| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0007711973224028966, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.542394644805793e-05, | |
| "eval_loss": 2.7992300987243652, | |
| "eval_runtime": 2235.1802, | |
| "eval_samples_per_second": 12.213, | |
| "eval_steps_per_second": 6.107, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.711973224028966e-05, | |
| "grad_norm": 2.202889919281006, | |
| "learning_rate": 5e-05, | |
| "loss": 2.6748, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00015423946448057932, | |
| "grad_norm": 2.989361524581909, | |
| "learning_rate": 0.0001, | |
| "loss": 2.7346, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00015423946448057932, | |
| "eval_loss": 2.4348955154418945, | |
| "eval_runtime": 2264.5204, | |
| "eval_samples_per_second": 12.055, | |
| "eval_steps_per_second": 6.028, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.000231359196720869, | |
| "grad_norm": 3.690640449523926, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.8237, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00030847892896115864, | |
| "grad_norm": 3.5385003089904785, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.509, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00030847892896115864, | |
| "eval_loss": 1.5317597389221191, | |
| "eval_runtime": 2264.3254, | |
| "eval_samples_per_second": 12.056, | |
| "eval_steps_per_second": 6.028, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0003855986612014483, | |
| "grad_norm": 2.908796548843384, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.5962, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.000462718393441738, | |
| "grad_norm": 2.8132200241088867, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5365, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.000462718393441738, | |
| "eval_loss": 1.4702589511871338, | |
| "eval_runtime": 2264.0789, | |
| "eval_samples_per_second": 12.057, | |
| "eval_steps_per_second": 6.029, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0005398381256820277, | |
| "grad_norm": 4.012539863586426, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.5411, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0006169578579223173, | |
| "grad_norm": 4.415103912353516, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.542, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0006169578579223173, | |
| "eval_loss": 1.4406354427337646, | |
| "eval_runtime": 2262.4038, | |
| "eval_samples_per_second": 12.066, | |
| "eval_steps_per_second": 6.033, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0006940775901626069, | |
| "grad_norm": 2.8680806159973145, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.3983, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0007711973224028966, | |
| "grad_norm": 2.7566418647766113, | |
| "learning_rate": 0.0, | |
| "loss": 1.3613, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0007711973224028966, | |
| "eval_loss": 1.43626070022583, | |
| "eval_runtime": 2265.8907, | |
| "eval_samples_per_second": 12.048, | |
| "eval_steps_per_second": 6.024, | |
| "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": 9247821240729600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |