| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0036999352511331053, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00014799741004532422, | |
| "grad_norm": 25.31769561767578, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 8.1636, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00014799741004532422, | |
| "eval_loss": 8.671719551086426, | |
| "eval_runtime": 262.1288, | |
| "eval_samples_per_second": 21.707, | |
| "eval_steps_per_second": 10.853, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00029599482009064844, | |
| "grad_norm": 28.9766902923584, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 8.3506, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0004439922301359726, | |
| "grad_norm": 37.51851272583008, | |
| "learning_rate": 0.0002, | |
| "loss": 7.7496, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0005919896401812969, | |
| "grad_norm": 17.686782836914062, | |
| "learning_rate": 0.0001999048221581858, | |
| "loss": 6.2181, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.000739987050226621, | |
| "grad_norm": 19.165815353393555, | |
| "learning_rate": 0.00019961946980917456, | |
| "loss": 5.9745, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0008879844602719452, | |
| "grad_norm": 9.92040729522705, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 4.5077, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0010359818703172695, | |
| "grad_norm": 10.178970336914062, | |
| "learning_rate": 0.00019848077530122083, | |
| "loss": 3.2111, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0011839792803625938, | |
| "grad_norm": 13.662432670593262, | |
| "learning_rate": 0.00019762960071199333, | |
| "loss": 3.2317, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0013319766904079178, | |
| "grad_norm": 10.111414909362793, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 3.1016, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.001479974100453242, | |
| "grad_norm": 6.914839744567871, | |
| "learning_rate": 0.0001953716950748227, | |
| "loss": 2.0293, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0016279715104985664, | |
| "grad_norm": 11.782793998718262, | |
| "learning_rate": 0.00019396926207859084, | |
| "loss": 2.6581, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0017759689205438904, | |
| "grad_norm": 7.749815464019775, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 2.3704, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0019239663305892147, | |
| "grad_norm": 31.856861114501953, | |
| "learning_rate": 0.000190630778703665, | |
| "loss": 2.5376, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.002071963740634539, | |
| "grad_norm": 10.559371948242188, | |
| "learning_rate": 0.00018870108331782217, | |
| "loss": 2.3736, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.002219961150679863, | |
| "grad_norm": 5.9514665603637695, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 2.4374, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0023679585607251875, | |
| "grad_norm": 6.814925193786621, | |
| "learning_rate": 0.0001843391445812886, | |
| "loss": 2.1366, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0025159559707705116, | |
| "grad_norm": 10.532800674438477, | |
| "learning_rate": 0.0001819152044288992, | |
| "loss": 2.6406, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0026639533808158356, | |
| "grad_norm": 6.617628574371338, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 2.0348, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00281195079086116, | |
| "grad_norm": 5.439142227172852, | |
| "learning_rate": 0.0001766044443118978, | |
| "loss": 1.9106, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.002959948200906484, | |
| "grad_norm": 4.196650505065918, | |
| "learning_rate": 0.0001737277336810124, | |
| "loss": 1.7394, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0031079456109518082, | |
| "grad_norm": 6.421461582183838, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 2.0149, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0032559430209971327, | |
| "grad_norm": 4.891075134277344, | |
| "learning_rate": 0.00016755902076156604, | |
| "loss": 1.8183, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0034039404310424568, | |
| "grad_norm": 3.9953277111053467, | |
| "learning_rate": 0.00016427876096865394, | |
| "loss": 1.8134, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.003551937841087781, | |
| "grad_norm": 4.448080539703369, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 1.8657, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0036999352511331053, | |
| "grad_norm": 4.5448079109191895, | |
| "learning_rate": 0.0001573576436351046, | |
| "loss": 2.1479, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0036999352511331053, | |
| "eval_loss": 2.039273262023926, | |
| "eval_runtime": 262.3396, | |
| "eval_samples_per_second": 21.689, | |
| "eval_steps_per_second": 10.845, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5146843860172800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |