best_model_bert_uncasedbert-base-uncased-finetuned-sst2
/
run-0
/checkpoint-1263
/trainer_state.json
{ | |
"best_metric": 0.8256880733944955, | |
"best_model_checkpoint": "Tech-oriented/best_model_bert_uncasedbert-base-uncased-finetuned-sst2/run-0/checkpoint-1263", | |
"epoch": 3.0, | |
"eval_steps": 500, | |
"global_step": 1263, | |
"is_hyper_param_search": true, | |
"is_local_process_zero": true, | |
"is_world_process_zero": true, | |
"log_history": [ | |
{ | |
"epoch": 1.0, | |
"eval_accuracy": 0.5871559633027523, | |
"eval_loss": 0.6697461009025574, | |
"eval_runtime": 2.3652, | |
"eval_samples_per_second": 368.681, | |
"eval_steps_per_second": 23.254, | |
"step": 421 | |
}, | |
{ | |
"epoch": 2.0, | |
"eval_accuracy": 0.7717889908256881, | |
"eval_loss": 0.6226800084114075, | |
"eval_runtime": 2.335, | |
"eval_samples_per_second": 373.447, | |
"eval_steps_per_second": 23.555, | |
"step": 842 | |
}, | |
{ | |
"epoch": 3.0, | |
"eval_accuracy": 0.8256880733944955, | |
"eval_loss": 0.5877246856689453, | |
"eval_runtime": 2.3382, | |
"eval_samples_per_second": 372.942, | |
"eval_steps_per_second": 23.523, | |
"step": 1263 | |
} | |
], | |
"logging_steps": 4209, | |
"max_steps": 1263, | |
"num_input_tokens_seen": 0, | |
"num_train_epochs": 3, | |
"save_steps": 500, | |
"total_flos": 0, | |
"train_batch_size": 16, | |
"trial_name": null, | |
"trial_params": { | |
"learning_rate": 1.3048303331369337e-06, | |
"num_train_epochs": 3, | |
"per_device_train_batch_size": 16, | |
"seed": 6, | |
"weight_decay": 0.3377283287391723 | |
} | |
} | |