| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.010580331164365445, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002116066232873089, | |
| "eval_loss": 3.1842007637023926, | |
| "eval_runtime": 168.1217, | |
| "eval_samples_per_second": 11.837, | |
| "eval_steps_per_second": 5.918, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0010580331164365445, | |
| "grad_norm": 3.979726552963257, | |
| "learning_rate": 5e-05, | |
| "loss": 14.4595, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002116066232873089, | |
| "grad_norm": 5.464813232421875, | |
| "learning_rate": 0.0001, | |
| "loss": 13.1041, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002116066232873089, | |
| "eval_loss": 2.936410665512085, | |
| "eval_runtime": 175.2718, | |
| "eval_samples_per_second": 11.354, | |
| "eval_steps_per_second": 5.677, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0031740993493096334, | |
| "grad_norm": 5.5804901123046875, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 11.1546, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004232132465746178, | |
| "grad_norm": 7.533310413360596, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 10.4748, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004232132465746178, | |
| "eval_loss": 2.4879891872406006, | |
| "eval_runtime": 175.128, | |
| "eval_samples_per_second": 11.363, | |
| "eval_steps_per_second": 5.682, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0052901655821827225, | |
| "grad_norm": 4.8308939933776855, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 9.4416, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.006348198698619267, | |
| "grad_norm": 6.968542575836182, | |
| "learning_rate": 5e-05, | |
| "loss": 9.2187, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.006348198698619267, | |
| "eval_loss": 2.3295955657958984, | |
| "eval_runtime": 175.0121, | |
| "eval_samples_per_second": 11.371, | |
| "eval_steps_per_second": 5.685, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.007406231815055811, | |
| "grad_norm": 4.3836236000061035, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 8.9482, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.008464264931492356, | |
| "grad_norm": 4.832591533660889, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 8.9949, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.008464264931492356, | |
| "eval_loss": 2.2863879203796387, | |
| "eval_runtime": 175.0829, | |
| "eval_samples_per_second": 11.366, | |
| "eval_steps_per_second": 5.683, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0095222980479289, | |
| "grad_norm": 6.3857831954956055, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 10.4195, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.010580331164365445, | |
| "grad_norm": 4.938572406768799, | |
| "learning_rate": 0.0, | |
| "loss": 8.6652, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.010580331164365445, | |
| "eval_loss": 2.277858018875122, | |
| "eval_runtime": 174.7334, | |
| "eval_samples_per_second": 11.389, | |
| "eval_steps_per_second": 5.694, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7598059374692352.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |