checkpoint-12/trainer_state.json

{
 "best_metric": 1.1234140396118164,
 "best_model_checkpoint": "autotrain-Tweet-Classifier/checkpoint-12",
 "epoch": 2.0,
 "eval_steps": 500,
 "global_step": 12,
 "is_hyper_param_search": false,
 "is_local_process_zero": true,
 "is_world_process_zero": true,
 "log_history": [
 {
 "epoch": 0.17,
 "grad_norm": 12.977298736572266,
 "learning_rate": 2.5e-05,
 "loss": 1.0989,
 "step": 1
 },
 {
 "epoch": 0.33,
 "grad_norm": 5.110796928405762,
 "learning_rate": 5e-05,
 "loss": 1.0898,
 "step": 2
 },
 {
 "epoch": 0.5,
 "grad_norm": 6.790207862854004,
 "learning_rate": 4.6875e-05,
 "loss": 0.9728,
 "step": 3
 },
 {
 "epoch": 0.67,
 "grad_norm": 9.658609390258789,
 "learning_rate": 4.375e-05,
 "loss": 1.3658,
 "step": 4
 },
 {
 "epoch": 0.83,
 "grad_norm": 9.872339248657227,
 "learning_rate": 4.0625000000000005e-05,
 "loss": 1.3639,
 "step": 5
 },
 {
 "epoch": 1.0,
 "grad_norm": 17.13404655456543,
 "learning_rate": 3.7500000000000003e-05,
 "loss": 1.5233,
 "step": 6
 },
 {
 "epoch": 1.0,
 "eval_accuracy": 0.36363636363636365,
 "eval_f1_macro": 0.17777777777777778,
 "eval_f1_micro": 0.36363636363636365,
 "eval_f1_weighted": 0.19393939393939394,
 "eval_loss": 1.1655577421188354,
 "eval_precision_macro": 0.12121212121212122,
 "eval_precision_micro": 0.36363636363636365,
 "eval_precision_weighted": 0.1322314049586777,
 "eval_recall_macro": 0.3333333333333333,
 "eval_recall_micro": 0.36363636363636365,
 "eval_recall_weighted": 0.36363636363636365,
 "eval_runtime": 2.0574,
 "eval_samples_per_second": 5.346,
 "eval_steps_per_second": 0.486,
 "step": 6
 },
 {
 "epoch": 1.17,
 "grad_norm": 15.478323936462402,
 "learning_rate": 3.4375e-05,
 "loss": 1.2839,
 "step": 7
 },
 {
 "epoch": 1.33,
 "grad_norm": 8.981595039367676,
 "learning_rate": 3.125e-05,
 "loss": 1.1181,
 "step": 8
 },
 {
 "epoch": 1.5,
 "grad_norm": 8.584152221679688,
 "learning_rate": 2.8125000000000003e-05,
 "loss": 1.166,
 "step": 9
 },
 {
 "epoch": 1.67,
 "grad_norm": 4.148137092590332,
 "learning_rate": 2.5e-05,
 "loss": 1.0376,
 "step": 10
 },
 {
 "epoch": 1.83,
 "grad_norm": 5.527700424194336,
 "learning_rate": 2.1875e-05,
 "loss": 0.9684,
 "step": 11
 },
 {
 "epoch": 2.0,
 "grad_norm": 17.105709075927734,
 "learning_rate": 1.8750000000000002e-05,
 "loss": 0.7871,
 "step": 12
 },
 {
 "epoch": 2.0,
 "eval_accuracy": 0.36363636363636365,
 "eval_f1_macro": 0.17777777777777778,
 "eval_f1_micro": 0.36363636363636365,
 "eval_f1_weighted": 0.19393939393939394,
 "eval_loss": 1.1234140396118164,
 "eval_precision_macro": 0.12121212121212122,
 "eval_precision_micro": 0.36363636363636365,
 "eval_precision_weighted": 0.1322314049586777,
 "eval_recall_macro": 0.3333333333333333,
 "eval_recall_micro": 0.36363636363636365,
 "eval_recall_weighted": 0.36363636363636365,
 "eval_runtime": 2.0537,
 "eval_samples_per_second": 5.356,
 "eval_steps_per_second": 0.487,
 "step": 12
 }
 ],
 "logging_steps": 1,
 "max_steps": 18,
 "num_input_tokens_seen": 0,
 "num_train_epochs": 3,
 "save_steps": 500,
 "total_flos": 5788495190016.0,
 "train_batch_size": 8,
 "trial_name": null,
 "trial_params": null
}