| { | |
| "best_metric": 0.9119440459110474, | |
| "best_model_checkpoint": "output/fine_tuned/t5-base/MRPC/checkpoint-1035", | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 1150, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7107843137254902, | |
| "eval_combined_score": 0.767068803569332, | |
| "eval_f1": 0.8233532934131738, | |
| "eval_loss": 0.5475682020187378, | |
| "eval_runtime": 1.5083, | |
| "eval_samples_per_second": 270.506, | |
| "eval_steps_per_second": 33.813, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8700980392156863, | |
| "eval_combined_score": 0.8900575085721896, | |
| "eval_f1": 0.9100169779286927, | |
| "eval_loss": 0.35225751996040344, | |
| "eval_runtime": 1.5518, | |
| "eval_samples_per_second": 262.913, | |
| "eval_steps_per_second": 32.864, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8725490196078431, | |
| "eval_combined_score": 0.8923555908850027, | |
| "eval_f1": 0.9121621621621623, | |
| "eval_loss": 0.3623868525028229, | |
| "eval_runtime": 1.5259, | |
| "eval_samples_per_second": 267.39, | |
| "eval_steps_per_second": 33.424, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8774509803921569, | |
| "eval_combined_score": 0.8948658410732715, | |
| "eval_f1": 0.912280701754386, | |
| "eval_loss": 0.36461111903190613, | |
| "eval_runtime": 1.5073, | |
| "eval_samples_per_second": 270.69, | |
| "eval_steps_per_second": 33.836, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 4.3478260869565215, | |
| "grad_norm": 4.906887054443359, | |
| "learning_rate": 2.826086956521739e-05, | |
| "loss": 0.3744, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.8946078431372549, | |
| "eval_combined_score": 0.9099126172208014, | |
| "eval_f1": 0.9252173913043479, | |
| "eval_loss": 0.40538841485977173, | |
| "eval_runtime": 1.5339, | |
| "eval_samples_per_second": 265.981, | |
| "eval_steps_per_second": 33.248, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.8897058823529411, | |
| "eval_combined_score": 0.9057225063938619, | |
| "eval_f1": 0.9217391304347826, | |
| "eval_loss": 0.46239176392555237, | |
| "eval_runtime": 1.5008, | |
| "eval_samples_per_second": 271.86, | |
| "eval_steps_per_second": 33.982, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.8872549019607843, | |
| "eval_combined_score": 0.9042438893365565, | |
| "eval_f1": 0.9212328767123288, | |
| "eval_loss": 0.552967369556427, | |
| "eval_runtime": 0.8648, | |
| "eval_samples_per_second": 471.8, | |
| "eval_steps_per_second": 58.975, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.8897058823529411, | |
| "eval_combined_score": 0.9058581404832297, | |
| "eval_f1": 0.9220103986135182, | |
| "eval_loss": 0.5404660701751709, | |
| "eval_runtime": 0.8838, | |
| "eval_samples_per_second": 461.635, | |
| "eval_steps_per_second": 57.704, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 8.695652173913043, | |
| "grad_norm": 13.78760051727295, | |
| "learning_rate": 6.521739130434783e-06, | |
| "loss": 0.0877, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.8970588235294118, | |
| "eval_combined_score": 0.9119440459110474, | |
| "eval_f1": 0.926829268292683, | |
| "eval_loss": 0.5629165768623352, | |
| "eval_runtime": 0.8913, | |
| "eval_samples_per_second": 457.747, | |
| "eval_steps_per_second": 57.218, | |
| "step": 1035 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.8921568627450981, | |
| "eval_combined_score": 0.9081473968897904, | |
| "eval_f1": 0.9241379310344827, | |
| "eval_loss": 0.5856015086174011, | |
| "eval_runtime": 0.8578, | |
| "eval_samples_per_second": 475.635, | |
| "eval_steps_per_second": 59.454, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 1150, | |
| "total_flos": 5600824300646400.0, | |
| "train_loss": 0.03282318198162577, | |
| "train_runtime": 93.6204, | |
| "train_samples_per_second": 391.795, | |
| "train_steps_per_second": 12.284 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1150, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5600824300646400.0, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |