Megnis/rubert-tiny2-sentiment-analisys-RuSentimentUnion-9000

Evaluation results

{'eval_loss': 0.9916864037513733,
 'eval_accuracy': 0.8235294117647058,
 'eval_precision': 0.9411764705882353,
 'eval_recall': 0.8235294117647058,
 'eval_f1': 0.8571040080328006,
 'eval_runtime': 0.0836,
 'eval_samples_per_second': 406.832,
 'eval_steps_per_second': 35.897,
 'epoch': 10.0}

Training Parameters

{'output_dir': 'Megnis/rubert-tiny2-sentiment-analisys-RuSentimentUnion-9000',
 'overwrite_output_dir': False,
 'do_train': False,
 'do_eval': False,
 'do_predict': False,
 'eval_strategy': 'no',
 'prediction_loss_only': False,
 'per_device_train_batch_size': 16,
 'per_device_eval_batch_size': 16,
 'per_gpu_train_batch_size': None,
 'per_gpu_eval_batch_size': None,
 'gradient_accumulation_steps': 1,
 'eval_accumulation_steps': None,
 'eval_delay': 0,
 'torch_empty_cache_steps': None,
 'learning_rate': 0.0001,
 'weight_decay': 0.01,
 'adam_beta1': 0.9,
 'adam_beta2': 0.999,
 'adam_epsilon': 1e-08,
 'max_grad_norm': 1.0,
 'num_train_epochs': 10,
 'max_steps': -1,
 'lr_scheduler_type': 'linear',
 'lr_scheduler_kwargs': {},
 'warmup_ratio': 0.0,
 'warmup_steps': 0,
 'log_level': 'passive',
 'log_level_replica': 'warning',
 'log_on_each_node': True,
 'logging_dir': 'Megnis/rubert-tiny2-sentiment-analisys-RuSentimentUnion-9000/runs/Feb14_15-50-51_d29607a77ce5',
 'logging_strategy': 'steps',
 'logging_first_step': False,
 'logging_steps': 1000,
 'logging_nan_inf_filter': True,
 'save_strategy': 'epoch',
 'save_steps': 500,
 'save_total_limit': None,
 'save_safetensors': True,
 'save_on_each_node': False,
 'save_only_model': False,
 'restore_callback_states_from_checkpoint': False,
 'no_cuda': False,
 'use_cpu': False,
 'use_mps_device': False,
 'seed': 42,
 'data_seed': None,
 'jit_mode_eval': False,
 'use_ipex': False,
 'bf16': False,
 'fp16': False,
 'fp16_opt_level': 'O1',
 'half_precision_backend': 'auto',
 'bf16_full_eval': False,
 'fp16_full_eval': False,
 'tf32': None,
 'local_rank': 0,
 'ddp_backend': None,
 'tpu_num_cores': None,
 'tpu_metrics_debug': False,
 'debug': [],
 'dataloader_drop_last': False,
 'eval_steps': None,
 'dataloader_num_workers': 0,
 'dataloader_prefetch_factor': None,
 'past_index': -1,
 'run_name': 'Megnis/rubert-tiny2-sentiment-analisys-RuSentimentUnion-9000',
 'disable_tqdm': False,
 'remove_unused_columns': True,
 'label_names': None,
 'load_best_model_at_end': False,
 'metric_for_best_model': None,
 'greater_is_better': None,
 'ignore_data_skip': False,
 'fsdp': [],
 'fsdp_min_num_params': 0,
 'fsdp_config': {'min_num_params': 0,
  'xla': False,
  'xla_fsdp_v2': False,
  'xla_fsdp_grad_ckpt': False},
 'fsdp_transformer_layer_cls_to_wrap': None,
 'accelerator_config': {'split_batches': False,
  'dispatch_batches': None,
  'even_batches': True,
  'use_seedable_sampler': True,
  'non_blocking': False,
  'gradient_accumulation_kwargs': None},
 'deepspeed': None,
 'label_smoothing_factor': 0.0,
 'optim': 'adamw_torch',
 'optim_args': None,
 'adafactor': False,
 'group_by_length': False,
 'length_column_name': 'length',
 'report_to': [],
 'ddp_find_unused_parameters': None,
 'ddp_bucket_cap_mb': None,
 'ddp_broadcast_buffers': None,
 'dataloader_pin_memory': True,
 'dataloader_persistent_workers': False,
 'skip_memory_metrics': True,
 'use_legacy_prediction_loop': False,
 'push_to_hub': True,
 'resume_from_checkpoint': None,
 'hub_model_id': None,
 'hub_strategy': 'every_save',
 'hub_token': '<HUB_TOKEN>',
 'hub_private_repo': None,
 'hub_always_push': False,
 'gradient_checkpointing': False,
 'gradient_checkpointing_kwargs': None,
 'include_inputs_for_metrics': False,
 'include_for_metrics': [],
 'eval_do_concat_batches': True,
 'fp16_backend': 'auto',
 'evaluation_strategy': None,
 'push_to_hub_model_id': None,
 'push_to_hub_organization': None,
 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>',
 'mp_parameters': '',
 'auto_find_batch_size': False,
 'full_determinism': False,
 'torchdynamo': None,
 'ray_scope': 'last',
 'ddp_timeout': 1800,
 'torch_compile': False,
 'torch_compile_backend': None,
 'torch_compile_mode': None,
 'dispatch_batches': None,
 'split_batches': None,
 'include_tokens_per_second': False,
 'include_num_input_tokens_seen': False,
 'neftune_noise_alpha': None,
 'optim_target_modules': None,
 'batch_eval_metrics': False,
 'eval_on_start': False,
 'use_liger_kernel': False,
 'eval_use_gather_object': False,
 'average_tokens_across_devices': False}