| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.023980815347721823, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007993605115907274, | |
| "eval_loss": NaN, | |
| "eval_runtime": 13.6456, | |
| "eval_samples_per_second": 28.947, | |
| "eval_steps_per_second": 14.51, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002398081534772182, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004796163069544364, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.006394884092725819, | |
| "eval_loss": NaN, | |
| "eval_runtime": 12.5897, | |
| "eval_samples_per_second": 31.375, | |
| "eval_steps_per_second": 15.727, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.007194244604316547, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00027, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.009592326139088728, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00029265847744427303, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.011990407673860911, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00025606601717798207, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.012789768185451638, | |
| "eval_loss": NaN, | |
| "eval_runtime": 12.6257, | |
| "eval_samples_per_second": 31.285, | |
| "eval_steps_per_second": 15.682, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.014388489208633094, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001963525491562421, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.016786570743405275, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012653483024396533, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.019184652278177457, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.183221215612904e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.019184652278177457, | |
| "eval_loss": NaN, | |
| "eval_runtime": 12.6342, | |
| "eval_samples_per_second": 31.264, | |
| "eval_steps_per_second": 15.672, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.02158273381294964, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.634902137174483e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.023980815347721823, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1469552441425920.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |