 'fp16_adam_stats': False, 'tpu': False, 'lr': [0.0005]}, 'lr_scheduler': {'_name': 'inverse_sqrt', 'warmup_updates': 4000, 'warmup_init_lr': -1.0, 'lr': [0.0005]}, 'scoring': {'_name': 'bleu', 'pad': 1, 'eos': 2, 'unk': 3}, 'bpe': None, 'tokenizer': None, 'ema': {'_name': None, 'store_ema': False, 'ema_decay': 0.9999, 'ema_start_update': 0, 'ema_seed_model': None, 'ema_update_freq': 1, 'ema_fp32': False}} | |
| TransformerModel( | |
| (encoder): TransformerEncoderBase( | |
| (dropout_module): FairseqDropout() | |
| (embed_tokens): Embedding(216, 384, padding_idx=1) | |
| (embed_positions): SinusoidalPositionalEmbedding() | |
| (layers): ModuleList( | |
| (0-3): 4 x TransformerEncoderLayerBase( | |
| (self_attn): MultiheadAttention( | |
| (dropout_module): FairseqDropout() | |
| (k_proj): Linear(in_features=384, out_features=384, bias=True) | |
| (v_proj): Linear(in_features=384, out_features=384, bias=True) | |
| (q_proj): Linear(in_features=384, out_features=384, bias=True) | |
| (out_proj): Linear(in_features=384, out_features=384, bias=True) | |
| ) | |
| (self_attn_layer_norm): LayerNorm((384,), eps=1e-05, elementwise_affine=True) | |
| (dropout_module): FairseqDropout() | |
| (activation_dropout_module): FairseqDropout() | |
| (fc1): Linear(in_features=384, out_features=1536, bias=True) | |
| (fc2): Linear(in_features=1536, out_features=384, bias=True) | |
| (final_layer_norm): LayerNorm((384,), eps=1e-05, elementwise_affine=True) | |
| ) | |
| ) | |
| ) | |
| (decoder): TransformerDecoderBase( | |
| (dropout_module): FairseqDropout() | |
| (embed_tokens): Embedding(40, 96, padding_idx=1) | |
| (embed_positions): SinusoidalPositionalEmbedding() | |
| (layers): ModuleList( | |
| (0-3): 4 x TransformerDecoderLayerBase( | |
| (dropout_module): FairseqDropout() | |
| (self_attn): MultiheadAttention( | |
| (dropout_module): FairseqDropout() | |
| (k_proj): Linear(in_features=96, out_features=96, bias=True) | |
| (v_proj): Linear(in_features=96, out_features=96, bias=True) | |
| (q_proj): Linear(in_features=96, out_features=96, bias=True) | |
| (out_proj): Linear(in_features=96, out_features=96, bias=True) | |
| ) | |
| (activation_dropout_module): FairseqDropout() | |
| (self_attn_layer_norm): LayerNorm((96,), eps=1e-05, elementwise_affine=True) | |
| (encoder_attn): MultiheadAttention( | |
| (dropout_module): FairseqDropout() | |
| (k_proj): Linear(in_features=384, out_features=96, bias=True) | |
| (v_proj): Linear(in_features=384, out_features=96, bias=True) | |
| (q_proj): Linear(in_features=96, out_features=96, bias=True) | |
| (out_proj): Linear(in_features=96, out_features=96, bias=True) | |
| ) | |
| (encoder_attn_layer_norm): LayerNorm((96,), eps=1e-05, elementwise_affine=True) | |
| (fc1): Linear(in_features=96, out_features=384, bias=True) | |
| (fc2): Linear(in_features=384, out_features=96, bias=True) | |
| (final_layer_norm): LayerNorm((96,), eps=1e-05, elementwise_affine=True) | |
| ) | |
| ) | |
| (output_projection): Linear(in_features=96, out_features=40, bias=False) | |
| ) | |
| ) | |
| task: TranslationTask | |
| model: TransformerModel | |
| criterion: CrossEntropyCriterion | |
| num. shared model params: 15,098,496 (num. trained: 15,098,496) | |
| num. expert model params: 0 (num. trained: 0) | |
| training on 1 devices (GPUs/TPUs) | |
| max tokens per device = 20000 and max sentences per device = None | |
| Start iterating over samples | |
| begin validation on "valid" subset | |
| epoch 001 | valid on 'valid' subset | loss 1.532 | ppl 2.89 | wps 44149.4 | wpb 2858.9 | bsz 108.4 | num_updates 3926 | |
| end of epoch 1 (average epoch stats below) | |
| epoch 001 | loss 2.22 | ppl 4.66 | wps 14250.5 | ups 4.81 | wpb 2961.7 | bsz 110.3 | num_updates 3926 | lr 0.00049075 | gnorm 2.478 | train_wall 800 | gb_free 13.9 | wall 817 | |
| Start iterating over samples | |
| begin validation on "valid" subset | |
| epoch 002 | valid on 'valid' subset | loss 0.887 | ppl 1.85 | wps 44076.7 | wpb 2858.9 | bsz 108.4 | num_updates 7852 | best_loss 0.887 | |
| epoch 002 | valid on 'valid' subset | loss 0.887 | ppl 1.85 | wps 44076.7 | wpb 2858.9 | bsz 108.4 | num_updates 7852 | best_loss 0.887 | |
| end of epoch 2 (average epoch stats below) | |
| epoch 002 | loss 1.238 | ppl 2.36 | wps 14211.8 | ups 4.8 | wpb 2961.7 | bsz 110.3 | num_updates 7852 | lr 0.00035687 | gnorm 1.187 | train_wall 802 | gb_free 13.4 | wall 1635 | |
| epoch 002 | loss 1.238 | ppl 2.36 | wps 14211.8 | ups 4.8 | wpb 2961.7 | bsz 110.3 | num_updates 7852 | lr 0.00035687 | gnorm 1.187 | train_wall 802 | gb_free 13.4 | wall 1635 | |
| Start iterating over samples | |
| begin validation on "valid" subset | |
| epoch 003 | valid on 'valid' subset | loss 0.664 | ppl 1.58 | wps 43946.5 | wpb 2858.9 | bsz 108.4 | num_updates 11778 | best_loss 0.664 | |
| epoch 003 | valid on 'valid' subset | loss 0.664 | ppl 1.58 | wps 43946.5 | wpb 2858.9 | bsz 108.4 | num_updates 11778 | best_loss 0.664 | |
| epoch 003 | valid on 'valid' subset | loss 0.664 | ppl 1.58 | wps 43946.5 | wpb 2858.9 | bsz 108.4 | num_updates 11778 | best_loss 0.664 | |
| end of epoch 3 (average epoch stats below) | |
| epoch 003 | loss 0.78 | ppl 1.72 | wps 14233.1 | ups 4.81 | wpb 2961.7 | bsz 110.3 | num_updates 11778 | lr 0.000291383 | gnorm 0.943 | train_wall 801 | gb_free 13 | wall 2452 | |
| epoch 003 | loss 0.78 | ppl 1.72 | wps 14233.1 | ups 4.81 | wpb 2961.7 | bsz 110.3 | num_updates 11778 | lr 0.000291383 | gnorm 0.943 | train_wall 801 | gb_free 13 | wall 2452 | |
| epoch 003 | loss 0.78 | ppl 1.72 | wps 14233.1 | ups 4.81 | wpb 2961.7 | bsz 110.3 | num_updates 11778 | lr 0.000291383 | gnorm 0.943 | train_wall 801 | gb_free 13 | wall 2452 | |
| Start iterating over samples | |
| begin validation on "valid" subset | |
| epoch 004 | valid on 'valid' subset | loss 0.554 | ppl 1.47 | wps 44110 | wpb 2858.9 | bsz 108.4 | num_updates 15704 | best_loss 0.554 | |
| epoch 004 | valid on 'valid' subset | loss 0.554 | ppl 1.47 | wps 44110 | wpb 2858.9 | bsz 108.4 | num_updates 15704 | best_loss 0.554 | |
| epoch 004 | valid on 'valid' subset | loss 0.554 | ppl 1.47 | wps 44110 | wpb 2858.9 | bsz 108.4 | num_updates 15704 | best_loss 0.554 | |
| epoch 004 | valid on 'valid' subset | loss 0.554 | ppl 1.47 | wps 44110 | wpb 2858.9 | bsz 108.4 | num_updates 15704 | best_loss 0.554 | |
| end of epoch 4 (average epoch stats below) | |
| epoch 004 | loss 0.571 | ppl 1.49 | wps 14206.7 | ups 4.8 | wpb 2961.7 | bsz 110.3 | num_updates 15704 | lr 0.000252345 | gnorm 0.79 | train_wall 802 | gb_free 13.3 | wall 3270 | |
| epoch 004 | loss 0.571 | ppl 1.49 | wps 14206.7 | ups 4.8 | wpb 2961.7 | bsz 110.3 | num_updates 15704 | lr 0.000252345 | gnorm 0.79 | train_wall 802 | gb_free 13.3 | wall 3270 | |
| epoch 004 | loss 0.571 | ppl 1.49 | wps 14206.7 | ups 4.8 | wpb 2961.7 | bsz 110.3 | num_updates 15704 | lr 0.000252345 | gnorm 0.79 | train_wall 802 | gb_free 13.3 | wall 3270 | |
| epoch 004 | loss 0.571 | ppl 1.49 | wps 14206.7 | ups 4.8 | wpb 2961.7 | bsz 110.3 | num_updates 15704 | lr 0.000252345 | gnorm 0.79 | train_wall 802 | gb_free 13.3 | wall 3270 | |
| Start iterating over samples | |
| begin validation on "valid" subset | |
| epoch 005 | valid on 'valid' subset | loss 0.496 | ppl 1.41 | wps 43747.4 | wpb 2858.9 | bsz 108.4 | num_updates 19630 | best_loss 0.496 | |
| epoch 005 | valid on 'valid' subset | loss 0.496 | ppl 1.41 | wps 43747.4 | wpb 2858.9 | bsz 108.4 | num_updates 19630 | best_loss 0.496 | |
| epoch 005 | valid on 'valid' subset | loss 0.496 | ppl 1.41 | wps 43747.4 | wpb 2858.9 | bsz 108.4 | num_updates 19630 | best_loss 0.496 | |
| epoch 005 | valid on 'valid' subset | loss 0.496 | ppl 1.41 | wps 43747.4 | wpb 2858.9 | bsz 108.4 | num_updates 19630 | best_loss 0.496 | |
| epoch 005 | valid on 'valid' subset | loss 0.496 | ppl 1.41 | wps 43747.4 | wpb 2858.9 | bsz 108.4 | num_updates 19630 | best_loss 0.496 | |
| end of epoch 5 (average epoch stats below) | |
| epoch 005 | loss 0.454 | ppl 1.37 | wps 14205.6 | ups 4.8 | wpb 2961.7 | bsz 110.3 | num_updates 19630 | lr 0.000225704 | gnorm 0.705 | train_wall 802 | gb_free 13.8 | wall 4089 | |
| epoch 005 | loss 0.454 | ppl 1.37 | wps 14205.6 | ups 4.8 | wpb 2961.7 | bsz 110.3 | num_updates 19630 | lr 0.000225704 | gnorm 0.705 | train_wall 802 | gb_free 13.8 | wall 4089 | |
| epoch 005 | loss 0.454 | ppl 1.37 | wps 14205.6 | ups 4.8 | wpb 2961.7 | bsz 110.3 | num_updates 19630 | lr 0.000225704 | gnorm 0.705 | train_wall 802 | gb_free 13.8 | wall 4089 | |
| epoch 005 | loss 0.454 | ppl 1.37 | wps 14205.6 | ups 4.8 | wpb 2961.7 | bsz 110.3 | num_updates 19630 | lr 0.000225704 | gnorm 0.705 | train_wall 802 | gb_free 13.8 | wall 4089 | |
| epoch 005 | loss 0.454 | ppl 1.37 | wps 14205.6 | ups 4.8 | wpb 2961.7 | bsz 110.3 | num_updates 19630 | lr 0.000225704 | gnorm 0.705 | train_wall 802 | gb_free 13.8 | wall 4089 | |
| Start iterating over samples | |
| begin validation on "valid" subset | |
| epoch 006 | valid on 'valid' subset | loss 0.49 | ppl 1.4 | wps 43929.7 | wpb 2858.9 | bsz 108.4 | num_updates 23556 | best_loss 0.49 | |
| epoch 006 | valid on 'valid' subset | loss 0.49 | ppl 1.4 | wps 43929.7 | wpb 2858.9 | bsz 108.4 | num_updates 23556 | best_loss 0.49 | |
| epoch 006 | valid on 'valid' subset | loss 0.49 | ppl 1.4 | wps 43929.7 | wpb 2858.9 | bsz 108.4 | num_updates 23556 | best_loss 0.49 | |
| epoch 006 | valid on 'valid' subset | loss 0.49 | ppl 1.4 | wps 43929.7 | wpb 2858.9 | bsz 108.4 | num_updates 23556 | best_loss 0.49 | |
| epoch 006 | valid on 'valid' subset | loss 0.49 | ppl 1.4 | wps 43929.7 | wpb 2858.9 | bsz 108.4 | num_updates 23556 | best_loss 0.49 | |
| epoch 006 | valid on 'valid' subset | loss 0.49 | ppl 1.4 | wps 43929.7 | wpb 2858.9 | bsz 108.4 | num_updates 23556 | best_loss 0.49 | |
| end of epoch 6 (average epoch stats below) | |
| epoch 006 | loss 0.385 | ppl 1.31 | wps 14223.3 | ups 4.8 | wpb 2961.7 | bsz 110.3 | num_updates 23556 | lr 0.000206039 | gnorm 0.657 | train_wall 801 | gb_free 13.7 | wall 4906 | |
| epoch 006 | loss 0.385 | ppl 1.31 | wps 14223.3 | ups 4.8 | wpb 2961.7 | bsz 110.3 | num_updates 23556 | lr 0.000206039 | gnorm 0.657 | train_wall 801 | gb_free 13.7 | wall 4906 | |
| epoch 006 | loss 0.385 | ppl 1.31 | wps 14223.3 | ups 4.8 | wpb 2961.7 | bsz 110.3 | num_updates 23556 | lr 0.000206039 | gnorm 0.657 | train_wall 801 | gb_free 13.7 | wall 4906 | |
| epoch 006 | loss 0.385 | ppl 1.31 | wps 14223.3 | ups 4.8 | wpb 2961.7 | bsz 110.3 | num_updates 23556 | lr 0.000206039 | gnorm 0.657 | train_wall 801 | gb_free 13.7 | wall 4906 | |
| epoch 006 | loss 0.385 | ppl 1.31 | wps 14223.3 | ups 4.8 | wpb 2961.7 | bsz 110.3 | num_updates 23556 | lr 0.000206039 | gnorm 0.657 | train_wall 801 | gb_free 13.7 | wall 4906 | |
| epoch 006 | loss 0.385 | ppl 1.31 | wps 14223.3 | ups 4.8 | wpb 2961.7 | bsz 110.3 | num_updates 23556 | lr 0.000206039 | gnorm 0.657 | train_wall 801 | gb_free 13.7 | wall 4906 | |
| Start iterating over samples | |
| begin validation on "valid" subset | |
| epoch 007 | valid on 'valid' subset | loss 0.485 | ppl 1.4 | wps 43868.1 | wpb 2858.9 | bsz 108.4 | num_updates 27482 | best_loss 0.485 | |
| epoch 007 | valid on 'valid' subset | loss 0.485 | ppl 1.4 | wps 43868.1 | wpb 2858.9 | bsz 108.4 | num_updates 27482 | best_loss 0.485 | |
| epoch 007 | valid on 'valid' subset | loss 0.485 | ppl 1.4 | wps 43868.1 | wpb 2858.9 | bsz 108.4 | num_updates 27482 | best_loss 0.485 | |
| epoch 007 | valid on 'valid' subset | loss 0.485 | ppl 1.4 | wps 43868.1 | wpb 2858.9 | bsz 108.4 | num_updates 27482 | best_loss 0.485 | |
| epoch 007 | valid on 'valid' subset | loss 0.485 | ppl 1.4 | wps 43868.1 | wpb 2858.9 | bsz 108.4 | num_updates 27482 | best_loss 0.485 | |
| epoch 007 | valid on 'valid' subset | loss 0.485 | ppl 1.4 | wps 43868.1 | wpb 2858.9 | bsz 108.4 | num_updates 27482 | best_loss 0.485 | |
| epoch 007 | valid on 'valid' subset | loss 0.485 | ppl 1.4 | wps 43868.1 | wpb 2858.9 | bsz 108.4 | num_updates 27482 | best_loss 0.485 | |
| end of epoch 7 (average epoch stats below) | |
| epoch 007 | loss 0.334 | ppl 1.26 | wps 14209.5 | ups 4.8 | wpb 2961.7 | bsz 110.3 | num_updates 27482 | lr 0.000190755 | gnorm 0.637 | train_wall 802 | gb_free 13.6 | wall 5725 | |
| epoch 007 | loss 0.334 | ppl 1.26 | wps 14209.5 | ups 4.8 | wpb 2961.7 | bsz 110.3 | num_updates 27482 | lr 0.000190755 | gnorm 0.637 | train_wall 802 | gb_free 13.6 | wall 5725 | |
| epoch 007 | loss 0.334 | ppl 1.26 | wps 14209.5 | ups 4.8 | wpb 2961.7 | bsz 110.3 | num_updates 27482 | lr 0.000190755 | gnorm 0.637 | train_wall 802 | gb_free 13.6 | wall 5725 | |
| epoch 007 | loss 0.334 | ppl 1.26 | wps 14209.5 | ups 4.8 | wpb 2961.7 | bsz 110.3 | num_updates 27482 | lr 0.000190755 | gnorm 0.637 | train_wall 802 | gb_free 13.6 | wall 5725 | |
| epoch 007 | loss 0.334 | ppl 1.26 | wps 14209.5 | ups 4.8 | wpb 2961.7 | bsz 110.3 | num_updates 27482 | lr 0.000190755 | gnorm 0.637 | train_wall 802 | gb_free 13.6 | wall 5725 | |
| epoch 007 | loss 0.334 | ppl 1.26 | wps 14209.5 | ups 4.8 | wpb 2961.7 | bsz 110.3 | num_updates 27482 | lr 0.000190755 | gnorm 0.637 | train_wall 802 | gb_free 13.6 | wall 5725 | |
| epoch 007 | loss 0.334 | ppl 1.26 | wps 14209.5 | ups 4.8 | wpb 2961.7 | bsz 110.3 | num_updates 27482 | lr 0.000190755 | gnorm 0.637 | train_wall 802 | gb_free 13.6 | wall 5725 | |
| Start iterating over samples | |
| begin validation on "valid" subset | |
| epoch 008 | valid on 'valid' subset | loss 0.503 | ppl 1.42 | wps 44034.7 | wpb 2858.9 | bsz 108.4 | num_updates 31408 | best_loss 0.485 | |
| epoch 008 | valid on 'valid' subset | loss 0.503 | ppl 1.42 | wps 44034.7 | wpb 2858.9 | bsz 108.4 | num_updates 31408 | best_loss 0.485 | |
| epoch 008 | valid on 'valid' subset | loss 0.503 | ppl 1.42 | wps 44034.7 | wpb 2858.9 | bsz 108.4 | num_updates 31408 | best_loss 0.485 | |
| epoch 008 | valid on 'valid' subset | loss 0.503 | ppl 1.42 | wps 44034.7 | wpb 2858.9 | bsz 108.4 | num_updates 31408 | best_loss 0.485 | |
| epoch 008 | valid on 'valid' subset | loss 0.503 | ppl 1.42 | wps 44034.7 | wpb 2858.9 | bsz 108.4 | num_updates 31408 | best_loss 0.485 | |
| epoch 008 | valid on 'valid' subset | loss 0.503 | ppl 1.42 | wps 44034.7 | wpb 2858.9 | bsz 108.4 | num_updates 31408 | best_loss 0.485 | |
| epoch 008 | valid on 'valid' subset | loss 0.503 | ppl 1.42 | wps 44034.7 | wpb 2858.9 | bsz 108.4 | num_updates 31408 | best_loss 0.485 | |
| epoch 008 | valid on 'valid' subset | loss 0.503 | ppl 1.42 | wps 44034.7 | wpb 2858.9 | bsz 108.4 | num_updates 31408 | best_loss 0.485 | |
| end of epoch 8 (average epoch stats below) | |
| epoch 008 | loss 0.291 | ppl 1.22 | wps 14209.8 | ups 4.8 | wpb 2961.7 | bsz 110.3 | num_updates 31408 | lr 0.000178435 | gnorm 0.627 | train_wall 802 | gb_free 13.5 | wall 6543 | |
| epoch 008 | loss 0.291 | ppl 1.22 | wps 14209.8 | ups 4.8 | wpb 2961.7 | bsz 110.3 | num_updates 31408 | lr 0.000178435 | gnorm 0.627 | train_wall 802 | gb_free 13.5 | wall 6543 | |
| epoch 008 | loss 0.291 | ppl 1.22 | wps 14209.8 | ups 4.8 | wpb 2961.7 | bsz 110.3 | num_updates 31408 | lr 0.000178435 | gnorm 0.627 | train_wall 802 | gb_free 13.5 | wall 6543 | |
| epoch 008 | loss 0.291 | ppl 1.22 | wps 14209.8 | ups 4.8 | wpb 2961.7 | bsz 110.3 | num_updates 31408 | lr 0.000178435 | gnorm 0.627 | train_wall 802 | gb_free 13.5 | wall 6543 | |
| epoch 008 | loss 0.291 | ppl 1.22 | wps 14209.8 | ups 4.8 | wpb 2961.7 | bsz 110.3 | num_updates 31408 | lr 0.000178435 | gnorm 0.627 | train_wall 802 | gb_free 13.5 | wall 6543 | |
| epoch 008 | loss 0.291 | ppl 1.22 | wps 14209.8 | ups 4.8 | wpb 2961.7 | bsz 110.3 | num_updates 31408 | lr 0.000178435 | gnorm 0.627 | train_wall 802 | gb_free 13.5 | wall 6543 | |
| epoch 008 | loss 0.291 | ppl 1.22 | wps 14209.8 | ups 4.8 | wpb 2961.7 | bsz 110.3 | num_updates 31408 | lr 0.000178435 | gnorm 0.627 | train_wall 802 | gb_free 13.5 | wall 6543 | |
| epoch 008 | loss 0.291 | ppl 1.22 | wps 14209.8 | ups 4.8 | wpb 2961.7 | bsz 110.3 | num_updates 31408 | lr 0.000178435 | gnorm 0.627 | train_wall 802 | gb_free 13.5 | wall 6543 | |
| Start iterating over samples | |
| begin validation on "valid" subset | |
| epoch 009 | valid on 'valid' subset | loss 0.541 | ppl 1.46 | wps 43993.1 | wpb 2858.9 | bsz 108.4 | num_updates 35334 | best_loss 0.485 | |
| epoch 009 | valid on 'valid' subset | loss 0.541 | ppl 1.46 | wps 43993.1 | wpb 2858.9 | bsz 108.4 | num_updates 35334 | best_loss 0.485 | |
| epoch 009 | valid on 'valid' subset | loss 0.541 | ppl 1.46 | wps 43993.1 | wpb 2858.9 | bsz 108.4 | num_updates 35334 | best_loss 0.485 | |
| epoch 009 | valid on 'valid' subset | loss 0.541 | ppl 1.46 | wps 43993.1 | wpb 2858.9 | bsz 108.4 | num_updates 35334 | best_loss 0.485 | |
| epoch 009 | valid on 'valid' subset | loss 0.541 | ppl 1.46 | wps 43993.1 | wpb 2858.9 | bsz 108.4 | num_updates 35334 | best_loss 0.485 | |
| epoch 009 | valid on 'valid' subset | loss 0.541 | ppl 1.46 | wps 43993.1 | wpb 2858.9 | bsz 108.4 | num_updates 35334 | best_loss 0.485 | |
| epoch 009 | valid on 'valid' subset | loss 0.541 | ppl 1.46 | wps 43993.1 | wpb 2858.9 | bsz 108.4 | num_updates 35334 | best_loss 0.485 | |
| epoch 009 | valid on 'valid' subset | loss 0.541 | ppl 1.46 | wps 43993.1 | wpb 2858.9 | bsz 108.4 | num_updates 35334 | best_loss 0.485 | |
| epoch 009 | valid on 'valid' subset | loss 0.541 | ppl 1.46 | wps 43993.1 | wpb 2858.9 | bsz 108.4 | num_updates 35334 | best_loss 0.485 | |
| end of epoch 9 (average epoch stats below) | |
| epoch 009 | loss 0.254 | ppl 1.19 | wps 14221.9 | ups 4.8 | wpb 2961.7 | bsz 110.3 | num_updates 35334 | lr 0.00016823 | gnorm 0.626 | train_wall 802 | gb_free 13.7 | wall 7361 | |
| epoch 009 | loss 0.254 | ppl 1.19 | wps 14221.9 | ups 4.8 | wpb 2961.7 | bsz 110.3 | num_updates 35334 | lr 0.00016823 | gnorm 0.626 | train_wall 802 | gb_free 13.7 | wall 7361 | |
| epoch 009 | loss 0.254 | ppl 1.19 | wps 14221.9 | ups 4.8 | wpb 2961.7 | bsz 110.3 | num_updates 35334 | lr 0.00016823 | gnorm 0.626 | train_wall 802 | gb_free 13.7 | wall 7361 | |
| epoch 009 | loss 0.254 | ppl 1.19 | wps 14221.9 | ups 4.8 | wpb 2961.7 | bsz 110.3 | num_updates 35334 | lr 0.00016823 | gnorm 0.626 | train_wall 802 | gb_free 13.7 | wall 7361 | |
| epoch 009 | loss 0.254 | ppl 1.19 | wps 14221.9 | ups 4.8 | wpb 2961.7 | bsz 110.3 | num_updates 35334 | lr 0.00016823 | gnorm 0.626 | train_wall 802 | gb_free 13.7 | wall 7361 | |
| epoch 009 | loss 0.254 | ppl 1.19 | wps 14221.9 | ups 4.8 | wpb 2961.7 | bsz 110.3 | num_updates 35334 | lr 0.00016823 | gnorm 0.626 | train_wall 802 | gb_free 13.7 | wall 7361 | |
| epoch 009 | loss 0.254 | ppl 1.19 | wps 14221.9 | ups 4.8 | wpb 2961.7 | bsz 110.3 | num_updates 35334 | lr 0.00016823 | gnorm 0.626 | train_wall 802 | gb_free 13.7 | wall 7361 | |
| epoch 009 | loss 0.254 | ppl 1.19 | wps 14221.9 | ups 4.8 | wpb 2961.7 | bsz 110.3 | num_updates 35334 | lr 0.00016823 | gnorm 0.626 | train_wall 802 | gb_free 13.7 | wall 7361 | |
| epoch 009 | loss 0.254 | ppl 1.19 | wps 14221.9 | ups 4.8 | wpb 2961.7 | bsz 110.3 | num_updates 35334 | lr 0.00016823 | gnorm 0.626 | train_wall 802 | gb_free 13.7 | wall 7361 | |
| Start iterating over samples | |
| begin validation on "valid" subset | |
| epoch 010 | valid on 'valid' subset | loss 0.57 | ppl 1.48 | wps 43885.5 | wpb 2858.9 | bsz 108.4 | num_updates 39260 | best_loss 0.485 | |
| epoch 010 | valid on 'valid' subset | loss 0.57 | ppl 1.48 | wps 43885.5 | wpb 2858.9 | bsz 108.4 | num_updates 39260 | best_loss 0.485 | |
| epoch 010 | valid on 'valid' subset | loss 0.57 | ppl 1.48 | wps 43885.5 | wpb 2858.9 | bsz 108.4 | num_updates 39260 | best_loss 0.485 | |
| epoch 010 | valid on 'valid' subset | loss 0.57 | ppl 1.48 | wps 43885.5 | wpb 2858.9 | bsz 108.4 | num_updates 39260 | best_loss 0.485 | |
| epoch 010 | valid on 'valid' subset | loss 0.57 | ppl 1.48 | wps 43885.5 | wpb 2858.9 | bsz 108.4 | num_updates 39260 | best_loss 0.485 | |
| epoch 010 | valid on 'valid' subset | loss 0.57 | ppl 1.48 | wps 43885.5 | wpb 2858.9 | bsz 108.4 | num_updates 39260 | best_loss 0.485 | |
| epoch 010 | valid on 'valid' subset | loss 0.57 | ppl 1.48 | wps 43885.5 | wpb 2858.9 | bsz 108.4 | num_updates 39260 | best_loss 0.485 | |
| epoch 010 | valid on 'valid' subset | loss 0.57 | ppl 1.48 | wps 43885.5 | wpb 2858.9 | bsz 108.4 | num_updates 39260 | best_loss 0.485 | |
| epoch 010 | valid on 'valid' subset | loss 0.57 | ppl 1.48 | wps 43885.5 | wpb 2858.9 | bsz 108.4 | num_updates 39260 | best_loss 0.485 | |
| epoch 010 | valid on 'valid' subset | loss 0.57 | ppl 1.48 | wps 43885.5 | wpb 2858.9 | bsz 108.4 | num_updates 39260 | best_loss 0.485 | |
| end of epoch 10 (average epoch stats below) | |
| epoch 010 | loss 0.22 | ppl 1.16 | wps 14234.6 | ups 4.81 | wpb 2961.7 | bsz 110.3 | num_updates 39260 | lr 0.000159597 | gnorm 0.62 | train_wall 801 | gb_free 13.7 | wall 8177 | |
| epoch 010 | loss 0.22 | ppl 1.16 | wps 14234.6 | ups 4.81 | wpb 2961.7 | bsz 110.3 | num_updates 39260 | lr 0.000159597 | gnorm 0.62 | train_wall 801 | gb_free 13.7 | wall 8177 | |
| epoch 010 | loss 0.22 | ppl 1.16 | wps 14234.6 | ups 4.81 | wpb 2961.7 | bsz 110.3 | num_updates 39260 | lr 0.000159597 | gnorm 0.62 | train_wall 801 | gb_free 13.7 | wall 8177 | |
| epoch 010 | loss 0.22 | ppl 1.16 | wps 14234.6 | ups 4.81 | wpb 2961.7 | bsz 110.3 | num_updates 39260 | lr 0.000159597 | gnorm 0.62 | train_wall 801 | gb_free 13.7 | wall 8177 | |
| epoch 010 | loss 0.22 | ppl 1.16 | wps 14234.6 | ups 4.81 | wpb 2961.7 | bsz 110.3 | num_updates 39260 | lr 0.000159597 | gnorm 0.62 | train_wall 801 | gb_free 13.7 | wall 8177 | |
| epoch 010 | loss 0.22 | ppl 1.16 | wps 14234.6 | ups 4.81 | wpb 2961.7 | bsz 110.3 | num_updates 39260 | lr 0.000159597 | gnorm 0.62 | train_wall 801 | gb_free 13.7 | wall 8177 | |
| epoch 010 | loss 0.22 | ppl 1.16 | wps 14234.6 | ups 4.81 | wpb 2961.7 | bsz 110.3 | num_updates 39260 | lr 0.000159597 | gnorm 0.62 | train_wall 801 | gb_free 13.7 | wall 8177 | |
| epoch 010 | loss 0.22 | ppl 1.16 | wps 14234.6 | ups 4.81 | wpb 2961.7 | bsz 110.3 | num_updates 39260 | lr 0.000159597 | gnorm 0.62 | train_wall 801 | gb_free 13.7 | wall 8177 | |
| epoch 010 | loss 0.22 | ppl 1.16 | wps 14234.6 | ups 4.81 | wpb 2961.7 | bsz 110.3 | num_updates 39260 | lr 0.000159597 | gnorm 0.62 | train_wall 801 | gb_free 13.7 | wall 8177 | |
| epoch 010 | loss 0.22 | ppl 1.16 | wps 14234.6 | ups 4.81 | wpb 2961.7 | bsz 110.3 | num_updates 39260 | lr 0.000159597 | gnorm 0.62 | train_wall 801 | gb_free 13.7 | wall 8177 | |
| Start iterating over samples | |
| begin validation on "valid" subset | |
| epoch 011 | valid on 'valid' subset | loss 0.598 | ppl 1.51 | wps 44069.5 | wpb 2858.9 | bsz 108.4 | num_updates 43186 | best_loss 0.485 | |
| epoch 011 | valid on 'valid' subset | loss 0.598 | ppl 1.51 | wps 44069.5 | wpb 2858.9 | bsz 108.4 | num_updates 43186 | best_loss 0.485 | |
| epoch 011 | valid on 'valid' subset | loss 0.598 | ppl 1.51 | wps 44069.5 | wpb 2858.9 | bsz 108.4 | num_updates 43186 | best_loss 0.485 | |
