| { | |
| "best_metric": 0.40057066082954407, | |
| "best_model_checkpoint": "distilbert_lda_50_v1_sst2/checkpoint-264", | |
| "epoch": 6.0, | |
| "eval_steps": 500, | |
| "global_step": 1584, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 8.42946720123291, | |
| "learning_rate": 4.9e-05, | |
| "loss": 0.3785, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8291284403669725, | |
| "eval_loss": 0.40057066082954407, | |
| "eval_runtime": 0.3872, | |
| "eval_samples_per_second": 2251.83, | |
| "eval_steps_per_second": 10.329, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 6.42087984085083, | |
| "learning_rate": 4.8e-05, | |
| "loss": 0.2139, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8405963302752294, | |
| "eval_loss": 0.42612364888191223, | |
| "eval_runtime": 0.4877, | |
| "eval_samples_per_second": 1787.91, | |
| "eval_steps_per_second": 8.201, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 5.889172554016113, | |
| "learning_rate": 4.7e-05, | |
| "loss": 0.1523, | |
| "step": 792 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8153669724770642, | |
| "eval_loss": 0.4885922968387604, | |
| "eval_runtime": 0.3795, | |
| "eval_samples_per_second": 2297.458, | |
| "eval_steps_per_second": 10.539, | |
| "step": 792 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 5.110029220581055, | |
| "learning_rate": 4.600000000000001e-05, | |
| "loss": 0.1085, | |
| "step": 1056 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8268348623853211, | |
| "eval_loss": 0.5391777753829956, | |
| "eval_runtime": 0.3802, | |
| "eval_samples_per_second": 2293.654, | |
| "eval_steps_per_second": 10.521, | |
| "step": 1056 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 0.9452471137046814, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.0809, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.8302752293577982, | |
| "eval_loss": 0.5835925340652466, | |
| "eval_runtime": 0.3806, | |
| "eval_samples_per_second": 2291.343, | |
| "eval_steps_per_second": 10.511, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 5.266055107116699, | |
| "learning_rate": 4.4000000000000006e-05, | |
| "loss": 0.0646, | |
| "step": 1584 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.8176605504587156, | |
| "eval_loss": 0.5851426124572754, | |
| "eval_runtime": 0.3834, | |
| "eval_samples_per_second": 2274.1, | |
| "eval_steps_per_second": 10.432, | |
| "step": 1584 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "step": 1584, | |
| "total_flos": 2.676464049624883e+16, | |
| "train_loss": 0.16643811115110763, | |
| "train_runtime": 389.8795, | |
| "train_samples_per_second": 8637.157, | |
| "train_steps_per_second": 33.857 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 13200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 50, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 5 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.676464049624883e+16, | |
| "train_batch_size": 256, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |