GuiltRoBERTa_hu / checkpoint-384 /trainer_state.json
ringorsolya's picture
Upload folder using huggingface_hub
654825b verified
{
"best_metric": 0.09880195558071136,
"best_model_checkpoint": "/content/drive/MyDrive/checkpoint-384",
"epoch": 3.0,
"eval_steps": 100,
"global_step": 384,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"grad_norm": 5.293990612030029,
"learning_rate": 4.5e-06,
"loss": 0.5772,
"step": 128
},
{
"epoch": 1.0,
"eval_accuracy": 0.90625,
"eval_f1": 0.9056919642857143,
"eval_loss": 0.2875204086303711,
"eval_precision": 0.9092216981132075,
"eval_recall": 0.90625,
"eval_runtime": 7.6037,
"eval_samples_per_second": 33.668,
"eval_steps_per_second": 2.104,
"step": 128
},
{
"epoch": 2.0,
"grad_norm": 1.1265126466751099,
"learning_rate": 4.000000000000001e-06,
"loss": 0.2107,
"step": 256
},
{
"epoch": 2.0,
"eval_accuracy": 0.95703125,
"eval_f1": 0.957080593238505,
"eval_loss": 0.1508919596672058,
"eval_precision": 0.9578610206919738,
"eval_recall": 0.95703125,
"eval_runtime": 7.4102,
"eval_samples_per_second": 34.547,
"eval_steps_per_second": 2.159,
"step": 256
},
{
"epoch": 3.0,
"grad_norm": 0.41782641410827637,
"learning_rate": 3.5e-06,
"loss": 0.1371,
"step": 384
},
{
"epoch": 3.0,
"eval_accuracy": 0.9765625,
"eval_f1": 0.9765625,
"eval_loss": 0.09880195558071136,
"eval_precision": 0.9765625,
"eval_recall": 0.9765625,
"eval_runtime": 7.4477,
"eval_samples_per_second": 34.373,
"eval_steps_per_second": 2.148,
"step": 384
}
],
"logging_steps": 100,
"max_steps": 1280,
"num_input_tokens_seen": 0,
"num_train_epochs": 10,
"save_steps": 100,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 2,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1614975657799680.0,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}