| epoch 011 | valid on 'valid' subset | loss 0.598 | ppl 1.51 | wps 44069.5 | wpb 2858.9 | bsz 108.4 | num_updates 43186 | best_loss 0.485 | |
| epoch 011 | valid on 'valid' subset | loss 0.598 | ppl 1.51 | wps 44069.5 | wpb 2858.9 | bsz 108.4 | num_updates 43186 | best_loss 0.485 | |
| epoch 011 | valid on 'valid' subset | loss 0.598 | ppl 1.51 | wps 44069.5 | wpb 2858.9 | bsz 108.4 | num_updates 43186 | best_loss 0.485 | |
| epoch 011 | valid on 'valid' subset | loss 0.598 | ppl 1.51 | wps 44069.5 | wpb 2858.9 | bsz 108.4 | num_updates 43186 | best_loss 0.485 | |
| epoch 011 | valid on 'valid' subset | loss 0.598 | ppl 1.51 | wps 44069.5 | wpb 2858.9 | bsz 108.4 | num_updates 43186 | best_loss 0.485 | |
| epoch 011 | valid on 'valid' subset | loss 0.598 | ppl 1.51 | wps 44069.5 | wpb 2858.9 | bsz 108.4 | num_updates 43186 | best_loss 0.485 | |
| epoch 011 | valid on 'valid' subset | loss 0.598 | ppl 1.51 | wps 44069.5 | wpb 2858.9 | bsz 108.4 | num_updates 43186 | best_loss 0.485 | |
| epoch 011 | valid on 'valid' subset | loss 0.598 | ppl 1.51 | wps 44069.5 | wpb 2858.9 | bsz 108.4 | num_updates 43186 | best_loss 0.485 | |
| early stop since valid performance hasn't improved for last 4 runs | |
| end of epoch 11 (average epoch stats below) | |
| epoch 011 | loss 0.19 | ppl 1.14 | wps 14240.1 | ups 4.81 | wpb 2961.7 | bsz 110.3 | num_updates 43186 | lr 0.00015217 | gnorm 0.623 | train_wall 801 | gb_free 13.7 | wall 8994 | |
| epoch 011 | loss 0.19 | ppl 1.14 | wps 14240.1 | ups 4.81 | wpb 2961.7 | bsz 110.3 | num_updates 43186 | lr 0.00015217 | gnorm 0.623 | train_wall 801 | gb_free 13.7 | wall 8994 | |
| epoch 011 | loss 0.19 | ppl 1.14 | wps 14240.1 | ups 4.81 | wpb 2961.7 | bsz 110.3 | num_updates 43186 | lr 0.00015217 | gnorm 0.623 | train_wall 801 | gb_free 13.7 | wall 8994 | |
| epoch 011 | loss 0.19 | ppl 1.14 | wps 14240.1 | ups 4.81 | wpb 2961.7 | bsz 110.3 | num_updates 43186 | lr 0.00015217 | gnorm 0.623 | train_wall 801 | gb_free 13.7 | wall 8994 | |
| epoch 011 | loss 0.19 | ppl 1.14 | wps 14240.1 | ups 4.81 | wpb 2961.7 | bsz 110.3 | num_updates 43186 | lr 0.00015217 | gnorm 0.623 | train_wall 801 | gb_free 13.7 | wall 8994 | |
| epoch 011 | loss 0.19 | ppl 1.14 | wps 14240.1 | ups 4.81 | wpb 2961.7 | bsz 110.3 | num_updates 43186 | lr 0.00015217 | gnorm 0.623 | train_wall 801 | gb_free 13.7 | wall 8994 | |
| epoch 011 | loss 0.19 | ppl 1.14 | wps 14240.1 | ups 4.81 | wpb 2961.7 | bsz 110.3 | num_updates 43186 | lr 0.00015217 | gnorm 0.623 | train_wall 801 | gb_free 13.7 | wall 8994 | |
| epoch 011 | loss 0.19 | ppl 1.14 | wps 14240.1 | ups 4.81 | wpb 2961.7 | bsz 110.3 | num_updates 43186 | lr 0.00015217 | gnorm 0.623 | train_wall 801 | gb_free 13.7 | wall 8994 | |
| epoch 011 | loss 0.19 | ppl 1.14 | wps 14240.1 | ups 4.81 | wpb 2961.7 | bsz 110.3 | num_updates 43186 | lr 0.00015217 | gnorm 0.623 | train_wall 801 | gb_free 13.7 | wall 8994 | |
| epoch 011 | loss 0.19 | ppl 1.14 | wps 14240.1 | ups 4.81 | wpb 2961.7 | bsz 110.3 | num_updates 43186 | lr 0.00015217 | gnorm 0.623 | train_wall 801 | gb_free 13.7 | wall 8994 | |
| epoch 011 | loss 0.19 | ppl 1.14 | wps 14240.1 | ups 4.81 | wpb 2961.7 | bsz 110.3 | num_updates 43186 | lr 0.00015217 | gnorm 0.623 | train_wall 801 | gb_free 13.7 | wall 8994 | |
| done training in 8993.5 seconds | |