| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 36, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08695652173913043, | |
| "grad_norm": 23.72541725578798, | |
| "learning_rate": 1.5e-07, | |
| "loss": 2.5595, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.17391304347826086, | |
| "grad_norm": 25.577125119073894, | |
| "learning_rate": 3e-07, | |
| "loss": 2.5723, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.2608695652173913, | |
| "grad_norm": 24.323731617199012, | |
| "learning_rate": 4.5000000000000003e-07, | |
| "loss": 2.5538, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.34782608695652173, | |
| "grad_norm": 22.635470184221006, | |
| "learning_rate": 6e-07, | |
| "loss": 2.5638, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.43478260869565216, | |
| "grad_norm": 18.81006443117675, | |
| "learning_rate": 7.5e-07, | |
| "loss": 2.5169, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.5217391304347826, | |
| "grad_norm": 10.31372875147129, | |
| "learning_rate": 9.000000000000001e-07, | |
| "loss": 2.4823, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.6086956521739131, | |
| "grad_norm": 6.047487766464625, | |
| "learning_rate": 1.0500000000000001e-06, | |
| "loss": 2.4305, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.6956521739130435, | |
| "grad_norm": 5.1448782163300795, | |
| "learning_rate": 1.2e-06, | |
| "loss": 2.3992, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.782608695652174, | |
| "grad_norm": 6.319527460032345, | |
| "learning_rate": 1.35e-06, | |
| "loss": 2.3569, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.8695652173913043, | |
| "grad_norm": 5.178587770323235, | |
| "learning_rate": 1.5e-06, | |
| "loss": 2.3823, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.9565217391304348, | |
| "grad_norm": 4.345035693656394, | |
| "learning_rate": 1.6499999999999999e-06, | |
| "loss": 2.3763, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 4.345035693656394, | |
| "learning_rate": 1.8000000000000001e-06, | |
| "loss": 2.3516, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.0869565217391304, | |
| "grad_norm": 6.8965483544750485, | |
| "learning_rate": 1.95e-06, | |
| "loss": 2.3247, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.1739130434782608, | |
| "grad_norm": 4.514037765648883, | |
| "learning_rate": 2.1000000000000002e-06, | |
| "loss": 2.2789, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.2608695652173914, | |
| "grad_norm": 4.1037697641805675, | |
| "learning_rate": 2.25e-06, | |
| "loss": 2.2809, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.3478260869565217, | |
| "grad_norm": 9.467321099804414, | |
| "learning_rate": 2.2434052017986548e-06, | |
| "loss": 2.3034, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.434782608695652, | |
| "grad_norm": 3.846412370193112, | |
| "learning_rate": 2.2236981251738474e-06, | |
| "loss": 2.2531, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.5217391304347827, | |
| "grad_norm": 2.8638861083008282, | |
| "learning_rate": 2.191109817580653e-06, | |
| "loss": 2.2658, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.608695652173913, | |
| "grad_norm": 3.3754061157050796, | |
| "learning_rate": 2.146022347129827e-06, | |
| "loss": 2.248, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.6956521739130435, | |
| "grad_norm": 2.872218160561474, | |
| "learning_rate": 2.0889643231885378e-06, | |
| "loss": 2.2285, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.7826086956521738, | |
| "grad_norm": 3.1083184333248832, | |
| "learning_rate": 2.020604698918849e-06, | |
| "loss": 2.234, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.8695652173913042, | |
| "grad_norm": 3.56307962249585, | |
| "learning_rate": 1.9417449284135222e-06, | |
| "loss": 2.2117, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.9565217391304348, | |
| "grad_norm": 3.0969922866527027, | |
| "learning_rate": 1.8533095703795562e-06, | |
| "loss": 2.2288, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 4.56206180106739, | |
| "learning_rate": 1.7563354485326805e-06, | |
| "loss": 2.1789, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.0869565217391304, | |
| "grad_norm": 3.422562132986128, | |
| "learning_rate": 1.651959495787264e-06, | |
| "loss": 2.1124, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.1739130434782608, | |
| "grad_norm": 3.06225251545429, | |
| "learning_rate": 1.541405424757404e-06, | |
| "loss": 2.0822, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.260869565217391, | |
| "grad_norm": 3.5739299601482335, | |
| "learning_rate": 1.4259693808453737e-06, | |
| "loss": 2.0819, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.3478260869565215, | |
| "grad_norm": 3.27633625675635, | |
| "learning_rate": 1.3070047461218605e-06, | |
| "loss": 2.0425, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.4347826086956523, | |
| "grad_norm": 3.0275645098802992, | |
| "learning_rate": 1.1859062721585949e-06, | |
| "loss": 2.033, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.5217391304347827, | |
| "grad_norm": 3.2107781378583473, | |
| "learning_rate": 1.0640937278414054e-06, | |
| "loss": 2.0222, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.608695652173913, | |
| "grad_norm": 3.0228540401061905, | |
| "learning_rate": 9.429952538781398e-07, | |
| "loss": 2.0408, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.6956521739130435, | |
| "grad_norm": 3.3959547075086522, | |
| "learning_rate": 8.240306191546268e-07, | |
| "loss": 2.0087, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.782608695652174, | |
| "grad_norm": 2.7681067030431485, | |
| "learning_rate": 7.085945752425963e-07, | |
| "loss": 2.0291, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.869565217391304, | |
| "grad_norm": 2.845753287691284, | |
| "learning_rate": 5.980405042127362e-07, | |
| "loss": 2.017, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.9565217391304346, | |
| "grad_norm": 2.97978202958994, | |
| "learning_rate": 4.936645514673199e-07, | |
| "loss": 2.0195, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 2.97978202958994, | |
| "learning_rate": 3.9669042962044397e-07, | |
| "loss": 2.0179, | |
| "step": 36 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 44, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 6, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.849397348401152e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |