| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0476190476190474, | |
| "eval_steps": 50, | |
| "global_step": 16, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.19047619047619047, | |
| "grad_norm": 1.869409203529358, | |
| "learning_rate": 5.000000000000001e-07, | |
| "loss": 5.0509, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.19047619047619047, | |
| "eval_loss": 4.9529218673706055, | |
| "eval_runtime": 0.6553, | |
| "eval_samples_per_second": 13.734, | |
| "eval_steps_per_second": 3.052, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.38095238095238093, | |
| "grad_norm": 1.981248378753662, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 4.6691, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 2.0131425857543945, | |
| "learning_rate": 1.5e-06, | |
| "loss": 4.9716, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.7619047619047619, | |
| "grad_norm": 2.0012943744659424, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 5.3829, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.9523809523809523, | |
| "grad_norm": 1.8608438968658447, | |
| "learning_rate": 2.5e-06, | |
| "loss": 5.1384, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.1428571428571428, | |
| "grad_norm": 3.8675358295440674, | |
| "learning_rate": 3e-06, | |
| "loss": 9.6879, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 1.9214471578598022, | |
| "learning_rate": 3.5e-06, | |
| "loss": 5.1229, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 1.5238095238095237, | |
| "grad_norm": 2.0400009155273438, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 4.7002, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 1.7142857142857144, | |
| "grad_norm": 1.9419265985488892, | |
| "learning_rate": 4.5e-06, | |
| "loss": 5.2229, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 1.9047619047619047, | |
| "grad_norm": 1.9313769340515137, | |
| "learning_rate": 5e-06, | |
| "loss": 5.2099, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.0952380952380953, | |
| "grad_norm": 3.5392918586730957, | |
| "learning_rate": 4.665063509461098e-06, | |
| "loss": 8.8352, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 2.2857142857142856, | |
| "grad_norm": 1.8467406034469604, | |
| "learning_rate": 3.7500000000000005e-06, | |
| "loss": 4.8335, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 2.4761904761904763, | |
| "grad_norm": 2.1296801567077637, | |
| "learning_rate": 2.5e-06, | |
| "loss": 5.1836, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": 1.7837193012237549, | |
| "learning_rate": 1.2500000000000007e-06, | |
| "loss": 4.7968, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 2.857142857142857, | |
| "grad_norm": 2.0977296829223633, | |
| "learning_rate": 3.3493649053890325e-07, | |
| "loss": 5.1121, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 3.0476190476190474, | |
| "grad_norm": 3.3787589073181152, | |
| "learning_rate": 0.0, | |
| "loss": 8.0154, | |
| "step": 16 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 16, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4309761310851072.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |